Personalization of queries, conversations, and searches

Abstract

Personalization of user interactions may be provided. Upon receiving a phrase from a user, a plurality of semantic concepts associated with the user may be loaded. If the phrase is determined to comprise at least one of the plurality of semantic concepts associated with the user, a first action may be performed according to the phrase. If the phrase is determined not to comprise at least one of the plurality of semantic concepts associated with the user, a second action may be performed according to the phrase.

Description

RELATED APPLICATIONS

This patent application is also related to and filed concurrently with U.S. patent application Ser. No. 13/076,862 entitled “Augmented Conversational Understanding Agent,” filed on Mar. 31, 2011; U.S. patent application Ser. No. 13/077,233 entitled “Conversational Dialog Learning and Correction,” filed on Mar. 31, 2011; U.S. patent application Ser. No. 13/077,368, entitled “Combined Activation for Natural User Interface Systems,” filed on Mar. 31, 2011; U.S. patent application Ser. No. 13/077,396, entitled “Task Driven User Intents,” filed on Mar. 31, 2011; U.S. patent application Ser. No. 13/077,431, entitled “Augmented Conversational Understanding Architecture,” filed on Mar. 31, 2011; U.S. patent application Ser. No. 13/077,455 entitled “Location-Based Conversational Understanding,” filed on Mar. 31, 2011; which are assigned to the same assignee as the present application and expressly incorporated herein, in their entirety, by reference.

BACKGROUND

An augmented conversational understanding architecture may provide a mechanism for personalizing queries, conversations and searches. In some situations, personal assistant programs and/or search engines often require specialized formatting and syntax. For example, a user's query of “I want to go see ‘Inception’ around 7” may be ineffective at communicating the user's true intentions when provided to a conventional system. Such systems may generally be incapable of deriving the context that the user is referring to a movie, and that the user desires results informing them of local theatres showing that movie around 7:00.

SUMMARY

This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter. Nor is this Summary intended to be used to limit the claimed subject matter's scope.

Personalization of user interactions may be provided. Upon receiving a phrase from a user, a plurality of semantic concepts associated with the user may be loaded. If the phrase is determined to comprise at least one of the plurality of semantic concepts associated with the user, a first action may be performed according to the phrase. If the phrase is determined not to comprise at least one of the plurality of semantic concepts associated with the user, a second action may be performed according to the phrase.

Both the foregoing general description and the following detailed description provide examples and are explanatory only. Accordingly, the foregoing general description and the following detailed description should not be considered to be restrictive. Further, features or variations may be provided in addition to those set forth herein. For example, embodiments may be directed to various feature combinations and sub-combinations described in the detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various embodiments of the present invention. In the drawings:

FIG. 1 is a block diagram of an operating environment;

FIG. 2 is a flow chart of a method for providing an augmented conversational understanding architecture;

FIGS. 3A-3B are illustrations of example ontologies; and

FIG. 4 is a block diagram of a system including a computing device.

DETAILED DESCRIPTION

The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar elements. While embodiments of the invention may be described, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, or modifications may be made to the elements illustrated in the drawings, and the methods described herein may be modified by substituting, reordering, or adding stages to the disclosed methods. Accordingly, the following detailed description does not limit the invention. Instead, the proper scope of the invention is defined by the appended claims.

A cloud (e.g., network storage-based) based service may allow for user personalization of searches, queries or instructions to a personal assistant (e.g., a software program). The ability to personalize such queries or instructions may be provided by rule driven techniques in conjunction with various ontologies and using the search terms, instruction statements and the user contexts to provide more accurate search or query results.

Natural language speech recognition applications may allow for personalization of searches and actions. Components may focus on the user experience and/or provide a personalization engine, such as via components of a SDS. A user experience component may be available as part of a web search application via a browser running on a general purpose desktop or laptop computer or a specialized computing device such as a smart phone or a information kiosk in a mall. A personalization engine component may store various ontologies, iterate through a query to identify a user's intent, and attempt to match a semantic representation of the query to a particular ontology. For example, ABC Company may populate a shared ontology that may define semantic concepts such as creating an appointment. The semantic concept may be associated with attributes such as calendar servers, scheduling services, and synonyms (e.g., the term “S+” may be defined as a shortcut synonym for setting up a meeting). If the user is an employee of ABC Co., the term S+ (“S plus”) may be inherited from the shared ontology and recognized as a shortcut to setting up an appointment using Outlook®. The personalization engine may also use additional user contexts (e.g., location, or previous state information) to merge additional shared ontologies.

Other examples of personalization may comprise the user asking for “John Hardy's”; because the user is originally from Minnesota, the SDS may retrieve this information from the user's personal ontology (derived from profile, usage history, and other sources such as contacts and messaging content) and know that the user is looking for the BBQ restaurant located in Rochester, Minn. If the user refers to “Rangers” the SDS may be able to infer, based on the personal ontology, that the user intends “NY Rangers” since they are a hockey fan. If the user were known to be a baseball fan, the user's intent may be interpreted as referring instead to the “Texas Rangers.” Such intent deciphering may be in combination with contextual information such as the time of year, what teams are playing that day, etc.

A Spoken Language Understanding (SLU) component (e.g., a translator) may receive a spoken or written conversation between users and/or a single-user originating query. The SLU may parse the words of a voice or text conversation and select certain items which may be used to fill out an XML data frame for particular contexts. For example, a restaurant context may have certain slots such as “type of food”, “location/address”, “outdoor dining”, “reservations required”, “hours open”, “day of week”, “time”, “number of persons”, etc. The SLU may attempt to fill different context data frames with both the parsed words from the conversation or query, and with other external information, such as GPS location information. The SLU may keep state during the conversation and fill the slots over the course of the conversation. For example, if user 1 says “How about tonight” and user 2 says “Saturday is better”, the SLU may initially fill tonight in the day of the week slot and then fill Saturday in the day of the week slot. If a certain number of the slots in a particular context frame are filled, the SLU may infer that the context is correct and estimate the user intention. The SLU may also prompt the user for more information related to the intent. The SLU may then provide options to the user based on the determined user intent.

FIG. 1 is a block diagram of an operating environment 100 comprising a spoken dialog system (SDS) 110. SDS 110 may comprise assorted computing and/or software modules such as a personal assistant program 112, a dialog manager 114, an ontology 116, and/or a search agent 118. SDS 110 may receive queries and/or action requests from users over network 120. Such queries may be transmitted, for example, from a first user device 130 and/or a second user device 135 such as a computer and/or cellular phone. Network 120 may comprise, for example, a private network, a cellular data network, and/or a public network such as the Internet. Consistent with embodiments of the invention, SDS 110 may be operative to monitor conversations between first user device 130 and second user device 135.

Spoken dialog systems enable people to interact with computers with their voice. The primary component that drives the SDS may comprise dialog manager 114. This component may manage the dialog-based conversation with the user. Dialog manager 114 may determine the intention of the user through a combination of multiple sources of input, such as speech recognition and natural language understanding component outputs, context from the prior dialog turns, user context, and/or results returned from a knowledge base (e.g., search engine). After determining the intention, dialog manager 114 may take an action, such as displaying the final results to the user and/or continuing in a dialog with the user to satisfy their intent.

FIG. 2 is a flow chart setting forth the general stages involved in a method 200 consistent with an embodiment of the invention for providing a personalized user experience. Method 200 may be implemented using a computing device 400 as described in more detail below with respect to FIG. 4. Ways to implement the stages of method 200 will be described in greater detail below. Method 200 may begin at starting block 205 and proceed to stage 210 where computing device 400 may identify a plurality of users associated with a conversation. For example, SDS 110 may monitor a conversation between a first user of first user device 130 and a second user of second user device 135. The first user and second user may be identified, for example, via an authenticated sign-in with SDS 110 and/or via identifying software and/or hardware IDs associated with their respective devices.

Method 200 may then advance to stage 215 where computing device 400 may merge a plurality of ontologies. For example, SDS 110 may load an ontology associated with the first user and the second user from ontology database 116. Each of the plurality of ontologies may comprise a plurality of semantic concepts and/or attributes associated with characteristics of at least one of the users, such as a workplace associated with a user, a contacts database, a calendar, a previous action, a previous communication made by and/or between the users, a context, and/or a profile. Consistent with embodiments of the invention, the merger may comprise merging either and/or both users' ontologies with a shared/global ontology. For example, a search engine may provide a shared ontology comprising data gathered and synthesized across many users, while a network application may publish an ontology comprising attributes associated with publicly available applications. A shared ontology may also be associated with an organization and may comprise attributes common to multiple employees. Merging one ontology with another may comprise, for example, creating associations between common terms, adding synonyms to a node, adding additional attribute nodes, sub nodes, and/or branches, and/or adding connections between nodes.

Method 200 may then advance to stage 220 where computing device 400 may receive a natural language phrase from a user. For example, SDS 110 may receive a phrase spoken and/or typed by the user into first user device 130.

Method 200 may then advance to stage 225 where computing device 400 may load a model associated with a spoken dialog system. For example, SDS 110 may load a language dictionary associated with the user's preferred spoken language.

Method 200 may then advance to stage 230 where computing device 400 may translate the natural language phrase into an agent action. For example, the phrase may be scanned for concepts that correlate to a search domain and/or an executable action associated with a network application. Words such as “dinner tonight” may scan to a “restaurant” search domain associated with a search action. Each domain may be associated with a plurality of slots that may comprise attributes for defining the scope of the action. For example, a restaurant domain may comprise slots for party size, type of cuisine, time, whether outdoor seating is available, etc. Dialog manager 114 may attempt to fill these slots based on the natural language phrase.

Method 200 may then advance to stage 235 where computing device 400 may determine whether the recognition is acceptable. For example, dialog manager 114 may be unable to fill enough slots to provide a complete action, and/or additional phrases may be received from the initial user and/or another user involved in the conversation that modify the agent action prior to execution.

In such cases, method 200 may advance to stage 240 where computing device 400 may receive an update to the agent action. For example, dialog manager may create a restaurant domain agent action for making a reservation. Upon receiving a phrase from a user such as “what about tomorrow instead?”, dialog manager may return to stage 230 to translate the new input and update the action accordingly.

Otherwise, once the action is acceptable, method 200 may advance to stage 245 where computing device 400 may perform the action. For example, dialog manager 114 may create a lunch appointment calendar event.

Method 200 may then advance to stage 250 where computing device 400 may display at least one result associated with the performed action to at least one of the plurality of users. For example, SDS 110 may populate the created lunch appointment to calendars associated with each of the first user and second user and/or display a confirmation that the event was created on their respective user devices. Method 200 may then end at stage 265.

FIG. 3A is an illustration of a shared ontology 300. An ontology may generally comprise a plurality of semantic relationships between concept nodes. Each concept node may comprise a generalized grouping, an abstract idea, and/or a mental symbol and that node's associated attributes. For example, one concept may comprise a person associated with attributes such as name, job function, home location, etc. The ontology may comprise, for example, a semantic relationship between the person concept and a job concept connected by the person's job function attribute. Shared ontology 300 may comprise a plurality of concept nodes 310(A)-(F). Each of the concept nodes may be associated with attribute nodes. For example, person concept node 310(C) may be associated with a plurality of attributes 315(A)-(D). Attributes may be further associated with sub-nodes, such as where contact info attribute node 315(B) is associated with a plurality of sub-nodes 320(A)-(C). Similarly, attribute nodes may be associated with synonyms, such as where name attribute node 315(A) is associated with a nicknames synonym 325. Concept nodes 310(A)-(F) may be interconnected via a plurality of semantic relationships 330(A)-(B). For example, person attribute 310(C) may be connected to location attribute 310(F) via work semantic relationship 330(A) and/or home semantic relationship 330(B).

FIG. 3B is an illustration of a personal ontology 350 comprising a user concept node 360. User concept node 360 may comprise a plurality of attribute nodes 370(A)-(D) associated with user details such as preferences, activities, relationships, and/or previous choices. User concept node 360 may comprise a semantic connection 375 associated with another concept node, such as a second user node 380 associated with a child of the user.

An embodiment consistent with the invention may comprise a system for providing a context-aware environment. The system may comprise a memory storage and a processing unit coupled to the memory storage. The processing unit may be operative to receive a phrase from a user, load an ontology associated with the user, determine whether the phrase comprises at least one semantic concept associated with the ontology, and, if not, perform a first action according to the phrase. In response to determining that the phrase comprises a semantic concept associated with the ontology, the processing unit may be operative to perform a second action according to the phrase. The phrase may comprise a spoken natural language phrase and the processing unit may be operative to convert the spoken phrase to a text-based phrase. Consistent with embodiments of the invention, the natural language phrase may comprise a typed phrase.

The ontology may comprise, for example, terms and/or concepts associated with the user's workplace, previous actions, learned phrasing, slang, contact-derived references (e.g., “Billy-boy” equates to a contact named Bill Smith, Jr.), and/or previous communications.

Another embodiment consistent with the invention may comprise a system for providing a personalized user interaction. The system may comprise a memory storage and a processing unit coupled to the memory storage. The processing unit may be operative to receive a phrase from a user, load an ontology associated with the user, translate the received phrase into an agent action, determine whether the phrase comprises at least one of the semantic concepts associated with the ontology, and, if so, modify the agent action, perform the modified agent action, and display at least one result associated with the performed agent action to the user.

The agent action may comprise, for example, a search query, and being operative to modify the action may comprise the processing unit being operative to add a term to the query and/or replace a term of the query with a synonym. The agent action may comprise performing a task within an application, wherein an attribute associated with the ontology comprises a shortcut synonym associated with a semantic concept of performing the task within the application (e.g., a spoken command “exit” may be translated into application tasks of saving all open files and quitting the application). The context associated with the user may comprise, for example, a location of the user, a time the phrase was received, and a date the phrase was received.

The received phrase may be associated with a conversation between the user and at least one second user. The processing unit may then be operative to receive a second phrase from the second user, load a second ontology associated with the second user, merge the two users' ontologies, translate the second received phrase into a second agent action, determine whether the second phrase comprises a semantic concept associated with the merged ontologies, and, if so, modify the agent action, perform the modified agent action, and display at least one result associated with the performed agent action to the second user.

Yet another embodiment consistent with the invention may comprise a system for providing a context-aware environment. The system may comprise a memory storage and a processing unit coupled to the memory storage. The processing unit may be operative to identify a plurality of users associated with a conversation, merge a plurality of ontologies, each associated with one of the users, receive a first natural language phrase from a first user of the plurality of users, translate the natural language phrase into an agent action, and determine whether the agent action is associated with at least one of the semantic concepts associated with the merged ontologies. In response to determining that the phrase comprises the semantic concept associated with the merged ontologies, the processing unit may be operative to modify the agent action. The processing unit may then be operative to receive a second natural language phrase from a second user of the plurality of users, and determine whether the second natural language phrase is associated with the agent action. If so, the processing unit may be operative to update the agent action according to the second natural language phrase. The processing unit may then be operative to perform the agent action and display at least one result associated with the performed agent action to at least one of the plurality of users.

FIG. 4 is a block diagram of a system including computing device 400. Consistent with an embodiment of the invention, the aforementioned memory storage and processing unit may be implemented in a computing device, such as computing device 400 of FIG. 4. Any suitable combination of hardware, software, or firmware may be used to implement the memory storage and processing unit. For example, the memory storage and processing unit may be implemented with computing device 400 or any of other computing devices 418, in combination with computing device 400. The aforementioned system, device, and processors are examples and other systems, devices, and processors may comprise the aforementioned memory storage and processing unit, consistent with embodiments of the invention. Furthermore, computing device 400 may comprise operating environment 100 as described above. System 100 may operate in other environments and is not limited to computing device 400.

With reference to FIG. 4, a system consistent with an embodiment of the invention may include a computing device, such as computing device 400. In a basic configuration, computing device 400 may include at least one processing unit 402 and a system memory 404. Depending on the configuration and type of computing device, system memory 404 may comprise, but is not limited to, volatile (e.g., random access memory (RAM)), non-volatile (e.g., read-only memory (ROM)), flash memory, or any combination. System memory 404 may include operating system 405, one or more programming modules 406, and may include personal assistant program 112. Operating system 405, for example, may be suitable for controlling computing device 400's operation. Furthermore, embodiments of the invention may be practiced in conjunction with a graphics library, other operating systems, or any other application program and is not limited to any particular application or system. This basic configuration is illustrated in FIG. 4 by those components within a dashed line 408.

Computing device 400 may have additional features or functionality. For example, computing device 400 may also include additional data storage devices (removable and/or non-removable) such as, for example, magnetic disks, optical disks, or tape. Such additional storage is illustrated in FIG. 4 by a removable storage 409 and a non-removable storage 410. Computer storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. System memory 404, removable storage 409, and non-removable storage 410 are all computer storage media examples (i.e., memory storage.) Computer storage media may include, but is not limited to, RAM, ROM, electrically erasable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store information and which can be accessed by computing device 400. Any such computer storage media may be part of device 400. Computing device 400 may also have input device(s) 412 such as a keyboard, a mouse, a pen, a sound input device, a touch input device, etc. Output device(s) 414 such as a display, speakers, a printer, etc. may also be included. The aforementioned devices are examples and others may be used.

Computing device 400 may also contain a communication connection 416 that may allow device 400 to communicate with other computing devices 418, such as over a network in a distributed computing environment, for example, an Intranet or the Internet. Communication connection 416 is one example of communication media. Communication media may typically be embodied by computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes any information delivery media. The term “modulated data signal” may describe a signal that has one or more characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media may include wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, radio frequency (RF), infrared, and other wireless media. The term computer readable media as used herein may include both storage media and communication media.

As stated above, a number of program modules and data files may be stored in system memory 404, including operating system 405. While executing on processing unit 402, programming modules 406 (e.g., personal assistant program 112) may perform processes including, for example, one or more of method 200's stages as described above. The aforementioned process is an example, and processing unit 402 may perform other processes. Other programming modules that may be used in accordance with embodiments of the present invention may include electronic mail and contacts applications, word processing applications, spreadsheet applications, database applications, slide presentation applications, drawing or computer-aided application programs, etc.

Generally, consistent with embodiments of the invention, program modules may include routines, programs, components, data structures, and other types of structures that may perform particular tasks or that may implement particular abstract data types. Moreover, embodiments of the invention may be practiced with other computer system configurations, including hand-held devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, minicomputers, mainframe computers, and the like. Embodiments of the invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Furthermore, embodiments of the invention may be practiced in an electrical circuit comprising discrete electronic elements, packaged or integrated electronic chips containing logic gates, a circuit utilizing a microprocessor, or on a single chip containing electronic elements or microprocessors. Embodiments of the invention may also be practiced using other technologies capable of performing logical operations such as, for example, AND, OR, and NOT, including but not limited to, mechanical, optical, fluidic, and quantum technologies. In addition, embodiments of the invention may be practiced within a general purpose computer or in any other circuits or systems.

Embodiments of the invention, for example, may be implemented as a computer process (method), a computing system, or as an article of manufacture, such as a computer program product or computer readable media. The computer program product may be a computer storage media readable by a computer system and encoding a computer program of instructions for executing a computer process. The computer program product may also be a propagated signal on a carrier readable by a computing system and encoding a computer program of instructions for executing a computer process. Accordingly, the present invention may be embodied in hardware and/or in software (including firmware, resident software, micro-code, etc.). In other words, embodiments of the present invention may take the form of a computer program product on a computer-usable or computer-readable storage medium having computer-usable or computer-readable program code embodied in the medium for use by or in connection with an instruction execution system. A computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

The computer-usable or computer-readable medium may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. More specific computer-readable medium examples (a non-exhaustive list), the computer-readable medium may include the following: an electrical connection having one or more wires, a portable computer diskette, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CD-ROM). Note that the computer-usable or computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

Embodiments of the present invention, for example, are described above with reference to block diagrams and/or operational illustrations of methods, systems, and computer program products according to embodiments of the invention. The functions/acts noted in the blocks may occur out of the order as shown in any flowchart. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved.

While certain embodiments of the invention have been described, other embodiments may exist. Furthermore, although embodiments of the present invention have been described as being associated with data stored in memory and other storage mediums, data can also be stored on or read from other types of computer-readable media, such as secondary storage devices, like hard disks, floppy disks, or a CD-ROM, a carrier wave from the Internet, or other forms of RAM or ROM. Further, the disclosed methods' stages may be modified in any manner, including by reordering stages and/or inserting or deleting stages, without departing from the invention.

All rights including copyrights in the code included herein are vested in and the property of the Applicant. The Applicant retains and reserves all rights in the code included herein, and grants permission to reproduce the material only in connection with reproduction of the granted patent and for no other purpose.

While the specification includes examples, the invention's scope is indicated by the following claims. Furthermore, while the specification has been described in language specific to structural features and/or methodological acts, the claims are not limited to the features or acts described above. Rather, the specific features and acts described above are disclosed as example for embodiments of the invention.

Claims

1. A computer-readable data storage device which stores a set of instructions which when executed performs a method for providing a personalized user interaction with a computing device, the method executed by the set of instructions comprising: receiving a phrase from a user, wherein the received phrase is associated with a conversation between the user and at least one second user;translating the received phrase into an initial agent action by scanning the received phrase to a search domain associated with a search action;loading, by a spoken dialog system, an ontology associated with the user, wherein the ontology comprises a plurality of semantic concepts associated with at least one of the following: a workplace associated with the user, a contacts database associated with the user, a calendar associated with the user, a previous action associated with the user, a previous communication associated with the user, a context associated with the user, and a profile associated with the user;selecting at least one pre-defined shared ontology based on a context associated with the user, the at least one pre-defined shared ontology comprising a plurality of semantic concepts and a plurality of semantic connections between the semantic concepts that are usable to determine intents of phrases associated with the context;merging the ontology associated with the user with the at least one pre-defined shared ontology to generate a merged ontology;determining whether the phrase comprises at least one of the plurality of semantic concepts associated with the merged ontology;in response to determining that the phrase comprises the at least one of the plurality of semantic concepts associated with the merged ontology:modifying the initial agent action according to the merged ontology to generate a modified agent action, the modified agent action being different than the initial agent action,performing the modified agent action,displaying at least one result associated with the performed agent action to the user;receiving a second phrase from the at least one second user;loading a second ontology associated with the at least one second user;merging the second ontology with the ontology associated with the user;determining whether the second phrase comprises a response to the received phrase;in response to determining that the second phrase comprises the response to the received phrase, determining whether the second phrase comprises at least one second semantic concept associated with the merged ontologies; andin response to determining that the second phrase comprises the at least one second semantic concept associated with the merged ontologies:updating the agent action,performing the updated agent action, anddisplaying at least one result associated with the performed updated agent action to the user and the at least one second user.

2. The computer-readable data storage device of claim 1, wherein the agent action comprises a search query.

3. The computer-readable data storage device of claim 2, wherein modifying the agent action comprises adding a search term to the search query.

4. The computer-readable data storage device of claim 2, wherein modifying the action comprises replacing at least one term of the search query with a synonym of the at least one of the plurality of semantic concepts associated with the ontology.

5. The computer-readable data storage device of claim 1, wherein the agent action comprises performing a task within an application.

6. The computer-readable data storage device of claim 5, wherein the at least one of the plurality of semantic concepts associated with the ontology comprises a shortcut synonym associated with performing the task within the application.

7. The computer-readable data storage device of claim 1, wherein the context associated with the user comprises at least one of the following: a location of the user, a time the phrase was received, and a date the phrase was received.

8. A computer-readable data storage device which stores a set of instructions which when executed performs a method for providing a personalized user interaction, the method executed by the set of instructions comprising: receiving a phrase from a user, wherein the received phrase is associated with a conversation between the user and at least one second user;translating the received phrase into an agent action;loading an ontology associated with the user, wherein the ontology comprises a plurality of semantic concepts associated with at least one of the following: a workplace associated with the user, a contacts database associated with the user, a calendar associated with the user, a previous action associated with the user, a previous communication associated with the user, a context associated with the user, and a profile associated with the user;determining whether the phrase comprises at least one of the plurality of semantic concepts associated with the ontology;in response to determining that the phrase comprises the at least one of the plurality of semantic concepts associated with the ontology: modifying the agent action according to the ontology,performing the modified agent action, anddisplaying at least one result associated with the performed agent action to the user;receiving a second phrase from the at least one second user;loading a second ontology associated with the at least one second user;merging the second ontology with the ontology associated with the user;determining whether the second phrase comprises a response to the received phrase;in response to determining that the second phrase comprises the response to the received phrase, determining whether the second phrase comprises at least one second semantic concept associated with the merged ontologies; andin response to determining that the second phrase comprises the at least one second semantic concept associated with the merged ontologies: updating the agent action,performing the updated agent action, anddisplaying at least one result associated with the performed updated agent action to the user and the at least one second user.

9. The computer-readable data storage device of claim 8, wherein the agent action comprises a search query.

10. The computer-readable data storage device of claim 9, wherein modifying the agent action comprises adding a search term to the search query.

11. The computer-readable data storage device of claim 9, wherein modifying the action comprises replacing at least one term of the search query with a synonym of the at least one of the plurality of semantic concepts associated with the ontology.

12. The computer-readable data storage device of claim 8, wherein the agent action comprises performing a task within an application.

13. The computer-readable data storage device of claim 12, wherein the at least one of the plurality of semantic concepts associated with the ontology comprises a shortcut synonym associated with performing the task within the application.

14. The computer-readable data storage device of claim 8, wherein the context associated with the user comprises at least one of the following: a location of the user, a time the phrase was received, and a date the phrase was received.

15. A system for providing a personalized user interaction with a computing device, the system comprising: a memory storage; anda processing unit coupled to the memory storage, wherein the processing unit is operative to: receive a phrase from a user, wherein the received phrase is associated with a conversation between the user and at least one second user;translate the received phrase into an agent action;load an ontology associated with the user, wherein the ontology comprises a plurality of semantic concepts associated with at least one of the following: a workplace associated with the user, a contacts database associated with the user, a calendar associated with the user, a previous action associated with the user, a previous communication associated with the user, a context associated with the user, and a profile associated with the user;determine whether the phrase comprises at least one of the plurality of semantic concepts associated with the ontology;in response to determining that the phrase comprises the at least one of the plurality of semantic concepts associated with the ontology: modify the agent action according to the ontology,perform the modified agent action, anddisplay at least one result associated with the performed agent action to the user;receive a second phrase from the at least one second user;load a second ontology associated with the at least one second user;merge the second ontology with the ontology associated with the user;determine whether the second phrase comprises a response to the received phrase;in response to determining that the second phrase comprises the response to the received phrase, determine whether the second phrase comprises at least one second semantic concept associated with the merged ontologies; andin response to determining that the second phrase comprises the at least one second semantic concept associated with the merged ontologies: update the agent action,perform the updated agent action, anddisplay at least one result associated with the performed updated agent action to the user and the at least one second user.

16. The system of claim 15, wherein the phrase comprises a natural language phrase.

17. The system of claim 16, wherein the natural language phrase comprises a spoken phrase.

18. The system of claim 17, wherein the processing unit is further operative to convert the spoken phrase to a text-based phrase.

19. The system of claim 16, wherein the natural language phrase comprises a typed phrase.

20. The system of claim 15, wherein the processing unit is configured to translate the received phrase by abstracting at least one word of the phrase into a plurality of synonyms.