PREDICTIVE CONVERSION OF LANGUAGE INPUT

Abstract

Systems and processes for predictive conversion of language input are provided. In one example process, text composed by a user can be obtained. Input comprising a sequence of symbols of a first symbolic system can be received from the user. Candidate word strings corresponding to the sequence of symbols can be determined. Each candidate word string can comprise two or more words of a second symbolic system. The candidate word strings can be ranked based on a probability of occurrence of each candidate word string in the obtained text. Based on the ranking, a portion of the candidate word strings can be displayed for selection by the user.

Description

FIELD

This relates generally to language input in electronic devices and, more specifically, to predictive conversion of language input in electronic devices.

BACKGROUND

Pinyin is a phonetic system for transcribing Mandarin Chinese using the Roman alphabet. In a pinyin transliteration, the phonetic pronunciations of Chinese characters can be mapped to syllables composed of Roman letters. Pinyin is commonly used to input Chinese characters into a computer via a conversion system. For a given pinyin input, the conversion system can output Chinese characters that most likely correspond to the pinyin input. Such a system often incorporates statistical language models to improve conversion accuracy. However, while conventional language models can be helpful for determining commonly used Chinese character sequences, they can be less successful at determining Chinese character sequences that are not frequently used in the Chinese language. This can present difficulties to users who frequently need to input particular sequences of Chinese characters that are less common in the Chinese language, such as the names of friends or family members or the names of locations frequented by the user.

SUMMARY

Systems and processes for predictive conversion of language input are provided. In one example process, text composed by a user can be obtained. Input that includes a sequence of symbols of a first symbolic system can be received. A plurality of candidate word strings corresponding to the sequence of symbols can be determined. Each candidate word string of the plurality of candidate word strings can include two or more words of a second symbolic system. The plurality of candidate word strings can be ranked based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text. A portion of the plurality of candidate word strings can be displayed for selection by the user based on the ranking.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates an exemplary language model having a hierarchical context tree structure according to various examples.

FIG. 2 illustrates an exemplary process for predictive text input according to various examples.

FIG. 3 illustrates an exemplary process for predictive text input according to various examples.

FIG. 4 illustrates an exemplary process for predictive text input according to various examples.

FIGS. 5A-B illustrate an exemplary process for predictive conversion of language input according to various examples.

FIGS. 6A-C illustrate exemplary screenshots of an electronic device at various stages of an exemplary process for predictive conversion of language input according to various examples.

FIGS. 7A-D illustrate an exemplary process for predictive conversion of language input according to various examples.

FIGS. 8A-F illustrate exemplary screenshots of an electronic device at various stages of an exemplary process for predictive conversion of language input according to various examples.

FIG. 9 illustrates an exemplary user device for carrying out aspects of predictive text input or predictive conversion of language input according to various examples.

FIG. 10 illustrates an exemplary system and environment for carrying out aspects of predictive text input or predictive conversion of language input according to various examples.

FIG. 11 illustrates a functional block diagram of an exemplary electronic device according to various examples.

FIG. 12 illustrates a functional block diagram of an exemplary electronic device according to various examples

FIG. 13 illustrates a functional block diagram of an exemplary electronic device according to various examples.

DETAILED DESCRIPTION

In the following description of examples, reference is made to the accompanying drawings in which it is shown by way of illustration specific examples that can be practiced. It is to be understood that other examples can be used and structural changes can be made without departing from the scope of the various examples.

The present disclosure relates to systems and processes for predictive conversion of language input. In an exemplary process, text composed by a user can be obtained. The obtained text can be used to generate a user-specific language model. Input that includes a sequence of symbols of a first symbolic system (e.g., pinyin input) can be received. A plurality of candidate word strings corresponding to the sequence of symbols can be determined. Each candidate word string can include two or more words of a second symbolic system (e.g., Chinese words). The probability of occurrence of each candidate word string in the obtained text can be determined using the generated user-specific language model. The plurality of candidate word strings can be ranked based on a probability of occurrence of each candidate word string in the obtained text. A portion of the plurality of candidate word strings can be displayed for user selection based on the ranking. A selection of a candidate word string from the displayed portion can cause the selected candidate word to be displayed in a text field.

By utilizing text composed by the user to generate a user-specific language model, candidate word strings that are more frequently used by the user, but uncommon in typical collections of text, can be displayed for user selection. Further, unlike deterministic conversion methods where fixed conversion rules are set up for specific inputs, the processes for predictive conversion of language input described herein can incorporate dynamic learning where the probability of occurrence of a particular candidate word string can change based on input collected from the user over time. This can improve the accuracy of predicting the most likely candidate word string corresponding to the inputted sequence of symbols of the first symbolic system.

The present disclosure further relates to systems and processes for predictive text input. In various examples described herein, a language model can be used to generate predictive text given input text. In some examples, the language model can be a user language model having a hierarchical context tree structure. For example, the language model can be built from user text and thus can more closely model the intent of the user. This enables greater accuracy in generating predictive text for the user. In addition, the language model can include various sub-models associated with various specific contexts. The language model can thus be used to model various specific contexts, thereby improving accuracy in generating predictive text. The hierarchical context tree structure can enable information to be shared between the sub-models and can prevent redundancy among the sub-models. This allows the language model to be stored and implemented efficiently.

In one example process for predictive text input, a text input can be received. The text input can be associated with an input context. A frequency of occurrence of an m-gram with respect to a subset of a corpus can be determined using a language model. The m-gram can include at least one word in the text input. A weighting factor can be determined based on a degree of similarity between the input context and the context. A weighted probability of a predicted text given the text input can be determined based on the frequency of occurrence of the m-gram and the weighting factor. The m-gram can include at least one word in the predicted text. The predicted text can be presented via a user interface of an electronic device.

In some examples, physical context can be used to improve the accuracy of predictive text. Physical context can refer to a time period, a location, an environment, a situation, or a circumstance associated with the user at the time the text input is received. For example, physical context can include the situation of being on an airplane. The physical context can be determined using a sensor of an electronic device. In addition, the physical context can be determined using data obtained from an application of the electronic device. In one example, the physical context of being on an airplane can be determined based on audio detected by the microphone of the electronic device. In another example, the physical context of being on an airplane can be determined based on a user calendar entry obtained from the calendar application on the electronic device.

In one example process of predictive text using physical context, a text input can be received. A physical context that is associated with the text input can be determined. A weighted probability of a predicted text given the text input can be determined using a language model and the physical context. The predicted text can be presented via a user interface of an electronic device.

1. Language Model

A language model generally assigns to an n-gram a frequency of occurrence of that n-gram with respect to a corpus of natural language text. An n-gram refers to a sequence of n words, where n is any integer greater than zero. In some cases, the frequency of occurrence can be in the form of raw counts. For example, a particular 2-gram can occur 25 times within a corpus of natural language text. Accordingly, the frequency of occurrence of that 2-gram within the corpus can be 25 counts. In other cases, the frequency of occurrence can be a normalized value. For example, the frequency of occurrence can be in the form of a likelihood or probability (e.g., probability distribution or probability of occurrence). In one such example, a corpus of natural language text can include 25 counts of a particular 2-gram and 1000 counts of all 2-grams. Accordingly, the frequency of occurrence of that 2-gram within the corpus can be equal to 25/1000.

A language model can be built from a corpus. In some cases, the language model can be a general language model built from a corpus that includes a large volume of text associated with various contexts. In other cases, the language model can be a context-specific language model where the language model is built from a corpus that is associated with a specific context. The specific context can be, for example, a subject, an author, a source of text, an application for inputting text, a recipient of text, or the like. Context-specific language models can be desirable to improve accuracy in text predictions. However, because each context-specific language model can be associated with only one context, multiple context-specific language models can be required to cover a range of contexts. This can be an inefficient use of resources where significant memory and computational power can be required to store and implement a large number of context-specific language models. It should be recognized that that the term “context” described herein can refer to a scope or a domain.

FIG. 1 depicts language model 100 having a hierarchical context tree structure. The hierarchical context tree structure can be advantageous in enabling multiple contexts to be efficiently integrated within a single language model. Language model 100 can thus be used to efficiently model a variety of contexts.

As shown in FIG. 1, language model 100 can include multiple nodes that extend from root node 102 in a tree structure. The nodes can be arranged in multiple hierarchical levels where each hierarchical level can represent a different category of context. For example, hierarchical level 132 can represent application context while hierarchical level 134 can represent recipient context. Having only a single category of context for each hierarchical level can be advantageous in preventing redundancy between the nodes of language model 100. This reduces the memory required to store language model 100 and also enables greater efficiency in determining text predictions.

Each node of language model 100 can correspond to a sub-model of language model 100. Each sub-model within a hierarchical level can be associated with a specific context of the category of context of the hierarchical level. For example, hierarchical level 132 can include sub-models that are each associated with a specific application of the user device. Specifically, sub-models 104, 106, and 108 can be associated with the messaging application, the email application, and the word processor application, respectively. Similarly, hierarchical level 134 can include sub-models that are each associated with a specific recipient. Specifically, sub-models 110, 112, and 114 can be associated with the spouse of the user, a first friend of the user, and a second friend of the user, respectively. In addition, a child sub-model can be associated with the context of its parent sub-model. For example, children sub-models 110, 112, and 114 can extend from parent sub-model 104 and thus children sub-models 110, 112, and 114 can be associated with the messaging application of parent sub-model 104. Further, the sub-models can be independent of one another such that each sub-model is associated with a unique context. This prevents redundancy between the sub-models.

Language model 100 can be built from a corpus that includes multiple subsets where each subset can be associated with a specific context. In this example, language model 100 can be an n-gram statistical language model that includes a plurality of n-grams. Each n-gram can be associated with a frequency of occurrence. The frequency of occurrence of each n-gram can be with respect to a subset or a plurality of subsets of the corpus. Thus, each n-gram can be associated with a specific context of a subset or of a plurality of subsets.

Each sub-model of language model 100 can be built from a subset of the corpus and can be associated with the specific context of the subset. For example, sub-model 110 can be built from a first subset of the corpus. The first subset can include text that is associated with the messaging application of the user device and that is directed to the spouse of the user. Thus, sub-model 110 can be associated with a first context where the first context can include the messaging application and the spouse of the user. Further, the frequency of occurrence of an n-gram of sub-model 110 can be with respect to the first subset.

In some examples, a parent sub-model can be based on its children sub-models. For example, the frequency of occurrence of a specific n-gram with respect to parent sub-model 104 can be derived by combining the frequencies of occurrence of that n-gram with respect to children sub-models 110, 112, and 114. In some examples, the result from each child sub-model can be weighted by a weighting factor prior to being combined. For example, the frequency of occurrence of a particular 2-gram with respect to parent sub-model 104 can be equal to the sum of the weighted frequencies of occurrence of that 2-gram with respect to children sub-models 110, 112, and 114. This can be expressed as: C(w₁ w₂)_messaging=λ₁C(w₁ w₂)_{messaging,spouse}+λ₂C(w₁ w₂)_{messaging,friend1}+λ₃C(w₁ w₂)_{messaging,friend2}, where C(w₁ w₂)_messaging denotes the frequency of occurrence of the 2-gram with respect to sub-model 104, C(w₁ w₂)_{messaging,spouse} denotes the frequency of occurrence of the 2-gram with respect to sub-model 110, C(w₁ w₂)_{messaging,friend1} denotes the frequency of occurrence of the 2-gram with respect to sub-model 112, C(w₁ w₂)_{messaging,friend2} denotes the frequency of occurrence of the 2-gram with respect to sub-model 114, and λ₁, λ₂, λ₃ are different weighting factors.

Language model 100 can further include a plurality of hierarchical context tags to encode the context associated with each n-gram. Each context can thus be represented by one or more hierarchical context tags. For example, an n-gram of sub-model 104 can be represented by the hierarchical context tag “messaging” while an n-gram of sub-model 110 can be represented by the hierarchical context tags “messaging, spouse”. Identical n-grams from different sub-models can thus be differentiated by the hierarchical context tags associated with each n-gram.

In some examples, language model 100 can be a general language model. In other examples, language model 100 can be user language model that is built from a corpus of user text. User text or user text input can refer to text that is inputted by a user of the user device. The user can be an individual or a group of individuals. Further, language model 100 can be a static language model or dynamic language model.

It should be recognized that language model 100 can include any number of hierarchical levels representing a respective number of categories of context. The hierarchical levels can be arranged in any suitable order. For instance, in some examples, hierarchical level 134 can extend from root 102 while hierarchical level 132 can extend from hierarchical level 134. Each hierarchical level can include any number of sub-models associated with a respective number of specific contexts. For example, hierarchical level 132 can include additional sub-models that are associated with other applications of the user device. The applications can include, for example, web browser, social media, chat, calendar scheduler, spreadsheets, presentations, notes, media, virtual assistant, or the like. Similarly, hierarchical level 134 can include additional sub-models that are associated with other recipients. The recipients can include any specific individual, any group of individuals, or any category of people. For example, the recipients can include a family member, a friend, a colleague, a group of friends, children within a particular age range, or the like. Further, in some examples, language model 100 can include an additional hierarchical level representing physical context. The sub-models of the hierarchical level can be associated with a specific physical context. For example, physical context can include one or more of an environment, situation, circumstance, weather, time period, location, and the like.

Below, FIGS. 2, 3, 4, 5, and 7 provide a description of exemplary processes 200, 300, 400, 500, and 700 for predictive text input or predictive conversion of language input. In some examples, each of processes 200, 300, 400, 500, and 700 can be implemented by a user device (e.g., user device 900, described below). In some examples, the user device can be part of a server-client system (e.g., system 1000, described below). In these examples, each of processes 200, 300, 400, 500, and 700 can be implemented by the server-client system where different portions of each process can be divided between the user device (e.g., user device 900) and the server (e.g., server system 1010, described below)

2. Process for Predictive Text Input

FIG. 2 illustrates exemplary process 200 for predictive text input according to various examples. At block 202 of process 200, a text input can be received. In some examples, the text input can be received via an interface of the user device (e.g., touch screen 946 or other input/control devices 948 of user device 900, described below). The interface can be any suitable device for inputting text. For example, the interface can be a keyboard/keypad, a touch screen implementing a virtual keyboard or a handwriting recognition interface, a remote control (e.g., television remote control), a scroll wheel interface, an audio input interface implementing speech-to-text conversion, or the like. The received text input can be in any language and can include at least one word. In some examples, the text input can include a sequence of words. In some cases, a character (e.g., symbols and punctuation) can be considered a word.

The received text input can be associated with an input context. The input context can include any contextual information related to the received text input. The input context can include a single context or a combination of contexts. In some examples, the input context can include an application of the user device with which the received text input is associated. The application can be any application configured to receive text input, such as, for example, email, text messaging, web browser, calendar scheduler, word processing, spreadsheets, presentations, notes, media, virtual assistant, or the like. In addition, the input context can include the recipient to which the received text input is directed. The recipient can include, for example, a family member, a friend, a colleague, or the like. The recipient can also include a particular group of people or a category of people, such as, for example, best friends, professional acquaintances, children of a particular age group, or the like.

The recipient can be determined using a language model. In some examples, the language model can be the same language model used in block 204 for determining a first frequency of occurrence of an m-gram with respect to a first subset of a corpus. In other examples, the language model used to determine the recipient can be different from that used in block 204. The language model used to determine the recipient can include sub-models that are associated with various recipients (e.g., recipient A, B, C . . . Z). The most likely recipient to which the input text is directed can be determined from the input text using the language model. For example, the probability that the recipient is recipient A given the text input can be determined as follows: P(recipient A|text input)=P(text input|recipient A)*P(recipient A)/P(text input). The input context can thus include the most likely recipient determined based on the input text and using the language model.

In some examples, the input context can include a physical context. The physical context can refer to an environment, a situation, or a circumstance associated with the user at the time the text input is received. For example, the physical context can include a time, a location, a weather condition, a speed of travel, a noise level, or a brightness level. The physical context can also include traveling on a vehicle (e.g., car, bus, subway, airplane, boat, etc.), engaging in a particular activity (e.g., sports, hobby, shopping, etc.), or attending a particular event (e.g., dinner, conference, show, etc.).

In some examples, the input context can be determined using a sensor of the user device. The sensor can include, for example, a microphone, a motion sensor, a GPS receiver, a light/brightness sensor, an image sensor, a moisture sensor, a temperature sensor, or the like. In a specific example, the user can be inputting text to the user device while traveling on an airplane. In such an example, the microphone of the user device can receive audio that is characteristic of an airplane and a sound classifier can be used to determine that the received audio is associated with an airplane. Further, the motion sensor and GPS sensor (e.g., GPS receiver) of the user device can be used to determine that the speed, altitude, and location of the user are consistent with being on an airplane. The input context of traveling on an airplane can thus be determined using information obtained from the microphone, motion sensor, and GPS sensor.

In another example, the user can be inputting text to the user device while jogging. In such an example, the motion sensor can detect oscillations and vibration associated with jogging while the microphone can receive audio that is consistent with a person jogging. The input context of jogging can thus be determined based on the information from the microphone and motion sensor.

In yet another example, the user can be inputting text to the user device while in a dark environment. In such an example, the image sensor or the brightness sensor can be used to detect that the user is in a dark environment. The physical context of being in a dark environment can thus be determined based on the information from the image or brightness sensor. Further, in some cases, other physical context can be determined based on determining that the user is in a dark environment. For example, the user device can determine the physical context of watching a movie in a movie theater based on determining the location of the user using the GPS sensor and determining that the user is in a dark environment.

In some examples, the input context can be represented by one or more hierarchical context tags. For example, the received text input can be associated with the email application and spouse of the user as the recipient. In such an example, the input context can be represented by the hierarchical context tags “email, spouse”.

At block 204 of process 200, a first frequency of occurrence of an m-gram with respect to a first subset of a corpus can be determined using a first language model. In some examples, the first language model can be an n-gram statistical language model having a hierarchical context tree structure. Specifically, the first language model can be similar or identical to language model 100 described above with reference to FIG. 1.

The first language model can be built from a corpus having a plurality of subsets where each subset is associated with a context. Thus, the first subset can be associated with a first context. In one example, with reference to FIG. 1, sub-model 110 can be built from the first subset of the corpus. In this example, the first subset can include a collection of text that is associated with the messaging application and directed to the spouse of the user. Accordingly, in this example, the first context can include the messaging application and the spouse as the recipient.

The m-gram can be a sequence of m words where m is a specific positive integer. The m-gram can include at least one word in the text input received at block 202. In one example, the text input can include the word “apple” and the m-gram can be the 2-gram “apple cider”. In one example, the first frequency of occurrence of the 2-gram “apple cider” can be determined from sub-model 110 of language model 100.

It should be recognized that in other examples, the first frequency of occurrence of the m-gram with respect to the first subset can be determined from any sub-model of language model 100 and the first subset can be associated with the context of the respective sub-model. For instance, in one example, a sub-model of language model 100 can be built from a first subset that includes a collection of text associated with a specific physical context (e.g., environment, situation, circumstance, time period, location, etc.). In this example, the sub-model can be a physical context sub-model that is associated with the specific physical context. The first frequency of occurrence of the m-gram with respect to the first subset can be determined from the physical context sub-model where the first context includes the specific physical context.

In some examples, the first language model can be a general language model. In other examples, the first language model can be a user language model built using a corpus that includes a collection of user input text received prior to receiving the text input. In some examples, the first language model can be a static language model that is not modified or updated using the input text. In other examples, the first language model can be a dynamic language model. For example, learning based on received input text can be performed to update the dynamic language model. Specifically, the first language model can be updated using the input text received at block 202. Further, the first language model can be pruned (e.g., unlearned) using methods known in the art to enable the efficient use of the language model and to limit the memory required to store the language model.

At block 206 of process 200, a first weighting factor to apply to the first frequency of occurrence of the m-gram can be determined based on a degree of similarity between the input context and the first context. For example, a higher first weighting factor can be determined based on a higher degree of similarity between the input context and the first context. Conversely, a lower first weighting factor can be determined based on a lower degree of similarity between the input context and the first context.

In some example, the input context and the first context can be represented by hierarchical context tags and the degree of similarity can be determined based on the number of matching hierarchical context tags between the input context and the first context. For example, the input context can be represented by the hierarchical context tags “messaging, spouse” and the first context can be represented by the hierarchical context tags “messaging, spouse”. In this example, the degree of similarity can be high based on the matching of both the application context tags and the recipient context tags. Therefore, in this example, the first weighting factor can be determined to have a high value. In another example, the input context can be represented by the hierarchical context tags “messaging, spouse” and first context can be represented by the hierarchical context tags “email, colleague1”. In this example, the degree of similarity can be low due to neither the application context tags nor the recipient context tags matching. Therefore, in this example, the first weighting factor can be determined to have a low value.

In some examples, the first weighting factor can be determined using a look-up table. The look-up table can have predetermined values of the first weighting factor based on various combinations of input context and first context. In other examples, the first weighting factor can be determined by performing calculations based on predetermined logic.

At block 208 of process 200, a first weighted probability of a first predicted text given the text input can be determined based on the first frequency of occurrence of the m-gram and the first weighting factor. The m-gram at block 204 can include at least one word in the first predicted text. In one example, the text input can be the word “apple”, the first predicted text can be the word “cider”, and the m-gram can be the 2-gram “apple cider”. In this example, the first weighted probability of the word “cider” given the word “apple” can be determined as follows:

$P_{w1}\left(\mathrm{cider}\mathrm{apple}\right)={\lambda }_1\frac{{C_1\left(\mathrm{apple}\mathrm{cider}\right)}_{\mathrm{message},\mathrm{spouse}}}{{C_1(\mathrm{apple})}_{\mathrm{message},\mathrm{spouse}}}$

where C₁(apple cider)_{message,spouse} denotes the first frequency of occurrence of the 2-gram “apple cider” with respect to the first subset determined using sub-model 110 of language model 100, C₁(apple)_{message,spouse} denotes the frequency of occurrence of the 1-gram “apple” with respect to the first subset determined using sub-model 110 of language model 100, and λ₁ denotes the first weighting factor.

At block 210 of process 200, the first predicted text can be presented via a user interface of the user device. The first predicted text can be presented in a variety of ways. For example, the first predicted text can be displayed via a user interface displayed on the touchscreen of the user device. The manner in which the first predicted text is displayed can be based at least in part on the first probability of the first predicted text given the text input. For example, a list of predicted text can be presented and the position of the first predicted text on the list can be based at least in part on the first probability. A higher first probability can result in the first predicted text being positioned closer to the front or top of the list.

Although process 200 is described above with reference to blocks 202 through 210, it should be appreciated that in some cases, one or more blocks of process 200 can be optional and additional blocks can also be performed.

Further, it should be recognized that the first weighted probability of the first predicted text given the text input at block 208 can be determined based on any number of frequencies of occurrence of the m-gram and a respective number of the weighting factors. This enables information from other sub-models to be leveraged in determining the first weighted probability. For instance, in some examples, the first weighted probability of the first predicted text given the text input can be determined based on a first frequency of occurrence of the m-gram with respect to a first subset of the corpus, a first weighting factor, a second frequency of occurrence of the m-gram with respect to a second subset of the corpus, and a second weighting factor. In these examples, process 200 can further include determining, using the first language model, the second frequency of occurrence of the m-gram with respect to a second subset of the corpus. The second subset can be different from the first subset and the second subset can be associated with a second context that is different from the first context. For example, as described above with reference to block 204, the first frequency of occurrence of the m-gram with respect to the first subset can be determined using sub-model 110 of language model 100. Sub-model 110 can be built using the first subset of the corpus and the first context of the first subset can be associated with the messaging application and the spouse of the user. In addition, the second frequency of occurrence of the m-gram with respect to the second subset can be determining using sub-model 112 of language model 100. Sub-model 112 can be built using the second subset of the corpus and the second context of the second subset can be associated with the messaging application and the first friend of the user.

Further, process 200 can include determining the second weighting factor to apply to the second frequency of occurrence of the m-gram based on a degree of similarity between the input context and the second context. For example, the input context can be represented by “messaging, spouse”, the first context can be represented by “messaging, spouse”, and the second context can be represented by “messaging, friend1”. In this example, the degree of similarity between the input context and the first context can be greater than the degree of similarity between the input context and the second context. Accordingly, in this example, the first weighting factor can be greater than the second weighting factor. It should be appreciated that in other examples, the degree of similarity between the input context and the first context can be less than the degree of similarity between the input context and the second context and thus the first weighting factor can be less than the second weighting factor.

As described above, the first weighted probability of the first predicted text given the text input can be determined based on the first frequency of occurrence of the m-gram, the first weighting factor, the second frequency of occurrence of the m-gram, and the second weighting factor. In an example where the text input is “apple” and the predicted text is “cider”, the first weighted probability of the word “cider” given the word “apple” can be determined as follows:

$P_{w1}\left(\mathrm{cider}\mathrm{apple}\right)={\lambda }_1\frac{{C_1\left(\mathrm{apple}\mathrm{cider}\right)}_{\mathrm{message},\mathrm{spouse}}}{{C_1(\mathrm{apple})}_{\mathrm{message},\mathrm{spouse}}}+{\lambda }_2\frac{{C_2\left(\mathrm{apple}\mathrm{cider}\right)}_{\mathrm{message},\mathrm{friend}1}}{{C_2(\mathrm{apple})}_{\mathrm{message},\mathrm{friend}1}}$

where C₁(apple cider)_{message,spouse} denotes the first frequency of occurrence of the 2-gram “apple cider” with respect to the first subset determined using sub-model 110, C₁(apple)_{message,spouse} denotes the first frequency of occurrence of the 1-gram “apple” with respect to the first subset determined using sub-model 110, λ₁ denotes the first weighting factor, C₂(apple cider)_{message,friend1} denotes the second frequency of occurrence of the 2-gram “apple cider” with respect to the second subset determined using sub-model 112, C₂(apple)_{message,friend1} denotes the second frequency of occurrence of the 1-gram “apple” with respect to the second subset determined using sub-model 112, and λ₂ denotes the second weighting factor. In this example, the probability of each sub-model is calculated and each probability is weighted separately before being combined.

In another example, the first weighted probability of the word “cider” given the word “apple” can be determined as follows:

$P_{w1}\left(\mathrm{cider}\mathrm{apple}\right)=\frac{{\lambda }_1{C_1\left(\mathrm{apple}\mathrm{cider}\right)}_{\mathrm{message},\mathrm{spouse}}+{\lambda }_2{C_2\left(\mathrm{apple}\mathrm{cider}\right)}_{\mathrm{message},\mathrm{friend}1}}{{\lambda }_1{C_1(\mathrm{apple})}_{\mathrm{message},\mathrm{spouse}}+{\lambda }_2{C_2(\mathrm{apple})}_{\mathrm{message},\mathrm{friend}1}}$

In this example, the frequencies of occurrence are combined separately in the numerator and the denominator to derive the first weighting probability.

Further, in this example, the first weighted probability of the word “cider” given the word “apple” (e.g., P_w1(cider|apple)) can be based on the first weighted probability of the 1-gram “apple” with respect to the first subset (e.g., λ₁C₁(apple)_{message,spouse}). Therefore, in this example, process 200 can include determining, using the first language model, a first frequency of occurrence of an (m−1)-gram with respect to the first subset (e.g., C₁(apple)_{message,spouse}). The m-gram (e.g., “apple cider”) can include one or more words in the (m−1)-gram (e.g., “apple”). The first weighting factor (e.g., λ₁) can be applied to the first frequency of occurrence of the (m−1)-gram (e.g., C₁(apple)_{message,spouse}) to obtain the weighted frequency of occurrence of the (m−1)-gram (e.g., λ₁C₁(apple)_{message,spouse}). The first weighted probability of the first predicted text given the text input (e.g., P_w1(cider|apple)) can thus be determined based on the first weighted frequency of occurrence of the (m−1)-gram (e.g., λ₁C₁(apple)_{message,spouse}).

In some examples, the weighted probability of a second predicted text given the text input and the first predicted text can be determined in response to the first weighted probability of the first predicted text given the text input being greater than a predetermined threshold. In these examples, process 200 can further include determining, using the language model, a frequency of occurrence of an (m+1)-gram with respect to the first subset of the corpus. The (m+1)-gram can include one or more words in the m-gram and at least one word in the second predicted text. The weighted probability of the second predicted text given the text input and the first predicted text can be determined based on the frequency of occurrence of the (m+1)-gram and the first weighting factor. In one example, the m-gram can be the 2-gram “apple cider” and the (m+1)-gram can be the 3-gram “apple cider vinegar”. In response to the first weighted probability of the word “cider” given the word “apple” (e.g., P_w1(cider|apple)) being greater than a predetermined threshold, the frequency of occurrence of the 3-gram “apple cider vinegar” (e.g., C(apple cider vinegar)_{message,spouse}) with respect to the first subset of the corpus can be determined using sub-model 110 of language model 100. A weighted probability of the word “vinegar” given the words “apple cider” can be determined based on the frequency of occurrence of the 3-gram “apple cider vinegar” and the first weighting factor λ₁. In particular:

$P_{w1}\left(\mathrm{vinegar}\mathrm{apple}\mathrm{cider}\right)={\lambda }_1\frac{{C\left(\mathrm{apple}\mathrm{cider}\mathrm{vinegar}\right)}_{\mathrm{message},\mathrm{spouse}}}{{C\left(\mathrm{apple}\mathrm{cider}\right)}_{\mathrm{message},\mathrm{spouse}}}$

It should be recognized that weighted probabilities can be determined for any number of additional predicted texts in response to the weighted probability of the previous predicted text being greater than a predetermined threshold. In some examples, weighted probabilities of predicted text can be determined for up to five words using process 200. This can be desirable for enabling the generation of predictive text that includes a sequence of up to five words.

In some examples, additional language models can be used to determine a weighted probability of the first predicted text given the text input. Additional language models enable the use of additional statistical or contextual information for determining weighted probability of the first predicted text given the text input. This can be desirable for achieving greater accuracy and robustness in text prediction. For example, process 200 can include determining a second weighted probability of the first predicted text given the text input (e.g., P_w2(cider|apple)) based on the first weighted probability of the first predicted text given the text input (e.g., P_w1(cider|apple)) and a probability of the first predicted text given the text input (e.g., P(cider|apple)). In this example, the probability of the first predicted text given the text input (e.g., P(cider|apple)) can be determined using a second language model. The second language model can be any suitable language model. In one example, the second language model can be a general language model. In another example, the second language model can be a static language model. In a specific example, the first language model can be a dynamic user language model while the second language model can be a static general language model. Determining the second weighted probability of the first predicted text given the text input (e.g., P_w2(cider|apple)) can include applying a third weighting factor (e.g., λ₃) to the first weighted probability of the first predicted text given the text input (e.g., P_w1(cider|apple)) and applying a fourth weighting factor (e.g., λ₄) to the probability of the first predicted text given the text input (e.g., P(cider|apple)). In particular, the second weighted probability of the first predicted text given the text input can be determined as follows: P_w2(cider|apple)=λ₃P_w1(cider|apple)+λ₄P (cider|apple).

In examples where the language model is a dynamic language model, process 200 can further include updating the language model using the text input of block 202. In some examples, process 200 can include updating the language model using the text input of block 202 and the predicted text of block 208. Further, the input context can be used to update the language model. In an example where the input context is associated with “messaging, spouse”, the text input and predicted text of “apple cider” can be used to update the sub-model 110 of language model 100. Further, in some examples, only certain text is used to update the model. For example, only text that is accepted by the user can be used to update the model. In one example, text that is transmitted, sent, published, or posted via an application of the user device (e.g., email, messenger, chat, social media, etc.) can be considered to be accepted by the user.

Although in the above examples the language model can be an n-gram statistical language model having a hierarchical context tree structure (e.g., language model 100), it should be recognized that various other language models can be suitable for implementing process 200. For example, the language model can be a neural network based language model that is trained using a corpus. The corpus can include multiple subsets where each subset is associated with a specific context. The neural network based language model can be configured to receive an input that includes the m-gram and the input context and output a frequency of occurrence of the m-gram with respect to a first subset of the corpus and a first weighting factor to apply to the frequency of occurrence of the m-gram.

FIG. 3 illustrates another exemplary process 300 for predictive text input according to various examples. At block 302 of process 300, a first text input can be received. The first text input can be associated with a first input context. Block 302 can be similar or identical to block 202 described above.

At block 304 of process 300, a first weighted probability of a predicted text given the first text input can be determined using a language model and based on the first input context. The first weighted probability can be determined in a similar or identical manner as described above with respect to blocks 204 through 208.

At block 306 of process 300, a second text input can be received. In some examples, the second text input can be received after the first text input is received. The second text input can be associated with a second input context. The first text input can be identical to the second text input. However, the first input context can be different from the second input context. Block 306 can be similar or identical to block 202 described above.

At block 308 of process 300, a second weighted probability of the predicted text given the second text input can be determined using the language model and based on the second input context. The second weighted probability can be determined in a similar or identical manner as described above with respect to blocks 204 through 208.

The language model can take into account the differences in the first input context and the second input context in determining the first weighted probability and the second weighted probability, respectively. For example, different weighting factors can be determined at block 206 due to differences in the first input context and the second input context. Further, in some examples, different sub-models of the language model can be used to determine the second weighted probability at block 308 compared to the first weighted probability at block 304. Therefore, although the first input text and the second input text are identical, the first weighted probability can be different from the second weighted probability due to different sub-models being used to determine the frequency of occurrence of an m-gram or different weighting factors being determined.

3. Predictive Text Input Using Physical Context

FIG. 4 illustrates exemplary process 400 for predictive text input using physical context according to various examples. In process 400, physical context information can be used to improve the accuracy of a predicted text given a text input such that the predicted text is more likely to include the user's intent.

At block 402 of process 400, a text input can be received. Block 402 can be similar or identical to block 202 of process 200 described above.

At block 404 of process 400, a physical context associated with the text input can be determined. As described above, the physical context can refer to an environment, a situation, or a circumstance associated with the user at the time the text input is received. In some examples, the physical context can include a time, a location, a weather condition, a speed of travel, a noise level, a brightness level, or the like. The physical context can also include a situation or circumstance such as, traveling on a vehicle (e.g., car, bus, subway, airplane, boat, etc.), engaging in a particular activity (e.g., sports, hobby, shopping, etc.), or attending a particular event (e.g., dinner, conference, show, etc.).

In some examples, the physical context can be determined using a sensor of the user device. For example, the physical context can be determine in a similar or identical manner as determining the input context using a sensor of the user device at block 202 of process 200, described above.

In other examples, the physical context can be determined using data obtained from an application of the user device. The data can be obtained from any suitable application of the user device. For example, the physical context can be determined using the entries of the calendar application and the time of the clock application. In a specific example, it can be determined using the clock application and the calendar application that the text input is received while the user is attending a work meeting. According, the physical context associated with the text input can be determined to be the situation of attending a work meeting.

In other examples, the physical context can be determined to be a particular time period. The time period can be determined from data obtained from a clock application, a calendar application, or a weather application. In one example, the physical context can include a convenient time period for the user to schedule an outdoor activity. In this example, the convenient time period can be determined using the current time from the clock application, the user's schedule from the calendar application, and the weather forecast using the weather application.

At block 406 of process 400, a first weighted probability of a predicted text given the text input can be determined using a first language model and the physical context. The first language model can be any suitable language model for determining a probability of a predicted text given the text input. The first language model can be a general language model or a user language model. In an example where the first language model is a user language model, the first language model can be built from a corpus that includes a collection of user input text received prior to receiving the text input at block 302. In some examples, the first language model can be a static language model or a dynamic language model. In an example where the first language model is a dynamic language model, the first language model can be updating using the received text input.

In some examples, the first weighted probability of the predicted text given the text input can be determined based on a first probability of the predicted text given the text input and a first weighting factor. Block 406 can include determining, using the first language model, the first probability of the predicted text given the text input. Further, block 406 can include determining the first weighting factor based on the physical context. For example, if the physical context includes the situation of traveling in Paris and the text input includes the phrase, “I'm having fun at the”, the first weighting factor can be determined to be higher for a predicted text that is associated with Paris (e.g., Eiffel tower, Louvre, or Notre Dame) and lower for a predicted text associated with San Francisco (e.g., Union Square, Pier 39, or Alcatraz). The first weighting factor can be apply to the first probability of the predicted text given the text input to obtained the first weighted probability of a predicted text given the text input.

In some examples, the first language model can be a class-based language model that includes a class and a first sub-model. The first sub-model can be associated with the physical context. Block 406 can include determining, using the first language model, a probability of a class given the input text (e.g., P(class|text input)). Block 406 can further include determining, using the first sub-model, a first probability of the predicted text given the class (e.g., P₁(predicted text|class)). The first weighted probability of the predicted text given the text input (e.g., P_w1(predicted text|text input) can be determined based on the probability of the class given the input text (e.g., P(class|text input)) and the first probability of the predicted text given the class (e.g., P₁(predicted text|class)). For example, the first weighted probability of the predicted text given the text input can be determined as follows:

P _w1(predicted text|text input)=P(class|text input)P₁(predicted text|class)

In some example, the first language model can include a second sub-model. The second sub-model can be associated with a context that is different from that of the first sub-model. For example, the second sub-model can be associated with a general context. The second sub-model can be built from a corpus that is different from that of the first sub-model. Block 406 can further include determining, using the second sub-model, a second probability of the predicted text given the class (e.g., P₂(predicted text|class)). The first weighted probability of the predicted text given the text input can be determined based on the second probability of the predicted text given the class. In one example, the first weighted probability of the predicted text given the text input can be based on a linear combination of the first probability of the predicted text given the class and second probability of the predicted text given the class. In particular:

P _w1(predicted text|text input)=P(class|text input){λ₁P₁(predictedtext|class)+λ₂P₂(predictedtext|class)}

where λ₁ and λ₂ are weighting factors.

It should be recognized that the first language model can include any number of sub-models. For instance, in some examples, the first language model can include n sub-models, where n is a positive integer. In these examples, the first weighted probability of the predicted text given the text input can be determined as follows:

$P_{w1}\left(\mathrm{predicted}\mathrm{text}\mathrm{text}\mathrm{input}\right)=P\left(\mathrm{class}\mathrm{text}\mathrm{input}\right)\sum _{i=1}^n{\lambda }_iP_i\left(\mathrm{predicted}\mathrm{text}\mathrm{class}\right)$

Further, it should be recognized that, in some example, the first language model can include multiple classes. In these examples, the first weighted probability of the predicted text given the text input can be determined based on the combined probabilities across the multiple classes. For example:

$P_{w1}\left(\mathrm{predicted}\mathrm{text}\mathrm{text}\mathrm{input}\right)=\sum _{\mathrm{class}\epsilon L}\left[P\left(\mathrm{class}\mathrm{text}\mathrm{input}\right)\sum _{i=1}^n{\lambda }_iP_i\left(\mathrm{predicted}\mathrm{text}\mathrm{class}\right)\right]$

where L denotes the first language model and P (class|text input)P₁(predicted text|class) is summed over all classes in the first language model, L.

In some examples, the first language model can be an n-gram statistical language model. In particular, the first language model can be an n-gram statistical language model having a hierarchical context tree structure (e.g., language model 100, described above). In these examples, the first language model can be built from a corpus that includes a plurality of subsets where each subset is associated with a context. Further, the first language model can include a hierarchical level representing physical context where the sub-models in the hierarchical level can each be associated with a specific physical context. In these examples, the first weighted probability of the predicted text given the text input can be determined using similar or identical methods described above with respect to blocks 204 through 208 of process 200. For example, block 406 can include determining, using the first language model, a first frequency of occurrence of an m-gram with respect to a first subset of the plurality of subsets. The first subset can be associated with a first context and the m-gram can include at least one word in the text input and at least one word in the predicted text. In addition, block 406 can include determining, based on a degree of matching between the physical context and the first context, a first weighting factor to apply to the first frequency of occurrence of the m-gram. The first weighting factor can be determined to be higher if the first context is more similar to the physical context. Conversely, the first weighting factor can be determined to be lower if the first context is less similar to the physical context. The first weighted probability of the predicted text given the text input can be based on the first frequency of occurrence of the m-gram and the first weighting factor.

It should be recognized that the first weighted probability of the predicted text given the text input can be based on any number of frequencies of occurrence of the m-gram and a respective number of weighting factors. For example, the first weighted probability of the predicted text given the text input can also be based on a second frequency of occurrence of the m-gram and a third weighting factor. In such an example, block 406 can further include determining, using the first language model, a second frequency of occurrence of the m-gram with respect to a second subset of the plurality of subsets. The second subset can be associated with a second context. Block 406 can further include determining a third weighting factor to apply to the second frequency of occurrence of the m-gram based on a degree of matching between the input context and the second context.

In yet other examples, the first language model can be a context-specific language model that is associated with the physical context. In these examples, the physical context can be used to select the first language model among a plurality of context-specific language models. The selected first language model can thus be used to determine the first weighted probability of the predicted text given the text input. In some cases, no weighting is performed in determining the first weighted probability of the predicted text given the text input. For example, the probability of the predicted text given the text input can be determined from the first language model and first weighted probability of the predicted text given the text input can equal the determined probability of the predicted text given the text input.

At block 408 of process 400, the predicted text can be presented via a user interface of the electronic device. Block 408 can be similar or identical to block 210 of process 200 described above.

Although process 400 is described above with reference to blocks 402 through 408, it should be appreciated that in some cases, one or more blocks of process 400 can be optional and additional blocks can also be performed. For instance, in examples where the first language model is a dynamic language model, process 400 can include updating the first language model using the received text input at block 402.

Further, in some examples, additional language models can be used to determine a second weighted probability of the predicted text given the text input. Using additional language models can be desirable for achieving greater accuracy in predicting text. In these examples, process 400 can include determining, using a second language model, a third probability of the predicted text given the text input. In addition, a second weighted probability of the predicted text given the text input can be determined based on the first weighted probability and the third probability. In some examples, determining the second weighted probability can include applying a third weighting factor to the first weighted probability and applying a fourth weighting factor to the third probability. For example, P_w2(predicted text|text input)=λ₃P_w1(predicted text|text input)+λ₄P₃(predicted text|text input), where P_w2(predicted text|text input) denotes the second weighted probability of the predicted text given the text input, P_w1 (predicted text|text input) denotes the first weighted probability of the predicted text given the text input, P₃(predicted text|text input) denotes the third probability of the predicted text given the text input, λ₃ denotes the third weighting factor, and λ₄ denotes the fourth weighting factor.

4. Predictive Conversion of Language Input

FIGS. 5A-B illustrate exemplary process 500 for predictive conversion of language input according to various examples. FIGS. 6A-C are exemplary screenshots of an electronic device illustrating various stages of exemplary process 500. Process 500 is described below with simultaneous reference to FIGS. 5A-B and 6A-C.

At block 502 of process 500, text composed by a user can be obtained. In some examples, the text can be obtained directly from the user by collecting text input as it is received from the user (e.g., via a language input interface displayed on touch screen 946). In other examples, the text can be obtained from identifying and retrieving stored text that was composed by the user. The stored text can be text that is stored on the user device (e.g., stored in user data and models 966) or on a remote server accessible by the user device (e.g., stored in user data and models 1020). In some examples, text composed by a user can be identified based on authentication information. In particular, authentication information (e.g., user name and/or passcode) used to obtain access to the user device can be associated with a particular user. In these examples, any text input received by the user device while being accessed using the authentication information can be identified and retrieved as text composed by the particular user. In other examples, text composed by a user can be identified based on sender information associated with the text. In particular, sender information (e.g., a phone number, email address, etc.) can be associated with a particular user. Thus, in these examples, text (e.g., from messages, emails, social media posts, etc.) can be determined to be composed by the sender of the text.

The obtained text can comprise words of a second symbolic system of a language. In the present example described in process 500, the second symbolic system can be written Chinese characters (e.g., “Han characters”). However, it should be recognized that, in other examples, the second symbolic system can be any script type of any language.

In some examples, the obtained text can be associated with a first context. The first context can be any context discussed above with respect to processes 200, 300, or 400. For example, the obtained text can be directed toward a first recipient and/or composed using a first application (e.g., messages, email, word processing, etc.). In this example, the first context can include the first recipient and/or first application. In other examples, the first context can be a context that is determined using a sensor of the user device. For example, as described above in processes 200, 300, and 400, the first context can be one or more physical contexts that are determined based on data obtained from one or more sensors of the user device. In a specific example, the one or more physical contexts can include determining whether the user is standing or sitting based on data received from an accelerometer sensor of the user device. In another example, the one or more physical contexts can include determining the location (e.g., address, city, country, landmark, restaurant, etc.) of the user based on data received from the GPS sensor of the user device and from a maps service.

It should be appreciated that additional text composed by the user can be obtained. The additional text can be associated with other contexts. For example, block 502 can further include obtaining second text composed by the user where the second text is associated with a second context that is different from the first context.

At block 504 of process 500, a first language model can be generated using the obtained text. Because the first language model is generated using text composed by the user, the first language model can predict the language style and tendencies of the user. Further, the first language model can better predict particular phrases that are frequently used by the user (e.g., names, locations, etc.) but are found less frequently in typical collections of text. In some examples, the first language model can be an n-gram language model. In other examples, the first language model can be a neural network based language model. It should be understood that other types of language models can be contemplated. The first language model can be stored on the user device or remotely on a server. Further, the first language model can be configured to be dynamically updated as the user inputs additional text.

In some examples, the first language model can have a hierarchical context tree structure similar to language model 100, described above. In these examples, the first language model can have multiple nodes representing various contexts. In particular, a first node of the first language model can be based on the text obtained in block 502 and can be associated with the first context. Similarly, a second node of the first language model can be based on the second text obtained in block 502 and can be associated with the second context. In this way, the first language model can take into account the input context associated with the input received at block 506.

At block 506 of process 500, input that includes a sequence of symbols can be received from the user. The input can be received via a user interface (e.g., a keyboard interface displayed on touch screen 946). The sequence of symbols can include symbols of a first symbolic system. The first symbolic system can be different from the second symbolic system. In the present example described in process 500, the first symbolic system can be a system of phonetic notations for transcribing the Mandarin pronunciations of Chinese characters (e.g., Chinese pinyin phonetic system or Chinese zhuyin phonetic system). For example, as shown in FIG. 6A, the input received at block 506 can include the pinyin input 604 “liumingjie,” which is intended to correspond to the Chinese characters “” (a person's name). Pinyin input 604 can be received via keyboard interface 602. It should be recognized that, in other examples, the first symbolic system can be any script type of any language. In particular, the first symbolic system can be any phonetic system for transcribing a language.

In some examples, the received input can be associated with an input context. Input context can be a context similar or identical to the first context described above in block 502. In particular, the input context can be any context described above in processes 200, 300, or 400. In some examples, the received input can be directed to a second recipient and/or composed using a second application of the device. In these examples, the input context can include the second recipient and/or the second application. Further, in some examples, the input context can be determined using a sensor of the device. For example, as described above in processes 200, 300, or 400 the input context can be one or more of the physical contexts determined using one or more sensors of the device.

At block 508 of process 500, a plurality of candidate word strings corresponding to the sequence of symbols can be determined. Each candidate word string of the plurality of candidate word strings can include two or more words of the second symbolic system. In some examples, each candidate words string can include one or more words of the second symbolic system. The plurality of candidate word strings can thus include words from the same second symbolic system as the text obtained in block 502. In the present example, each word of the two or more words can be a monosyllabic Chinese character.

The plurality of candidate word strings can be determined by initially resolving the sequence of symbols of the first symbolic system into groups of symbols that correspond to a single word of the second symbolic system. For example, the pinyin input of “liumingjie” can be resolved into the groups “liu,” “ming,” and “jie” that each correspond to a monosyllable of the Chinese language. The resolved groups of symbols can then be converted into the plurality of candidate word strings using a dictionary or look-up table that maps predefined groups of symbols of the first symbolic system to multiple words of the second symbolic system. For example, “liu” can be mapped to Chinese words such as “,” “,” and “,” “ming” can be mapped to Chinese words such as “,” and “,” and “” can be mapped to Chinese words such as “,” “,” and “”. The plurality of candidate word strings can then be determined based on various combinations of the mapped Chinese words. For example, the plurality of candidate word strings can include candidate word strings such as “”, “” and “” that correspond to the pinyin input of “liumingjie.” Further, in some examples, the plurality of candidate word strings can include candidate word strings that correspond to a portion of the sequence of symbols of the first symbolic system. For example, the plurality of candidate word strings can include candidate word strings such as “,” “,” or “.”

At block 510 of process 500, a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text can be determined. In particular, the probability of occurrence of each candidate word string in the obtained text can be determined using the first language model generated at block 504. For example, each candidate word string can be an n-gram, and the probability of occurrence of the respective n-gram in the obtained text can be determined using the first language model. Further, in examples where second text associated with a second context is obtained at block 502, a probability of occurrence of each candidate word string in the obtained second text can be determined using the first language model.

At block 512 of process 500, a probability of occurrence of each candidate word string in a corpus of text can be determined. The corpus of text can be a collection of text that is not composed by the user. For example, the corpus of text can contain text authored by several individuals that do not include the user. A second language model can be trained using the corpus of text, and the probability of occurrence of each candidate word string in the corpus of text can be determined using the second language model. In particular, each candidate word string can be an n-gram, and the probability of occurrence of the respective n-gram in the corpus of text can be determined using the second n-gram language model.

At block 514 of process 500, the plurality of candidate word strings can be ranked. The ranking can be based on an overall probability that the input received at block 506 corresponds to each candidate word string. In particular, the plurality of candidate word strings can be ranked in decreasing order from the highest overall probability to the lowest overall probability.

The overall probability can be determined based on the probability of occurrence of each candidate word string in the obtained text. In examples where second text associated with a second context is obtained at block 502, the overall probability can additionally or alternatively be determined based on the probability of occurrence of each candidate word string in the obtained second text. By utilizing the probability of occurrence of each candidate word string in text composed by the user (e.g., text obtained at block 502) to rank the plurality of candidate word strings, candidate word strings that are frequently used by the user (e.g., particular proper nouns) but uncommon in other corpuses of text can be ranked higher at block 514. In this way, these frequently used candidate word strings can be displayed at block 516 for user selection. This can improve user experience by personalizing the candidate word strings that are displayed at block 516 according to the text input habits of the user.

Further, in some examples, the overall probability can be determined based on the probability of occurrence of each candidate word string in the corpus of text. As described above, the corpus of text may not be composed by the user. In some examples, the overall probability can comprise a combination of the probability of occurrence of each candidate word string in the obtained text, the probability of occurrence of each candidate word string in the obtained second text, and the probability of occurrence of each candidate word string in the corpus of text. In some examples, as described in processes 200, 300, or 400, appropriate weighting factors can be applied to each probability to obtain the overall probability.

In some examples, the overall probability can be based on a degree of similarity between the input context and the first context. In particular, when determining the overall probability, a larger weighting factor can be applied to the probability of occurrence of each candidate word string in the obtained text in accordance with a determination that the degree of similarity between the input context and the first context is high. Conversely, a smaller weighting factor can be applied to the probability of occurrence of each candidate word string in the obtained text in accordance with a determination that the degree of similarity between the input context and the first context is low. Similarly, the overall probability can be based on a degree of similarity between the input context and the second context in examples where second text associated with a second context is obtained at block 502.

At block 516 of process 500, a portion of the plurality of candidate word strings can be displayed (e.g., using touch screen 946) for selection by the user. For example, as shown in FIG. 6A, candidate word strings 606 can be displayed in language input interface 608. Candidate word strings 606 can include a portion of the plurality of candidate word strings determined at block 508. The portion of the plurality of candidate word strings that is displayed can be based on the ranking of block 514. For example, the N highest ranked candidate word strings can be displayed, where N is a predetermined number. Further, the displayed portion of the plurality of candidate word strings can be arranged based on the ranking of block 514. In particular, the displayed portion of the plurality of candidate word strings can be arranged in decreasing order from the highest ranked candidate word string (e.g., candidate word string 612 “”) to the lowest ranked candidate word string (e.g., candidate word string 613 “”).

It should be recognized that the ranking of block 514 may not be based on a deterministic rule where a particular candidate word string (e.g., “”) is always determined to rank within the top N candidate word strings whenever a particular sequence of symbols (e.g., pinyin input “liumingjie”) is received. Rather, the ranking of block 514 and thus the portion of the plurality of candidate word strings displayed at block 516 can dynamically change based on the text inputted by the user over time. Further, as described above, the plurality of candidate word strings displayed at block 516 can change in accordance with different input contexts associated with the input received at block 506.

At block 518 of process 500, a selection of a candidate word string from the displayed portion of the plurality of candidate word strings can be detected (e.g., via touch screen 946). For example, as shown in FIG. 6A, a selection of candidate word string 612 “” can be detected via language input interface 608. Candidate word string 612 “” can be the word string that pinyin input 604 “liumingjie” is intended to represent. In response to detecting the selection of the candidate word string, block 520 can be performed.

At block 520 of process 500, the selected candidate word string can be displayed in a text field of the device. For example, as shown in FIG. 6B, selected candidate word string 612 “” can be displayed in text field 610. In particular, display of pinyin input 604 “liumingjie” can be replaced by the display of selected candidate word string 612 “.” In this example, the text field can be the body of a word processing document. In other examples, the text field can be any field of an application where text can be entered. For example, the text field can be a text field for composing a text message, the body of a draft email message, or the search field of a web browser.

At block 522 of process 500, an indication that the user has committed to the selected candidate word string can be received (e.g., via a user interface on touch screen 946). In some examples, the indication can be a full stop input for a sentence containing the selected candidate word string. For example, as shown in FIG. 6C, full stop 614 can be inputted at the end of sentence 616 containing the selected candidate word string 612 “.” Full stop 614 can thus be an indication that the user has committed to the selected candidate word string 612 “.” In other examples, the indication can be a command to store text containing the selected candidate word string on the device. In yet other examples, the indication can be a command to send a message, email, document, search string, or the like containing the candidate word string to a device separate from the user device. In response to receiving the indication, block 524 can be performed.

At block 524 of process 500, the first language model can be updated using the selected candidate word string. For example, in the example shown in FIG. 6C, sentence 616 and selected candidate word string 612 “” can be used to train the first language model. In particular, the selected candidate word string can be used to increase the probability of occurrence of the selected candidate word string in the first language model. In this way, the first language model can be dynamically updated to better predict the language input characteristics of the user.

At block 526 of process 500, a predicted word of the second symbolic system can be determined. The predicted word can be determined using the predictive text methods described above with respect to processes 200, 300, or 400. For instance, the predicted word can be determined based on a probability of occurrence of a sequence of words in the obtained text. In some examples, the sequence of words can include the predicted text and one or more words of the selected candidate word string. Specifically, the predicted word can be determined based on a probability of occurrence of the predicted word in the obtained text given one or more words of the selected candidate word string.

At block 528 of process 500, the predicted word can be displayed (e.g., using touch screen 946) for user selection. For example, as shown in FIG. 6B, a plurality of candidate predicted words 618 can be displayed in language input interface 608. In this example, predicted word 620 “” can have the highest probability of occurrence given one or more words of selected candidate word string 612 “.” In other examples, predicted word 620 can be alternatively or additionally displayed adjacent to selected candidate word string 612 “” in text field 610.

Although process 500 is described above with reference to blocks 502 through 528, it should be appreciated that, in some cases, one or more blocks of process 500 can be optional and additional blocks can also be performed.

Turning now to FIGS. 7A-D, exemplary process 700 for predictive conversion of language input is described below. FIGS. 8A-F illustrate exemplary screenshots of a user device at various stages of exemplary process 700. Process 700 is described below with simultaneous reference to FIGS. 7A-D and FIGS. 8A-F.

At block 702 of process 700, text composed by the user can be obtained. Block 702 can be similar or identical to block 502 of process 500, described above. The obtained text can be text currently being inputted by the user on the user device (e.g., via touch screen 946). Alternatively or additionally, the obtained text can be text previously composed by the user and stored remotely (e.g., in user data and models 1020) or on the user device (e.g., in user data and models 966).

The obtained text can include words of a second symbolic system of a language. For example, the second symbolic system can include Chinese characters (e.g., Han characters). It should be recognized that, in other examples, the second symbolic system can be any script type of any language.

In some examples, the obtained text can be associated with a first context. The first context can be any context discussed above with respect to processes 200, 300, or 400. For example, the first context can include a first recipient and a first application of the device. In another example, the first context can be a context determined using a sensor of the device. It should be appreciated that additional text composed by the user and associated with other contexts can be obtained. For example, block 702 can further include obtaining second text composed by the user where the second text is associated with a second context that is different from the first context.

At block 704 of process 700, a first language model can be generated using the text composed by the user. Block 704 can be similar or identical to block 504 of process 500, described above. In some examples, the first language model can be an n-gram language model. It should be recognized that other types of language models can be contemplated.

At block 706 of process 700, first input can be received (e.g., via a user interface on touch screen 946) from a user. The first input can include a sequence of symbols of a first symbolic system. The sequence of symbols can represent a sequence of three or more words of a second symbolic system. The first symbolic system can be different from the second symbolic system. In some examples, the first symbolic system can be the pinyin phonetic system for transcription of Mandarin Chinese. It should be recognized that, in other examples, the first symbolic system can include other symbolic systems such as Chinese Zhuyin, Japanese hiragana, or other types of written scripts.

In one example, as shown in FIG. 8A, first input 804 can be received from a user via keyboard interface 802 and displayed in text field 810. First input 804 includes the sequence of symbols “liumingjie” of the pinyin phonetic system. In this example, first input 804 “liumingjie” can be intended to represent the sequence of three monosyllabic Chinese words “”.

At block 708 of process 700, a plurality of candidate word strings corresponding to the sequence of symbols can be displayed in a language input interface (e.g. using touch screen 946). For example, the plurality of candidate word strings can be determined, ranked, and displayed in a similar manner as described in blocks 508-516 above. Each candidate word string of the plurality of candidate word strings can include two or more words of the second symbolic system. In some examples, each candidate word string can include one or more words of the second symbolic system. In the examples depicted in FIGS. 8A-F, each word can be a monosyllabic Chinese character.

As shown in FIG. 8A, candidate word strings 806 are displayed in language input interface 808. Each of candidate word strings 806 can correspond to at least a portion of first input 804 “liumingjie.” In this example, candidate word strings 806 include “,”“,” and “,” which each include two or more Chinese words. As shown, displayed candidate word strings 806 do not include the intended sequence of three Chinese words “.” In particular, “” is a person's name, which may not be commonly found in general corpuses of Chinese texts. Further, the user may not have previously inputted the Chinese words “” on user device. Thus, the probability of occurrence of “” in a general corpus of Chinese text or in Chinese text composed by the user can be low, which may result in “” not being ranked high enough to be displayed in language input interface 808.

At block 710 of process 700, second input indicating that the sequence of symbols of the first symbolic system correspond to the intended sequence of three or more words of the second symbolic system can be received (e.g., via a user interface on touch screen 946) from the user. The second input can include mapping individual words of the second symbolic system to respective portions of the sequence of symbols. In this way, the user device can learn the sequence of three of more words that are intended to correspond to the first input. In some examples, block 710 can include one or more of blocks 712-716.

At block 712 of process 700, a selection of the first word corresponding to a first portion of the sequence of symbols can be received. For example, as shown in FIG. 8A, first word 812 “,” which is intended to correspond to the first portion “liu” of first input 804, can be selected via language input interface 808. As shown in FIG. 8B, in response to receiving the selection of first word 812 “,” first word 812 “” can be displayed in lieu of the first portion “liu” of first input 804 in text field 810. Further, candidate words 814 corresponding to at least a portion of “mingjie” of pinyin input 804 can be displayed in language input interface 808.

At block 714 of process 700, a selection of the second word corresponding to a second portion of the sequence of symbols can be received. For example, as shown in FIG. 8B, second word 816 “,” which is intended to correspond to the second portion “ming” of first input 804, can be selected via language input interface 808. As shown in FIG. 8C, in response to receiving the selection of second word 816 “,” second word 816 “” can be displayed in lieu of the second portion “ming” of first input 804 in text field 810. Further, candidate words 818 corresponding to “jie” of pinyin input 804 can be displayed in language input interface 808.

At block 716 of process 700, a selection of the third word corresponding to a third portion of the sequence of symbols can be received. For example, as shown in FIG. 8C, third word 820 “,” which is intended to correspond to the third portion “jie” of first input 804, can be selected via language input interface 808. As shown in FIG. 8D, in response to receiving the selection of third word 820 “,” third word 820 “” can be displayed in lieu of the third portion “jie” of first input 804 in text field 810.

Although in the present example described above, the second input includes mapping individual words of the second symbolic system to respective portions of the sequence of symbols, it should be recognized that other input methods can be contemplated to achieve the mapping. For example, the second input could alternatively include selecting “” via language input interface 808 to correspond to “liuming” and then selecting “” via language input 808 to correspond to “jie.”

At block 718 of process 700, the first language model can be updated using the second input. Block 718 can be similar or identical to block 524 described above. In particular, the word string “” can be used to train the first language model to increase the probability of occurrence of “” in the obtained text. By dynamically updating the first language model, the word string “” can be more likely to be displayed in language input interface 808 when the pinyin input “liumingjie” is received in the future. It should be appreciated that the updating of block 718 may not create a fixed deterministic rule where the word string “” is always be displayed in language input interface 808 when the pinyin input “liumingjie” is received. Rather, the updating of block 718 can incorporate the second input as part of the obtained collection of text composed by the user and can dynamically adjust the probability of occurrence of “” in the obtained collection of text composed by the user.

In some examples, block 718 can be performed in response to receiving an indication that the user has committed to the second input. The indication can be similar or identical to the indication discussed above in block 522. In particular, the indication can be a full stop input received at the end of a sentence containing “” of the second input. In other examples, the indication can be a command to send text containing “” of the second input. After receiving the second input at block 710, one or more of blocks 718-734 can be performed.

At block 720 of process 700, third input can be received (e.g., via a user interface on touch screen 946). The third input can include the first word (e.g., “”) and the second word (e.g., “”) of the intended sequence of three or more words (e.g., “”) of the second symbolic system. In some examples, block 720 can include blocks 722-726.

At block 722 of process 700, a second sequence of symbols of the first symbolic system can be received. The second sequence of symbols can be intended to correspond to the first word and the second word of the intended sequence of three or more words of the second symbolic system. For example, as shown in FIG. 8E, second sequence of symbols 828 can be received and displayed in text field 810. As shown in this example, second sequence of symbols 828 is the pinyin input “liuming.” In response to receiving the second sequence of symbols, block 724 can be performed.

At block 724 of process 700, the first word and the second word of the intended sequence of three or more words can be displayed as candidate words that correspond to a first and second portion of the second sequence of symbols, respectively. For example, as shown in FIG. 8E, candidate words 831 corresponding to a first and second portion of second sequence of symbols 828 can be displayed. In particular, first word 830 “” and second word 832 “” corresponding to second sequence of symbols 828 “liuming” can be displayed in language input interface 808. In this example, first word 830 “” and second word 832 “” are displayed together as a candidate word string. In other examples, first word 830 “” and second word 832 “” can be displayed separately as individual words. Further, first word 830 “” and second word 832 “” can be displayed at separate instances.

At block 726, a selection of the first word and the second word of the intended sequence of three or more words can be received. For example, with reference to FIG. 8E, a selection of first word 830 “” and second word 832 “” can be received via language input interface 808. In this example, first word 830 “” and second word 832 “” can be selected together as a candidate word string. It should be recognized that, in other examples, first word 830 “” and second word 832 “” can be selected separately. As shown in FIG. 8F, in response to receiving the selection of first word 830 “” and second word 832 “”, first word 830 “” and second word 832 “” can be displayed in text field 810. In particular, display of second sequence of symbols 828 “liuming” in text field 810 can be replaced with display of first word 830 “” and second word 832 “.”

In some examples, the third input can be associated with an input context. The input context can be similar to that described above at block 506. In particular, the input context can be any context described above in process 200, 300, 400, or 500. For example, the input context can include a second recipient and a second application of the device. Further, in some examples, input context can be a context determined using a sensor of the user device. In particular, as described above with respect to processes 200, 300, or 400, input context can be a physical context determined using a sensor of the user device.

At block 728 of process 700, the probability of occurrence of the intended sequence of three or more words in the text composed by the user can be determined using the first language model. In the present example, the probability of occurrence of the 3-gram “” in the text obtained in block 702 can be determined using the first language model.

At block 730 of process 700, a probability of occurrence of the sequence of three or more words in a corpus of text can be determined using a second language model. The corpus of text can be text that is not composed by the user. In the present example, the probability of occurrence of the 3-gram “” in the corpus of text can be determined using the second language model.

At block 732 of process 700, a predicted word based on the first word and the second word of the sequence of three or more words can be determined. In this example, the determined predicted word can include the third word (e.g, “”) of the sequence of three or more words. The predicted word can be determined using predictive text methods described above in processes 200, 300, or 400. In particular, the predicted word can be determined based on the probability of occurrence of the predicted word given the first word and the second word of the sequence of three of more words.

In some examples, the predicted word can be determined using the probability of occurrence of the sequence of three or more words in the text composed by the user. In examples where the text obtained at block 702 is associated with the first context, the predicted text can be determined based on a degree of similarity between the input context and the first context. In particular, as described above, the probability of occurrence of the sequence of three or more words in the text obtained at block 702 can be weighted based on the degree of similarity between the input context and the first context. Further, in examples where second text is obtained at block 702 and the second text is associated with a second context, the predicted word can be determined based on the probability of occurrence of the sequence of three or more words in the second text. The probability of occurrence of the sequence of three or more words in the second text can be weighted based on the degree of similarity between the input context and the second context.

In some examples, the predicted word can be determined based on the probability of occurrence of the sequence of three or more words in the corpus of text. In particular, the predicted word can be determined based on a combined probability of occurrence of the predicted word given the first word and the second word of the sequence of three or more words. The combined probability can be determined based on one or more of the probability of occurrence of the sequence of three or more words in the corpus of text, the probability of occurrence of the sequence of three or more words in the text obtained in block 702, or the probability of occurrence of the sequence of three or more words in the second text obtained in block 702. Further, as described above, each of the probabilities can be weighted using suitable weighting factors. In particular, the weighting factors can be based on the degree of similarity between the input context and the first context. In examples where second text is obtained in block 702, the weighting factors can be based on the degree of similarity between the input context and the second context.

At block 734 of process 700, the predicted word can be displayed (e.g., using touch screen 946) for user selection. For example, as shown in FIG. 8F, candidate predicted words 835 can be displayed in language input interface 808 for user selection. Candidate predicted words 835 can be displayed based on the probability of occurrence of each predicted word given first word 830 “” and second word 832 “.” As shown in FIG. 8F, candidate predicted words 835 can include predicted word 834 “.” In this example, predicted word 834 “” can have the highest probability of occurrence given first word 830 “” and second word 832 “.” Additionally or alternatively, as shown in FIG. 8F, predicted word 834 “” can be displayed in the text field adjacent to the displayed second word 832 “” (as indicated by brackets 836).

Although process 700 is described above with reference to blocks 702 through 734, it should be appreciated that, in some cases, one or more blocks of process 700 can be optional and additional blocks can also be performed.

5. User Device for Predictive Text Input

FIG. 9 is a block diagram of user device 900 for carrying out various aspects of predictive text input according to various examples. User device 900 can be any electronic device that is configured to receive a text input. For example, user device 900 can include a cellular telephone (e.g., smartphone), tablet computer, laptop computer, desktop computer, portable media player, wearable digital device (e.g., digital glasses, wristband, wristwatch, brooch, armbands, etc.), television, set top box (e.g., cable box, video player, video streaming device, etc.), gaming system, or the like. As shown in FIG. 9, user device 900 can include a memory interface 902, one or more processors 904, and a peripherals interface 906. The various components in user device 900 can be together coupled by one or more communication buses or signal lines. User device 900 can further include various sensors, subsystems, and peripheral devices that are coupled to peripherals interface 906. The sensors, subsystems, and peripheral devices gather information and/or facilitate various functionalities of user device 900.

In some examples, user device 900 can include a motion sensor 910, a light sensor 912 (e.g., a brightness sensor), and a proximity sensor 914 coupled to peripherals interface 906 to facilitate orientation, light, and proximity sensing functions. One or more other sensors 916, such as a positioning system (e.g., a GPS receiver), a temperature sensor, a biometric sensor, a gyroscope, a compass, an accelerometer (e.g., a motion sensor), and the like, are also connected to peripherals interface 906 to facilitate related functionalities. Further, the various sensors of user device 900 described above can be used to determine an input context at block 202 of process 200 or a physical context at block 404 of process 400.

In some examples, a camera subsystem 920 and an optical sensor 922 (e.g., an image sensor or brightness sensor) can be utilized to facilitate camera functions, such as taking photographs and recording video clips. Communication functions can be facilitated through one or more wired and/or wireless communication subsystems 924, which can include various communication ports, radio frequency receivers and transmitters, and/or optical (e.g., infrared) receivers and transmitters. An audio subsystem 926 can be coupled to speakers 928 and a microphone 930 to facilitate audio-enabled functions, such as voice recognition, music recognition, voice replication, digital recording, telephony functions, and speech-to-text conversion. In one example, the text input at block 202, 302, and 402 described above can be received by means of speech-to-text conversion facilitated by microphone 930. Optical sensor 922 and microphone 930 can be used to determine an input context at block 202 of process 200 or a physical context at block 404 of process 400.

In some examples, user device 900 can further include an I/O subsystem 940 coupled to peripherals interface 906. I/O subsystem 940 can include a touch screen controller 942 and/or other input controller(s) 944. Touch-screen controller 942 can be coupled to a touch screen 946. Touch screen 946 and the touch screen controller 942 can, for example, detect contact and movement or a break thereof using any of a plurality of touch sensitivity technologies, such as capacitive, resistive, infrared, surface acoustic wave technologies, proximity sensor arrays, and the like. Other input controller(s) 944 can be coupled to other input/control devices 948, such as one or more buttons, rocker switches, a thumb-wheel, an infrared port, a USB port, and/or a pointer device such as a stylus. In some examples, a signal to begin receiving an audio input can be received by user device 900 via input to touch screen 946 (e.g., a virtual button) or other input/control devices 948. The text input at blocks 202, 302, and 402 can be received via touch screen 946 and/or other input/control devices 948.

In some examples, user device 900 can further include a memory interface 902 coupled to memory 950. Memory 950 can include any electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, a portable computer diskette (magnetic), a random access memory (RAM) (magnetic), a read-only memory (ROM) (magnetic), an erasable programmable read-only memory (EPROM) (magnetic), a portable optical disc such as CD, CD-R, CD-RW, DVD, DVD-R, or DVD-RW, or flash memory such as compact flash cards, secured digital cards, USB memory devices, memory sticks, and the like. In some examples, a non-transitory computer-readable storage medium of memory 950 can be used to store instructions (e.g., for performing processes 200, 300, 400, 500, or 700, described above) for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In other examples, the instructions (e.g., for performing processes 200, 300, 400, 500, or 700, described above) can be stored on a non-transitory computer-readable storage medium of server system 1010 described below, or can be divided between the non-transitory computer-readable storage medium of memory 950 and the non-transitory computer-readable storage medium of server system 1010.

In some examples, memory 950 can store an operating system 952, a communication module 954, a graphical user interface module 956, a sensor processing module 958, a phone module 960, and applications 962. Operating system 952 can include instructions for handling basic system services and for performing hardware dependent tasks. Communication module 954 can facilitate communicating with one or more additional devices, one or more computers, and/or one or more servers. Graphical user interface module 956 can facilitate graphic user interface processing. Sensor processing module 958 can facilitate sensor related processing and functions. Phone module 960 can facilitate phone-related processes and functions. Applications module 962 can facilitate various functionalities of user applications, such as electronic-messaging, web browsing, media processing, navigation, imaging, virtual assistant functions, and/or other processes and functions.

As described herein, memory 950 can also store predictive text input module 964 and various user data and models 966 to provide the client-side functionalities of the virtual assistant. The predictive text input module 964 can include modules, instructions, and programs for performing various aspects of processes 200, 300, 400, 500, or 700 described above. User data and models 966 can include various language models, look-up tables, and text described above with respect to processes 200, 300, 400, 500, or 700 that are used for predictive text input. For example, user data and models 966 can include user language models built using a corpus that includes a collection of user text.

In various examples, memory 950 can include additional instructions or fewer instructions. Furthermore, various functions of user device 900 can be implemented in hardware and/or in firmware, including in one or more signal processing and/or application specific integrated circuits. Further, processes for predictive text input described above can be implemented as a stand-alone application installed on user device 900. Alternatively, processes for predictive text input can be implemented according to a client-server model as described below with reference to FIG. 10.

6. System for Predictive Text Input

FIG. 10 illustrates exemplary client-server system 1000 for carrying out various aspects of predictive text input according to various examples. System 1000 can include a client-side portion executed on user device 900 and a server-side portion executed on server system 1010. User device 900 can communicate with server system 1010 through one or more networks 1008, which can include the Internet, an intranet, or any other wired or wireless public or private network. The client-side portion executed on user device 900 can provide client-side functionalities, such as user-facing input and output processing and communications with server system 1010. Server system 1010 can provide server-side functionalities for any number of clients residing on a respective user device 900.

As shown in FIG. 10, server system 1010 can include memory 1028, one or more processors 1026, client-facing I/O interface 1022, and I/O interface to external services 1016. The various components of server system 1010 can be coupled together by one or more communication buses or signal lines. Memory 1028, or the computer-readable storage media of memory 1028, can include one or more processing modules 1018 and user data and model storage 1020. The one or more processing modules 1018 can include various programs and instructions. The one or more processors 1026 can execute the programs and instructions of the one or more processing modules 1018 and read/write to/from user data and model storage 1020. In the context of this document, a “non-transitory computer-readable storage medium” can be any medium that can contain or store the program for use by or in connection with the instruction execution system, apparatus, or device.

In some examples, the one or more processing modules 1018 can include various programs and instructions for performing various aspects of processes 200, 300, 400, 500, or 700, described above. In particular, the one or more processing modules 1018 can include a predictive text input module for performing various aspects of processes 200, 300, 400, 500, or 700 described above. User data and models 1020 can include various user data and models that can be accessed or referenced when performing various aspects of predictive text input. For example, user data and models 1020 can include various language models used for predictive text input described above with reference to processes 200, 300, 400, 500, or 700. Further user data can include various user application data that can be used to determine an input context or a physical context associated with a received text input.

In some examples, system server 1010 can communicate with external services 1024, such as telephony services, calendar services, information services, messaging services, navigation services, and the like, through network(s) 1008. In some examples, external services can provide relevant application data for determining input context or physical context associated with a received text input. Further, in some examples, system server 1010 can access one or more language models stored on external services 1024 for performing predictive text input. The I/O interface to external services 1016 can facilitate communications between system server 1010 and external services 1024.

Server system 1010 can be implemented on one or more stand-alone data processing devices or a distributed network of computers. In some examples, server system 1010 can employ various virtual devices and/or services of third-party service providers (e.g., third-party cloud service providers) to provide the underlying computing resources and/or infrastructure resources of server system 1010.

The division of functionalities between the client and server portions of the virtual assistant can vary in different examples. For instance, in some examples, one or more processing modules 1018 and user data and models 1020 can be stored in the memory of user device 900 to enable the user device to perform a greater proportion or all of the functionalities associated with predictive text input. In other examples, the client executed on user device 900 can be a thin-client that provides only user-facing input and output processing functions, and delegates all other functionalities of predictive text input to a back-end server.

7. Electronic Device

FIG. 11 shows a functional block diagram of an electronic device 1100 configured in accordance with the principles of the various described examples. The functional blocks of the device can be, optionally, implemented by hardware, software, or a combination of hardware and software to carry out the principles of the various described examples. It is understood by persons of skill in the art that the functional blocks described in FIG. 11 can be, optionally, combined or separated into sub-blocks to implement the principles of the various described examples. Therefore, the description herein optionally supports any possible combination, separation, or further definition of the functional blocks described herein.

As shown in FIG. 11, electronic device 1100 can include touch screen display unit 1102 configured to display a user interface for receiving text input and to receive touch input, and text receiving unit 1104 configured to receive text input. In some examples, electronic device 1100 can include sensor unit 1106 that is configured to sense a physical context. Sensor unit 1106 can include any sensor for sensing a physical context, such as, for example, a microphone, an image sensor, a brightness sensor, a motion sensor, a GPS sensor, and the like. Electronic device 1100 can further include processing unit 1110 coupled to touch screen display unit 1102 and text receiving unit 1104 (and, optionally, coupled to sensor unit 1106). In some examples, processing unit 1110 can include receiving unit 1112, frequency of occurrence determining unit 1114, weighting factor determining unit 1116, weighted probability determining unit 1118, probability determining unit 1120, language model updating unit 1122, and presenting unit 1124.

Processing unit 1110 can be configured to receive a text input (e.g., from text receiving unit 1104 and using receiving unit 1112). The text input can be associated with an input context. Processing unit 1110 can be configured to determine, using a first language model, a first frequency of occurrence of an m-gram with respect to a first subset of a corpus (e.g., using frequency of occurrence determining unit 1114). The first subset can be associated with a first context and the m-gram can include at least one word in the text input. Processing unit 1110 can be configured to determining (e.g., using weighting factor determining unit 1116), based on a degree of similarity between the input context and the first context, a first weighting factor to apply to the first frequency of occurrence of the m-gram. Processing unit 1110 can be configured to determining (e.g., using weighted probability determining unit 1118), based on the first frequency of occurrence of the m-gram and the first weighting factor, a first weighted probability of a first predicted text given the text input. The m-gram can include at least one word in the first predicted text.

In some examples, processing unit 1110 can be configured to determine, using the first language model, a second frequency of occurrence of the m-gram with respect to a second subset of the corpus (e.g., using frequency of occurrence determining unit 1114). The second subset can be associated with a second context. Processing unit 1110 can be configured to determine (e.g., using weighting factor determining unit 1116), based on a degree of similarity between the input context and the second context, a second weighting factor to apply to the second frequency of occurrence of the m-gram. Processing unit 1110 can be configured to determine the first weighted probability of the first predicted text given the text input (e.g., using weighted probability determining unit 1118) based on the second frequency of occurrence of the m-gram and the second weighting factor.

In some examples, the first context and the second context can be different, and the first weighting factor and the second weighting factor can be different.

In some examples, processing unit 1110 can be configured to determine, using the first language model, a first frequency of occurrence of an (m−1)-gram with respect to the first subset of the corpus (e.g., using frequency of occurrence determining unit 1114). The m-gram can include one or more words in the (m−1)-gram. Processing unit 1110 can be configured to determine the first weighted probability of the first predicted text given the text input (e.g., using weighted probability determining unit 1118) based on a first weighted frequency of occurrence of the (m−1)-gram. The first weighting factor can be applied to the first frequency of occurrence of the (m−1)-gram to obtain the first weighted frequency of occurrence of the (m−1)-gram.

In some examples, the first language model can be a user language model that is built from the corpus and the corpus can include a collection of user input text received prior to receiving the text input.

In some examples, processing unit 1110 can be configured to update (e.g., using language model updating unit 1122) the first language model using the text input.

In some examples, processing unit 1110 can be configured to determine, using a second language model, a probability of the first predicted text given the text input (e.g., using probability determining unit 1120). Processing unit 1110 can be configured to determine (e.g., using weighted probability determining unit 1118) a second weighted probability of the first predicted text given the text input based on the first weighted probability of the first predicted text given the text input and the probability of the first predicted text given the text input.

In some examples, processing unit 1110 can be configured to apply a third weighting factor to the first weighted probability of the first predicted text given the text input and apply a fourth weighting factor to the probability of the first predicted text given the text input (e.g., using weighted probability determining unit 1118) to determine the second weighted probability of the first predicted text given the text input.

In some examples, the first language model can be built from the corpus. The corpus can include a plurality of subsets where each subset can be associated with a context of a plurality of contexts. Each context of the plurality of contexts can be represented by one or more hierarchical context tags of the first language model.

In some examples, the first language model can include a plurality of n-grams including the m-gram where each n-gram of the plurality of n-grams can be associated with one or more hierarchical context tags and a frequency of occurrence of the n-gram with respect to a subset of the corpus.

In some examples, the first language model can include a plurality of sub-models arranged in a hierarchical context tree where each sub-model can be associated with a specific context.

In some examples, the first weighted probability of the first predicted text given the text input can be greater than a predetermined threshold. Processing unit 1110 can be configured to determine, using the first language model, a frequency of occurrence of an (m+1)-gram with respect to the first subset of the corpus (e.g., using frequency of occurrence determining unit 1114). The (m+1)-gram can include one or more words in the m-gram. Processing unit 1110 can be configured to determine (e.g., using weighted probability determining unit 1118), based on the frequency of occurrence of the (m+1)-gram and the first weighting factor, a weighted probability of a second predicted text given the text input and the first predicted text. The (m+1)-gram can include at least one word in the second predicted text.

In some examples, the first context can include a first application of the electronic device and the first subset can include a collection of user text that is associated with the first application.

In some examples, the first context can include a first recipient and the first subset can include a collection of user text that is directed to the first recipient. In some examples, the first context can include a physical context determined using a sensor of the electronic device (e.g., sensor unit 1106). The first subset can include a collection of user text that is associated with the physical context.

In some examples, the first context can include a time period or a location and the first subset can include a collection of user text that is associated with the time period or the location.

In some examples, the first context can include an environment, a situation, or a circumstance and the first subset can include a collection of user text that is associated with the environment, the situation, or the circumstance.

In some examples, the text input can be associated with a second application of the electronic device and the input context can include the second application. In some examples, the text input can be directed to a second recipient, and wherein the input context includes the second recipient. In some examples, the second recipient can be determined based on the text input and using the first language model. In some examples, the input context can be determined using a sensor of the electronic device (e.g., sensor unit 1106). In some examples, the input context can be determined from data obtained from one or more applications of the electronic device.

In some examples, processing unit 1110 can be configured to presenting (e.g., using presenting unit 1124) the first predicted text via a user interface of the electronic device.

In some examples, processing unit 1110 can be configured to receive (e.g., from text receiving unit 1104 and using receiving unit 1112) a first text input where the first text input can be associated with a first input context. Processing unit 1110 can be configured to determine, using a language model and based on the first input context, a first weighted probability of a predicted text given the first text input (e.g., using one or more of frequency of occurrence determining unit 1114, weighting factor determining unit 1116, weighted probability determining unit 1118, and probability determining unit 1120). Processing unit 1110 can be configured to receive (e.g., from text receiving unit 1104 and using receiving unit 1112) a second text input where the second text input can be associated with a second input context. The first text input can be identical to the second text input and the first input context can be different from the second input context. Processing unit 1110 can be configured to determine, using the language model and based on the second input context, a second weighted probability of the predicted text given the second text input (e.g., using one or more of frequency of occurrence determining unit 1114, weighting factor determining unit 1116, weighted probability determining unit 1118, and probability determining unit 1120). The first weighted probability can be different from the second weighted probability. In some examples, the language model can be similar or identical to the first language model described above.

In some examples, the first text input can be associated with a first application of the electronic device and the first input context can include the first application. The second text input can be associated with a second application of the electronic device and the second input context can include the second application. The first application can be different from the second application.

In some examples, the first text input can be directed to a first recipient and the first input context can include the first recipient. The second text input can be directed to a second recipient and the second input context can include the second recipient. The first recipient can be different from the second recipient.

In some examples, the first recipient can be determined based on the first text input and using a second language model. In some examples, the first input context can be determined using a sensor of the electronic device (e.g., sensor unit 1106). In some examples, the first input context can be determined using data obtained from one or more applications of the electronic device.

FIG. 12 shows a functional block diagram of an electronic device 1200 configured in accordance with the principles of the various described examples. The functional blocks of the device can be, optionally, implemented by hardware, software, or a combination of hardware and software to carry out the principles of the various described examples. It is understood by persons of skill in the art that the functional blocks described in FIG. 12 can be, optionally, combined or separated into sub-blocks to implement the principles of the various described examples. Therefore, the description herein optionally supports any possible combination, separation, or further definition of the functional blocks described herein.

As shown in FIG. 12, electronic device 1200 can include touch screen display unit 1202 configured to display a user interface for receiving text input and to receive touch input, and text receiving unit 1204 configured to receive text input. In some examples, electronic device 1200 can include sensor unit 1206 that is configured to sense a physical context. Sensor unit 1206 can include any sensor for sensing a physical context, such as, for example, a microphone, an image sensor, a brightness sensor, a motion sensor, a GPS sensor, and the like. Electronic device 1200 can further include processing unit 1210 coupled to touch screen display unit 1202 and text receiving unit 1204 (and, optionally, coupled to sensor unit 1206). In some examples, processing unit 1210 can include receiving unit 1212, physical context determining unit 1214, frequency of occurrence determining unit 1216, weighting factor determining unit 1218, weighted probability determining unit 1220, probability determining unit 1222, language model updating unit 1224, and presenting unit 1226.

Processing unit 1210 can be configured to receive a text input (e.g., from text receiving unit 1204 and using receiving unit 1212). Processing unit 1210 can be configured to determine (e.g., using physical context determining unit 1214) a physical context associated with the text input. Processing unit 1210 can be configured to determine, using a first language model and the physical context, a first weighted probability of a predicted text given the text input (e.g., using one or more of frequency of occurrence determining unit 1216, weighting factor determining unit 1218, weighted probability determining unit 1220, and probability determining unit 1222). Processing unit 1210 can be configured to present (e.g., using presenting unit 1226) the predicted text via a user interface of the electronic device.

In some examples, the physical context can be determined using a sensor of the electronic device (e.g., sensor unit 1206). In some examples, the physical context can be determined using data obtained from an application of the electronic device.

In some examples, processing unit 1210 can be configured to determine, using the first language model, a first probability of the predicted text given the text input (e.g., using probability determining unit 1222). Processing unit 1210 can be configured to determine (e.g., using weighting factor determining unit 1218), based on the physical context, a first weighting factor to apply to the first probability of the predicted text given the text input. Processing unit 1210 can be configured to determine (e.g., using weighted probability determining unit 1220) the first weighted probability of the predicted text given the text input based on the first probability of the predicted text given the text input and the first weighting factor.

In some examples, the first language model can be a class-based language model that includes a first sub-model. The first sub-model can be associated with the physical context. Processing unit 1210 can be configured to determine, using the first language model, a probability of a class given the input text (e.g., using probability determining unit 1222). Processing unit 1210 can be configured to determine, using the first sub-model, a first probability of the predicted text given the class (e.g., using probability determining unit 1222). The first weighted probability of the predicted text given the text input can be determined based on the probability of the class given the input text and the first probability of the predicted text given the class. In some examples, the first language model can include a second sub-model. The second sub-model can be associated with a general context. Processing unit 1210 can be configured to determine, using the second sub-model, a second probability of the predicted text given the class (e.g., using probability determining unit 1222). The first weighted probability of the predicted text given the text input can be determined based on the first probability of the predicted text given the class.

In some examples, the first language model can be a general language model. In some examples, the first language model can be a user language model that is built from a corpus where the corpus can include a collection of user input text received prior to receiving the text input. In some examples, processing unit 1210 can be configured to update (e.g., using language model updating unit 1224) the first language model using the text input and the predicted text.

In some examples, the physical context can include a time period. In some examples, the time period can be determined from data obtained from an application of the electronic device. The application can be one of a clock application, a scheduler application, and a weather application.

In some examples, the physical context can include an environment, a situation, or a circumstance experienced by a user of the electronic device when the text input is received. In some examples, the environment, the situation, or the circumstance can be determined using a microphone of the electronic device (e.g., sensor unit 1206). In some examples, the environment, the situation, or the circumstance can be determined using a light sensor or an image sensor of the electronic device (e.g., sensor unit 1206). In some examples, the environment, the situation, or the circumstance can be determined using a motion sensor of the electronic device (e.g., sensor unit 1206).

In some examples, the first language model can be built from a corpus that includes a plurality of subsets, where each subset can be associated with a context. Processing unit 1210 can be configured to determine, using the first language model, a first frequency of occurrence of an m-gram with respect to a first subset of the plurality of subsets (e.g., using frequency of occurrence determining unit 1216). The first subset can be associated with a first context and the m-gram can include at least one word in the text input and at least one word in the predicted text. Processing unit 1210 can be configured to determine (e.g., using weighting factor determining unit 1218), based on a degree of similarity between the physical context and the first context, a first weighting factor to apply to the first frequency of occurrence of the m-gram. The first weighted probability can be based on the first frequency of occurrence of the m-gram and the first weighting factor.

In some examples, processing unit 1210 can be configured to determine, using the first language model, a second frequency of occurrence of the m-gram with respect to a second subset of the plurality of subsets (e.g., using frequency of occurrence determining unit 1216). The second subset can be associated with a second context. Processing unit 1210 can be configured to determine, based on a degree of similarity between the input context and the second context, a third weighting factor to apply to the second frequency of occurrence of the m-gram (e.g., using frequency of occurrence determining unit 1216). The first weighted probability of the predicted text given the text input can be determined based on the second frequency of occurrence of the m-gram and the third weighting factor.

In some examples, processing unit 1210 can be configured to determine, using a second language model, a third probability of the predicted text given the text input (e.g., using probability determining unit 1222). Processing unit 1210 can be configured to determine (e.g., using weighted probability determining unit 1220) a second weighted probability of the predicted text given the text input based on the first weighted probability and the third probability. In some examples, processing unit 1210 can be configured to apply a third weighting factor to the first weighted probability and apply a fourth weighting factor to the third probability (e.g., using weighted probability determining unit 1220) to determine the second weighted probability. In some examples, the first language model can be a user language model and the second language model can be a general language model.

FIG. 13 shows a functional block diagram of an electronic device 1300 configured in accordance with the principles of the various described examples. The functional blocks of the device can be, optionally, implemented by hardware, software, or a combination of hardware and software to carry out the principles of the various described examples. It is understood by persons of skill in the art that the functional blocks described in FIG. 13 can be, optionally, combined or separated into sub-blocks to implement the principles of the various described examples. Therefore, the description herein optionally supports any possible combination, separation, or further definition of the functional blocks described herein.

As shown in FIG. 13, electronic device 1300 can include touch screen display unit 1302 configured to display a user interface for receiving language input and to receive touch input, and text input unit 1304 configured to receive text input. In some examples, electronic device 1300 can include sensor unit 1306 that is configured to sense a physical context. Sensor unit 1306 can include any sensor for sensing a physical context, such as, for example, a microphone, an image sensor, a brightness sensor, a motion sensor, a GPS sensor, and the like. Electronic device 1300 can further include processing unit 1310 coupled to touch screen display unit 1302 and text input unit 1304 (and, optionally, coupled to sensor unit 1306). In some examples, processing unit 1310 can include obtaining unit 1312, generating unit 1314, receiving unit 1316, determining unit 1318, ranking unit 1320, displaying unit 1322, detecting unit 1324, and updating unit 1326.

In some embodiments, processing unit 1310 is configured to obtain (e.g., with obtaining unit 1312) text composed by a user. Processing unit 1310 is further configured to receive (e.g., with receiving unit 1316), via touch screen display unit 1302 or text input unit 1304, input comprising a sequence of symbols of a first symbolic system. Processing unit 1310 is further configured to determine (e.g., with determining unit 1318) a plurality of candidate word strings corresponding to the sequence of symbols. Each candidate word string of the plurality of candidate word strings comprises two or more words of a second symbolic system. Processing unit 1310 is further configured to rank (e.g., with ranking unit 1320) the plurality of candidate word strings based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text. Processing unit 1310 is further configured to display (e.g., with displaying unit 1322), via touch screen display unit 1302, a portion of the plurality of candidate word strings for selection by the user based on the ranking.

In some examples, the first symbolic system is different from the second symbolic system.

In some examples, processing unit 1310 is further configured to generate (e.g., with generating unit 1314) a first language model using the obtained text. Processing unit 1310 is further configured to determine (e.g., with determining unit 1318), using the first language model, the probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text.

In some examples, the first language model is an n-gram language model.

In some examples, processing unit 1310 is further configured to receive (e.g., with receiving unit 1316), via touch screen display unit 1302, a selection of a candidate word string from the displayed portion of the plurality of candidate word strings. Processing unit 1310 is further configured to display (e.g., with displaying unit 1322), via touch screen display unit 1302, the selected candidate word string in a text field of the device.

In some examples, processing unit 1310 is further configured to receive (e.g., with receiving unit 1316), via touch screen display unit 1302, an indication that the user has committed to the selected candidate word string. Processing unit 1310 is further configured to, in response to receiving the indication, update (e.g., with updating unit 1326) the first language model using the selected candidate word string.

In some examples, processing unit 1310 is further configured to receive (e.g., with receiving unit 1316) via touch screen display unit 1302 or text input unit 1304, a full stop input for a sentence containing the selected candidate word string.

In some examples, processing unit 1310 is further configured to receive (e.g., with receiving unit 1316), via touch screen display unit 1302, a command to send a message containing the selected candidate word string.

In some examples, processing unit 1310 is further configured to determine (e.g., with determining unit 1318) a predicted word of the second symbolic system based on a probability of occurrence of a sequence of words in the obtained text. The sequence of words comprises the selected candidate word string and the predicted text. Processing unit 1310 is further configured to display (e.g., with displaying unit 1322), via touch screen display unit 1302, the predicted word adjacent to the selected candidate word string in the text field.

In some examples, the obtained text is associated with a first context, the input is associated with an input context, and ranking the plurality of candidate word strings is based on a degree of similarity between the input context and the first context.

In some examples, the first context includes a first recipient and a first application of the device. Further, the input context includes a second recipient and a second application of the device.

In some examples, the first context and input context are determined using a sensor of the device.

In some examples, processing unit 1310 is further configured to obtain (e.g., with obtaining unit 1312) second text composed by the user. The obtained second text is associated with a second context. Additionally, ranking the plurality of candidate word strings is based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the second obtained text. Further, ranking the plurality of candidate word strings is based on a degree of similarity between the input context and the second context.

In some examples, the obtained second text comprises words of the second symbolic system. In some examples, the obtained text comprises words of the second symbolic system.

In some examples, processing unit 1310 is further configured to determine (e.g., with determining unit 1318), using a second language model, a probability of occurrence of each candidate word string of the plurality of candidate word strings in a corpus of text. The corpus of text is not composed by the user. Further, ranking the plurality of candidate word strings is based on the probability of occurrence of each candidate word string of the plurality of candidate word strings in the corpus of text.

In some examples, the first symbolic system comprises a phonetic system for transcribing a language. In some examples, the first symbolic system comprises Chinese Pinyin. In some examples, the first symbolic system comprises Chinese Zhuyin. In some examples, the second symbolic system comprises Chinese characters. In some examples, each word of the two or more words is a monosyllabic Chinese word.

In some embodiments, processing unit 1310 is configured to receive (e.g., with receiving unit 1316) via touch screen display unit 1302 or text input unit 1304, first input comprising a sequence of symbols of a first symbolic system. The sequence of symbols represents an intended sequence of three or more words of a second symbolic system. Processing unit 1310 is further configured to display on a language input interface (e.g., with displaying unit 1322), via touch screen display unit 1302, a plurality of candidate word strings corresponding to the sequence of symbols. Each candidate word string of the plurality of candidate word strings comprises two or more words of the second symbolic system. The plurality of candidate word strings does not include the intended sequence of three or more words. Processing unit 1310 is further configured to receive (e.g., with receiving unit 1316) via touch screen display unit 1302 or text input unit 1304, second input indicating that the sequence of symbols of the first symbolic system corresponds to the intended sequence of three or more words of the second symbolic system. Processing unit 1310 is further configured to, after receiving the second input, receive (e.g., with receiving unit 1316) via touch screen display unit 1302 or text input unit 1304, third input comprising a first word and a second word of the intended sequence of three or more words of the second symbolic system. Processing unit 1310 is further configured to determine (e.g., with determining unit 1318) a predicted word based on the first word and the second word of the intended sequence of three or more words. The predicted word comprises a third word of the intended sequence of three or more words. Processing unit 1310 is further configured to display (e.g., with displaying unit 1322), via touch screen display unit, the predicted word for user selection.

In some examples, the first symbolic system is different from the second symbolic system.

In some examples, processing unit 1310 is further configured to receive (e.g., with receiving unit 1316) via the language input interface (e.g., displayed on touch screen display unit 1302) a selection of the first word corresponding to a first portion of the sequence of symbols, the second word corresponding to a second portion of sequence of symbols, and the third word corresponding to a third portion of sequence of symbols.

In some examples, processing unit 1310 is further configured to receive (e.g., with receiving unit 1316) via touch screen display unit 1302 or text input unit, a second sequence of symbols of the first symbolic system. The second sequence of symbols corresponds to the first word and the second word of the intended sequence of three or more words of the second symbolic system. Processing unit 1310 is further configured to display on the language input interface (e.g., with displaying unit 1322), via touch screen display unit 1302, the first word and the second word as candidate words corresponding to a first portion of the second sequence of symbols and a second portion of the second sequence of symbols, respectively. Processing unit 1310 is further configured to receive (e.g., with receiving unit 1316) via the language input interface (e.g., displayed on touch screen display unit 1302) a selection of the first word and the second word.

In some examples, processing unit 1310 is further configured to, in response to receiving the selection of the first word and the second word, display (e.g., with displaying unit 1322), via touch screen display unit 1302, the first word and the second word in a text field. The predicted word is displayed in the text field adjacent to the displayed second word.

In some examples, processing unit 1310 is further configured to obtain (e.g., with obtaining unit 1312) text composed by the user. The predicted word is determined based on a probability of occurrence of the intended sequence of three or more words in the text composed by the user.

In some examples, the obtained text comprises words of the second symbolic system.

In some examples, processing unit 1310 is further configured to generate (e.g., with generating unit 1314) a first language model using the text composed by the user. Processing unit 1310 is further configured to determine (e.g., with determining unit 1314), using the first language model, the probability of occurrence of the intended sequence of three or more words in the text composed by the user.

In some examples, the first language model is an n-gram language model.

In some examples, processing unit 1310 is further configured to update (e.g., with updating unit 1326) the first language model using the second input.

In some examples, the text composed by the user is associated with a first context, the third input is associated with an input context, and the predicted text is determined based on a degree of similarity between the input context and the first context.

In some examples, the first context includes a first recipient and a first application of the device. Further, the input context includes a second recipient and a second application of the device.

In some examples, the first context and input context are determined using a sensor of the device.

In some examples, processing unit 1310 is further configured to obtain (e.g., with obtaining unit 1312) second text composed by the user. The predicted word is determined based on a probability of occurrence of the intended sequence of three or more words in the second text composed by the user. The second text composed by the user is associated with a second context. The predicted text is determined based on a degree of similarity between the input context and the second context.

In some examples, processing unit 1310 is further configured to determine (e.g., with determining unit 1318), using a second language model, a probability of occurrence of the intended sequence of three or more words in a corpus of text. The corpus of text is not composed by the user. Further, the predicted word is determined based on the probability of occurrence of the intended sequence of three or more words in the corpus of text.

In some examples, the first symbolic system is a phonetic system for transcription of a language. In some examples, the first symbolic system comprises Chinese Pinyin. In some examples, the first symbolic system comprises Chinese Zhuyin. In some examples, the second symbolic system comprises Chinese characters. In some examples, each word of the intended sequence of three or more words is a monosyllabic Chinese word.

Although examples have been fully described with reference to the accompanying drawings, it is to be noted that various changes and modifications will become apparent to those skilled in the art. Such changes and modifications are to be understood as being included within the scope of the various examples as defined by the appended claims. For example, it should be recognized that the processes for predictive conversion of language input described above can be implemented to convert any script type of a first symbolic system to another script type of a second symbolic system. In particular, the processes can be applied to translate a first language of a first symbolic system to a second language of a second symbolic system. Further, a word of a symbolic system can refer to a character (e.g., a monosyllabic Chinese character) or a plurality of characters.

In some cases, the systems, processes, and devices described above can include the gathering and use of data available from various sources to improve the delivery to users of invitational content or any other content that may be of interest to them. The present disclosure contemplates that in some instances, this gathered data may include personal information data that uniquely identifies or can be used to contact or locate a specific person. Such personal information data can include demographic data, location-based data, telephone numbers, email addresses, home addresses, or any other identifying information.

The present disclosure recognizes that the use of such personal information data in connection with the systems, processes, and devices described above, can be used to the benefit of users. For example, the personal information data can be used to deliver targeted content that is of greater interest to the user. Accordingly, use of such personal information data enables calculated control of the delivered content. Further, other uses for personal information data that benefit the user are also contemplated by the present disclosure.

The present disclosure further contemplates that the entities responsible for the collection, analysis, disclosure, transfer, storage, or other use of such personal information data will comply with well-established privacy policies and/or privacy practices. In particular, such entities should implement and consistently use privacy policies and practices that are generally recognized as meeting or exceeding industry or governmental requirements for maintaining personal information data private and secure. For example, personal information from users should be collected for legitimate and reasonable uses of the entity and not shared or sold outside of those legitimate uses. Further, such collection should occur only after receiving the informed consent of the users. Additionally, such entities would take any needed steps for safeguarding and securing access to such personal information data and ensuring that others with access to the personal information data adhere to their privacy policies and procedures. Further, such entities can subject themselves to evaluation by third parties to certify their adherence to widely accepted privacy policies and practices.

Despite the foregoing, the present disclosure also contemplates examples in which users selectively block the use of, or access to, personal information data. That is, the present disclosure contemplates that hardware and/or software elements can be provided to prevent or block access to such personal information data. For example, in the case of advertisement delivery services, the systems and devices described above can be configured to allow users to select to “opt in” or “opt out” of participation in the collection of personal information data during registration for services. In another example, users can select not to provide location information for targeted content delivery services. In yet another example, users can select to not provide precise location information, but permit the transfer of location zone information.

Therefore, although the present disclosure broadly covers use of personal information data to implement one or more various disclosed examples, the present disclosure also contemplates that the various examples can also be implemented without the need for accessing such personal information data. That is, the various examples disclosed herein are not rendered inoperable due to the lack of all or a portion of such personal information data. For example, content can be selected and delivered to users by inferring preferences based on non-personal information data or a bare minimum amount of personal information, such as the content being requested by the device associated with a user, other non-personal information available to the content delivery services, or publicly available information.

Claims

1. A method for converting language input, the method comprising: at an electronic device having one or more processors and memory: obtaining text composed by a user;receiving, from the user, input comprising a sequence of symbols of a first symbolic system;determining a plurality of candidate word strings corresponding to the sequence of symbols, each candidate word string of the plurality of candidate word strings comprising two or more words of a second symbolic system;ranking the plurality of candidate word strings based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text; anddisplaying, based on the ranking, a portion of the plurality of candidate word strings for selection by the user.

2. The method of claim 1, wherein the first symbolic system is different from the second symbolic system.

3. The method of claim 1, further comprising: generating a first language model using the obtained text; anddetermining, using the first language model, the probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text.

4. The method of claim 3, wherein the first language model is an n-gram language model.

5. The method of claim 3, further comprising: receiving, from the user, a selection of a candidate word string from the displayed portion of the plurality of candidate word strings; anddisplaying the selected candidate word string in a text field of the electronic device.

6. The method of claim 5, further comprising: receiving an indication that the user has committed to the selected candidate word string; andin response to receiving the indication, updating the first language model using the selected candidate word string.

7. The method of claim 6, wherein receiving the indication further comprises receiving a full stop input for a sentence containing the selected candidate word string.

8. The method of claim 6, wherein receiving the indication further comprises receiving a command to send a message containing the selected candidate word string.

9. The method of claim 5, further comprising: determining a predicted word of the second symbolic system based on a probability of occurrence of a sequence of words in the obtained text, the sequence of words comprising the selected candidate word string and the predicted text; anddisplaying the predicted word adjacent to the selected candidate word string in the text field.

10. The method of claim 1, wherein: the obtained text is associated with a first context;the input is associated with an input context; andranking the plurality of candidate word strings is based on a degree of similarity between the input context and the first context.

11. The method of claim 10, wherein the first context includes a first recipient and a first application of the electronic device, and wherein the input context includes a second recipient and a second application of the electronic device.

12. The method of claim 10, wherein the first context and input context are determined using a sensor of the electronic device.

13. The method of claim 1, further comprising: obtaining second text composed by the user, wherein: the obtained second text is associated with a second context;ranking the plurality of candidate word strings is based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the second obtained text; andthe ranking the plurality of candidate word strings is based on a degree of similarity between the input context and the second context.

14. The method of claim 13, wherein the obtained second text comprises words of the second symbolic system.

15. The method of claim 1, wherein the obtained text comprises words of the second symbolic system.

16. The method of claim 1, further comprising: determining, using a second language model, a probability of occurrence of each candidate word string of the plurality of candidate word strings in a corpus of text, wherein ranking the plurality of candidate word strings is based on the probability of occurrence of each candidate word string of the plurality of candidate word strings in the corpus of text, and wherein the corpus of text is not composed by the user.

17. The method of claim 1, wherein the first symbolic system comprises a phonetic system for transcribing a language.

18. The method of claim 1, wherein the first symbolic system comprises Chinese Pinyin.

19. The method of claim 1, wherein the first symbolic system comprises Chinese Zhuyin.

20. The method of claim 1, wherein the second symbolic system comprises Chinese characters.

21. The method of claim 1, wherein each word of the two or more words is a monosyllabic Chinese character.

22. A non-transitory computer-readable storage medium comprising computer-executable instructions, which when executed by one or more processors, causes the one or more processors to: obtain text composed by a user;receive, from the user, input comprising a sequence of symbols of a first symbolic system;determine a plurality of candidate word strings corresponding to the sequence of symbols, each candidate word string of the plurality of candidate word strings comprising two or more words of a second symbolic system;rank the plurality of candidate word strings based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text; anddisplay, based on the ranking, a portion of the plurality of candidate word strings for selection by the user.

23. A system comprising: one or more processors;memory storing computer-readable instructions, which when executed by the one or more processors, cause the one or more processors to: obtain text composed by a user;receive, from the user, input comprising a sequence of symbols of a first symbolic system;determine a plurality of candidate word strings corresponding to the sequence of symbols, each candidate word string of the plurality of candidate word strings comprising two or more words of a second symbolic system;rank the plurality of candidate word strings based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text; anddisplay, based on the ranking, a portion of the plurality of candidate word strings for selection by the user.

24. The system of claim 23, wherein the computer-readable instructions further cause the one or more processors to: generate a first language model using the obtained text; anddetermine, using the first language model, the probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text.

25. The system of claim 24, wherein the computer-readable instructions further cause the one or more processors to: receive, from the user, a selection of a candidate word string from the displayed portion of the plurality of candidate word strings; anddisplay the selected candidate word string in a text field.