METHODS AND SYSTEMS FOR IDENTIFICATION AND CORRECTION OF CONTROLLED SYSTEM DATA

• US 20150161515A1
• Filed: 12/08/2014
• Published: 06/11/2015
• Est. Priority Date: 12/08/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Matsuoka, Yoky
• Granted Patent: US 10,002,184 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2614 HVAC, heating, ventillation, climate control
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent

Abstract

Computational methods and systems that collect operational data from an intelligent controller to identify information, or correct information, about a device and system controlled by the intelligent controller are disclosed. Computational methods and systems use a set of operational data and information known about other devices and systems controlled by similar intelligent controllers to process the operational data and generate information, or correct information, about the device and system.

Claims

1. A computer system comprising:

one or more processors;

one or more data-storage devices; and

machine-readable instructions stored in one or more of the one or more data-storage devices that, when executed by the one or more processors;

receives operational data generated by an intelligent controller;

retrieves registration data associated with the intelligent controller from the one or more data-storage devices;

examines the registration data for defects; and

when the registration data includes defects;

generates approximate registration data based on the operational data and a set of operational data and registration data collected from a number of similar intelligent controllers, and

corrects defective registration data with corresponding approximate registration data.

2. The computer system of claim 1, wherein examines the registration data for defects further comprises:

examines the registration data for inconsistencies between the registration data and the operational data; and

examines the registration data for incomplete registration data.

3. The computer system of claim 2, wherein examines the registration data for inconsistencies further comprises:

generating approximate operational data based on the registration data and the set of operational data and registration data collected from a number of similar intelligent controllers; and

comparing elements of the operational data with elements of the approximate operational data.

4. The computer system of claim 3, wherein generates approximate operational data based on the registration data and the set of operational data and registration data collected from the similar intelligent controllers further comprises:

calculating weights that relate the set of operational data and registration data collected from the similar intelligent controllers using a feed-forward neural network with back propagation; and

calculating approximate operational data from the registration data and the weights.

5. The computer system of claim 1, wherein corrects defective registration data with corresponding approximate registration data further comprises:

when the registration data is inconsistent with the operational data, replaces inconsistent registration data elements with corresponding generated registration data elements; and

when the registration data is incomplete, filling in missing registration data elements with corresponding approximate registration data elements.

6. The computer system of claim 1, wherein generates approximate registration data based on the operational data and the set of operational data and registration data collected from the similar intelligent controllers further comprises:

calculating weights that relate the set of operational data and registration data collected from the similar intelligent controllers using a feed-forward neural network with back propagation; and

calculating approximate registration data from the operational data and the weights.

7. The computer system of claim 1, wherein the operational data further comprises data collected from intelligent controller sensors, control schedules, and data generated by the intelligent controller.

8. The computer system of claim 1, wherein the intelligent controller further comprises an intelligent thermostat.

9. The computer system of claim 1, wherein when the registration data does not include defects, add the operation data and registration data associated with the intelligent controller to the set of operational data and registration collected from the similar intelligent controllers.

10. A method to be carried out by a computer system that includes one or more processors and one or more data-storage devices, the method comprising:

receiving operational data and registration data associated with an intelligent controller;

examining the registration data for defects;

when the registration data includes defects;

generating approximate registration data based on the operational data and a set of operational data and registration data collected from a number of similar intelligent controllers, and

correcting defective registration data with corresponding approximate registration data; and

when the registration data does not include defects, adding the operation data and registration data associated with an intelligent controller to the set of operational data and registration collected from a number of similar intelligent controllers.

11. The method of claim 10, wherein examining the registration data for defects further comprises:

examining the registration data for inconsistencies between the registration data and the operational data; and

examining the registration data for incomplete registration data.

12. The method of claim 11, wherein examines the registration data for inconsistencies further comprises:

generating approximate operational data based on the registration data and the set of operational data and registration data collected from a number of similar intelligent controllers; and

comparing elements of the operational data with elements of the approximate operational data.

13. The method of claim 12, wherein generates approximate operational data based on the registration data and the set of operational data and registration data collected from the similar intelligent controllers further comprises:

calculating weights that relate the set of operational data and registration data collected from the similar intelligent controllers using a feed-forward neural network with back propagation; and

calculating approximate operational data from the registration data and the weights.

14. The method of claim 10, wherein corrects defective registration data with corresponding approximate registration data further comprises:

when the registration data is inconsistent with the operational data, replaces inconsistent registration data elements with corresponding generated registration data elements; and

when the registration data is incomplete, filling in missing registration data elements with corresponding approximate registration data elements.

15. The method of claim 10, wherein generates approximate registration data based on the operational data and the set of operational data and registration data collected from the similar intelligent controllers further comprises:

calculating weights that relate the set of operational data and registration data collected from the similar intelligent controllers using a feed-forward neural network with back propagation; and

calculating approximate registration data from the operational data and the weights.

16. The method of claim 10, wherein the operational data further comprises data collected from intelligent controller sensors, control schedules, and data generated by the intelligent controller.

17. The method of claim 10, wherein the intelligent controller further comprises an intelligent thermostat.

18. A computer-readable medium having machine-readable instructions encoded thereon for enabling one or more processors to perform the operations of:

receiving operational data and registration data from one or more memories, the operational data and registration data associated with an intelligent controller;

examining the registration data for defects;

when the registration data includes defects;

generating approximate registration data based on the operational data and a set of operational data and registration data collected from a number of similar intelligent controllers, and

correcting defective registration data with corresponding approximate registration data; and

when the registration data does not include defects, adding the operation data and registration data associated with an intelligent controller to the set of operational data and registration collected from a number of similar intelligent controllers.

19. The medium of claim 18, wherein generates approximate registration data based on the operational data and the set of operational data and registration data collected from the similar intelligent controllers further comprises:

calculating weights that relate the set of operational data and registration data collected from the similar intelligent controllers using a feed-forward neural network with back propagation; and

calculating approximate registration data from the operational data and the weights.

20. The medium of claim 18, wherein correcting defective registration data with corresponding approximate registration data further comprises:

when the registration data is inconsistent with the operational data, replaces inconsistent registration data elements with corresponding generated registration data elements; and

when the registration data is incomplete, filling in missing registration data elements with corresponding approximate registration data elements.