US 11,699,039 B2Granted

Virtual assistant providing enhanced communication session services

AssigneeMicrosoft Technology Licensing, LLC

InventorsHaim Somech, Shira Weinberg, Adi Miller

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods for providing enhanced services to users participating in communication sessions (CS), via a virtual assistant, are disclosed. One method receives content that is exchanged by users participating in the CS. The content includes natural language expressions that encode a conversation carried out by users. The method determines content features based on natural language models. The content features indicate intended semantics of the natural language expressions. The method determines a relevance of the content and identifies portions of the content that are likely relevant to the user. Determining the relevance is based on the content features, a context of the CS, a user-interest model, and a content-relevance model of the natural language models. Identifying the likely relevant content is based on the determined relevance of the content and a relevance threshold. A summary of the CS is automatically generated from summarized versions of the likely relevant portions of the content.

Claims17

Dependent claims

A computerized system comprising:

one or more processors;
and
computer storage memory having computer-executable instructions stored thereon which, when executed by the one or more processors, implement a method comprising:
receiving content that is exchanged within a communication session (CS), wherein the content includes one or more natural language expressions that encode a portion of a conversation carried out by a plurality of users participating in the CS;
determining one or more content features based on the content and one or more natural language models;
determining a relevance of the content based on the content features using one or more models indicating user interests or content-relevance for a first user of the plurality of users, the one or more models comprising a content-relevance model;
determining, using the one or more models, the relevance comprises a temporal urgency that indicates that the content is of an urgent nature to the first user and should be displayed differently relative to other content;
based on the temporal urgency and a highly relevant temporal urgency associated with a temporal urgency threshold for identifying highly relevant portions of content, identifying a highly relevant portion of the content, wherein the highly relevant portion of the content is a sub-portion of the content that is highly relevant to the first user;
providing a real-time notification of the identified highly relevant portion of the content to the first user by highlighting or positioning the highly relevant portion of the content in a foreground of a user interface of a display device of the first user;
generating a first summary of the CS comprising a summarized version of the content;
communicating the first summary of the CS to a first user;
receiving a second summary of the CS from the first user;
generating a comparison of the first summary and the second summary;
updating the content-relevance model based on the comparison of the first summary and the second summary;
and
providing the updated content-relevance model to support identifying relevant content in communication sessions.

13 more elements

A method comprising:

receiving content that is exchanged within a communication session (CS), wherein the content includes one or more natural language expressions that encode a conversation carried out by a plurality of users participating in the CS;
determining one or more content features based on the content and one or more natural language models;
determining a relevance of the content based on the content features using one or more models indicating user interests or content-relevance for a first user of the plurality of users, the one or more models comprising a content-relevance model;
determining, using the one or more models, the relevance comprises a temporal urgency that indicates that the content is of an urgent nature to the first user and should be displayed differently relative to other content;
based on the temporal urgency and a highly relevant temporal urgency associated with a temporal urgency threshold for identifying highly relevant portions of content, identifying a highly relevant portion of the content, wherein the highly relevant portion of the content is a sub-portion of the content that is highly relevant to the first user;
providing a real-time notification of the identified highly relevant portion of the content to the first user by highlighting or positioning the highly relevant portion of the content in a foreground of a user interface of a display device of the first user;
generating a first summary of the CS comprising a summarized version of the content;
communicating the first summary of the CS to a first user;
receiving a second summary of the CS from the first user;
generating a comparison of the first summary and the second summary;
updating the content-relevance model based on the comparison of the first summary and the second summary;
and
providing the updated content-relevance model to support identifying relevant content in communication sessions.

10 more elements

One or more hardware computer storage media and having instructions stored thereon, wherein the instructions, when executed by one or more hardware processors of a computing device, cause the one or more hardware processors of the computing device to perform actions including:

receiving content that is exchanged within a communication session (CS), wherein the content includes one or more natural language expressions that encode a conversation carried out by a plurality of users participating in the CS;
determining one or more content features based on the content and one or more natural language models;
determining a relevance of the content based on the content features using one or more models indicating user interests or content-relevance for a first user of the plurality of users, the one or more models comprising a content-relevance model;
determining, using the one or more models, the relevance comprises a temporal urgency that indicates that the content is of an urgent nature to the first user and should be displayed differently relative to other content;
based on the temporal urgency and a highly relevant temporal urgency associated with a temporal urgency threshold for identifying highly relevant portions of content, identifying a highly relevant portion of the content, wherein the highly relevant portion of the content is a sub-portion of the content that is highly relevant to the first user;
providing a real-time notification of the identified highly relevant portion of the content to the first user by highlighting or positioning the highly relevant portion of the content in a foreground of a user interface of a display device of the first user;
generating a first summary of the CS comprising a summarized version of the content;
communicating the first summary of the CS to a first user;
receiving a second summary of the CS from the first user;
generating a comparison of the first summary and the second summary;
updating the content-relevance model based on the comparison of the first summary and the second summary;
and
providing the updated content-relevance model to support identifying relevant content in communication sessions.

10 more elements

Dependencies are inferred from the claim text.