EP2691870A2

EP2691870A2 - Task driven user intents

Info

Publication number: EP2691870A2
Application number: EP20120764494
Authority: EP
Inventors: Larry Paul Heck; Madhusudan Chinthakunta; David Mitby; Lisa Stifelman
Original assignee: Microsoft Corp
Current assignee: Microsoft Technology Licensing LLC
Priority date: 2011-03-31
Filing date: 2012-03-27
Publication date: 2014-02-05
Also published as: CN102737101A; CN102750270A; EP2691885A4; CN102737104B; JP6105552B2; EP2691876A4; JP2014515853A; CN102750311B; WO2012135157A3; EP2691877A4; CN102737099B; KR101963915B1; JP2014512046A; JP2014509757A; WO2012135210A3; WO2012135218A2; JP2017123187A; EP2691875A2; WO2012135226A1; CN106383866B

Abstract

Identification of user intents may be provided. A plurality of network applications may be identified, and an ontology associated with each of the plurality of applications may be defined. If a phrase received from a user is associated with at least one of the defined ontologies, an action associated with the network application may be executed.

Description

TASK DRIVEN USER INTENTS

BACKGROUND

[001] Task driven user intents may provide a mechanism for facilitating natural language understanding of user queries and conversations. In some situations, web and/or cloud-based network services may offer a wide array of information to users, but a search agent may not be able to understand a user's context to choose which service to query. For example, a natural language phrase of "let's do Italian tonight" may not be understood by a search engine, which may return results associated with translating the phrase into Italian rather than searching for an Italian restaurant. Thus, conventional systems require specific syntax to define a search domain rather than being able to identify that domain from the context of the search.

SUMMARY

[002] 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.

[003] Identification of user intents may be provided. A plurality of network applications may be identified, and an ontology associated with each of the plurality of applications may be defined. If a phrase received from a user is associated with at least one of the defined ontologies, an action associated with the network application may be executed.

[004] 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

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

[006] FIG. 1 is a block diagram of an operating environment; [007] FIG. 2 is a flow chart of a method for providing an understanding of user intents; and

[008] FIG. 3 is a block diagram of a system including a computing device.

DETAILED DESCRIPTION

[009] 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.

[010] Spoken dialog systems (SDS) enable people to interact with computers with their voice. The primary component that drives the SDS may comprise a dialog manager: this component manages the dialog-based conversation with the user. The dialog manager 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 semantic concepts and data associated with an ontology. After determining the intention, the dialog manager 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.

[011] FIG. 1 is a block diagram of an operating environment 100 comprising a server 105 comprising a spoken dialog system (SDS) 110. Server 105 may comprise software applications such as a personal assistant program 1 12 and/or a search agent 1 14. SDS 110 may comprise a dialog manager 1 15 and may be operative to receive user phrases, queries, and/or action requests via a network 120. Network 120 may comprise a private network (e.g., a corporate intranet), a cellular network, and/or a public network such as the Internet. Operating environment 100 may further comprise a plurality of network applications 150(A)-(C). Network applications 150(A)-(C) may comprise data sources, such as a stock market quote service and/or a weather data service, and/or web services such as a restaurant reservation tool.

[012] 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 understanding of user intents. Method 200 may be implemented using a computing device 300 as described in more detail below with respect to FIG. 3. 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 300 may identify a plurality of network applications. For example, SDS 1 10 may parse web pages provided by each of plurality of network applications 150(A)-(C). Those web pages may comprise publically accessible APIs that may be called by a remote process, such as search agent 1 14. Such APIs may comprise functional definitions within the web page that may identify required parameters in order to successfully call the API. For another example, application-specific ontologies may be provided by the network applications.

[013] Method 200 may then advance to stage 215 where computing device 300 may receive and/or define an ontology for each of the identified applications. For example, SDS 110 may receive a "restaurant" ontology for a restaurant rating website such as Zagat® or reservation site OpenTable®. Similarly, a "travel" ontology may be defined for a travel booking website such as Expedia®. Each identified application, it's associated ontology, and any required parameters may then be stored in a database associated with SDS 1 10.

[014] Method 200 may then advance to stage 220 where computing device 300 may receive a phrase from a user. For example, a user may speak into a cellular phone comprising user device 130 and say "let's get dinner tonight."

[015] Method 200 may then advance to stage 225 where computing device 300 may determine whether the phrase is associated with one of the defined ontologies. For example, "dinner" may comprise a keyword associated with a "restaurant" ontology. Consistent with embodiments of the invention, the ontology associated with the application may comprise a shared ontology that may be merged with a personal ontology of the user. The received phrase may be compared to semantic concepts associated with the merged ontology (and/or multiple merged ontologies) to identify an intent of the received phrase.

[016] If an associated semantic concept is identified, method 200 may advance to stage 227 where computing device 300 may translate the phrase into an agent action associated with at least one of the plurality of network-based applications according to the merged ontology. For example, the received phrase "let's get dinner tonight" may be translated into a search action for nearby restaurants with reservations available tonight. [017] Method 200 may then advance to stage 230 where computing device 300 may determine whether the required parameters were received. For example, to perform a search on a restaurant reservation network service, a time-frame may be required. The concept "tonight" may be translated into the required time-frame for the associated application.

[018] If no ontology is matched at stage 225, or if required parameters are not found at stage 230, method 200 may advance to stage 235 where computing device 300 may request more information. For example, personal assistant program 1 12 may ask the user for the required information via a voice prompt and/or a display on user device 130.

[019] If the required parameters are found at stage 230, method 200 may advance to stage 240 where computing device 300 may execute the translated action on the associated application. For example, server 105 may execute a remote procedure call to network application 150(A) using the required parameters from the user phrase.

[020] Method 200 may then advance to stage 245 where computing device 300 may display a result to the user. For example, server 105 may receive a result associated with the executed action from network application 150(A). This result may then be transmitted to user device 130 for display on a screen and/or for being output via audio (e.g., text-to-speech). Method 200 may then end at stage 250.

[021] An embodiment consistent with the invention may comprise a system for providing identification of a user intent. 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 applications define a domain associated with each of the plurality of applications, receive a phrase from a user, and determine whether the phrase is associated with at least one domain associated with at least one of the applications. In response to determining that the phrase comprises the context associated with the at least one domain associated with the at least one of the applications, the processing unit may be operative to perform a call to the at least one of the applications according to the phrase. Each application may be associated with a network resource, such as a search function of a web page. Some and/or all of the applications may comprise a set of related application programming interfaces (APIs). For example, the set of APIs may be associated with different functions available at a web page.

[022] The processing unit may be further operative to display a result associated with performing the call to the at least one of the applications according to the phrase, determine whether a second phrase has been received from the user, and, if so, determine whether the second phrase is associated with the same application. In response to determining that the second phrase is associated with the same application, the processing unit may be operative to perform a second call to the at least one of the set of related APIs according to the second phrase and display a result associated with the second call.

[023] Another embodiment consistent with the invention may comprise a system for providing identification of a user intent. 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, parse the phrase into a plurality of words, identify a domain associated with the phrase according to the plurality of words, determine whether at least one of a plurality of applications is associated with the identified domain, and, if so, prepare a call to execute an action associated with the application using at least one of the plurality of words as a parameter of the call. The processing unit may be further operative to receive a second phrase, parse the phrase into a second plurality of words, determine whether the second phrase is associated with the domain, and, if so, update the agent action associated with the application with at least one of the plurality of second words comprising a second parameter of the call. The second phrase may be received from the same user and/or a second user, such as when two users are involved in a conversation. In response to determining that the second phrase is not associated with the domain, the processing unit may execute the call to the at least one of the plurality of APIs, receive a response associated with the executed call to the at least one of the plurality of APIs, and display the received response to the user. Consistent with embodiments of the invention, the domain associated with the phrase may comprise, for example, a work domain, a restaurant domain, a calendaring domain, a travel domain, an entertainment domain, and a map domain.

[024] Yet another embodiment consistent with the invention may comprise a system for providing identification of a user intent. 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 applications, define an ontology associated with each of the plurality of applications, receive a first phrase from a user, and determine whether the phrase is associated with at least one ontology associated with at least one of the plurality of applications. Each of the plurality of applications may comprise at least one required parameter. In response to determining that the phrase is associated with the at least one ontology, the processing unit may be operative to merge the defined ontology with a second ontology associated with the user, translate the first phrase into an agent action associated with at least one of the plurality of network-based applications according to the merged ontology, and determine whether the phrase comprises sufficient information to execute the agent action (e.g., the at least one required parameter associated with the at least one of the plurality of applications). If so, the processing unit may be operative to execute the agent action, such as by performing a call comprising the at least one required parameter to the network application associated, and display a result associated with executing the agent action.

[025] FIG. 3 is a block diagram of a system including computing device 300. 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 300 of FIG. 3. 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 300 or any of other computing devices 318, in combination with computing device 300. 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 300 may comprise an operating environment for system 100 as described above. System 100 may operate in other environments and is not limited to computing device 300.

[026] With reference to FIG. 3, a system consistent with an embodiment of the invention may include a computing device, such as computing device 300. In a basic configuration, computing device 300 may include at least one processing unit 302 and a system memory 304. Depending on the configuration and type of computing device, system memory 304 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 304 may include operating system 305, one or more programming modules 306, and may include personal assistant program 1 12. Operating system 305, for example, may be suitable for controlling computing device 300'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. 3 by those components within a dashed line 308.

[027] Computing device 300 may have additional features or functionality. For example, computing device 300 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. 3 by a removable storage 309 and a non-removable storage 310. 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 304, removable storage 309, and non-removable storage 310 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 300. Any such computer storage media may be part of device 300. Computing device 300 may also have input device(s) 312 such as a keyboard, a mouse, a pen, a sound input device, a touch input device, etc. Output device(s) 314 such as a display, speakers, a printer, etc. may also be included. The aforementioned devices are examples and others may be used.

[028] Computing device 300 may also contain a communication connection 316 that may allow device 300 to communicate with other computing devices 318, such as over a network in a distributed computing environment, for example, an Intranet or the Internet. Communication connection 316 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.

[029] As stated above, a number of program modules and data files may be stored in system memory 304, including operating system 305. While executing on processing unit 302, programming modules 306 (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 302 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.

[030] 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.

[031] 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.

[032] 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.

[033] 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.

[034] 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.

[035] 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. [036] 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.

[037] 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

WHAT IS CLAIMED IS:

1. A method for providing a user intent identification, the method comprising: identifying a plurality of network-based applications;

generating an ontology associated with each of the plurality of network-based applications;

receiving a natural language phrase from a user;

determining whether the natural language phrase is associated with at least one ontology associated with at least one of the applications; and

in response to determining that the natural language phrase is associated with the at least one ontology, executing an agent action associated with the at least one of the plurality of network-based applications according to the natural language phrase.

2. The method of claim 1, further comprising merging a shared ontology associated with at least one of the network-based applications with a personal ontology associated with the user.

3. The method of claim 1, wherein defining the ontology associated with each of the plurality of applications comprises identifying at least one required parameter associated with each of the plurality of applications.

4. The method of claim 3, wherein determining whether the natural language phrase is associated with at least one ontology associated with at least one of the applications comprises determining whether the phrase comprises the at least one required parameter associated with the at least one of the applications.

5. The method of claim 1, wherein at least one of the plurality of applications is associated with a plurality of related APIs each associated a shared ontology and further comprising:

displaying a result associated with performing the action on the at least one of the applications;

determining whether a second phrase has been received from the user; and in response to determining that the second phrase has been received from the user, determining whether the second phrase is associated with the shared ontology.

6. A computer-readable medium which stores a set of instructions which when executed performs a method for providing an identification of a user intent, the method executed by the set of instructions comprising:

receiving a phrase from a user;

identifying an ontology associated with the phrase;

determining whether at least one of a plurality of applications is associated with the identified ontology; and

in response to determining that the at least one of the plurality of applications is associated with the identified ontology, creating an agent action on the at least one of the plurality of applications according to the received phrase.

7. The computer-readable medium of claim 6, further comprising:

receiving a second phrase;

determining whether the second phrase is associated with the ontology; and in response to determining that the second phrase is associated with the ontology, updating the agent action to the at least one of the plurality of applications according to the second phrase.

8. The computer-readable medium of claim 7, further comprising:

in response to determining that the second phrase is not associated with the itology, executing the agent action on the at least one of the plurality of applications.

9. The computer-readable medium of claim 6, wherein the ontology associated with the phrase comprises at least one of the following: a work domain, a restaurant domain, a calendaring domain, a travel domain, an entertainment domain, and a map domain.

10. A system for providing an identification of a user intent, the system comprising:

a memory storage; and

a processing unit coupled to the memory storage, wherein the processing unit is operative to:

identify a plurality of network-based applications, wherein each of the plurality of network-based application is associated with a web page,, define an ontology associated with each of the plurality of applications, wherein the domain is defined according to at least one of the following: an application programming interface (API) associated with the application and an ontology provided by the application,,

receive a first phrase from a user, wherein the first phrase comprises a natural language phrase,

determine whether the first phrase is associated with at least one defined ontology, in response to determining that the phrase is associated with the at least one defined ontology, translate the first phrase into an agent action associated with at least one of the plurality of network-based applications according to the merged ontology,

determine whether the translation of the first phrase into the agent action comprises sufficient information to execute the agent action,

in response to determining that the translation of the first phrase into the agent action does not comprise sufficient information to execute the agent action, request at least one element of additional information from the user,

execute the agent action on the associated at least one of the plurality of network- based applications, and

display a result associated with executing the agent action.