Measuring and diagnosing noise in an urban environment

• US 10,444,062 B2
• Filed: 09/12/2014
• Issued: 10/15/2019
• Est. Priority Date: 09/12/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Zheng, Yu, Chang, Eric
• Primary Examiner(s): Bloss, Stephanie E
• Application Number:
  US15/509,521
• Publication Number:
  US 20170299424A1
• Time in Patent Office: 1,859 Days
• CPC Class Codes: G01H 3/10 Amplitude; Power
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: H04W 4/02 Services making use of location information

Abstract

A computer system measures noise in an urban environment using data records providing a location of a noise, a time stamp associated with the noise, and a noise category. Such data records are sparse with respect to both locations and time. The computer system also accesses other information that defines correlations of among different locations and among different time slots. Such correlation data can include geographic information and historical sample data. By applying this correlated information to the sparse data records about noise, the computer system can derive noise level and noise category information over a larger geographical area. Such information can be provided continually based on received data records about noise, typically in a matter of minutes after receiving the noise data for any given time slot.

Claims

1. A computer system for measuring noise conditions in regions of an urban environment, comprising:

computer storage comprising;

noise sample data associating a noise with a location and a point in time in a plurality of time slots, wherein at least one location does not have noise sample data for at least one time slot;

correlation data defining correlations among regions indicating regions which are geographically similar and temporal correlations among the plurality of time slots indicating time slots having similar noise conditions;

one or more processing units programmed to access the computer storage to process the sample data using the correlation data to provide an output describing, for each region, at least a noise condition for the region for at least the current time slot, by;

computing data comprising at least the noise condition for locations having noise sample data in the current time slot; and

applying the correlation data to compute at least the noise condition for locations not having sample data in the current time slot.

2. The computer system of claim 1, wherein the correlation data comprises road features for each region.

3. The computer system of claim 2, wherein the road features comprise a number of intersections in the region.

4. The computer system of claim 1, wherein the correlation data comprises correlations between noise categories derived from historic noise sample data.

5. The computer system of claim 1, wherein the correlation data comprises user location data providing a number of individuals in a region in a time slot.

6. The computer system of claim 1, wherein the noise sample data includes a matrix of per-region geographical features and a matrix of users located in each region in each of a set of time slots and wherein processing the sample data using the correlation data includes factorizing the matrices to determine noise conditions for other regions where noise samples have not been received in the current time slot.

7. The computer system of claim 1, wherein the processing of the sample data by the one or more processing units for a current time slot occurs in real time within a time slot of receiving the sample data.

8. The computer system of claim 1, wherein the noise sample data comprises called complaint information received through a telephone system and providing a noise category, time and location.

9. The computer system of claim 1, wherein the correlation data includes data derived from user check-in information for a social network.

10. The computer system of claim 1, wherein the correlation data includes traffic data received through sensors.

11. A computer-implemented process comprising:

receiving noise sample data associating noise with a location and a point in time in a plurality of time slots, wherein at least one location does not have noise sample data for at least one time slot;

accessing correlation data defining correlations among regions indicating regions which are geographically similar and temporal correlations among the plurality of time slots indicating time slots having similar noise conditions;

processing the noise sample data using the correlation data to provide an output describing, for each region, at least noise conditions for the region for at least the current time slot, by;

computing data comprising at least the noise condition for locations having noise sample data in the current time slot; and

applying the correlation data to compute at least the noise condition for locations not having sample data in the current time slot.

12. The computer-implemented process of claim 11, wherein the correlation data comprises road features for each region.

13. The computer-implemented process of claim 12, wherein the road features comprise a number of intersections in the region.

14. The computer-implemented process of claim 11, wherein the correlation data comprises correlations between noise categories derived from historic noise sample data.

15. An article of manufacture, comprising:

one or more computer storage media comprising at least one of a memory device and a storage device;

computer program instructions stored on the one or more computer storage media which, when processed by a computer, configure the computer to implement a process, comprising;

receiving noise sample data associating noise with a location and a point in time in a plurality of time slots, wherein at least one location does not have noise sample data for at least one time slot;

accessing correlation data defining correlations among regions indicating regions which are geographically similar and temporal correlations among the plurality of time slots indicating time slots having similar noise conditions;

processing the noise sample data using the correlation data to provide an output describing, for each region, at least noise conditions for the region for at least the current time slot, by;

computing data comprising at least the noise condition for locations having noise sample data in the current time slot; and

applying the correlation data to compute at least the noise condition for locations not having sample data in the current time slot.

16. The article of manufacture of claim 15, wherein the correlation data comprises correlations between noise categories derived from historic noise sample data.

17. The article of manufacture of claim 15, wherein the correlation data comprises user location data providing a number of individuals in a region in a time slot.

18. The article of manufacture of claim 15, wherein the processing of the sample data by the one or more processing units for a current time slot occurs in real time within a time slot of receiving the sample data.

19. The article of manufacture of claim 15, wherein the noise sample data comprises called complaint information received through a telephone system and providing a noise category, time and location.

20. The article of manufacture of claim 15, wherein the correlation data includes traffic data received through sensors.