Systems and methods for key phrase characterization of documents

Abstract

Systems and methods are disclosed for key phrase characterization of documents. In accordance with one implementation, a method is provided for key phrase characterization of documents. The method includes obtaining a first plurality of documents based at least on a user input, obtaining a statistical model based at least on the user input, and obtaining, from content of the first plurality of documents, a plurality of segments. The method also includes determining statistical significance of the plurality of segments based at least on the statistical model and the content, and providing for display a representative segment from the plurality of segments, the representative segment being determined based at least on the statistical significance.

Description

BACKGROUND

Vast amounts of data are readily available to readers, analysts, and researchers today, on the one hand allowing them to perform more complicated and detailed data analyses than ever, but on the other hand making it more difficult to quickly sort through the data. Automatically characterizing the data in a concise and informative way can help users to identify data that is most relevant for their particular needs.

BRIEF DESCRIPTION OF THE DRAWINGS

Reference will now be made to the accompanying drawings, which illustrate exemplary embodiments of the present disclosure. In the drawings:

FIG. 1 is a block diagram of an exemplary electronic device, consistent with embodiments of the present disclosure;

FIG. 2 is a flowchart of an exemplary method for generating a statistical model, consistent with embodiments of the present disclosure;

FIG. 3 is a flowchart of an exemplary method for key phrase characterization of documents, consistent with embodiments of the present disclosure; and

FIGS. 4A-4C illustrate an exemplary display showing exemplary user interactions, consistent with embodiments of the present disclosure.

DESCRIPTION OF EXEMPLARY EMBODIMENTS

Reference will now be made in detail to several exemplary embodiments of the present disclosure, including those illustrated in the accompanying drawings. Whenever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.

Embodiments disclosed herein are directed to, among other things, systems and methods that automatically characterize documents by identifying key phrases describing the contents of those documents. More specifically, the systems and methods can, among other things, obtain a first plurality of documents based at least on a user input; obtain a statistical model based at least on the user input; obtain, from content of the first plurality of documents, a plurality of segments; determine statistical significance of the plurality of segments based at least on the statistical model and the content; and provide for display a representative segment from the plurality of segments, the representative segment being determined based at least on the statistical significance.

According to some embodiments, the operations, techniques, and/or components described herein can be implemented by an electronic device, which can include one or more special-purpose computing devices. The special-purpose computing devices can be hard-wired to perform the operations, techniques, and/or components described herein, or can include digital electronic devices such as one or more application-specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs) that are persistently programmed to perform the operations, techniques and/or components described herein, or can include one or more hardware processors programmed to perform such features of the present disclosure pursuant to program instructions in firmware, memory, other storage, or a combination. Such special-purpose computing devices can also combine custom hard-wired logic, ASICs, or FPGAs with custom programming to accomplish the technique and other features of the present disclosure. The special-purpose computing devices can be desktop computer systems, portable computer systems, handheld devices, networking devices, or any other device that incorporates hard-wired and/or program logic to implement the techniques and other features of the present disclosure.

The one or more special-purpose computing devices can be generally controlled and coordinated by operating system software, such as iOS, Android, Blackberry, Chrome OS, Windows XP, Windows Vista, Windows 7, Windows 8, Windows Server, Windows CE, Unix, Linux, SunOS, Solaris, VxWorks, or other compatible operating systems. In other embodiments, the computing device can be controlled by a proprietary operating system. Operating systems control and schedule computer processes for execution, perform memory management, provide file system, networking, I/O services, and provide a user interface functionality, such as a graphical user interface (“GUI”), among other things.

By way of example, FIG. 1 is a block diagram that illustrates an implementation of an electronic device 110, which, as described above, can comprise one or more electronic devices. Electronic device 110 includes a bus 102 or other communication mechanism for communicating information, and one or more hardware processors 104, coupled with bus 102 for processing information. One or more hardware processors 104 can be, for example, one or more microprocessors.

Electronic device 110 also includes a main memory 106, such as a random access memory (RAM) or other dynamic storage device, coupled to bus 102 for storing information and instructions to be executed by processor 104. Main memory 106 also can be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 104. Such instructions, when stored in non-transitory storage media accessible to one or more processors 104, render electronic device 110 into a special-purpose machine that is customized to perform the operations specified in the instructions.

Electronic device 110 further includes a read only memory (ROM) 108 or other static storage device coupled to bus 102 for storing static information and instructions for processor 104. A storage device 150, such as a magnetic disk, optical disk, or USB thumb drive (Flash drive), etc., is provided and coupled to bus 102 for storing information and instructions.

Electronic device 110 can be coupled via bus 102 to a display 112, such as a cathode ray tube (CRT), an LCD display, or a touchscreen, for displaying information to a computer user. An input device 114, including alphanumeric and other keys, is coupled to bus 102 for communicating information and command selections to processor 104. Another type of user input device is cursor control 116, such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to processor 104 and for controlling cursor movement on display 112. The input device typically has two degrees of freedom in two axes, a first axis (for example, x) and a second axis (for example, y), that allows the device to specify positions in a plane. In some embodiments, the same direction information and command selections as cursor control may be implemented via receiving touches on a touch screen without a cursor.

Electronic device 110 can include a user interface module to implement a GUI that may be stored in a mass storage device as executable software codes that are executed by the one or more computing devices. This and other modules may include, by way of example, components, such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

In general, the word “module,” as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions, possibly having entry and exit points, written in a programming language, such as, for example, Java, Lua, C, and C++. A software module can be compiled and linked into an executable program, installed in a dynamic link library, or written in an interpreted programming language such as, for example, BASIC, Perl, Python, or Pig. It will be appreciated that software modules can be callable from other modules or from themselves, and/or can be invoked in response to detected events or interrupts. Software modules configured for execution on computing devices can be provided on a computer readable medium, such as a compact disc, digital video disc, flash drive, magnetic disc, or any other tangible medium, or as a digital download (and can be originally stored in a compressed or installable format that requires installation, decompression, or decryption prior to execution). Such software code can be stored, partially or fully, on a memory device of the executing computing device, for execution by the computing device. Software instructions can be embedded in firmware, such as an EPROM. It will be further appreciated that hardware modules can be comprised of connected logic units, such as gates and flip-flops, and/or can be comprised of programmable units, such as programmable gate arrays or processors. The modules or computing device functionality described herein are preferably implemented as software modules, but can be represented in hardware or firmware. Generally, the modules described herein refer to logical modules that may be combined with other modules or divided into sub-modules despite their physical organization or storage.

Electronic device 110 can implement the techniques and other features described herein using customized hard-wired logic, one or more ASICs or FPGAs, firmware and/or program logic which in combination with the electronic device causes or programs electronic device 110 to be a special-purpose machine. According to some embodiments, the techniques and other features described herein are performed by electronic device 110 in response to one or more processors 104 executing one or more sequences of one or more instructions contained in main memory 106. Such instructions can be read into main memory 106 from another storage medium, such as storage device 150. Execution of the sequences of instructions contained in main memory 106 causes processor 104 to perform the process steps described herein. In alternative embodiments, hard-wired circuitry can be used in place of or in combination with software instructions.

The term “non-transitory media” as used herein refers to any media storing data and/or instructions that cause a machine to operate in a specific fashion. Such non-transitory media can comprise non-volatile media and/or volatile media. Non-volatile media includes, for example, optical or magnetic disks, such as storage device 150. Volatile media includes dynamic memory, such as main memory 106. Common forms of non-transitory media include, for example, a floppy disk, a flexible disk, hard disk, solid state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, any other memory chip or cartridge, and networked versions of the same.

Non-transitory media is distinct from, but can be used in conjunction with, transmission media. Transmission media participates in transferring information between storage media. For example, transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise bus 102. Transmission media can also take the form of acoustic or light waves, such as those generated during radio-wave and infra-red data communications.

Various forms of media can be involved in carrying one or more sequences of one or more instructions to processor 104 for execution. For example, the instructions can initially be carried on a magnetic disk or solid state drive of a remote computer. The remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to electronic device 110 can receive the data on the telephone line and use an infra-red transmitter to convert the data to an infra-red signal. An infra-red detector can receive the data carried in the infra-red signal and appropriate circuitry can place the data on bus 102. Bus 102 carries the data to main memory 106, from which processor 104 retrieves and executes the instructions. The instructions received by main memory 106 can optionally be stored on storage device 150 either before or after execution by processor 104.

Electronic device 110 also includes a communication interface 118 coupled to bus 102. Communication interface 118 provides a two-way data communication coupling to a network link 120 that is connected to a local network 122. For example, communication interface 118 can be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, communication interface 118 can be a local area network (LAN) card to provide a data communication connection to a compatible LAN. Wireless links can also be implemented. In any such implementation, communication interface 118 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.

Network link 120 typically provides data communication through one or more networks to other data devices. For example, network link 120 can provide a connection through local network 122 to a host computer 124 or to data equipment operated by an Internet Service Provider (ISP) 126. ISP 126 in turn provides data communication services through the world wide packet data communication network now commonly referred to as the “Internet” 128. Local network 122 and Internet 128 both use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals on network link 120 and through communication interface 118, which carry the digital data to and from electronic device 110, are example forms of transmission media.

Electronic device 110 can send messages and receive data, including program code, through the network(s), network link 120 and communication interface 118. In the Internet example, a server 130 might transmit a requested code for an application program through Internet 128, ISP 126, local network 122 and communication interface 118.

The received code can be executed by processor 104 as it is received, and/or stored in storage device 150, or other non-volatile storage for later execution.

FIG. 2 shows a flowchart representing an exemplary method 200 for generating a statistical model representing a plurality of documents. In some embodiments, method 200 can be performed by a client application (e.g., a web browser, a plug-in to a web browser, a standalone executable application, etc.) running on a client device, by a server (e.g., a web server), or it can have some steps or parts thereof executed on the client device, and some steps or parts thereof executed on the server. Thus, method 200 can be performed by one or more electronic devices, such as electronic device 110. And while method 200 and the other following embodiments described herein can be performed by multiple electronic devices each having one or more processors, for purposes of simplicity and without limitation, these embodiments will be explained with respect to a single electronic device (e.g., electronic device 110). While the flowchart discloses the following steps in a particular order, it is appreciated that at least some of the steps can be moved, modified, or deleted where appropriate, consistent with the teachings of the present disclosure.

Referring to FIG. 2, at step 210, the electronic device obtains a plurality (a corpus) of documents. The electronic device can obtain the documents from one or more databases that can be stored locally at the electronic device and/or on one or more remote devices. The documents can be of any type of digital format (e.g., HTML, PDF, MS Word, or any other format containing digital text) and can originate from different public or private sources, for example, from Internet webpages, library archives, proprietary subscription-based archives such as IEEE technical articles or Dow Jones's collection of news articles, or any other source of information. The documents can also be obtained by searching the Internet, and include, for example, some or all search results returned by a search engine in response to a user search query. In some embodiments, the documents can be associated with a date, such as the date of publication, the date of the most recent update, and so forth.

In some embodiments, the documents can also be associated with one or more entities, such as one or more companies or industries. For example, a document can be associated with tags, codes, or other types of metadata that describe one or more product, companies or industries, such as companies or industries discussed in the documents. As an example, a news article discussing a new iPhone® device being released by Apple Inc., can be pre-tagged (e.g., automatically or manually by a person) with one or more tags such as “iPhone,” “Apple,” “AAPL,” “consumer electronics,” and the like.

In some embodiments, the electronic device obtains at step 210 all documents that are associated with at least one common entity. For example, the electronic device can obtain all documents that are associated with the company Apple Inc., for example, by obtaining all documents tagged with one of the tags associated with Apple Inc., such as “AAPL,” “Apple” “Apple, Inc.,” etc. The particular common entity can be arbitrarily selected by the user, or it can be automatically selected by the electronic device. For example, the electronic device can automatically run method 200 several times, each time obtaining, at step 210, all documents associated with the next entity from a list of entities.

At step 220, the electronic device can obtain the content of the documents obtained at step 210. In some embodiments, for reasons of performance, the obtained content can include the headlines or titles of the documents, but not contain the entire text (the body) of the document. In other embodiments, in addition or instead of the headlines or titles of the documents, the obtained content can include the entire text (the body) of the documents. In yet other embodiments, the obtained content can also contain additional text associated with the documents, such as meta data, user comments, or any other additional text associated with the documents.

At step 230, the electronic device can segment the obtained contents of each document, e.g., break down the contents of each document into segments. Each segment can include, for example, one or more characters, which can include parts of words, single words (e.g., tokens), multiple words (e.g., n-grams), or entire phrases or clauses, such as noun phrases or clauses. For example, if document's content includes a headline “Apple releases a new iPhone device in October,” the electronic device can break this content into single-word segments (or tokens) “Apple,” “releases,” “a,” “new,” “iPhone,” “device,” “in,” “October.” As another example, the electronic device can break this content into bigram segments, e.g., “Apple releases,” “new iPhone,” “iPhone device,” “in October.” As seen from the last example, the electronic device can, in some embodiments, omit some content (e.g., articles, prepositions, etc.), and in some embodiments the same content can be included in more than one segment (e.g., the word “iPhone” in the above example appears in segments “new iPhone” and “iPhone device”).

In some embodiments, before or after breaking the content into segments, the electronic device can also perform various processing of the contents. For example, the electronic device can remove some words from the contents (e.g., articles and prepositions), normalize the contents by reducing each word to its morphological root or lemma, and so forth.

At step 240, the electronic device can generate a statistical model based on the frequencies at which the different segments obtained at step 230 occur within the contents of the documents. For example, the statistical model can contain a number associated with each segment, the number reflecting the number of times the segment was found across all contents of all the documents obtained at 210. In other words, the statistical model can include information reflecting, for various segments, how frequent or rare that segment is found within the plurality of documents. For example, the model is likely to indicate English words like “a,” “the,” “has,” “is,” etc., as frequently occurring words. Moreover, if the plurality of documents obtained at step 210 were all associated with a common entity (e.g., “Apple Inc.”), the model is also likely to indicate the segments related to that entity (e.g., “Apple,” “Steve Jobs,” etc.) as relatively frequent, because these segments are more likely to occur in this plurality of documents than in pluralities of documents not necessarily associated with the same entity.

In some embodiments, the statistical model can store, in addition to the segments and their frequencies, statistical information for sequences of subsequent segments. For example, the statistical model can store frequency information for the segment “new,” for the segment “iPhone,” and also frequency information of the segment “new” being followed by the segment “iPhone.” As discussed above, segments can include more than one word (e.g., bigrams), and therefore in some embodiments a bigram “new iPhone” can be a single segment for which the statistical model calculates an independent frequency.

At step 250, the electronic device can store the statistical model in a data storage, for example, in a volatile memory (e.g., in main memory 106), in a non-volatile memory (e.g., in storage device 150), or in both. In some embodiments, the statistical model can be stored in cache memory to allow quick access and update in the future.

As discussed above, the electronic device can perform method many times, each time for a different plurality of documents. Accordingly, the electronic device can generate and store more than one statistical model. In some embodiments, each statistical model can be associated with a different plurality of documents. For example, if a particular plurality of documents is associated with one or more entities (e.g., with Apple Inc., and/or with the consumer electronics industry) the statistical model generated based on that plurality of documents can be stored in association with those entities. Thus, the electronic device can maintain a set of statistical models, and maintain, for example, a look-up table associating one or ore entities with one or ore statistical models. Each statistical model can be associated with one or more entities, and each entity can be associated with either exactly one statistical model, or, in some embodiments, more than one statistical model. In some embodiments, the electronic device can store, in addition to or instead of statistical models associated with particular entities, a default statistical model that is not necessarily associated with any particular entity and that was generated, for example, based on all documents available to the electronic device.

FIG. 3 shows a flowchart representing an exemplary method 300 for key phrase characterization of documents. In some embodiments, method 300 can be performed by a client application (e.g., a web browser, a plug-in to a web browser, a standalone executable application, etc.) running on a client device, by a server (e.g., a web server), or it can have some steps or parts thereof executed on the client device, and some steps or parts thereof executed on the server. Thus, method 300 can be performed by one or more electronic devices, such as electronic device 110. And while method 300 and the other following embodiments described herein can be performed by multiple electronic devices each having one or more processors, for purposes of simplicity and without limitation, these embodiments will be explained with respect to a single electronic device (e.g., electronic device 110). While the flowchart discloses the following steps in a particular order, it is appreciated that at least some of the steps can be moved, modified, or deleted where appropriate, consistent with the teachings of the present disclosure.

At step 310, the electronic device can obtain a user input. The user input can include any input that identifies or defines, either directly or indirectly, a set of documents that are of interest to the user. User input can also include selection or specification, by the user, of an entity (e.g., a product, a company, an industry, etc.) for example, using that entity's name, symbol, stock ticker, etc. In some embodiments, user input can include selection or specification, by the user, of multiple entities. In some embodiments, user input can also specify desired (or undesired) date ranges, geographical regions, document sizes, document sources, or other types of filters indicating the scope of desired documents. In some embodiments, the user input can include a search query from the user, such as “Apple news for April 2014.”

In some embodiments, as illustrated in FIG. 4A, user input can include user's selection of a stock ticker 420 and a desired date range 440. In some embodiments, selecting a stock ticker can cause the electronic device to present a stock chart 410 corresponding to the selected stock ticker and showing, for example, changes in stock prices and trading volume. The user can then select the date range directly from the stock chart. For example, the user can identify an unusual spike in stock price or in trading volume and select a date range 430 around that spike.

In some embodiments, the date range can be initially set by the electronic device to a predetermined date range, allowing the user the modify it if necessary. For example, the electronic device can preset the date range to include a predetermined number of days, weeks, months, etc., ending with the current date. In some embodiments, the electronic device can preset the date range in accordance with prior date ranges used by the user. In some embodiments, the user can select, instead of whole date ranges, time intervals in resolution of hours, minutes, seconds, etc.

At step 320, the electronic device can obtain a set of one or more documents based on the user input received at step 310. For example, if user input specifies a particular entity (e.g., the company Apple Inc.), the electronic device can obtain, from all the documents available to the electronic device, a set of documents associated with the particular entity, such as a set of documents tagged with a tag “Apple Inc.,” “Apple,” or “AAPL.” If the user input also specifies a date range (e.g., Jun. 15, 2007-Jul. 16, 2007, as in the example of FIG. 4A), the electronic device can limit the obtained documents only to documents corresponding to (e.g., published on) dates that fall within the specified date range. Similarly, the electronic device can limit the scope of the obtained documents based on any other types of filters specified by the user.

In some embodiments, step 310 can be omitted, and the electronic device can obtain the set of documents without relying on user input. In some embodiments, when step 310 is omitted, or when it is performed but the user input fails to clearly define the desired scope of documents, the electronic device can obtain a predetermined (e.g., default) set of documents, for example, all documents available to the electronic device.

At step 330, the electronic device can dynamically select a statistical model based on the user input. In some embodiments, the electronic device can select, from a plurality of statistical models, a statistical model that best corresponds to the user input. The plurality of statistical models can be pre-generated, for example, by method 300, and stored, for example, in a data storage (e.g., cache, volatile, and/or non-volatile memory) accessible by the electronic device.

As discussed above, in some embodiments, each statistical model can correspond to and be stored in association with one or more entities. For example, the electronic device can maintain a look-up table associating one or more entities with one or more statistical models. Accordingly, in some embodiments, if the user input indicates a particular entity, the electronic device can obtain a statistical model that best corresponds to the particular entity, for example, a statistical model that was generated based on a plurality of documents associated with the particular entity. To illustrate, if the user input indicates that the user is interested in documents related to Apple Inc., (e.g., the user inputs a search query “Apple news for April 2014” or selects a stock-price graph corresponding to stock ticker AAPL) the electronic device can automatically obtain a statistical model that was generated based on a plurality of documents tagged with “Apple Inc.,” “Apple,” or “AAPL” Thus, in some embodiments, the set of documents obtained at step 320 can be a subset of the plurality of documents obtained at step 210 of method 200, based on which the statistical model was generated.

In some embodiments, if the electronic device cannot obtain a statistical model that was generated based on a plurality of documents associated with a particular entity specified by the user, the electronic device can obtain, instead, a statistical model that was generated based on a plurality of documents associated with another entity that is related to the particular entity. For example, if the user-specified entity is Apple Inc., and the electronic device cannot obtain a statistical model associated with Apple Inc. (e.g., if it has not been generated or is inaccessible) the electronic device can obtain, instead, a statistical model associated with the consumer-electronics industry, because that is an industry associated with Apple Inc. In some embodiments, the electronic device can access a designated database to determine which entities are associated with each other.

In some embodiments, if the electronic device cannot obtain a statistical model associated with the user-specified entity, the electronic device can generate such a statistical model (e.g., using method 200) in real time, after receiving user input at step 310. In some embodiments, the electronic device can generate a new statistical model in real time based on the user input, by using one or more previously generated statistical models. For example, if the documents obtained at step 210 were search results obtained based on user search query related to more than one distinct concept (e.g., “Apple versus Samsung”) the electronic device can generate a new statistical model by merging two previously generated models (e.g., a model associated with Apple, Inc. and a model associated with Samsung Group).

In some embodiments, if the electronic device cannot obtain a statistical model associated with the user-specified entity, the electronic device can obtain a predetermined (default) statistical model that is not necessarily associated with any particular entity and that was generated, for example, based on all documents available to the electronic device.

While step 330 is listed in the exemplary flowchart of FIG. 3 as being performed before step 340, it is appreciated that step 330 can be performed after step 340, or, generally, at any time before step 360.

At step 340, the electronic device can obtain the contents of the set of documents obtained at step 320. In some embodiments, for reasons of performance, the obtained content can include the headlines or titles of the documents, but not contain the entire text (the body) of the document. In other embodiments, in addition or instead of the headlines or titles of the documents, the obtained content can include the entire text (the body) of the documents. In yet other embodiments, the obtained content can also contain additional text associated with the documents, such as meta data, user comments, or any other additional text associated with the documents.

At step 350, the electronic device can segment the contents of the set of documents, e.g., break down the contents of each document into segments. Each segment can include one or more characters, which can include parts of words, single words (e.g., tokens), multiple words (e.g., n-grams), or entire phrases or clauses, such as noun phrases or clauses. For example, if document's content includes a headline “Apple releases a new iPhone device in October,” the electronic device can break this content into single-word segments “Apple,” “releases,” “a,” “new,” “iPhone,” “device,” “in,” “October.” As another example, the electronic device can break this content into bigram segments, e.g., “Apple releases,” “new iPhone,” “iPhone device,” “in October.” As seen from the last example, the electronic device can, in some embodiments, omit some content (e.g., articles, prepositions, etc.), and in some embodiments the same content can be included in more than one segment (e.g., the word “iPhone” in the above example appears in segments “new iPhone” and “iPhone device”).

In some embodiments, before or after breaking the content into segments, the electronic device can also perform various processing of the contents. For example, the electronic device can remove some words from the contents (e.g., articles and prepositions), normalize the contents by reducing each word in the to its morphological root or lemma, and so forth.

While steps 340 and 350 of method 300 for key phrase characterization of documents can be same or similar to steps 220 and 230 of method 200 for generating a statistical model, respectively, it is appreciated that steps 340 and 350 do not have to be same or similar to steps 220 and 230, respectively. In some embodiments, however, to achieve better results in terms of quality and/or performance, the electronic device can chose to use the same segmentation and processing methods at step 350 as the segmentation and processing methods performed at step 220.

At step 360, the electronic device can calculate the statistical significance of the segments obtained at step 350 based on the statistical model obtained at step 330. In some embodiments, the electronic device calculates the statistical significance of a segment by comparing the frequency with which the segment occurred in a particular document (or a set of documents) with the frequency of the segment as indicated in the statistical model. Because the statistical model can be generated based on a large corpus of documents, it can serve as an estimation of a typical or average frequency of a given segment within that corpus. Accordingly, by comparing the frequency of a given segment within a particular document to its frequency in the statistical model, the electronic device can determine whether the segment's frequency in the particular document is higher than average, which may be a good indication that the particular document is specifically directed to the concept or the subject matter described by the segment. For example, a segment “new iPhone” can have a frequency A in the particular document and a frequency B in the statistical model. If frequency A is higher than frequency B (e.g., higher by a predetermined threshold), i.e., the particular document mentions the term “new iPhone” more than usual, the electronic device can determine that the segment is statistically significant meaning that there is high likelihood that the particular document discusses a new iPhone® or some other closely related subject matter.

In some embodiments, the electronic device can calculate a statistical significance value for each segment obtained from the contents of a given document, where the calculation is based at least on the segment's frequency within the contents of the given document and the segment's frequency in the statistical model obtained based on user input in step 330. For example, the statistical significance value can be directly proportional to the segment's frequency within the contents of the given document and inversely proportional to the segment's frequency in the statistical model.

At step 370, the electronic device can determine one or more representative segments for each of the set of documents obtained at step 320. For example, the electronic device can determine, for each document, N segments having highest statistical significant values among segments of that document's contents, where N is an integer greater or equal to one. As discussed above, segments having higher statistical significance values are more likely to represent or correspond to the subject matter discussed in the document.

At step 380, the electronic device can determine, among all the representative segments obtained for the set of documents, one or more repetitive representative segments. For example, the electronic device can identify one or more groups of M or more identical or substantially identical representative segments, where M is a predetermined threshold that can be an integer greater or equal to two. For example, if the set of documents obtained at step 320 includes a thousand documents, and M=20, the electronic device can identify any groups of twenty or more documents having identical or substantially identical representative segments. In some embodiments, two segments can be considered substantially identical if the edit distance (e.g., Levenshtein distance) between them is small, e.g., lower than a predetermined threshold, and/or when the segments are synonyms of each other. Repetitive representative segments can indicate an important subject or event, such as a news event, that is described in multiple documents, such as multiple news sources.

In some embodiments, step 380 can be omitted, and each representative segment can be considered as a repetitive representative segment for the purposes of the following discussion.

At step 390, the electronic device can display (e.g., on display 112) or provide for display the one or more repetitive representative segments. For instance, in the example illustrated in FIG. 4A, the electronic device determines and displays in window 450 two repetitive representative segments: “Friday” and “Apple iPhone,” In some embodiments, as illustrated in FIGS. 4A and 4B, the electronic device can also allow the user to select one of the repetitive representative segments (e.g., “Apple iPhone” and “Friday,” respectively) and responsive to the user's selection, display (e.g., in an adjacent window 460) the contents of and/or links to the documents that contained the selected repetitive representative segment.

In some embodiments, to provide additional context to the segments and thereby improve readability, the electronic device can display or provide for display at step 390 a key phrase that includes the repetitive segment. The key phrase can include, for example, a complete sentence, a noun phrase, a verb phrase, or any other meaningful combination of words. The key phrase can be obtained by the electronic device, for example, from the contents of one of the documents having the repetitive representative segment. For example, if the repetitive representative segment “Apple iPhone” appeared in one of the documents (represented by the segment) as part of the phrase “AT&T stores getting ready for release of Apple iPhone,” the electronic device can display or provide for display (e.g., in key phrase window 470) the key phrase “release of Apple iPhone,” as illustrated in FIG. 4C. As another example, if the repetitive representative segment “Friday” appeared in one of the documents (represented by the segment) as part of the phrase “Consumers, industry eagerly await iPhone as Friday launch approaches,” the electronic device can display or provide for display the key phrase “Friday launch approaches,” as illustrated in FIG. 4C. In some embodiments, if the key phrase containing the repetitive representative segment is different in different documents represented by the segment, the electronic device can select, among the different key phrases, an “average” key phrase, i.e., the key phrase that is most similar to the other key phrases, as measured based on edit distance, based on the number of common words contained in the phrase, or any other suitable algorithm.

Allowing the user to select a particular date range, for example, around unusual changes in stock price or trading volume, and displaying repetitive segments or key phrases representing the documents (e.g., news articles) within that date range, allows the user to quickly determine which events may have caused the unusual changes.

Embodiments of the present disclosure have been described herein with reference to numerous specific details that can vary from implementation to implementation. Certain adaptations and modifications of the described embodiments can be made. Other embodiments can be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the present disclosure being indicated by the following claims. It is also intended that the sequence of steps shown in figures are only for illustrative purposes and are not intended to be limited to any particular sequence of steps. As such, it is appreciated that these steps can be performed in a different order while implementing the exemplary methods or processes disclosed herein.

Claims

1. An electronic device comprising: one or more computer-readable storage media configured to store instructions; andone or more processors configured to execute the instructions to cause the electronic device to: receive a user input indicative of an entity and a search query;identify a statistical model associated with the entity, wherein the statistical model is determined based on a first plurality of documents associated with the entity, the statistical model indicative at least of frequencies of one or more words within the first plurality of documents;identify, responsive to the user input, a second plurality of documents, at least partially different than the first plurality of documents, corresponding to the search query and the indicated entity;identify, for each of the second plurality of documents, one or more segments;apply the identified statistical model to each of the identified segments to determine, for each of the second plurality of documents, a statistical significance of segments identified in the documents, the statistical significance indicative of frequencies of the one or more words in the segment compared to the frequencies of the one or more words indicated in the statistical model;and provide for display at least a representative segment having a highest statistical significance and a link to the document containing the representative segment.

2. The electronic device of claim 1, wherein the second plurality of documents is a subset of the first plurality of documents.

3. The electronic device of claim 1, wherein the entity identifies a company, and the first plurality of documents are associated with an industry associated with the company.

4. The electronic device of claim 1, wherein the user input comprises user's selection of an area on a stock chart, and wherein the first plurality of documents have publication dates corresponding to a date range that corresponds to the area on the stock chart.

5. The electronic device of claim 1, wherein providing the representative segment for display comprises providing for display a phrase from the representative segment.

6. The electronic device of claim 1, wherein the one or more processors are further configured to execute the instructions to cause the electronic device to: after providing the representative segment for display, receive a selection input associated with the representative segment; andresponsive to the selection input, provide for display the contents of one or more of the second plurality of documents.

7. The electronic device of claim 1, wherein statistical significance of segments is further based on a comparison of the statistical model and content of the second plurality of documents.

8. A method comprising: by a computing system comprising a hardware computer processor and non-transitory storage medium storing software instructions,receive a user input indicative of an entity and a search query;identify a statistical model associated with the entity, wherein the statistical model is determined based on a first plurality of documents associated with the entity, the statistical model indicative at least of frequencies of one or more words within the first plurality of documents;identify a second plurality of documents, at least partially different than the first plurality of documents, corresponding to the search query and the indicated entity;identify, for each of the second plurality of documents, one or more segments;apply the identified statistical model to each of the identified segments to determine, for each of the second plurality of documents, a statistical significance of segments identified in the documents, the statistical significance indicative of frequencies of the one or more words in the segment compared to the frequencies of the one or more words indicated in the statistical model; andprovide for display at least a representative segment having a highest statistical significance and a link to the document containing the representative segment.

9. The method of claim 8, wherein the second plurality of documents is a subset of the first plurality of documents.

10. The method of claim 8, wherein the entity identifies a company, and the first plurality of documents are associated with an industry associated with the company.

11. The method of claim 8, further comprising: after providing the representative segment for display, receiving a selection input associated with the representative segment; andresponsive to the selection input, providing for display the contents of one or more of the second plurality of documents.

12. The method of claim 8, wherein statistical significance of segments is further based on comparing the statistical model and content of the second plurality of documents.

13. A non-transitory computer-readable medium storing a set of instructions that are executable by one or more electronic devices, each having one or more processors, to cause the one or more electronic devices to perform a method, the method comprising: receiving a user input indicative of an entity and a search query;identifying a statistical model associated with the entity, wherein the statistical model is determined based on a first plurality of documents associated with the entity, the statistical model indicative at least of frequencies of one or more words within the first plurality of documents;identifying a second plurality of documents, at least partially different than the first plurality of documents, corresponding to the search query and the indicated entity;identifying, for each of the second plurality of documents, one or more segments;applying the identified statistical model to each of the identified segments to determine, for each of the second plurality of documents, a statistical significance of segments identified in the documents, the statistical significance indicative of frequencies of the one or more words in the segment compared to the frequencies of the one or more words indicated in the statistical model; andproviding for display at least a representative segment having a highest statistical significance and a link to the document containing the representative segment.

14. The non-transitory computer-readable medium of claim 13, wherein the second plurality of documents is a subset of the first plurality of documents.

15. The non-transitory computer-readable medium of claim 13, wherein the entity identifies a company, and the first plurality of documents are associated with an industry associated with the company.

16. The non-transitory computer-readable medium of claim 13, wherein the user input comprises user's selection of an area on a stock chart, and wherein the first plurality of documents have publication dates corresponding to a date range that corresponds to the area on the stock chart.

17. The non-transitory computer-readable medium of claim 13, wherein providing the representative segment for display comprises providing for display a phrase from the representative segment.