UTILIZING CONTEXT INFORMATION OF ENVIRONMENT COMPONENT REGIONS FOR EVENT/ACTIVITY PREDICTION

• US 20180288161A1
• Filed: 04/13/2018
• Published: 10/04/2018
• Est. Priority Date: 11/17/2016
• Status: Active Grant

• Current Assignee: BrainofT, Inc.
• Original Assignee: BrainofT, Inc.
• Inventors: Saxena, Ashutosh, Zhou, Jinjing, Chu, Maurice, Deng, Deng, Lad, Kunal, Venkatesh, Ashwini
• Granted Patent: US 10,931,758 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 7/00 Computing arrangements based on specific mathematical models
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/33 for indoor environments, e.g. buildings
• CPC Class Codes: H04W 4/38 for collecting sensor information
• CPC Class Codes: H04W 4/70 Services for machine-to-machine communication [M2M] or machine type communication [MTC]
• CPC Class Codes: H04W 84/18 Self-organising networks, e.g. ad-hoc networks or sensor networks

Abstract

Sensor data is received from a physical environment sensor. A component region associated with at least a portion of the sensor data is identified. A physical environment has been defined to include a plurality of component regions. Context information associated with the identified component region is obtained. The context information is utilized in association with a prediction model.

Claims

1. A method, comprising:

receiving sensor data from a physical environment sensor;

identifying a component region associated with at least a portion of the sensor data, wherein a physical environment has been defined to include a plurality of component regions;

obtaining context information associated with the identified component region; and

utilizing the context information in association with a prediction model.

2. The method of claim 1, wherein the context information is utilized in association with the prediction model to detect an activity performed by a human user.

3. The method of claim 1, wherein the sensor data is processed by one or more signal aggregators selected based on the context information associated with the identified component region.

4. The method of claim 3, wherein each of the one or more signal aggregators aggregate different sensor data and associated context information, and one or more outputs of the signal is aggregators are utilized by the prediction model to identify an activity performed by a subject.

5. The method of claim 1, wherein when a user associated with the physical environment is in a new physical environment, the prediction model is transferred for application for the new physical environment.

6. The method of claim 1, wherein a plurality of physical environment sensors monitors the same identified component region and sensor data from the plurality of physical environment sensors is correlated together in response to an identification that the plurality of physical environment sensors monitor the same identified component region.

7. The method of claim 1, wherein utilizing the context information in association with the prediction model includes training the prediction model.

8. The method of claim 1, wherein utilizing the context information in association with the prediction model includes providing the context information to the prediction model to calculate a corresponding prediction value associated with a plurality of candidate activity states of a subject.

9. The method of claim 1, further comprising using a result of the prediction model to control a network connected device.

10. The method of claim 1, wherein the physical environment sensor includes at least one of the following:

a switch, a camera, a motion detector, an infrared detector, a light detector, an accelerometer, a thermal detector, a human pose detector, a thermometer, an air quality sensor, a smoke detector, a microphone, a humidity detector, a door sensor, a window sensor, a water detector, a glass breakage detector, and a power utilization sensor.

11. The method of claim 1, wherein the plurality of component regions includes a hierarchy of component regions.

12. The method of claim 1, wherein at least two of the plurality of component regions overlap each other.

13. The method of claim 1, wherein the plurality of component regions includes a three-dimensional space and a three-dimensional area.

14. The method of claim 1, wherein the identified component region has been defined as a physical region around an object in the physical environment.

15. The method of claim 1, wherein the physical environment is an apartment environment.

16. The method of claim 1, wherein the plurality of component regions of the physical environment has been at least in part defined using a graph model of the physical environment.

17. The method of claim 1, wherein identifying the component region associated with at least the portion of the sensor data includes determining which one or more component regions, if any, is detected by the physical environment sensor and associating at least the portion of the sensor data with the identified component region.

18. The method of claim 1, wherein obtaining the context information associated with the identified component region includes obtaining the context information from a graph model of the physical environment.

19. The method of claim 1, wherein the context information includes one or more of the following:

a spatial relationship information associated with the identified component region, a functional information associated with the identified component region, and information about an item associated with the identified component region, and information about functional capabilities of the item associated with the identified component region.

20. A system, comprising:

a processor configured to;

receive sensor data from a physical environment sensor;

identify a component region associated with at least a portion of the sensor data, wherein a physical environment has been defined to include a plurality of component regions;

obtain context information associated with the identified component region; and

utilize the context information in association with a prediction model; and

a memory coupled to the processor and configured to provide the processor with is instructions.

21. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

receiving sensor data from a physical environment sensor;

identifying a component region associated with at least a portion of the sensor data, wherein a physical environment has been defined to include a plurality of component regions;

obtaining context information associated with the identified component region; and

utilizing the context information in association with a prediction model.