Machine learned optimizing of health activity for participants during meeting times

Patent metadata

Field	Value
Publication number	US-10617362-B2
Application number	US-201615341597-A
Country	US
Kind code	B2
Filing date	Nov 2, 2016
Priority date	Nov 2, 2016
Publication date	Apr 14, 2020
Grant date	Apr 14, 2020

Abstract

Providing an activity for a participant may include receiving at least location data specifying a location of the participant. An engagement level of the participant may be predicted based on the location data. Sensor data associated with the participant may be received, the sensor data comprising at least current physiological data associated with the participant. Based at least on the predicted engagement level and the sensor data, an exercise for the participant to perform may be determined. A notification signal may be transmitted to the participant to perform the exercise.

First claim

We claim:

1. A method of providing health activity for a participant in a conference call, the method performed by a hardware processor, comprising:
receiving data associated with the conference call and location data specifying a location of the participant conducting the conference call; predicting an engagement level of the participant that is to participate in the conference call based on the received data and the location data by executing a trained machine model with the received data and the location data as input to the trained machine model, the trained machine model trained based on labeled historical data comprising at least historical data associated with historical conference calls and associated historical location data and historical engagement levels, the trained machine model trained to predict a level of engagement of the participant indicating how actively the participant participates in a meeting;
receiving sensor data associated with the participant, the sensor data comprising at least current physiological data associated with the participant;
identifying the participant's fitness goal stored in a network;
based on the predicted engagement level, the sensor data and the participant's fitness goal, determining an exercise for the participant to perform during the conference call from a predefined lookup table of suggested exercises,
wherein the hardware processor is a component of a smartphone device, the smartphone device interfaced with a plurality of wearable devices worn by the participant, the plurality of wearable devices continuing to communicate real-time physiological sensor data to the smartphone device during the conference call,
wherein the hardware processor further monitors during the conference call, an audio sensor coupled to the smartphone to determine current engagement level of the participant during the conference call,
wherein the determining an exercise for the participant to perform during the conference call comprises at least:
automatically updating a decision determined based on the predicted engagement level that an exercise should not be recommended, to recommending the exercise based on the real-time physiological sensor data and the current engagement level of the participant during the conference call, and
transmitting a notification signal to the participant during the conference call.

2. The method of claim 1 , wherein the data comprises a type of the conference meeting, a number of conference meetings being conducted at a time, agenda participation, context of the conference meeting, and a type of equipment used in the conference meeting.

3. The method of claim 1 , wherein the labeled historical data comprise a type of a conference meeting, a number of conference meetings being conducted at a time, agenda participation, location, context of the conference meeting, and a type of equipment used in the conference meeting.

4. The method of claim 3 , wherein the machine model is further trained based on sensor parameter data.

5. The method of claim 1 , wherein the sensor data further comprises acceleration data from an acceleration sensor coupled to the smartphone device that measures acceleration.

6. The method of claim 1 , wherein the machine model comprises a decision tree trained based on supervised machine learning algorithm.

7. A non-transitory computer readable storage medium storing a program of instructions executable by a machine to perform a method of providing heath activity for a participant in a conference call, the method comprising:
receiving data associated with the conference call and location data specifying a location of the participant conducting the conference call;
predicting an engagement level of the participant that is to participate in the conference call based on the received data and the location data by executing a trained machine model with the received data and the location data as input to the trained machine model, wherein the trained machine model is trained based on labeled historical data comprising at least historical data associated with historical conference calls and associated historical location data and historical engagement levels, the trained machine model trained to predict a level of engagement of the participant indicating how actively the participant participates in a meeting;
receiving sensor data associated with the participant, the sensor data comprising at least current physiological data associated with the participant;
identifying the participant's fitness goal stored in a network; based on the predicted engagement level, the sensor data and the participant's fitness goal,
determining an exercise for the participant to perform during the conference call from a predefined lookup table of suggested exercises,
wherein the machine comprises a hardware processor coupled to a smartphone device, the smartphone device interfaced with a plurality of wearable devices worn by the participant, the plurality of wearable devices continuing to communicate real-time physiological sensor data to the smartphone device during the conference call,
wherein the hardware processor further monitors during the conference call, an audio sensor coupled to the smartphone device to determine current engagement level of the participant during the conference call,
wherein determining an exercise for the participant to perform during the conference call at least by:
automatically updating a decision determined based on the predicted engagement level that an exercise should not be recommended, to recommending the exercise based on the real-time physiological sensor data and the current engagement level of the participant during the conference call; and
transmitting the notification signal to the participant during the conference call.

8. The non-transitory computer readable storage medium of claim 7 , wherein the data comprises a type of the conference meeting, a number of conference meetings being conducted at a time, agenda participation, context of the conference meeting, and a type of equipment used in the conference meeting.

9. The non-transitory computer readable storage medium of claim 7 , wherein the labeled historical data comprise a type of a conference meeting, a number of conference meetings being conducted at a time, agenda participation, location, context of the conference meeting, and a type of equipment used in the conference meeting.

10. The non-transitory computer readable storage medium of claim 9 , wherein the trained machine model is further trained based on sensor parameter data.

11. The non-transitory computer readable storage medium of claim 7 , wherein the sensor data further comprises acceleration data from an acceleration sensor coupled to the smartphone device that measures acceleration.

12. The non-transitory computer readable storage medium of claim 7 , wherein the trained machine model comprises a decision tree trained based on supervised machine learning algorithm.

13. A system of providing health activity for a participant in a conference call, comprising:
a predictive system executing on at least one hardware processor, the predictive system operable to train a machine model based on parameters labeled by analyzing historical pattern of engagement, the parameters comprising at least a type of a conference meeting, a number of conference meetings being conducted at a time, agenda participation, location, context of the conference meeting, and a type of equipment used in the conference meeting;
the predictive system receiving data associated with the conference call and location data specifying a location of the participant conducting the confe

Assignees

• IBM

Inventors

• Bastide Paul R
• Kiral-Kornek Filiz Isabell
• Mahapatra Dwarikanath
• Saha Susmita
• Vishwanath Arun
• von Cavallar Stefan

Classifications

• H04W4/027

  using movement velocity, acceleration information · CPC title

• A61B5/6898

  Portable consumer electronic devices, e.g. music players, telephones, tablet computers · CPC title

• A61B2503/10

  Athletes · CPC title

• H04M3/56 Primary

  Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities (video conference systems H04N7/15) · CPC title

• H04M2250/10

  including a GPS signal receiver · CPC title