Network-based learning models for natural language processing
AssigneeSony Interactive Entertainment Inc.
InventorStephen Yong
Life of this patent
Estimating the term…
Abstract
Systems and methods of network-based learning models for natural language processing are provided. Information may be stored information in memory regarding user interaction with network content. Further, a digital recording of a vocal utterance made by a user may be captured. The vocal utterance may be interpreted based on the stored user interaction information. An intent of the user may be identified based on the interpretation, and a prediction may be made based on the identified intent. The prediction may further correspond to a selected workflow.
Claims21
A system of network-based learning models for natural language processing, the system comprising:
- an end-user device comprising a microphone that captures a vocal utterance made by a user;
- and
- a network server comprising:
- a network interface that receives a digital recording of the vocal utterance, memory that stores:
- information regarding user interaction with network content, and
- a plurality of different workflows specific to the user, each workflow associated with one or more actions and one or more rules;
- a processor that executes instructions stored in memory, wherein execution of the instructions by the processor:
- interprets the vocal utterance based on the stored user interaction information,
- identifies an intent of the user based on the interpretation of the vocal utterance,
- makes a prediction based on the identified intent, wherein the prediction corresponds to a selected workflow, and
- executing the actions associated with the selected workflow, wherein the executed actions are based on applying the associated rules to the vocal utterance.
A method of network-based learning models for natural language processing, the method comprising:
- storing information in memory regarding:
- user interaction with network content, and
- a plurality of different workflows specific to the user, each workflow associated with one or more actions and one or more rules;
- capturing a digital recording of vocal utterance made by a user;
- and
- executing instructions stored in memory, wherein execution of the instructions by a processor:
- interprets the vocal utterance based on the stored user interaction information, identifies an intent of the user based on the interpretation of the vocal utterance,
- makes a prediction based on the identified intent, wherein the prediction corresponds to a selected workflow, and
- executes the actions associated with the selected workflow, wherein the executed actions are based on applying the associated rules to the vocal utterance.
A non-transitory computer-readable medium having embodied thereon a program executable by a processor to perform a method of network-based learning models for natural language processing, the method comprising:
- storing information in memory regarding:
- user interaction with network content, and
- a plurality of different workflows specific to the user, each workflow associated with one or more actions and one or more rules;
- capturing a digital recording of vocal utterance made by a user;
- interpreting the vocal utterance based on the stored user interaction information;
- identifying an intent of the user based on the interpretation of the vocal utterance;
- making a prediction based on the identified intent, wherein the prediction corresponds to a selected workflow;
- and
- executing the actions associated with the selected workflow, wherein the executed actions are based on applying the associated rules to the vocal utterance.
Dependencies are inferred from the claim text.