Assisted labeling of devices with disaggregation

• US 9,443,195 B2
• Filed: 05/08/2015
• Issued: 09/13/2016
• Est. Priority Date: 11/26/2014
• Status: Active Grant

• Current Assignee: Sense Labs, Inc.
• Original Assignee: Sense Labs, Inc.
• Inventors: MacAulay, Vanessa Lee, Micali, Christopher M., Phillips, Michael S., Houlette, Ryan T.
• Primary Examiner(s): Chang, Li-Wu
• Application Number:
  US14/707,665
• Publication Number:
  US 20160148099A1
• Time in Patent Office: 494 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01R 21/133 by using digital technique
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G06Q 50/06 Energy or water supply

Abstract

Electrical usage of devices in a building may be monitored to assist a user in labeling devices. In some implementations, an electrical signal corresponding to devices may be processed with models to determine first information about a device, and this first information may be presented to a user to receive second information about the device from the user. The device may then be labeled using the second information from the user. In some implementations, a user may provide first information about a device, and the first information may be used to obtain models for processing an electrical signal. A model may be selected from the obtained models by comparing the obtained models to an electrical signal. The device may then be labeled using the selected model or the first information.

Claims

1. A computer-implemented method for labeling devices in a building, the method comprising:

measuring an electrical signal from the building, wherein the electrical signal powers a plurality of devices;

computing a plurality of features from the measured electrical signal;

computing a plurality of scores using a plurality of mathematical models and the plurality of features, wherein (i) the plurality of mathematical models comprises a first mathematical model corresponding to a first class of devices and (ii) the plurality of scores comprises a first score computed using the first mathematical model and the plurality of features;

selecting the first mathematical model using the plurality of scores;

using the first mathematical model to obtain first information about the first class of devices;

causing the first information to be presented to a user;

prompting the user to provide second information about a first device in the building, wherein the first device corresponds to the first class of devices;

receiving the second information from the user;

associating the first device with a label using the second information;

obtaining a second mathematical model for the first device using the second information or the label; and

associating the second mathematical model with the first device.

2. The method of claim 1, wherein the second information or the label indicates a location in the building.

3. The method of claim 1, wherein the second information or the label indicates a make of the first device or a version of the first device.

4. The method of claim 1, wherein the first information comprises a make of the first device, a version of the first device, or a time corresponding to a state change of the first device.

5. The method of claim 1 wherein obtaining the second mathematical model comprises obtaining the second mathematical model from a server computer.

6. The method of claim 1, further comprising adding the first device to a device list.

7. The method of claim 1, wherein selecting the first mathematical model using the plurality of scores comprises selecting a model with a highest score.

8. A system for labeling devices in a building, the system comprising:

one or more computing devices comprising at least one processor and at least one memory, the one or more computing devices configured to;

measure an electrical signal from the building, wherein the electrical signal powers a plurality of devices;

compute a plurality of features from the measured electrical signal;

compute a plurality of scores using a plurality of mathematical models and the plurality of features, wherein (i) the plurality of mathematical models comprises a first mathematical model corresponding to a first class of devices and (ii) the plurality of scores comprises a first score computed using the first mathematical model and the plurality of features;

select the first mathematical model using the plurality of scores;

use the first mathematical model to obtain first information about the first class of devices;

based at least in part on the first information, cause a prompt to be displayed to a user requesting that the user provide second information about a first device in the building, wherein the first device corresponds to the first class of devices;

receive the second information from the user;

associate the first device with a label using the second information;

obtain a second mathematical model for the first device using the second information or the label; and

associate the second mathematical model with the first device.

9. The system of claim 8, wherein the second information or the label indicates a location in the building.

10. The system of claim 8, wherein the second information or the label indicates a make of the first device or a version of the first device.

11. The system of claim 8, wherein the first information indicates that a make or version of the first device is unknown.

12. The system of claim 8, obtaining the second mathematical model comprises obtaining the second mathematical model from a server computer.

13. The system of claim 8, wherein the prompt includes the first information.

14. The system of claim 8, wherein the one or more computing devices are further configured to select the first mathematical model using the plurality of scores by selecting a model with a highest score.

15. One or more non-transitory computer-readable media comprising computer executable instructions that, when executed, cause at least one processor to perform actions comprising:

measuring an electrical signal from the building, wherein the electrical signal powers a plurality of devices;

computing a plurality of features from the measured electrical signal;

computing a plurality of scores using a plurality of mathematical models and the plurality of features, wherein (i) the plurality of mathematical models comprises a first mathematical model corresponding to a first class of devices and (ii) the plurality of scores comprises a first score computed using the first mathematical model and the plurality of features;

selecting the first mathematical model using the plurality of scores;

using the first mathematical model to obtain first information about the first class of devices;

causing the first information to be presented to a user;

prompting the user to provide second information about a first device in the building, wherein the first device corresponds to the first class of devices;

receiving the second information from the user;

associating the first device with a label using the second information;

obtaining a second mathematical model for the first device using the second information or the label; and

associating the second mathematical model with the first device.

16. The one or more non-transitory computer-readable media of claim 15, wherein the second information or the label indicates a location in the building.

17. The one or more non-transitory computer-readable media of claim 15, wherein the second information or the label indicates a make of the first device or a version of the first device.

18. The one or more non-transitory computer-readable media of claim 15, wherein the first information comprises a make of the first device, a version of the first device, or a time corresponding to a state change of the first device.

19. The one or more non-transitory computer-readable media of claim 15, wherein obtaining the second mathematical model comprises obtaining the second mathematical model from a server computer.

20. The one or more non-transitory computer-readable media of claim 15, wherein the computer executable instructions further cause the at least one processor to perform actions comprising:

adding the first device to a device list.

21. The one or more non-transitory computer-readable media of claim 15, wherein selecting the first mathematical model using the plurality of scores comprises selecting a model with a highest score.