Detection, aggregation, and distribution of user and/or team effectiveness utilizing fatigue detection from online collaboration

Patent metadata

Field	Value
Publication number	US-12333465-B2
Application number	US-202217659906-A
Country	US
Kind code	B2
Filing date	Apr 20, 2022
Priority date	Apr 20, 2022
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

Detection, aggregation, and distribution of user and team effectiveness includes detecting, using one or more machine learning algorithms, user fatigue levels, based, at least in part, on detected attributes and evaluating and/or classifying, using one or more machine learning algorithms, user fatigue levels, based, at least in part, on detected attributes. Detection, aggregation, and distribution of user and team effectiveness further includes creating, using a plurality of artificial intelligence algorithms, a plurality of inference models, based at least in part on detected and evaluated and/or classified user fatigue levels, predicting, by a machine learning predictive services algorithm, using the plurality of created inference models, user effectiveness at different intervals, and providing, by the machine learning predictive services algorithm, effectiveness weights for requested collaboration sessions that include the user.

First claim

The invention claimed is:

1. A method to detect, aggregate, and distribute user and team effectiveness, comprising:
detecting, using one or more machine learning algorithms, fatigue levels of a user that is a member of a team, based, at least in part, on detected attributes comprising one or more of information handling system use telemetry, real time information handling system use, data from a calendaring application program and collaborative meeting services reporting data collected by a collaborative meeting services vendor;
evaluating and/or classifying, using one or more second machine learning algorithms, the fatigue levels of the user, based, at least in part, on the detected attributes;
implementing, using a plurality of artificial intelligence algorithms, a facial recognition inference model, based at least in part on resultingly detected and evaluated and/or classified visual fatigue levels of the user;
generating a plurality of effectiveness weights for performance of the user at different intervals and for performance of each member of the team at the different intervals, wherein the plurality of effectiveness weights are generated based on a combination of the facial recognition inference model, historical data for the user and for each member of the team, and user-specific collaboration factors; and
providing, by a machine learning predictive services algorithm, effectiveness weights for each of two or more requested collaboration sessions that include the user and other members of the team, wherein the effectiveness weights for each of the two or more requested collaboration sessions are calculated based on a combination of user-specific factors, historical performance data, and real-time collaboration metrics.

2. The method of claim 1 , wherein providing the effectiveness weights for each of the two or more requested collaboration sessions that include the user further comprises providing a recommendation value during collaboration configuring.

3. The method of claim 2 , wherein, in providing the recommendation value during the collaboration configuring, the recommendation value is a heat map dial indicating the effectiveness weights for each of the two or more requested collaboration sessions.

4. The method of claim 2 , wherein, in providing the recommendation value during the collaboration configuring, the recommendation value is a red, yellow, green indicator corresponding to the effectiveness weights for each of the two or more requested collaboration sessions.

5. The method of claim 2 wherein, in providing the recommendation value during the collaboration configuring, the collaboration configuring is carried out on the calendaring application program and the recommendation value is provided to the calendaring application program and presented by the calendaring application program as an indication of the recommendation value for a collaboration session.

6. The method of claim 2 , further comprising suggesting, by a bot, an optimum time for a collaboration session, based, at least in part, on recommendation values associated with different times.

7. The method of claim 6 , wherein the collaboration configuring is carried out on the calendaring application program and the method further comprises presenting, by the calendaring application program an option, to a collaboration organizer, for the bot to determine the optimum time for the requested collaboration session.

8. The method of claim 2 , further comprising monitoring, by a logic application program, changes in the recommendation value, following scheduling of a collaboration session, and reporting a change in the recommendation value for the collaboration session to a collaboration session organizer.

9. The method of claim 1 , wherein, in implementing, using the plurality of artificial intelligence algorithms, the facial recognition inference model, based at least in part on the resultingly detected and evaluated and/or classified visual fatigue levels of the user, the plurality of artificial intelligence algorithms comprise a cognitive service.

10. The method of claim 1 , wherein, in evaluating and/or classifying, using the one or more second machine learning algorithms, the fatigue levels of the user, based, at least in part, on the detected attributes, the one or more second machine learning algorithms comprise a face recognition application program interface, a text analytics application program interface and/or a language understanding service.

11. The method of claim 10 , wherein, in evaluating and/or classifying, using the one or more second machine learning algorithms, the fatigue levels of the user, based, at least in part, on the detected attributes, the face recognition application program interface provides, in the resultingly detected and evaluated and/or classified visual fatigue levels of the user to an artificial intelligence face service and the text analytics application program interface and/or the language understanding service provides the resultingly detected and evaluated and/or classified visual fatigue levels of the user to an artificial intelligence cognitive service.

12. The method of claim 11 , wherein, in evaluating and/or classifying, using the one or more second machine learning algorithms, the fatigue levels of the user, based, at least in part, on the detected attributes, the artificial intelligence face service uses an emotion inference model, based at least in part on the resultingly detected and evaluated and/or classified visual fatigue levels of the user, and the artificial intelligence cognitive service uses a sentiment inference model, based at least in part on the resultingly detected and evaluated and/or classified visual fatigue levels of the user.

13. A non-transitory computer readable medium having program instructions stored thereon that, upon execution by an information handling system, cause the information handling system to:
detect, using one or more machine learning algorithms, fatigue levels of a user that is a member of a team, based, at least in part, on detected attributes comprising one or more of information handling system use telemetry, real time information handling system use, data from a calendaring application program and collaborative meeting services reporting data collected by a collaborative meeting services vendor;
evaluate and/or classify, using one or more second machine learning algorithms, fatigue levels of the user, based, at least in part, on detected attributes;
implement, using a plurality of artificial intelligence algorithms, a facial recognition inference model, based at least in part on resultingly detected and evaluated and/or classified visual fatigue levels of the user;
generate a plurality of effectiveness weights for user performance at different intervals and for performance of each member of the team at the different intervals,

wherein the plurality of effectiveness weights are generated based on a combination of the facial recognition inference model, historical data for the user and for each member of the team, and user-specific collaboration factors; and
provide, by a machine learning predictive services algorithm, effectiveness weights for each of two or more requested collaboration sessions that include the user and other members of the team, wherein the effectiveness weights for each of the two or more requested collaboration sessions are calculated based on a combination of user-specific factors, historical performance data, and real-time collaboration metrics.

14. The non-transitory computer readable medium of claim 13 , wherein upon execution by the information hand

Assignees

• Dell Products Lp
• Dell Products Llp

Inventors

• Hamlin Daniel L
• Agudelo Juan C

Classifications

• G06Q10/063118

  Staff planning in a project environment · CPC title

• G06Q10/06398

  Performance of employee with respect to a job function · CPC title

• G06Q10/063114 Primary

  Status monitoring or status determination for a person or group · CPC title