Increasing the accuracy of information returned for context signals

• US 8,938,653 B2
• Filed: 12/14/2011
• Issued: 01/20/2015
• Est. Priority Date: 12/14/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Suzue, Yutaka, Apacible, Johnson T., Encarnacin, Mark J., Huynh, Jamie, Bernstein, Simon D.
• Primary Examiner(s): TU, CHRISTINE TRINH LE
• Application Number:
  US13/325,493
• Publication Number:
  US 20130159804A1
• Time in Patent Office: 1,133 Days
• Field of Search: 714/746, 714/747, 714/799, 714/699, 714/701, 455/404.2, 455/456.3, 455/456.1, 455/456.2, 455/450
• US Class Current: 714/746
• CPC Class Codes: H04L 2101/69 using geographic information, e.g. room number
• CPC Class Codes: H04L 61/45 Network directories; Name-to-address mapping
• 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 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Abstract

The subject disclosure is directed towards a technology by which the accuracy of context-based information provided by at least one data source for received context data is increased. Correctness information received in association with usage of looked up context-based information is logged. The correctness information may be processed to increase the overall accuracy by correcting a data source, and/or by creating a blended data source that includes the most likely accurate portions (segments) from among multiple data sources as determined via the correctness information.

Claims

1. In a computing environment, a method performed at least in part on at least one processor, comprising:

providing context signals associated with a mobile device to at least one data source;

receiving context-based information corresponding to the context signals from the at least one data source;

receiving correctness information corresponding to accuracy of the context-based information from a correctness measure based on crowd-sourced feedback; and

processing the correctness information to generate a blended data source to increase an overall accuracy corresponding to other context-based information provided by the at least one data source for other received context signals.

2. The method of claim 1 wherein receiving the context-based information further comprises receiving location information, and using the location information to provide a result set comprising at least one location-based result, wherein receiving the correctness information comprises receiving feedback indicative of whether the location-based result is likely correct.

3. The method of claim 1 wherein receiving the context-based information comprises receiving location information, wherein receiving the correctness information comprises receiving complementary location information from a likely more accurate data source, and wherein processing the correctness information to increase the overall accuracy comprises correcting the at least one data source if the location information is not consistent with the complementary location information.

4. The method of claim 1 wherein receiving the context-based information comprises receiving location information, wherein receiving the correctness information comprises receiving complementary location information from a likely more accurate data source, and wherein processing the correctness information to increase the overall accuracy comprises dynamically correcting output of the at least one data source if the location information is known to be incorrect based upon the complementary location information.

5. The method of claim 1 wherein receiving the context-based information comprises receiving Internet protocol (IP) address data that is used to obtain location information, and wherein receiving the correctness information comprises receiving user feedback indicative of whether the user was satisfied or dissatisfied with a result set that includes at least one result based upon the location information.

6. The method of claim 1 further comprising:

logging the correctness information received from the correctness measure for each of a plurality of data sources.

7. The method of claim 6 wherein the at least one data source comprises a plurality of independent data sources that each contain at least some inaccurate data, and wherein processing the correctness information to increase the overall accuracy comprises processing the logged correctness information of the plurality of data sources to create a blended data source from among the plurality of data sources, including, segmenting each data source into segments to provide a plurality of counterpart segments among the plurality of data sources, determining a measure of correctness for each counterpart segment, and selecting selected segments for the blended data source from among the counterpart segments based at least in part upon the measure of correctness for each counterpart segment.

8. A system comprising:

a memory;

at least one processor coupled to the memory;

a service, implemented on the at least one processor, configured to provide context data to a plurality of data sources, receive context-based information from each of the plurality of data sources, receive correctness information from a correctness measure, the correctness information corresponding to the accuracy of the context-based information from each of the plurality of data sources, and process the correctness information to generate a blended data source having the highest accuracy of the context-based information.

9. The system of claim 8, further comprising:

a correctness log located in the memory and configured to store the correctness information corresponding to the context-based information from each of the plurality of data sources, wherein processing the correctness information includes segmenting each data source from the plurality of data sources to provide a plurality of counterpart segments among the plurality of data sources, determining a measure of correctness for each counterpart segment, and selecting segments for the blended data source from among the counterpart segments based at least in part upon the measure of correctness for each counterpart segment.

10. The system of claim 8, further comprising:

a data source segment mechanism configured to segment each data source from the plurality of data sources to provide a plurality of counterpart segments among the plurality of data sources;

a segment score computation mechanism configured to determine a measure of correctness for each of the plurality of counterpart segments; and

a blending mechanism configured to select a counterpart segment from the plurality of counterpart segments having the highest measure of correctness and use selected segments to build the blended data source.

11. The system of claim 8, further comprising:

a data source segment mechanism configured to segment each data source from the plurality of data sources to provide a plurality of counterpart segments among the plurality of data sources;

a segment score computation mechanism configured to determine a measure of correctness for each of the plurality of counterpart segments; and

a mapping mechanism configured to dynamically select a counterpart segment from the plurality of counterpart segments having the highest measure of correctness and use selected segments to provide a result.

12. The system of claim 8, further comprising:

a correctness log located in the memory and configured to store the correctness information corresponding to the context-based information from each of the plurality of data sources; and

a data source correction mechanism configured to process the stored correctness information of the correctness log to provide updates to one or more of the plurality of data sources.

13. The system of claim 8, further comprising:

a correctness log located in the memory and configured to store the correctness information corresponding to the context-based information from each of the plurality of data sources; and

a data source correction mechanism configured to process the stored correctness information of the correctness log to provide dynamic correction data for one or more of the plurality of data sources.

14. One or more computer storage devices having computer-executable instructions, which when executed by a computer, cause the computer to perform steps comprising:

providing context data associated with a computing device to at least one data source;

receiving context-based information corresponding to the context data from the at least one data source;

receiving correctness information corresponding to accuracy of the context-based information from a correctness measure based on at least one of explicit or implicit feedback; and

processing the correctness information to increase an overall accuracy corresponding to other context-based information provided by the at least one data source for other received context data.

15. The one or more computer storage devices of claim 14, wherein the correctness measure comprises user feedback.

16. The one or more computer storage devices of claim 14 having further computer-executable instructions comprising:

logging the correctness information received from the correctness measure, wherein the at least one data source comprises a plurality of data sources, and wherein processing the correctness information to increase the overall accuracy comprises processing the logged correctness information corresponding to the plurality of data sources to generate a blended data source from among the plurality of data sources.

17. The one or more computer storage devices of claim 14 wherein the at least one data source comprises a plurality of data sources, and wherein processing the correctness information further comprises:

segmenting each data source into segments to provide a plurality of counterpart segments among the plurality of data sources;

determining a measure of correctness for each counterpart segment; and

selecting segments for a blended data source from among the counterpart segments based at least in part upon the measure of correctness for each counterpart segment.

18. The one or more computer storage devices of claim 14 having further computer-executable instructions comprising:

converting a logged user action corresponding to the context-based information into a value associated with the correctness measure.