Systems and methods for providing a virtual assistant
First Claim
Patent Images
1. A method comprising:
- using at least one computer to perform acts of;
accessing information specifying at least one user-specified condition and at least one corresponding user-specified action to be performed when the at least one user-specified condition is met, wherein the at least one user-specified condition specifies a topic and the at least one corresponding user-specified action comprises outputting for presentation to a user information related to the topic;
in response to determining that obtained information related to the topic meets the at least one user-specified condition, causing a virtual assistant executing on a mobile device to perform the at least one corresponding user-specified action, wherein performing the at least one corresponding user-specified action comprises outputting, by the virtual assistant, at least some of the obtained information related to the topic for presentation to a user via the mobile device; and
after causing the virtual assistant to output the at least some of the obtained information related to the topic to the user;
selecting a topic-dependent language model, from among a plurality of language models, based on the topic specified by the at least one user-specified condition that was met by the obtained information, wherein the topic-dependent language model is specifically adapted for recognition of input related to the topic;
receiving first voice input of the user including a request for additional information about the topic;
processing the first voice input using automatic speech recognition techniques at least in part by using the topic-dependent language model for the topic specified by the at least one user-specified condition.
3 Assignments
0 Petitions
Accused Products
Abstract
A method, performed by at least one computer, the method comprising using the at least one computer to perform acts of accessing information specifying at least one user-specified condition specified by a user and at least one corresponding user-specified action, the user-specified action to be performed when the user-specified condition is met; determining whether the at least one user-specified condition is met; and when it is determined that the at least one user-specified condition is met, causing a virtual assistant executing on a mobile device different from the at least one computer to perform the at least one user-specified action.
-
Citations
20 Claims
-
1. A method comprising:
using at least one computer to perform acts of; accessing information specifying at least one user-specified condition and at least one corresponding user-specified action to be performed when the at least one user-specified condition is met, wherein the at least one user-specified condition specifies a topic and the at least one corresponding user-specified action comprises outputting for presentation to a user information related to the topic; in response to determining that obtained information related to the topic meets the at least one user-specified condition, causing a virtual assistant executing on a mobile device to perform the at least one corresponding user-specified action, wherein performing the at least one corresponding user-specified action comprises outputting, by the virtual assistant, at least some of the obtained information related to the topic for presentation to a user via the mobile device; and after causing the virtual assistant to output the at least some of the obtained information related to the topic to the user; selecting a topic-dependent language model, from among a plurality of language models, based on the topic specified by the at least one user-specified condition that was met by the obtained information, wherein the topic-dependent language model is specifically adapted for recognition of input related to the topic; receiving first voice input of the user including a request for additional information about the topic; processing the first voice input using automatic speech recognition techniques at least in part by using the topic-dependent language model for the topic specified by the at least one user-specified condition. - View Dependent Claims (2, 3, 4, 13, 16, 17, 18)
-
5. A system comprising:
at least one computer configured to perform acts of; accessing information specifying at least one user-specified condition and at least one corresponding user-specified action to be performed when the at least one user-specified condition is met, wherein the at least one user-specified condition specifies a topic and the at least one corresponding user-specified action comprises outputting for presentation to a user information related to the topic; in response to determining that obtained information related to the topic meets the at least one user-specified condition, causing a virtual assistant executing on a mobile device to perform the at least one corresponding user-specified action, wherein performing the at least one corresponding user-specified action comprises outputting, by the virtual assistant, at least some of the obtained information related to the topic for presentation to a user via the mobile device; and after causing the virtual assistant to output the at least some of the obtained information related to the topic to the user; selecting a topic-dependent language model, from among a plurality of language models, based on the topic specified by the at least one user-specified condition that was met by the obtained information, wherein the topic-dependent language model is specifically adapted for recognition of input related to the topic; receiving first voice input of the user including a request for additional information about the topic; processing the first voice input using automatic speech recognition techniques at least in part by using the topic-dependent language model for the topic specified by the at least one user-specified condition. - View Dependent Claims (6, 7, 8, 14, 19)
-
9. At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer, cause the at least one computer to perform a method comprising acts of:
-
accessing information specifying at least one user-specified condition and at least one corresponding user-specified action to be performed when the at least one user-specified condition is met, wherein the at least one user-specified condition specifies a topic and the at least one corresponding user-specified action comprises outputting for presentation to a user information related to the topic; in response to determining that obtained information related to the topic meets the at least one user-specified condition, causing a virtual assistant executing on a mobile device to perform the at least one corresponding user-specified action, wherein performing the at least one corresponding user-specified action comprises outputting, by the virtual assistant, at least some of the obtained information related to the topic for presentation to a user via the mobile device; and after causing the virtual assistant to output the at least some of the obtained information related to the topic to the user; selecting a topic-dependent language model, from among a plurality of language models, based on the topic specified by the at least one user-specified condition that was met by the obtained information, wherein the topic-dependent language model is specifically adapted for recognition of input related to the topic; receiving first voice input of the user including a request for additional information about the topic; processing the first voice input using automatic speech recognition techniques at least in part by using the topic-dependent language model for the topic specified by the at least one user-specified condition. - View Dependent Claims (10, 11, 12, 15, 20)
-
Specification