IP Library › Granted Patent US 11,830,496
Granted Patent B2
US 11,830,496 · App. 17/108,464 · Granted Nov 28, 2023

Generating and providing inclusivity data insights for evaluating participants in a communication

Inventor: Gaurav Vinayak Tendolkar (San Jose, CA)
Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
G10L15/26G06F16/288G06Q10/06398G06Q10/109G06Q30/0201G10L15/04G10L15/22G10L25/78G06N20/00H04L67/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,830,496
App. No.
17/108,464
Granted
Nov 28, 2023
Kind
B2
Abstract

The present disclosure relates to determining communication inclusivity amongst speakers during a user communication. Communication inclusivity is a targeted analysis that collectively evaluates speaking opportunities (provided and taken by users) during a user communication and thought completion during speech associated with the user communication. To derive communication inclusivity, a user communication is modeled as a probabilistic interaction between speakers, where a sequence of speaking states of the user communication is identified and analyzed. Non-limiting examples of speaking states comprise: active user speech; periods of silence; overlapping speakers; icon indication; questions in corresponding chat windows; combination states; other contextual signals; and any combination thereof. With these observed sequences of speaking states, a probability distribution is modeled over transitions between states to predict inclusivity of a user communication. Data insights may be generated (and provided through a graphical user interface), thereby providing analytics that help users understand the concept of communication inclusivity.

Claims (81)

1. A computer-implemented method comprising:

generating a transcription of audio signals from participants during an electronic meeting;

determining occurrences of a plurality of speaking states during the electronic meeting based on analysis of the transcription, wherein:

the plurality of speaking states comprises:

a first state associated with active speech of a first user during the electronic meeting;

a second state associated with active speech of a second user during the electronic meeting; and

a third state indicating a state of silence between the first user and the second user, and

the determining the occurrences of the plurality of speaking states comprises:

segmenting the transcription into sentences;

analyzing whether the first state or the second state is associated with each of the sentences; and

determining whether the third state immediately followed a speaking of each of the sentences;

analyzing transitions between the plurality of speaking states for the electronic meeting based on analysis of the occurrences of the plurality of speaking states during the electronic meeting, wherein the analyzing the transitions between the plurality of speaking states comprises generating a count of transitions from:

the first state to the first state,

the first state to the second state,

the first state to the third state,

the second state to the first state,

the second state to the second state,

the second state to the third state, and

the third state to the third state;

generating a meeting inclusivity data insight based on a result of analyzing the transitions between the plurality of speaking states for the electronic meeting; and

transmitting, to a client computing device executing a productivity service, data for rendering of the meeting inclusivity data insight in the productivity service.

2. The computer-implemented method of claim 1 , wherein the analyzing of transitions between the plurality of speaking states for the electronic meeting further comprises:

generating a state transition probability matrix for the count of transitions, and wherein the generating of the state transition probability matrix comprises:

setting, in the state transition probability matrix, a value of a transition from the third state equal when transitioning to one of the first state and the second state.

3. The computer-implemented method of claim 2 , further comprising:

generating a stationary distribution of the state transition probability matrix, wherein the generating of the meeting inclusivity data insight is an automated process that occurs based on analysis of values of the stationary distribution.

4. The computer-implemented method of claim 1 , wherein the generating of the meeting inclusivity data insight comprises generating user-specific inclusivity analytics for an individual user based on analysis of the transitions between the plurality of speaking states for the electronic meeting, and wherein the user-specific inclusivity analytics comprise a first inclusivity analytic indicating a user opportunity to speak during the electronic meeting, and a second inclusivity analytic indicating whether the individual user completed their thoughts when speaking during the electronic meeting.

5. The computer-implemented method of claim 1 , further comprising: generating a summary report for the electronic meeting that is presentable in a graphical user interface of the productivity service, wherein the summary report comprises: the meeting inclusivity data insight and a visual mapping identifying the occurrences of the plurality of speaking states during the electronic meeting.

6. A system comprising:

at least one processor; and

a memory, operatively connected with the at least one processor, storing computer-executable instructions that, when executed by the at least one processor, causes the at least one processor to execute a method that comprises:

generating a transcription of audio signals from participants during an electronic meeting;

determining occurrences of a plurality of speaking states during the electronic meeting based on analysis of the transcription, wherein:

the plurality of speaking states comprises:

a first state associated with active speech of a first user during the electronic meeting,

a second state associated with active speech of a second user during the electronic meeting, and

a third state indicating silence between the first user and the second user; and

the determining the occurrences of the plurality of speaking states comprises:

segmenting the transcription into sentences,

analyzing whether the first state or the second state is associated with each of the sentences, and

determining whether the third state immediately followed a speaking of each of the sentences;

analyzing transitions between the plurality of speaking states for the electronic meeting based on analysis of the occurrences of the plurality of speaking states during the electronic meeting, wherein the analyzing the transitions between the plurality of speaking states comprises generating a count of transitions from:

the first state to the first state,

the first state to the second state,

the first state to the third state,

the second state to the first state,

the second state to the second state,

the second state to the third state, and

the third state to the third state;

generating a meeting inclusivity data insight based on a result of analyzing the transitions between the plurality of speaking states for the electronic meeting; and

transmitting, to a client computing device executing a productivity service, data for rendering of the meeting inclusivity data insight in the productivity service.

7. The system of claim 6 , wherein the analyzing of transitions between the plurality of speaking states for the electronic meeting further comprises:

generating a state transition probability matrix for the count of transitions, and wherein

the generating of the state transition probability matrix comprises:

setting, in the state transition probability matrix, a value of a transition from the third state equal when transitioning to one of the first state and the second state.

8. The system of claim 7 , wherein the method, executed by the at least one processor, further comprises:

generating a stationary distribution of the state transition probability matrix, wherein the generating of the meeting inclusivity data insight is an automated process that occurs based on analysis of values of the stationary distribution.

9. The system of claim 6 , wherein the generating of the meeting inclusivity data insight comprises generating user-specific inclusivity analytics for an individual user based on analysis of the transitions between the plurality of speaking states for the electronic meeting, and wherein the user-specific inclusivity analytics comprise a first inclusivity analytic indicating a user opportunity to speak during the electronic meeting, and a second inclusivity analytic indicating whether the individual user completed their thoughts when speaking during the electronic meeting.

10. The system of claim 6 , wherein the method, executed by the at least one processor, further comprises: generating a summary report for the electronic meeting that is presentable in a graphical user interface of the productivity service, wherein the summary report comprises: the meeting inclusivity data insight and a visual mapping identifying the occurrences of the plurality of speaking states during the electronic meeting.

11. A computer-implemented method comprising:

generating a transcription of audio signals from participants during an electronic meeting;

determining occurrences of a plurality of speaking states during the electronic meeting based on analysis of the transcription, wherein:

the plurality of speaking states comprises:

a first state associated with active speech of a first user during the electronic meeting;

a second state associated with active speech of a second user during the electronic meeting; and

a third state indicating silence between the first user and the second user, and

the determining the occurrences of the plurality of speaking states comprises:

segmenting the transcription into sentences;

analyzing whether the first state or the second state is associated with each of the sentences; and

determining whether the third state immediately followed a speaking of each of the sentences;

analyzing transitions between the plurality of speaking states for the electronic meeting based on analysis of the occurrences of the plurality of speaking states during the electronic meeting, wherein the analyzing the transitions between the plurality of speaking states comprises generating a count of transitions from:

the first state to the first state,

the first state to the second state,

the first state to the third state,

the second state to the first state,

the second state to the second state,

the second state to the third state, and

the third state to the third state;

generating a meeting inclusivity data insight based on a result of analyzing the transitions between the plurality of speaking states for the electronic meeting; and

rendering the meeting inclusivity data insight in a graphical user interface (GUI) of a productivity service.

12. The computer-implemented method of claim 11 , wherein the rendering of the meeting inclusivity metric comprises automatically presenting, in the GUI of the productivity service, a GUI notification that provides a textual representation of the meeting inclusivity data insight.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 1, 2020
From: TENDOLKAR, GAURAV VINAYAK
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 054506/0339 →
Continuity (1)
Related Publication 20220172723A1 · Jun 2, 2022