Mapping gathered location information to short form place names using correlations and confidence measures that pertain to lengths of overlaps of location data and calendar data sets

• US 9,792,556 B2
• Filed: 09/26/2014
• Issued: 10/17/2017
• Est. Priority Date: 09/26/2014
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Takaya, Norifumi, Gunatilake, Priyan Deveka, Balasubramanian, Guru Prashanth
• Primary Examiner(s): VINCENT, DAVID ROBERT
• Application Number:
  US14/498,106
• Publication Number:
  US 20160092785A1
• Time in Patent Office: 1,117 Days
• Field of Search: 706 45, 706 12
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

Using the short form information people tend to use in their calendar locations (not full address or GPS location), machine learning techniques are used to map gathered location information to these short form names.

Claims

1. A device comprising:

at least one non-transitory computer readable storage medium with instructions executable by at least one processor to configure the processor for;

receiving geographic location information from at least one source of location information;

receiving calendar information from at least one data storage;

correlating at least one calendar data set from the calendar information with at least first and second location data sets derived from the location information based at least in part on the first and second data sets temporally overlapping with the calendar data set to render first and second correlations;

associating the first and second correlations with respective first and second confidence measures, each confidence measure being based at least in part on a length of temporal overlap between the respective location data set and the calendar data set;

selecting one of the correlations based at least in part on a relationship between respective confidence measures; and

outputting human-perceptible user information associated with the calendar data set and the location data set associated with the correlation selected based at least in part on the confidence measures.

2. The device of claim 1, wherein the instructions when executed by the at least one processor configure the processor for:

determining a confidence measure based at least in part on a length of temporal overlap between the respective location data set and the calendar data set and a number of times the respective correlation has been recorded in temporally discontinuous recordings.

3. The device of claim 1, wherein the instructions when executed by the at least one processor configure the processor for:

selecting the first correlation based at least in part on the first confidence measure being greater than the second confidence measure.

4. The device of claim 1, wherein the source of location information is a location data set storage.

5. The device of claim 4, wherein the location data set storage includes geographically determinate names correlated to GPS locations.

6. The device of claim 1, wherein the user information includes an electronic map showing a geographic location of a place in the calendar data set, the calendar data set not including the geographic location.

7. The device of claim 1, wherein the user information includes alpha-numeric driving directions to a place in the calendar data set, the calendar data set not including the geographic location.

8. The device of claim 1, wherein the calendar data set includes a start time, an end time, and a geographically indeterminate place name.