Intelligent contextually aware digital assistants
First Claim
1. A computer-executable method for providing context-based web services to a user, comprising:
- receiving, by a computer, general knowledge and domain-specific knowledge extracted from a body of content;
training a model, using the received knowledge as input, based on machine learning to obtain a database which maps sentence structures to instructions on how to extract parameters from a sentence which corresponds to a respective sentence structure,wherein a respective sentence structure indicates an action to be performed or a question-and-answer sentence, andwherein a parameter includes one or more of a subject, a verb, and an object;
receiving a sentence as input from the user interacting with a visual interface that includes an animated agent;
determining a first sentence structure for the sentence based on the model;
retrieving, from the database by using the first sentence structure as a key, instructions which are mapped to the first sentence structure and which indicate how to extract parameters from the sentence;
extracting one or more parameters of the sentence based on the retrieved instructions and the first sentence structure;
obtaining current and historical contextual data associated with the user;
determining a set of arguments based on the parameters and the contextual data; and
using the set of arguments to produce an audio response with a text-speech translator and determine mouth positions synchronized with the audio response to animate the animated agent.
6 Assignments
0 Petitions
Accused Products
Abstract
One embodiment of the present invention provides a system for providing context-based web services to a user. During operation, the system may receive a sentence as input from a user. The system may determine a sentence structure of the sentence, and determine whether there is an entry in a database corresponding to the sentence structure. Responsive to determining that there is no entry in the database corresponding to the sentence structure, the system may engage in a dialog with the user. The system may extract one or more parameters of the sentence based on information from the dialog. The system may obtain contextual and background information associated with the parameters. The system may then determine a set of arguments based on the parameters and the contextual and background information, and interact with web services to perform an action and provide a response to the user.
-
Citations
20 Claims
-
1. A computer-executable method for providing context-based web services to a user, comprising:
-
receiving, by a computer, general knowledge and domain-specific knowledge extracted from a body of content; training a model, using the received knowledge as input, based on machine learning to obtain a database which maps sentence structures to instructions on how to extract parameters from a sentence which corresponds to a respective sentence structure, wherein a respective sentence structure indicates an action to be performed or a question-and-answer sentence, and wherein a parameter includes one or more of a subject, a verb, and an object; receiving a sentence as input from the user interacting with a visual interface that includes an animated agent; determining a first sentence structure for the sentence based on the model; retrieving, from the database by using the first sentence structure as a key, instructions which are mapped to the first sentence structure and which indicate how to extract parameters from the sentence; extracting one or more parameters of the sentence based on the retrieved instructions and the first sentence structure; obtaining current and historical contextual data associated with the user; determining a set of arguments based on the parameters and the contextual data; and using the set of arguments to produce an audio response with a text-speech translator and determine mouth positions synchronized with the audio response to animate the animated agent. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for providing context-based web services to a user, the method comprising:
-
receiving, by the computer, general knowledge and domain-specific knowledge extracted from a body of content; training a model, using the received knowledge as input, based on machine learning to obtain a database which maps sentence structures to instructions on how to extract parameters from a sentence which corresponds to a respective sentence structure, wherein a respective sentence structure indicates an action to be performed or a question-and-answer sentence, and wherein a parameter includes one or more of a subject, a verb, and an object; receiving a sentence as input from the user interacting with a visual interface that includes an animated agent; determining a first sentence structure for the sentence based on the model; retrieving, from the database by using the first sentence structure as a key, instructions which are mapped to the first sentence structure and which indicate how to extract parameters from the sentence; extracting one or more parameters of the sentence based on the retrieved instructions and the first sentence structure; obtaining current and historical contextual data associated with the user; determining a set of arguments based on the parameters and the contextual data; and using the set of arguments to produce an audio response with a text-speech translator and determine mouth positions synchronized with the audio response to animate the animated agent. - View Dependent Claims (12, 13, 14, 15, 16, 17)
-
-
18. A computing system for providing context-based web services to a user, the system comprising:
-
one or more processors, a non-transitory computer-readable medium coupled to the one or more processors having instructions stored thereon that, when executed by the one or more processors, cause the one or more processors to perform operations comprising; receiving, by the computing system, general knowledge and domain-specific knowledge extracted from a body of content; training a model, using the received knowledge as input, based on machine learning to obtain a database which maps sentence structures to instructions on how to extract parameters from a sentence which corresponds to a respective sentence structure, wherein a respective sentence structure indicates an action to be performed or a question-and-answer sentence, and wherein a parameter includes one or more of a subject, a verb, and an object; receiving a sentence as input from the user interacting with a visual interface that includes an animated agent; determining a first sentence structure for the sentence based on the model; retrieving, from the database by using the first sentence structure as a key, instructions which are mapped to the first sentence structure and which indicate how to extract parameters from the sentence; extracting one or more parameters of the sentence based on the retrieved instructions and the first sentence structure; obtaining current and historical contextual data associated with the user; determining a set of arguments based on the parameters and the contextual data; and using the set of arguments to produce an audio response with a text-speech translator and determine mouth positions synchronized with the audio response to animate the animated agent. - View Dependent Claims (19, 20)
-
Specification