Updating point of interest data based on an image

• US 9,165,206 B2
• Filed: 12/11/2012
• Issued: 10/20/2015
• Est. Priority Date: 12/12/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Corpet, Pascal, Ibrahim, Ammar, Leung, Patrick Pui Wah, Ryskamp, Robert Allen, McGlinchey, Andrew John, Assad, Iyad F. I., Versi, Jannine C., Terrenghi, Lucia, Adan, Yariv, Rogers, Steve Anthony
• Primary Examiner(s): Rush, Eric
• Application Number:
  US13/711,512
• Publication Number:
  US 20150169977A1
• Time in Patent Office: 1,043 Days
• Field of Search: 382/100, 382/103, 382/181, 382/182, 382/224, 382/229, 382/305, 382/306, 382/325, 707/915, 707917-921, 707/940
• US Class Current: 1/1
• CPC Class Codes: G06F 16/21 Design, administration or maintenance of databases
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/434 using image data, e.g. images, photos, pictures taken by a user
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/176 Urban or other man-made structures
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

Various aspects of the subject technology relate to systems, methods, and machine-readable media for updating a point of interest (POI) data repository. A system may be configured to receive a communication comprising an image associated with a point of interest, extract textual data from the image, identify a portion of the textual data that corresponds to a point of interest (POI) field in a point of interest listing, and update the point of interest (POI) data repository based on the portion of the textual data that corresponds to the POI field.

Claims

1. A computer-implemented method for updating a point of interest (POI) data repository, the method comprising:

receiving a communication comprising an image of an interior of a point of interest;

extracting textual data from the image;

identifying a portion of the textual data that corresponds to a point of interest (POI) field for a point of interest listing;

updating the point of interest (POI) data repository to include at least some of the textual data extracted from the image based at least in part on the portion of the textual data that corresponds to the POI field for the point of interest listing; and

updating the POI data repository with respect to a second point of interest (POI) field for the point of interest listing based on content depicted within the image that is associated with the interior of the point of interest.

2. The computer-implemented method of claim 1, wherein updating the POI data repository comprises:

determining if a POI listing in the POI data repository contains information that matches the portion of the textual data;

generating, if no POI listing contains information that matches with the portion of the textual data, a new POI listing that includes the at least some of the textual data extracted from the image based at least in part on the portion of the textual data that corresponds to the POI field; and

storing the new POI listing in the POI data repository.

3. The computer-implemented method of claim 2, further comprising:

providing the new POI listing to a system administrator for approval before storing the new POI listing in the POI data repository.

4. The computer-implemented method of claim 3, wherein the system administrator is a human operator.

5. The computer-implemented method of claim 2, wherein if an existing POI listing containing information that matches the portion of the textual data is found in the POI data repository, the method further comprising:

updating the existing POI listing to include the at least some of the textual data extracted from the image.

6. The computer-implemented method of claim 5, wherein the communication comprising the image further includes additional information, and wherein the existing POI listing is updated based on the additional information.

7. The computer-implemented method of claim 6, wherein the additional information comprises additional textual data that corresponds to a third POI field.

8. The computer-implemented method of claim 6, wherein the additional information includes location coordinates.

9. The computer-implemented method of claim 1, wherein the POI field includes one of a POI name, a POI address, a POI phone number, a POI website, POI business hours, or a POI type.

10. The computer-implemented method of claim 1, wherein the point of interest is a business.

11. A system for updating a point of interest (POI) data repository, the system comprising:

one or more processors; and

a machine-readable medium comprising instructions stored therein, which when executed by the one or more processors, cause the one or more processors to perform operations comprising;

receiving one or more communications comprising a plurality of images associated with a point of interest, a first image of the plurality of images being captured within an interior of the point of interest;

extracting textual data from at least one image of the plurality of images using optical character recognition;

identifying a portion of the textual data that corresponds to a point of interest (POI) field;

updating the point of interest (POI) data repository to include at least some of the textual data extracted from the at least one image based at least in part on the portion of the textual data that corresponds to the POI field; and

updating the POI data repository with respect to a second point of interest (POI) field based on content depicted within the first image that is associated with the interior of the point of interest.

12. The system of claim 11, the operations further comprising:

searching for a POI listing in a POI data repository containing information that matches the portion of the textual data;

generating a new POI listing that includes the at least some of the textual data extracted from the image if no POI listing is found; and

storing the new POI listing in the POI data repository.

13. The system of claim 12, wherein if an existing POI listing containing information that matches the portion of the textual data is found, the operations further comprise updating the existing POI listing to include the at least some of the textual data extracted from the image.

14. The system of claim 11, wherein the one or more communications further include additional information, and wherein the POI data repository is updated based on the additional information.

15. The system of claim 14, wherein the additional information comprises additional textual data that corresponds to a third POI field.

16. The system of claim 14, wherein the additional information includes at least one of location coordinates or text inputted by a user.

17. A non-transitory machine-readable medium comprising instructions stored therein, which when executed by a machine, cause the machine to perform operations comprising:

receiving a communication comprising an image of an interior of a point of interest;

extracting textual data from the image;

identifying a portion of the textual data that corresponds to a point of interest (POI) field;

identifying content depicted within the image that is associated with the interior of the point of interest, the content corresponding to a second point of interest (POI) field

generating a new point of interest (POI) listing based at least in part on the portion of the textual data that corresponds to the POI field and the content that corresponds to the second POI field, the new POI listing comprising at least some of the textual data extracted from the image.

18. The machine-readable medium of claim 17, wherein the operations further comprise:

providing the new POI listing to a system administrator for review;

receiving an approval indication from the system administrator, and

adding the new POI listing to a POI data repository based on the approval indication.

19. The machine-readable medium of claim 18, wherein the system administrator is a human operator.