Management and operation of loosely coupled internet of things devices

Patent metadata

Field	Value
Publication number	US-11599828-B2
Application number	US-202016803889-A
Country	US
Kind code	B2
Filing date	Feb 27, 2020
Priority date	Feb 27, 2020
Publication date	Mar 7, 2023
Grant date	Mar 7, 2023

Abstract

A loose coupling between Internet of Things (“IoT”) devices and environmental sensors is generated. Once the loose coupling has been generated, conditions in a physical environment can be managed utilizing the loosely coupled devices. For example, a hybrid machine learning/expert system can be utilized to activate the IoT devices in an environment to achieve a desired condition in an optimized manner.

First claim

What is claimed is:

1. A computer-implemented method performed by a computing device for provisioning Internet of things (IoT) devices in an environment to achieve a plurality of desired conditions without human interaction, the method comprising:
generating initial provisioning settings based upon information collected from the IoT devices in the environment, wherein the collected information also includes prior provisioning information from IoT devices in other environments similar to the environment, wherein the initial provisioning settings comprise data identifying a plurality of the IoT devices in the environment and operational parameters for the plurality of IoT devices in the environment to achieve the plurality of desired conditions of the environment;
generating modified provisioning settings by applying a plurality of rules specific to the environment to the initial provisioning settings, the plurality of rules configured to modify the initial provisioning settings by adding or removing IoT devices and modifying the operational parameters; and
provisioning the IoT devices in the environment according to the modified provisioning settings to achieve the plurality of desired conditions without human interaction.

2. The computer-implemented method of claim 1 , wherein the prior provisioning information is obtained by a machine learning (ML) model.

3. The computer-implemented method of claim 1 , wherein the plurality of rules specific to the environment are obtained from an expert system.

4. The computer-implemented method of claim 1 , wherein the plurality of rules are further configured to modify the initial provisioning settings by specifying a time at which the plurality of IoT devices are to be activated.

5. The computer-implemented method of claim 1 , wherein the plurality of rules are further configured to modify the initial provisioning settings by specifying one or more conditions under which the plurality of IoT devices are to be activated.

6. The computer-implemented method of claim 1 , wherein the plurality of rules are configured to increase an output of at least one of the plurality of IoT devices in the environment or decrease an output of at least one of the plurality of IoT devices in the environment.

7. The computer-implemented method of claim 1 , wherein the plurality of rules specify a minimum output for at least one of the plurality of IoT devices in the environment.

8. The computer-implemented method of claim 1 , wherein the plurality of rules specify a maximum output for at least one of the plurality of IoT devices in the environment.

9. A computing device, comprising:
a processor; and
a computer-readable storage media having instructions stored thereupon which, when executed by the processor, cause the computing device to:
generate initial provisioning settings based upon information collected from IoT devices in an environment, wherein the collected information also includes prior provisioning information from IoT devices in other environments similar to the environment, wherein the initial provisioning settings comprise data identifying a plurality of the IoT devices in the environment and operational parameters for the plurality of IoT devices in the environment to achieve the plurality of desired conditions of the environment;
generate modified provisioning settings by applying a plurality of rules specific to the environment to the initial provisioning settings, the plurality of rules configured to modify the initial provisioning settings by adding or removing IoT devices and modifying the operational parameters; and
provision the IoT devices in the environment according to the modified provisioning settings to achieve the plurality of desired conditions without human interaction.

10. The computing device of claim 9 , wherein the prior provisioning information is obtained by a machine learning (ML) model.

11. The computing device of claim 9 , wherein the plurality of rules are further configured to modify the initial provisioning settings by specifying a time at which the plurality of IoT devices are to be activated.

12. The computing device of claim 9 , wherein the plurality of rules are further configured to modify the initial provisioning settings by specifying one or more conditions under which the plurality of IoT devices are to be activated.

13. The computing device of claim 9 , wherein the plurality of rules are further configured to modify the initial provisioning settings by increasing an output of at least one of the plurality of IoT devices in the environment or decreasing an output of at least one of the plurality of IoT devices in the environment.

14. The computing device of claim 9 , wherein the plurality of rules specify a minimum output for at least one of the plurality of IoT devices in the environment or a maximum output for at least one of the plurality of IoT devices in the environment.

15. A non-transitory computer-readable storage media having instructions stored thereupon which, when executed by a processor, cause a computing device to:
generate initial provisioning settings based upon information collected from IoT devices in an environment, wherein the collected information also includes prior provisioning information from IoT devices in other environments similar to the environment, wherein the initial provisioning settings comprise data identifying a plurality of the IoT devices in the environment and operational parameters for the plurality of IoT devices in the environment to achieve the plurality of desired conditions of the environment;
generate modified provisioning settings by applying a plurality of rules specific to the environment to the initial provisioning settings, the plurality of rules configured to modify the initial provisioning settings by adding or removing IoT devices and modifying the operational parameters; and
provision the IoT devices in the environment according to the modified provisioning settings to achieve the plurality of desired conditions without human interaction.

16. The non-transitory computer-readable storage media of claim 15 , wherein the prior provisioning information is obtained by a machine learning (ML) model.

17. The non-transitory computer-readable storage media of claim 15 , wherein the plurality of rules are further configured to modify the initial provisioning settings by specifying a time at which the plurality of IoT devices are to be activated.

18. The non-transitory computer-readable storage media of claim 15 , wherein the plurality of rules are further configured to modify the initial provisioning settings by specifying one or more conditions under which the plurality of IoT devices are to be activated.

19. The non-transitory computer-readable storage media of claim 15 , wherein the plurality of rules are further configured to modify the initial provisioning settings by increasing an output of at least one of the plurality of IoT devices in the environment or decreasing an output of at least one of the plurality of IoT devices in the environment.

20. The non-transitory computer-readable storage media of claim 15 , wherein the plurality of rules specify a minimum output for at least one of the plurality of IoT devices in the environment or a maximum output for at least one of the plurality of IoT devices in the environment.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Wang Bin
• Zhu Robert
• Chin Ying N
• Zhang Dejun
• Cui Weiyou
• Zhao Pengxiang

Classifications

• H04L67/12

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• H04W12/009

  specially adapted for networks, e.g. wireless sensor networks, ad-hoc networks, RFID networks or cloud networks · CPC title

• H04W4/70

  Services for machine-to-machine communication [M2M] or machine type communication [MTC] · CPC title

• G06F16/906

  Clustering; Classification · CPC title