Automatic fixture monitoring using mobile location and sensor data with smart meter data

• US 9,417,092 B2
• Filed: 04/25/2014
• Issued: 08/16/2016
• Est. Priority Date: 04/25/2014
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Srinivasan, Vijay, Tapia, Emmanuel M.
• Primary Examiner(s): Phan, Hai
• Assistant Examiner(s): Wu, Zhen Y
• Application Number:
  US14/262,601
• Publication Number:
  US 20150308856A1
• Time in Patent Office: 844 Days
• Field of Search: 340/870
• US Class Current: 1/1
• CPC Class Codes: G01D 2204/125 Utility meter reading systems specially adapted for determining the environmental impact of user behaviour
• CPC Class Codes: G01D 2204/14 Displaying of utility usage with respect to time, e.g. for monitoring evolution of usage or with respect to weather conditions
• CPC Class Codes: G01D 2204/24 Identification of individual loads, e.g. by analysing current/voltage waveforms
• CPC Class Codes: G01D 4/002 Remote reading of utility meters
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network
• CPC Class Codes: Y02B 70/34 Smart metering supporting the carbon neutral operation of end-user applications in buildings
• CPC Class Codes: Y02B 90/20 Smart grids as enabling technology in buildings sector smart grids supporting the management or operation of end-user stationary applications in general, or like technologies with no associated climate change mitigation effect Y04S20/00
• CPC Class Codes: Y04S 20/30 Smart metering, e.g. specially adapted for remote reading
• CPC Class Codes: Y04S 40/18 Network protocols supporting networked applications, e.g. including control of end-device applications over a network

Abstract

A method and system for monitoring resource information and user activity. The method includes acquiring one or more data streams from one or more resource meters and one or more electronic device sensors. Discrete events are computed from each data stream. A sequence of discrete sensor-meter event itemsets are extracted based on the events. Frequent sensor-meter event itemsets are discovered from the sequence of discrete event itemsets that occur together, and a frequency of occurrence of each frequent co-occurrence itemset is discovered. Rising sensor-meter event itemsets and falling sensor-meter event itemsets are matched based on appliance state models and the frequency of occurrence of each sensor-meter event itemset. Each individual fixture is identified. Each fixture cluster is classified to a fixture category. Based on the matched fixture events, fixture clusters, and categories, resource usage information and user activities are determined for each fixture usage event identified.

Claims

1. A method for monitoring resource information and user activity comprising:

acquiring one or more data streams from one or more resource meters and one or more electronic device sensors;

computing discrete events from each data stream;

extracting a sequence of discrete sensor-meter event itemsets based on the discrete events;

discovering frequent sensor-meter event itemsets that occur together, and determining a frequency of occurrence for each sensor-meter event itemset;

matching rising and falling sensor-meter event itemsets based on appliance state models and the frequency of occurrence of each sensor-meter event itemset;

identifying each individual fixture based on clustering the matched sensor-meter event itemsets using sensor-meter event features;

classifying each fixture cluster to a fixture category using a multi-modal fixture model trained on sensor and meter event features; and

based on the matched fixture events, fixture clusters, and categories, determining resource usage information and user activities for each fixture usage event identified.

2. The method of claim 1, wherein:

the one or more electronic sensors provide location data;

the discrete sensor-meter event itemsets contain events that occur together within a same particular time frame; and

the resource information comprises at least one of;

location presence of electrical appliances and water fixtures;

location of fixtures on a floor plan;

use time of one or more of each individual fixture and electrical appliance; and

one or more of energy and water resource consumption of one or more of each individual fixture and electrical appliance.

3. The method of claim 2, wherein the one or more user activities comprise:

one or more particular users that used a particular appliance or fixture;

one or more resources wasted by the one or more particular users; and

related daily activities of the one or more particular users in view of appliance or fixture usage and activity area,

wherein based on the matched fixture events, fixture clusters, and categories, further determining user identifier and location for each fixture usage event identified.

4. The method of claim 3, further comprising:

computing discretized events from each data stream, computing sensor-meter event itemsets based on the sensor and meter events that occur together near a same time, and computing the frequent sensor-meter event itemsets along with the frequency of occurrence of each sensor-meter event itemset.

5. The method of claim 4, wherein matching the rising and the falling sensor-meter event itemsets further comprises using pre-stored appliance state machine models and frequencies of sensor-meter event itemsets for matching the rising sensor-meter event itemsets and the falling sensor-meter event itemsets to at least one appliance device usage instance.

6. The method of claim 5, wherein identifying each individual fixture comprises clustering the matched sensor-meter events to a set of unique clusters, and each cluster corresponds to a unique fixture at a location, and the sensor-meter event features comprise one or more of sensor event magnitude and meter event magnitude.

7. The method of claim 6, wherein classifying each fixture cluster identified to a fixture category comprises using a pre-stored multi-modal fixture classifier model that is trained on sensor-meter event features.

8. The method of claim 7, wherein:

determining related daily activities of the one or more particular users comprises using a pre-stored activity classifier trained on fixture usage data from a set of training locations; and

determining the location of fixtures on the floor plan comprises using a median location for all location events from a given fixture cluster.

9. The method of claim 1, wherein the one or more electronic device sensors comprise one or more of:

an accelerometer, a gyroscope, a microphone, a temperature sensor, a light sensor, a barometer, a magnetometer, and a compass.

10. The method of claim 9, wherein the one or more resource meters comprise one or more of a smart water meter and a smart electrical meter, and the electronic device comprises a mobile electronic device.

11. The method of claim 10, wherein the mobile electronic device comprises at least one of:

a mobile telephone, a wearable computing device, a tablet device, and a mobile computing device.

12. A system comprising:

an electronic device that includes a plurality of sensor devices, wherein the electronic device is configured to;

acquire one or more data streams from one or more resource meters and one or more electronic sensors;

compute discrete events from each data stream;

extract a sequence of discrete sensor-meter event itemsets based on the events that occur together;

discover the frequent sensor-meter event itemsets that occur together, and compute a frequency of occurrence for each sensor-meter event itemset;

match rising and falling sensor-meter event itemsets based on appliance state models and the frequency of occurrence of each sensor-meter event itemset;

identify each individual fixture based on clustering the matched sensor-meter event itemsets using sensor-meter event features;

classify each fixture cluster to a fixture category using a multi-modal fixture model trained on sensor and meter event features; and

based on the matched fixture events, fixture clusters, and categories, determine resource usage information and associated user activities for each fixture usage event identified.

13. The system of claim 12, wherein:

the one or more electronic sensors provide location data;

the discrete sensor-meter event itemsets contain events that occur together within a same particular time frame; and

the resource information comprises at least one of;

location presence information of electrical appliances and water fixtures at the location;

location of fixtures on a floor plan of the location;

use time of one or more of each individual fixture and electrical appliance at the location; and

one or more of energy and water resource consumption of one or more of each individual fixture and electrical appliance at the location.

14. The system of claim 13, wherein the one or more user activities comprise:

one or more particular users that used a particular appliance or fixture at the location;

one or more resources wasted by the one or more particular users; and

related daily activities of the one or more particular users in view of appliance or fixture usage and activity area at the location;

wherein based on the matched fixture events, fixture clusters, and categories, the electronic device determines user identifier and location for each fixture usage event identified.

15. The system of claim 14, wherein the electronic device is further configured to:

compute discretized events from each data stream, extract the sequence of discrete sensor-meter event itemsets based on the events that occur together within the same particular time frame, discover the frequent sensor-meter event itemsets that occur together, determine a frequency of occurrence for each sensor-meter event itemset, and match the rising and falling sensor-meter event itemsets based on pre-stored appliance state models and the frequency of occurrence of each sensor-meter event itemset, wherein each matched event corresponds to an instance of user usage of an appliance device.

16. The system of claim 15, wherein the electronic device is further configured to identify each individual fixture based on clustering the matched sensor-meter event itemsets using sensor-meter event features comprising one or more of sensor event magnitude and meter event magnitude.

17. The system of claim 16, wherein the electronic device is further configured to classify each fixture cluster to a fixture category using a pre-built multi-modal fixture model trained on sensor and meter event features.

18. The system of claim 17, wherein the electronic device is further configured to use the matched fixture events, fixture clusters and categories to:

determine related daily activities of the one or more particular users based on using a pre-stored activity classifier trained on fixture usage data from a set of training locations; and

determine the location of fixtures on the floor plan based on using a median location for all location events from a given fixture cluster.

19. The system of claim 12, wherein the plurality of electronic device sensors comprises at least one of:

an accelerometer, a gyroscope, a microphone, a temperature sensor, a light sensor, a barometer, a magnetometer, and a compass, and the one or more resource meters comprise one or more of a smart water meter and a smart electrical meter, and the electronic device comprises a mobile electronic device.

20. The system of claim 19, wherein the mobile electronic device comprises at least one of:

a mobile telephone, a wearable computing device, a tablet device, and a mobile computing device.

21. A non-transitory processor-readable medium that includes a program that when executed by a processor performs a method comprising:

acquiring one or more data streams from one or more resource meters and one or more electronic sensors;

computing discrete events from each data stream;

extracting a sequence of discrete sensor-meter event itemsets based on the events that occur together;

discovering the frequent sensor-meter event itemsets that occur together, and determining a frequency of occurrence for each sensor-meter event itemset;

matching rising and falling sensor-meter event itemsets based on appliance state models and the frequency of occurrence of each sensor-meter event itemset;

identifying each individual fixture based on clustering the matched sensor-meter event itemsets using sensor-meter event features;

classifying each fixture cluster to a fixture category using a multi-modal fixture model trained on sensor and meter event features; and

based on the matched fixture events, fixture clusters, and categories, determining resource usage information and associated user activities for each fixture usage event identified.

22. The non-transitory processor-readable medium of claim 21, wherein:

the one or more electronic sensors provide location data;

the discrete sensor-meter event itemsets contain events that occur together within a same particular time frame; and

the resource information comprises at least one of;

location presence of electrical appliances and water fixtures;

location of fixtures on a floor plan;

use time of one or more of each individual fixture and electrical appliance; and

one or more of energy and water resource consumption of one or more of each individual fixture and electrical appliance; and

the one or more user activities comprise;

one or more particular users that used a particular appliance or fixture;

one or more resources wasted by the one or more particular users; and

related daily activities of the one or more particular users in view of appliance or fixture usage and activity area.

23. The non-transitory processor-readable medium of claim 22, wherein the program when executed by the processor performs the method further comprising:

computing discretized events from each data stream, and extracting a sequence of discrete sensor-meter event itemsets based on the events that occur together around the same time, wherein based on the matched fixture events, fixture clusters, and categories, further determining user identifier and location for each fixture usage event identified.

24. The non-transitory processor-readable medium of claim 23, wherein the program when executed by the processor performs the method further comprising:

discovering the frequent sensor-meter event itemsets that occur together, and determining a frequency of occurrence for each frequent sensor-meter event itemset.

25. The non-transitory processor-readable medium of claim 24, wherein the program when executed by the processor performs the method further comprising:

matching rising and falling sensor-meter event itemsets based on pre-stored appliance state models and the frequency of occurrence of each sensor-meter event itemset, wherein each matched sensor-meter event corresponds to a specific instance of user usage of an appliance device.

26. The non-transitory processor-readable medium of claim 25, wherein identifying each individual fixture comprises clustering the matched sensor-meter event itemsets to a set of unique fixture clusters using sensor-meter event features comprising one or more of sensor event magnitude and meter event magnitude, classifying each fixture cluster to a fixture category comprises using a pre-built multi-modal fixture classifier model trained on sensor and meter event features.

27. The non-transitory processor-readable medium of claim 26, further comprising using the matched fixture events, fixture clusters, and categories to:

determine related daily activities of the one or more particular users using a pre-stored activity classifier trained on fixture usage data from a set of training locations; and

determine location of fixtures on a floor plan using a median location for multiple location events from a given fixture cluster.

28. The non-transitory processor-readable medium of claim 21, wherein the one or more electronic device sensors comprise one or more of:

an accelerometer, a gyroscope, a microphone, a temperature sensor, a light sensor, a barometer, a magnetometer, and a compass.

29. The non-transitory processor-readable medium of claim 28, wherein the one or more resource meters comprise one or more of a smart water meter and a smart electrical meter, and the electronic device comprises a mobile electronic device.

30. The non-transitory processor-readable medium of claim 29, wherein the mobile electronic device comprises at least one of:

a mobile telephone, a wearable computing device, a tablet device, and a mobile computing device.