Method of and system for parameter-free discovery and recommendation of areas-of-interest

• US 9,971,775 B2
• Filed: 06/23/2016
• Issued: 05/15/2018
• Est. Priority Date: 06/30/2015
• Status: Active Grant

• Current Assignee: YE Hub Armenia LLC
• Original Assignee: Yandex Europe AG (Yandex N.V.)
• Inventors: Laptev, Dmitry Anatolievich, Serdyukov, Pavel Viktorovich, Tikhonov, Aleksey Viktorovich, Gusev, Gleb Gennadievich
• Primary Examiner(s): Nakhjavan, Shervin
• Application Number:
  US15/190,684
• Publication Number:
  US 20170024397A1
• Time in Patent Office: 691 Days
• Field of Search: None
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/444 Spatial browsing, e.g. 2D maps, 3D or virtual spaces
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]

Abstract

A method and system for processing a user request for a recommended area of interest includes the steps of receiving the request including an indication of an electronic device geo-location and a user defined search constraint; receiving data associated with photographs associated with geo-objects, the data comprising geo-location coordinates of the photographs, the geo-location coordinates of the photographs being in proximity with the device geo-location; computing a plurality of region representations based on the geo-location coordinates of the photographs, each region representation being associated with a unique photograph density calculation parameter, the computing comprises determining a potential area of interest in each region representation, each region representation being a candidate for an optimal region representation; determining the optimal region representation based on the user defined search constraint; and displaying to the user the recommended area of interest that corresponds to the potential area of interest of the optimal region representation.

Claims

1. A method of processing a user request for a recommended area of interest, the method being executable at a server, the method comprising:

a. receiving the user request, the user request comprising an indication of an electronic device geo-location and a user defined search constraint;

b. receiving data associated with photographs, the photographs associated with geo-objects, the data comprising geo-location coordinates of the photographs, the geo-location coordinates of the photographs being in proximity with the electronic device geo-location;

c. computing a plurality of region representations based on the geo-location coordinates of the photographs, each region representation within the plurality of region representations being associated with a unique photograph density calculation parameter, the computing comprising;

i. computing a histogram representation of the geo-location coordinates of the photographs;

ii. calculating a plurality of density estimations of the histogram representation based on the unique photograph density calculation parameter;

iii. partitioning each density estimation of the plurality of density estimations, wherein each partitioned density estimation corresponds to each region representation, respectively; and

iv. determining a potential area of interest in each region representation, each region representation within the plurality of region representations being a candidate for an optimal region representation;

d. determining the optimal region representation based on the user defined search constraint; and

e. displaying to the user the recommended area of interest that corresponds to the potential area of interest of the optimal region representation.

2. The method of claim 1, wherein the unique photograph density calculation parameter is indicative of size and number of potential areas of interest within each region representation.

3. The method of claim 2, wherein each potential area of interest is associated with a density parameter, the density parameter being based on a number of the geo-location coordinates of the photographs having been mapped within the potential area of interest.

4. The method of claim 3, wherein the optimal region representation comprises multiple potential areas of interest, the method further comprises prior to step (d):

ranking the multiple potential areas of interest of the optimal region representation based on values of the density parameter of the potential areas of interest of the optimal region representation.

5. The method of claim 4, wherein determining the optimal region representation comprises calculating an average surface size of the potential areas of interest for each region representation within the plurality of the region representations.

6. The method of claim 1, wherein the user defined search constraint comprises an additional indication, the additional indication being at least one of:

a current time;

a period of the year; and

a mean for transportation.

7. The method of claim 6, wherein receiving the data associated with the photographs further comprises filtering the data associated with the photographs based on the at least one additional indication.

8. The method of claim 1, wherein the user defined search constraint is a measure of time.

9. The method of claim 1, wherein the data associated with the photographs originates from a public source.

10. The method of claim 1, wherein the data associated with the photographs originates from an electronic device.

11. The method of claim 1, wherein each density estimation of the plurality of density estimations is a kernel density estimation.

12. The method of claim 11, wherein calculating comprises convoluting the histogram representation with a kernel function.

13. The method of claim 1, wherein partitioning comprises executing a watershed segmentation.

14. A server for processing a user request for a recommended area of interest, the server comprising:

a processor; and

an information storage medium in communication with the processor and storing computer-readable instructions that cause the processor to;

a. receive the user request, the user request comprising an indication of an electronic device geo-location and a user defined search constraint;

b. receive data associated with photographs, the photographs associated with geo-objects, the data comprising geo-location coordinates of the photographs, the geo-location coordinates of the photographs being in proximity with the electronic device geo-location;

c. compute a plurality of region representations based on the geo-location coordinates of the photographs, each region representation within the plurality of region representations being associated with a unique photograph density calculation parameter, to compute the plurality of region representations comprising to;

i. compute a histogram representation of the geo-location coordinates of the photographs;

ii. calculate a plurality of density estimations of the histogram representation based on the unique photograph density calculation parameter;

iii. partition each density estimation of the plurality of density estimations, wherein each partitioned density estimation corresponds to one region representation; and

iv. determine a potential area of interest in each region representation, each region representation within the plurality of region representations being a candidate for an optimal region representation;

d. determine the optimal region representation based on the user defined search constraint; and

e. display to the user the recommended area of interest that corresponds to the potential area of interest of the optimal region representation.

15. The server of claim 14, wherein the unique photograph density calculation parameter is indicative of size and number of potential areas of interest within each region representation.

16. The server of claim 15, wherein each potential area of interest is associated with a density parameter, the density parameter being based on a number of the geo-location coordinates of the photographs having been mapped within the potential area of interest.

17. The server of claim 16, wherein the optimal region representation comprises multiple potential areas of interest, prior to step (d) the server is further configured to:

rank the multiple potential areas of interest of the optimal region representation based on values of the density parameter of the potential areas of interest of the optimal region representation.

18. The server of claim 17, wherein to determine the optimal region representation the server is further configure to calculate an average surface size of the potential areas of interest for each region representation within the plurality of the region representations.

19. The server of claim 14, wherein the user defined search constraint comprises an additional indication, the additional indication being at least one of:

a current time;

a period of the year; and

a mean for transportation.

20. The server of claim 19, wherein to receive the data associated with the photographs further comprises filtering the data associated with the photographs based on the at least one additional indication.

21. The server of claim 14, wherein the user defined search constraint is a measure of time.

22. The server of claim 14, wherein the data associated with the photographs originates from a public source.

23. The server of claim 14, wherein the data associated with the photographs originates from an electronic device.

24. The server of claim 14, wherein each density estimation of the plurality of density estimations is a kernel density estimation.

25. The server of claim 24, wherein to calculate comprises to convolute the histogram representation with a kernel function.

26. The server of claim 14, wherein to partition comprises to execute a watershed segmentation.