Providing Variable Responses in a Virtual-Assistant Environment

• US 20180095565A1
• Filed: 11/30/2017
• Published: 04/05/2018
• Est. Priority Date: 12/30/2011
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Next IT Corporation (Verint Systems Incorporated)
• Inventors: Brown, Fred A., Miller, Tanya M., Zartler, Mark
• Granted Patent: US 10,983,654 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 2203/04803 Split screen, i.e. subdividing the display area or the window area into separate subareas
• CPC Class Codes: G06F 3/048 Interaction techniques based on graphical user interfaces [GUI]
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

Virtual assistants intelligently emulate a representative of a service provider by providing variable responses to user queries received via the virtual assistants. These variable responses may take the context of a user'"'"'s query into account both when identifying an intent of a user'"'"'s query and when identifying an appropriate response to the user'"'"'s query.

Claims

1. (canceled)

2. One or more computing devices for implementing a virtual assistant that emulates human-to-human interaction, the one or more computing devices comprising:

one or more processors; and

one or more computer-readable media storing computer-executable instructions that, when executed on the one or more processors, cause the one or more processors to perform acts comprising;

causing display of the virtual assistant on or adjacent to a site of a service provider;

receiving, via an interface provided by the virtual assistant, a single query from a user device of a user while the user is engaged in a session on the site of the site provider, wherein the single query comprises a fixed word or phrase;

at least partly in response to receiving the single query;

parsing the single query to identify one or more concepts expressed in the single query;

identifying context associated with at least one of the user or the session of the user on the site;

identifying, from one or more datastores storing indications of intents and based at least in part on the one or more concepts, a first intent associated with the single query and a second intent associated with the single query, the first intent being mapped in the one or more datastores to a first plurality of responses and the second intent being mapped in the one or more datastores to a second plurality of

responses, wherein the first plurality of responses is different than the second plurality of responses;

mapping the single query to the first intent based at least in part on a first portion of the context;

identifying a response to the single query from the first plurality of responses and based at least in part on a second portion of the context, the second portion of the context being different than the first portion of the context; and

providing at least a portion of the response to the user via the virtual assistant.

3. The one or more computing devices as recited in claim 2, wherein the single query comprises a string of text, and the identifying of the one or more concepts comprises identifying one or more keywords within the string of text and mapping the one or more keywords to the one or more concepts.

4. The one or more computing devices as recited in claim 2, wherein the single query comprises a string of text, and the identifying of the one or more concepts comprises:

identifying one or more tokens within the string of text;

mapping the one or more tokens to one or more vocab items; and

pattern matching the one or more vocab items to the one or more concepts.

5. The one or more computing devices as recited in claim 2, wherein the context comprises at least one of:

a device type of the user device that is used by the user to interact with the virtual assistant;

a type of natural language of the single query received from the user;

whether or not the user has signed in with the service provider;

a status of the user with the service provider;

an age of the user;

a page of the site from which the user provides the single query to the virtual assistant;

how long the user has remained on the page of the site from which the user provides the single query to the virtual assistant;

a navigation history of the user during the session prior to the user providing the single query to the virtual assistant;

a location of a cursor when the user provides the single query to the virtual assistant;

a prior query provided by the user to the virtual assistant during the session or during a prior session with the site;

a date on which the single query is received;

a time of day at which the user provides the single query to the virtual assistant;

a location of the user;

or

a previous interaction between the user and the virtual assistant.

6. The one or more computing devices as recited in claim 2, wherein providing the at least the portion of the response to the user via the virtual assistant comprises:

causing content to be displayed on the user device of the user via the virtual assistant; and

causing performance of an action on behalf of the user.

7. The one or more computing devices as recited in claim 6, wherein the action comprises at least one of:

purchasing an item on behalf of the user;

initiating a request on behalf of the user;

initiating a communication on behalf of the user;

or

altering a reservation or order on behalf of the user.

8. The one or more computing devices as recited in claim 2, wherein mapping of the single query to the first intent based at least in part on the first portion of the context comprises:

identifying a value of a variable associated with the first portion of the context; and

determining that the value of the variable maps to the first intent.

9. The one or more computing devices as recited in claim 8, wherein the value comprises a first value, the variable comprises a first variable, and identifying the response from the plurality of responses based at least in part on the second portion of the context comprises:

identifying a second value of a second variable associated with the second portion of the context; and

determining that the second value of the second variable maps to the response.

10. A method for implementing a virtual assistant, the method comprising:

receiving, from a computing device associated with a user, a single request for information via the virtual assistant, wherein the single request is received while the user engages in a session on a site of a service provider associated with the virtual assistant, and wherein the single request comprises a fixed word or phrase;

parsing the single request to identify one or more concepts expressed in the fixed word or phrase;

identifying a context associated with at least one of the user or the session of the user on the site;

identifying, from one or more datastores storing indications of intents and based at least in part on the one or more concepts, a first intent associated with the single request and a second intent associated with the single request, the first intent being mapped in the one or more datastores to a first plurality of responses and the second intent being mapped in the one or more datastores to a second plurality of responses, wherein the first plurality of responses is different than the second plurality of responses;

mapping the single request to the first intent based at least in part on the context;

identifying, from the one or more datastores, a plurality of responses to the single request and associated with the first intent;

identifying a response to the single request from the plurality of responses and based at least in part on the context; and

providing at least a portion of the response to the user via the virtual assistant.

11. The method as recited in claim 10, wherein:

mapping of the single request to the first intent is based at least in part on a first portion of the context;

identifying of the response to the single request from the plurality of responses is based at least in part on a second portion of the context; and

the first portion of the context is different than the second portion of the context.

12. The method as recited in claim 11, wherein mapping of the single request to the first intent based at least in part on the first portion of the context comprises:

identifying a value of a variable associated with the first portion of the context; and

determining that the value of the variable maps to the first intent.

13. The method as recited in claim 12, wherein the value comprises a first value, the variable comprises a first variable, and identifying the response from the plurality of responses and based at least in part on the second portion of the context comprises:

identifying a second value of a second variable associated with the second portion of the context; and

determining that the second value of the second variable maps to the response.

14. The method as recited in claim 10, wherein providing the at least the portion of the response to the user via the virtual assistant comprises:

causing content to be displayed on the user device of the user via the virtual assistant; and

causing performance of an action on behalf of the user.

15. The method as recited in claim 14, wherein:

the service provider comprises an airline service; and

causing performance of the action comprises at least one of;

booking a flight via the site of the airline service;

or

altering a seat assignment of the user on a booked flight provided by the airline service.

16. A system comprising:

one or more processors; and

one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to serve or render a graphical user interface (GUI), the GUI comprising;

an avatar that emulates a human for conversing with a user, wherein the avatar is associated with a service provider;

a text box to receive, from the user, a single query comprising a string of text, wherein the single query is received while the user engages in a session on a site of the service provider; and

an area to display at least a portion of a response to the single query, the response having been determined subsequent to the single query and by;

parsing, by the one or more processors, the single query to identify one or more concepts expressed in the string of text;

identifying a first value of a first variable associated with the single query and a second value of a second variable associated with the single query, wherein the first value of the first variable and the second value of the second variable collectively define a context associated with the single query;

identifying, based at least in part on the one or more concepts, a first intent associated with the single query and a second intent associated with the single query, wherein the first intent is associated with a first plurality of responses and the second intent is associated with a second plurality of responses;

selecting, from amongst the first intent and the second intent, the first intent based at least in part on the first value of the first variable defining the context associated with the single query; and

selecting, from amongst the first plurality of responses, the response based at least in part on the second value of the second variable defining the context associated with the single query, wherein the at least the portion of the response to the single query comprises content displayed in the area.

17. The system as recited in claim 16, wherein:

the single query is received from the user via a first communication channel; and

the at least the portion of the response is displayed in the area via a second communication channel.

18. The system as recited in claim 17, wherein the computer-executable instructions further cause the one or more processors to perform acts comprising:

determining, based at least in part on the context, to switch from the first communication channel to the second communication channel to provide the at least the portion of the response; and

selecting the second communication channel from a plurality of communication channels to utilize to provide the at least the portion of the response to the user, the second communication channel being selected based at least in part on a communication channel that has been previously used to communicate by the user with the avatar.

19. The system as recited in claim 18, wherein the plurality of communication channels being selected from includes at least a web interface and a text message.

20. The system as recited in claim 18, wherein determining, based at least in part on context, to switch from the first communication channel to the second communication channel includes at least one of:

identifying an event in a schedule associated with the user;

or

identifying a change in a geo location of the user.

21. The system as recited in claim 16, wherein each of the first plurality of responses specify (i) respective content for output in the area of the GUI, and (ii) respective actions to perform on behalf of the user.