Hyperlocal smoothing

• US 8,788,447 B2
• Filed: 06/22/2010
• Issued: 07/22/2014
• Est. Priority Date: 06/22/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Dumais, Susan T., Gounares, Alexander George
• Primary Examiner(s): Chen, Alan
• Assistant Examiner(s): Chubb, Mikayla
• Application Number:
  US12/820,146
• Publication Number:
  US 20110313968A1
• Time in Patent Office: 1,491 Days
• Field of Search: None
• US Class Current: 706/52
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/29 Geographical information databases

Abstract

Concepts and technologies are described herein for hyperlocal smoothing. The hyperlocal smoothing solutions described herein provide a smooth view of data and events across hyperlocal geographic areas by combining sparse data available with inferred or extrapolated data. Additionally, the hyperlocal smoothing solutions described herein make use of contextual analysis to interpret service requests in a manner appropriate for a targeted hyperlocal area. Thus, the smooth view of data can be queried in a contextually sensitive manner to return relevant information for a hyperlocal geographic area, even in circumstances wherein data relevant to the hyperlocal geographic area is sparse or even non-existent.

Claims

1. A computer-implemented method for hyperlocal smoothing, the computer-implemented method comprising performing computer-implemented operations for:

receiving, at a computer executing a smoothing application, a request for explicit attribute data associated with an entity;

determining, by the computer, that the explicit attribute data relating to the entity is not available;

determining, by the computer, that the explicit attribute data relating to the entity or is unreliable by determining that the explicit attribute data is associated with an unreliable source;

in response to determining that the explicit attribute data is either not available or unreliable

analyzing, by the computer, attribute data comprising location data and related entities data,

identifying, by the computer, a further entity that is related to the entity based upon the location data and the related entities data;

obtaining, by the computer, related attribute data comprising attribute data relating to the further entity,

calculating, by the computer, inferred attribute data for the entity based, at least partially, upon the related attribute data; and

outputting, by the computer, the inferred attribute data.

2. The method of claim 1, wherein determining that the explicit attribute data is unreliable further comprises determining that the attribute data is sparse or outdated.

3. The method of claim 1, wherein calculating the inferred attribute data comprises extrapolating the related attribute data to obtain the inferred attribute data, and generating a confidence interval for the inferred attribute data.

4. The method of claim 1, further comprising receiving feedback relating to the inferred attribute data.

5. The method of claim 1, further comprising:

receiving an alert request relating to the inferred attribute data;

formatting at least one alert parameter relating to the alert request;

receiving the related attribute data;

calculating an updated value for the inferred attribute data;

determining if the at least one alert parameter is satisfied;

generating the alert, in response to determining that the at least one alert parameter is satisfied; and

outputting the updated value for the inferred attribute data.

6. The method of claim 5, wherein the at least one alert parameter comprises an inferred attribute data value threshold.

7. The method of claim 1, wherein the attribute data further comprises review data describing reviews associated with entities, locations of the reviews, and times associated with the reviews, and wherein identifying the further entity comprises identifying the further entity based upon similarities between review data associated with the entity and review data associated with the further entity.

8. The method of claim 1, wherein the attribute data further comprises demographics data describing a first population at a first location associated with the entity, and a second population at a second location associated with the further entity, and wherein identifying the further entity comprises identifying the further entity based upon similarities between the first population and the second population.

9. The method of claim 1, wherein the attribute data further comprises contextual data that provides context for the location data, and wherein identifying the further entity comprises identifying the further entity based upon the location data and the contextual data.

10. The method of claim 1, wherein the attribute data further comprises temporal data defining operating hours of entities, and wherein identifying the further entity comprises identifying the further entity based upon similarities between temporal data associated with the entity and temporal data associated with the further entity.

11. A computer-implemented method for hyperlocal smoothing, the computer-implemented method comprising performing computer-implemented operations for:

receiving, at a computer executing a smoothing application, a request for attribute data relating to an entity;

determining, by the computer, if explicit attribute data relating to the entity is available and is reliable;

in response to determining that the explicit attribute data is available and is reliable, outputting, by the computer, the explicit attribute data; and

in response to determining that the explicit attribute data is not available or is unreliable,

identifying, by the computer, at least one related entity located at a locale that is related to a location associated with the entity;

obtaining, by the computer, related attribute data comprising attribute data for the related entity;

calculating, by the computer, an inferred attribute data based, at least partially, upon the related attribute data; and

outputting, by the computer, the inferred attribute data.

12. The method of claim 11, further comprising accessing related entities data to identify at least one related entity, and wherein receiving the related attribute data comprises obtaining attribute data corresponding to the at least one related entity.

13. The method of claim 12, wherein calculating the inferred attribute data comprises extrapolating from the related attribute data to obtain the inferred attribute data, and generating a confidence interval for the inferred attribute data.

14. The method of claim 13, further comprising:

receiving an alert request relating to the inferred attribute data;

formatting at least one alert parameter relating to the alert request;

receiving the related attribute data;

calculating an updated value for the inferred attribute data;

determining if the at least one alert parameter is satisfied, wherein the at least one alert parameter comprises an inferred attribute data value threshold that must be satisfied to generate an alert relating to the inferred attribute data; and

generating the alert, in response to determining that the inferred attribute data value threshold is satisfied.

15. The method of claim 14, wherein calculating the updated value for the inferred attribute data comprises extrapolating the related attribute data to obtain the inferred attribute data, and generating a confidence interval for the updated value for the inferred attribute data.

16. The method of claim 15, further comprising receiving feedback relating to the inferred attribute data.

17. The method of claim 11, wherein the attribute data comprises

location data describing locations associated with the entity and the related entity, and

related entities data describing a relationship between the entity and the related entity.

18. A computer-readable storage medium having computer readable instructions stored thereupon that, when executed by a computer, cause the computer to:

receive a request for attribute data relating to an entity;

determine if explicit attribute data relating to the entity is available and is reliable; and

in response to determining that the explicit attribute data is not available or is unreliable,

access related entities data associated with the entity to identify at least one related entity located at a locale that is related to a location associated with the entity,

obtain attribute data corresponding to the at least one related entity,

smooth the related attribute data to obtain the inferred attribute data,

generate a confidence interval corresponding to the value determined for the inferred attribute data,

output the inferred attribute data,

receive an alert request relating to the inferred attribute data,

format at least one alert parameter relating to the alert request,

receive the related attribute data,

calculate an updated value for the inferred attribute data,

determine if the at least one alert parameter is satisfied, wherein the at least one alert parameter comprises an inferred attribute data value threshold that must be satisfied to generate an alert relating to the inferred attribute data, and

generate the alert, in response to determining that the inferred attribute data value threshold is satisfied.

19. The computer-readable storage medium of claim 18, wherein the attribute data comprises

location data describing locations associated with the entity and the related entity,

demographics data describing a first population associated with the entity and a second population associated with the related entity, and

related entities data describing a relationship between the entity and the related entity.