Method of using a virtual assistant

Patent metadata

Field	Value
Publication number	US-11960694-B2
Application number	US-202117232529-A
Country	US
Kind code	B2
Filing date	Apr 16, 2021
Priority date	Dec 30, 2011
Publication date	Apr 16, 2024
Grant date	Apr 16, 2024

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.

First claim

What is claimed is:

1. A method of using a virtual assistant as an interface between a user and information of a service provider, the method comprising:
a virtual assistant service that is running in parallel to the service provider causing rendering of a display of the virtual assistant on or adjacent to a site of the service provider, the rendering comprising content of the virtual assistant, wherein content of the service provider is provided on the site by the service provider;
receiving, via the virtual assistant service over a first communication channel, a query from a user while the user engages in a session with the service provider on the site of the service provider;
the virtual assistant service processing the query to identify one or more tokens in the query, the one or more tokens comprising words, phrases, or symbols;
the virtual assistant service mapping the identified tokens to a plurality of vocab items, wherein each vocab item comprises a general set of multiple different tokens having a common meaning amongst the identified tokens;
the virtual assistant service identifying a concept expressed in the query based on the plurality of vocab items;
the virtual assistant service identifying a context based on factors associated with at least one of the user or the session of the user on the site;
the virtual assistant service mapping at least one combination of an identified context and an identified concept to at least one intent, from one or more datastores storing indications of intents;
the virtual assistant service mapping the at least one intent associated in the one or more datastores to a plurality of responses;
the virtual assistant service determining an action to be performed in response to the query based at least in part on the intent and the context; and
causing the action to be performed by the site of the service provider and one of the responses of the plurality of responses to be provided to the user over a second communication channel selected based on the context.

2. The method of claim 1 , wherein the identifying the intent comprises mapping the one or more concepts to one of multiple different intents associated with the one or more concepts based at least in part on the context.

3. The method of claim 1 , wherein the determining of the action comprises mapping the intent to an action of multiple different actions associated with the intent based at least in part on the context.

4. The method of claim 3 , wherein the mapping of the intent to the action comprises: identifying respective values of multiple different variables associated with the query; and mapping the intent to the one of multiple actions based at least in part on the values of the variables associated with the query.

5. The method of claim 3 , wherein: the associating the intent with the query comprises: identifying multiple different concepts expressed in the query; identifying respective values of a first set of variables associated with the query; and mapping the query to the intent based at least in part on the concepts expressed in the query and the values of the first set of variables associated with the query; and the mapping of the intent to the response comprises identifying respective values of a second set of variables associated with the query; and mapping the intent to the response based at least in part on the values of the second set variables associated with the query.

6. The method of claim 5 , wherein the first and second sets of variables include at least one common variable.

7. The method of claim 5 , wherein the first and second sets of variables do not include a common variable.

8. The method of claim 1 , wherein the intent is identified with reference to at least a first portion of the context and the action is identified with reference to at least a second, different portion of the context.

9. The method of claim 1 , wherein the context comprises: whether or not the user has signed in with the site of the service provider; a status of the user with the service provider; a page of the site from which the user provides the query to the virtual assistant; how long the user has remained on the page of the site from which the user provides the query to the virtual assistant; a navigation history of the user during the session prior to the user providing the query to the virtual assistant; a location of a cursor when the user provides the 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 time of day at which the user provides the query to the virtual assistant; a date on which the user provides the query to the virtual assistant; an age of the user; a location of the user; a device type from which the user accesses the site; a language of the user; or a previous interaction between the user and the virtual assistant.

10. The method of claim 1 , further comprising providing a response based on the mapping, wherein providing the response comprises outputting content on a computing device of the user via the virtual assistant.

11. The method of claim 10 , wherein the outputting of the content comprises; displaying, by the virtual assistant, plain text and one or more hyperlinks related to the query; and audibly outputting content related to the query.

12. The method of claim 1 , wherein the user provided the query to the virtual assistant while on a first page of the site with content provided by the service provider, and the action comprises causing the computing device of the user to navigate to a second, different page of the site with content provided by the service provider.

13. The method of claim 1 , wherein the action comprises: 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.

14. The method of claim 1 , wherein the virtual assistant is configured to emulate human-to-human interaction between the user and a representative of the service provider.

15. The method of claim 1 , wherein the virtual assistant resembles a human when displayed on or adjacent to the site of the service provider.

16. The method of claim 1 , wherein the virtual assistant comprises a representation of a human face, the interface comprises a text box adjacent to the representation of the human face, and the query comprises a string of text input into the text box.

17. The method of claim 1 , wherein the association of the intent with the query comprises: identifying multiple different concepts expressed in the query; identifying respective values of multiple different variables associated with the query; and mapping the query to the intent based at least in part on the concepts expressed in the query and the values of the variables associated with the query.

18. The method of claim 1 , wherein the virtual assistant embodies a human representative.

19. The method of claim 1 , further comprising using pattern matching of the vocab item in identifying at least one of the one or more concepts.

20. The method of claim 1 , further comprising using a graph data structure that maintains correlations between words in identifying at least one of the one or more concepts.

Assignees

• Verint Americas Inc

Inventors

• Brown Fred A
• Miller Tanya M
• Zartler Mark

Classifications

• G06F3/048 Primary

  Interaction techniques based on graphical user interfaces [GUI] · CPC title

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• G06F2203/04803

  Split screen, i.e. subdividing the display area or the window area into separate subareas · CPC title