Granted Patent B2

US 12,219,021 · App. 18/537,443 · Granted Feb 4, 2025

Inventor: Shrey Shah (Redmond, WA)

Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC

H04L67/147G06N5/025

Abstract

Claims (69)

1. A receiving device for intelligent listening, the receiving device comprising:

one or more processors; and

a memory having stored thereon instructions that, upon execution by the one or more processors, cause the one or more processors to:

determine a scenario for completion between a transmitting device and the receiving device, wherein the scenario comprises an advertisement message transmitted from the transmitting device to the receiving device and an action performed by one of the transmitting device and the receiving device;

receive device signals associated with the scenario;

analyze, with a rules engine, the device signals based on the scenario to determine whether the transmitting device is ready to participate in the scenario, wherein the rules engine comprises a combination of static rules and machine learning models; and

in response to determining that the transmitting device is ready to participate in the scenario, listen for the advertisement message from the transmitting device to advance the scenario.

2. The receiving device of claim 1 , wherein the device signals comprise device state signals, connectivity signals, sensor signals, operating system signals, application signals, or a combination thereof.

3. The receiving device of claim 1 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

receive the static rules from a first remote hosting system;

receive general machine learning models from a second remote hosting system, wherein the general machine learning models comprise trained models trained using general data from a plurality of devices attempting to complete the scenario;

access personal machine learning models, wherein the personal machine learning models comprise trained models trained using personal data specific to the transmitting device attempting to complete the scenario, and wherein the personal data is restricted based on privacy settings; and

merge the static rules, the general machine learning models, and the personal machine learning models into a set of merged rules for the rules engine for analyzing the device signals based on the scenario.

4. The receiving device of claim 1 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

filter the device signals based on the scenario, wherein the rules engine analyzes the filtered device signals.

5. The receiving device of claim 1 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

provide the state of the scenario to the rules engine, wherein the rules engine uses the state of the scenario in the analyzing the device signals.

6. The receiving device of claim 1 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

use the state of the scenario to train personal machine learning models for use in the rules engine.

7. The receiving device of claim 1 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

receive the advertisement message; and

execute the action to advance the scenario in response to receiving the advertisement message.

8. The receiving device of claim 7 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

transmit feedback based on the state of the scenario and personal data associated with the scenario to the transmitting device.

9. The receiving device of claim 7 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

transmit feedback based on the state of the scenario and general data associated with the scenario to a remote training system.

10. A computer-readable media device having stored thereon instructions for intelligent listening that, upon execution by one or more processors, cause the one or more processors to:

determine a scenario for completion between a transmitting device and a receiving device, wherein the scenario comprises an advertisement message transmitted from the transmitting device to the receiving device and an action performed by one of the transmitting device and the receiving device;

receive device signals associated with the scenario;

analyze, with a rules engine, the device signals based on the scenario to determine whether the transmitting device is ready to participate in the scenario, wherein the rules engine comprises a combination of static rules and machine learning models; and

in response to determining that the transmitting device is ready to participate in the scenario, listen for the advertisement message from the transmitting device to advance the scenario.

11. The computer-readable media device of claim 10 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

receive the static rules from a first remote hosting system;

receive general machine learning models from a second remote hosting system, wherein the general machine learning models comprise trained models trained using general data from a plurality of devices attempting to complete the scenario;

access personal machine learning models, wherein the personal machine learning models comprise trained models trained using personal data specific to the transmitting device attempting to complete the scenario, and wherein the personal data is restricted based on privacy settings; and

merge the static rules, the general machine learning models, and the personal machine learning models into a set of merged rules for the rules engine for analyzing the device signals based on the scenario.

12. The computer-readable media device of claim 10 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

filter the device signals based on the scenario, wherein the rules engine analyzes the filtered device signals.

13. The computer-readable media device of claim 10 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

provide the state of the scenario to the rules engine, wherein the rules engine uses the state of the scenario in the analyzing the device signals.

14. The computer-readable media device of claim 10 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

use the state of the scenario to train personal machine learning models for use in the rules engine.

15. The computer-readable media device of claim 10 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

receive the advertisement message; and

execute the action to advance the scenario in response to receiving the advertisement message.

16. The computer-readable media device of claim 15 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

transmit feedback based on the state of the scenario and personal data associated with the scenario to the transmitting device.

17. The computer-readable media device of claim 15 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

track a state of the scenario; and

transmit feedback based on the state of the scenario and general data associated with the scenario to a remote training system.

18. A computer-readable media device having stored thereon instructions for intelligent transmission that, upon execution by one or more processors, cause the one or more processors to:

determine a scenario for completion between a transmitting device and a receiving device, wherein the scenario comprises an advertisement message transmitted from the transmitting device to the receiving device and an action performed by one of the transmitting device and the receiving device;

receive device signals associated with the scenario;

analyze, using a rules engine, the device signals based on the scenario to determine whether the receiving device is ready to participate in the scenario, wherein the rules engine comprises a combination of static rules and machine learning models; and

in response to determining that the receiving device is ready to participate in the scenario, transmit the advertisement message to the receiving device to advance the scenario.

19. The computer-readable media device of claim 18 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

select a transport based on the scenario and the device signals, wherein the advertisement message is transmitted on the selected transport.

20. The computer-readable media device of claim 18 , wherein the instructions comprise further instructions that, upon execution by the one or more processors, cause the one or more processors to:

receive the static rules from a first remote hosting system;

receive general machine learning models from a second remote hosting system, wherein the general machine learning models comprise trained models trained using general data from a plurality of devices attempting to complete the scenario;

access personal machine learning models, wherein the personal machine learning models comprise trained models trained using personal data specific to the transmitting device attempting to complete the scenario, and wherein the personal data is restricted based on privacy settings; and

merge the static rules, the general machine learning models, and the personal machine learning models into a set of merged rules for the rules engine for analyzing the device signals based on the scenario.

Assignments (1)

Continuity (2)

References Cited (16)