Providing Variable Responses in a Virtual-Assistant Environment
First Claim
Patent Images
1. One or more computer-readable media storing computer-executable instructions that, when executed on one or more processors, cause the one or more processors to perform acts comprising:
- causing display of a virtual assistant on or adjacent to a site of a service provider;
receiving, via the virtual assistant, a query from a user while the user engages in a session on the site of the service provider; and
at least partly in response to receiving the query;
parsing the query to identify one or more concepts expressed therein;
identifying a context associated with the user or associated with the session of the user on the site;
determining an intent of the query based at least in part on the one or more concepts and the context;
determining a response to the query based at least in part on the intent and the context; and
providing at least a portion of the response to the user via the virtual assistant.
7 Assignments
0 Petitions
Accused Products
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.
138 Citations
32 Claims
-
1. One or more computer-readable media storing computer-executable instructions that, when executed on one or more processors, cause the one or more processors to perform acts comprising:
-
causing display of a virtual assistant on or adjacent to a site of a service provider; receiving, via the virtual assistant, a query from a user while the user engages in a session on the site of the service provider; and at least partly in response to receiving the query; parsing the query to identify one or more concepts expressed therein; identifying a context associated with the user or associated with the session of the user on the site; determining an intent of the query based at least in part on the one or more concepts and the context; determining a response to the query based at least in part on the intent and the context; and providing at least a portion of the response to the user via the virtual assistant. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. 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; receiving a query via an interface provided by the virtual assistant; mapping the query to one of multiple different intents with reference to both contents of the query and a context in which the virtual assistant received the query; mapping the intent to one of multiple different responses with reference to the context in which the virtual assistant received the query; and providing at least a portion of the response via the virtual assistant. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
-
21. A method comprising:
under control of one or more computing systems configured to implement a virtual assistant, receiving a request for information from a user via the virtual assistant; identifying one or more concepts within the request for information; determining a value of a first variable associated with the user; mapping the request for information to one of multiple different intents based at least in part on the identified one or more concepts and the determined value of the first variable; determining a value of a second variable associated with the user; and identifying a reply to provide in response to the request for information based at least in part on the mapped intent and the determined value of the second variable. - View Dependent Claims (22, 23, 24, 25, 26, 27, 28)
-
29. One or more computer-readable media storing computer-executable instructions that, when executed on 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; a text box to receive, from the user, a query comprising a string of text; and an area to display at least a portion of a response to the query, the response having been determined by (i) mapping at least a portion of the string of text and a context associated with the query to an intent, and (ii) mapping the intent and the context to the response. - View Dependent Claims (30, 31, 32)
-
Specification