Ai-bot based in-meeting instant query assistant for conference meetings

Patent metadata

Field	Value
Publication number	US-2021390144-A1
Application number	US-202016901764-A
Country	US
Kind code	A1
Filing date	Jun 15, 2020
Priority date	Jun 15, 2020
Publication date	Dec 16, 2021
Grant date	—

Abstract

Methods and systems are provided for automatically, via an artificial-intelligence bot, receiving a query made by a participant in a conference meeting, determine one or more subject matter experts to contact outside of the conference meeting, receive a response to the query from at least one of the subject matter experts, and present the response to the query to the participants of the conference meeting. The artificial-intelligence bot presents the response to the query while the conference meeting is in progress without any participant of the conference meeting communicating with the subject matter expert, without ever connecting a client device of the subject matter expert to the conference meeting, and without ever including the subject matter expert in the conference meeting.

First claim

What is claimed is:

1 . A communication system, comprising:
a server, comprising:
a network communications interface;
a processor coupled to the network communications interface; and
a memory coupled to and readable by the processor and storing therein instructions that, when executed by the processor, cause the processor to:
receive a query from a conference client device participating in a conference meeting comprising a plurality of connected conference client devices, each conference client device of the plurality of conference client devices associated with a respective participant;
analyze the query to determine a subject matter expert absent from the conference meeting and associated with a topic of the query;
send a message to a client device of the subject matter expert requesting a response to the query from the subject matter expert while the conference meeting is in progress;
receive the response to the query from the client device of the subject matter expert; and
cause an automated bot to present the response to the query to the plurality of connected conference client devices on behalf of the subject matter expert without requiring the subject matter expert to be included in the conference meeting.

2 . The communication system of claim 1 , wherein the instructions further cause the processor to:
determine, automatically based on machine learning using historical data associated with a plurality of subject matter experts and using historical data of past conference meetings, an identification of a group of candidate subject matter experts to be considered for consultation while the conference meeting is in progress, and wherein the subject matter expert absent from the conference meeting and associated with the topic of the query is selected from the group of candidate subject matter experts.

3 . The communication system of claim 1 , wherein the automated bot is caused to present the response to the query to the plurality of connected conference client devices while the conference meeting is in progress without any participant of the conference meeting communicating with the subject matter expert and without ever connecting the client device of the subject matter expert to the conference meeting.

4 . The communication system of claim 3 , wherein the query is at least one of a voice-based query made as part of an audio communication in the conference meeting and a text-based query made as part of a chat communication in the conference meeting, and wherein prior to sending the message to the client device of the subject matter expert, the instructions further cause the processor to:
analyze content of the query using a natural language processing unit to determine a suggested response to the query from a plurality of stored responses.

5 . The communication system of claim 4 , wherein in response to analyzing the content of the query, the instructions further cause the processor to:
determine that there is no suggested response to the query in the plurality of stored responses, and wherein the message is absent the suggested response to the query.

6 . The communication system of claim 4 , wherein the message sent to the client device of the subject matter expert comprises the suggested response and an option for the subject matter expert to accept the suggested response as the response to the query via an input provided by the subject matter expert via the client device of the subject matter expert.

7 . The communication system of claim 6 , wherein prior to receiving the query, the instructions further cause the processor to:
receive, as a part of scheduling the conference meeting, an identification of a group of candidate subject matter experts to be considered for consultation while the conference meeting is in progress.

8 . The communication system of claim 6 , wherein prior to receiving the query, the instructions further cause the processor to:
determine, automatically based on information about the conference meeting, a group of subject matter experts available for consultation while the conference meeting is in progress; and send a consultation reminder message to the group of subject matter experts comprising an agenda of the conference meeting, a subject of the conference meeting, and a time that the group of subject matter experts are expected to remain available for consultation during the conference meeting, when the group of candidate subject matter experts are configured.

9 . The communication system of claim 8 , wherein after causing the response to the query to be presented to the plurality of connected conference client devices, the instructions further cause the processor to:
receive feedback from at least one conference client device of the plurality of conference client devices regarding an accuracy of the response to the query; and analyze the feedback to increase an accuracy of the plurality of stored responses.

10 . The communication system of claim 1 , wherein the server further comprises a machine learning engine that is executable by the processor and that enables the processor to:
analyze the query to determine a suggested response to the query; determine, in response to the analysis of the query and based on an identification of each participant in the conference meeting, and historical responses to queries stored in a database, a confidence level associated with each response in the historical responses to queries stored in the database relative to the query; and send the suggested response as part of the message sent to the client device of the subject matter expert when a confidence level of the suggested response in the historical responses to queries stored in the database relative to the query is higher than a confidence level of any other response in the historical responses to queries stored in the database relative to the query.

11 . A method, comprising:
receiving, by a processor via a network communications interface, a query from a conference client device participating in a conference meeting comprising a plurality of connected conference client devices, each conference client device of the plurality of conference client devices associated with a respective participant; analyzing, by the processor, the query to determine a subject matter expert absent from the conference meeting and associated with a topic of the query; sending, by the processor via the network communications interface, a message to a client device of the subject matter expert requesting a response to the query from the subject matter expert while the conference meeting is in progress; receiving, by the processor, the response to the query from the client device of the subject matter expert; and causing, by the processor, an automated bot to present the response to the to the plurality of connected conference client devices on behalf of the subject matter expert without requiring the subject matter expert to be included in the conference meeting.

12 . The method of claim 11 , wherein the automated bot is caused to present the response to the query to the plurality of connected conference client devices while the conference meeting is in progress without any participant of the conference meeting communicating with the subject matter expert and without ever connecting the client device of the subject matter expert to the conference meeting.

13 . The method of claim 12 , wherein the query is at least one of a voice-based query made as part of an audio communication in the conference meeting and a text-based query made as part of a chat communication in the conference meeting, and wherein

Assignees

• Avaya Man Lp

Inventors

• B M S Ganesh
• Soman Sumesh
• Banda Srinivas

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06F16/635 Primary

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06F16/3329 Primary

  Natural language query formulation · CPC title

• H04L12/1831

  Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status · CPC title