CONVERSION OF STATIC IMAGES INTO INTERACTIVE MAPS

• US 20180181807A1
• Filed: 12/22/2016
• Published: 06/28/2018
• Est. Priority Date: 12/22/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Yankov, Dragomir, Berkhin, Pavel, Evans, Michael Robert
• Granted Patent: US 10,417,492 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06T 3/40 Scaling of whole images or parts thereof, e.g. expanding or contracting
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 30/422 Technical drawings; Geographical maps
• CPC Class Codes: G09B 29/003 Maps

Abstract

The present disclosure is directed to systems, methods and devices for replacing a static map image with an interactive map that approximates the geographic area depicted by the static map image. A static image may be inspected and a determination may be made as to whether the static image meets a map identification threshold value. At least one signal associated with the static image may be evaluated and based on that evaluation at least one geo-entity of intent may be identified. The static image may be replaced with a static image corresponding to at least one of the identified geo-entities of intent.

Claims

1. A method for converting a static image into an interactive map, comprising:

inspecting the static image;

determining whether the static image meets a map identification threshold value;

evaluating at least one signal associated with the static image, the at least one signal including text extracted from the static image;

identifying, based on the evaluation of the at least one signal, at least one geo-entity of intent; and

replacing the static image with an interactive map corresponding to at least one of the identified geo-entities of intent.

2. The method of claim 1, wherein the evaluation of the at least one signal further comprises analyzing a plurality of candidate text strings determined from optical character recognition of the extracted text.

3. The method of claim 2, further comprising:

analyzing a font size of each of the candidate text strings; and

filtering out one or more of the candidate text strings determined to have a smaller font size relative to at least one other candidate text string.

4. The method of claim 2, further comprising:

evaluating the pixel distance of each of the candidate text strings relative to each of the other candidate text strings; and

determining, based on the evaluation of the pixel distance, a scale for the interactive map.

5. The method of claim 1, wherein the at least one signal further comprises a user image query and the identification of the at least one geo-entity of intent comprises determining at least one term from the user image query corresponding to a geo-entity.

6. The method of claim 1, wherein the at least one signal further comprises one or more words adjacent to the static image and the identification of the at least one geo-entity of intent comprises determining at least one term from the one or more words adjacent to the static image corresponding to a geo-entity.

7. The method of claim 1, wherein the at least one signal further comprises a URL for a webpage that the static image is embedded in and the identification of the at least one geo-entity of intent comprises determining at least one term from the URL corresponding to a geo-entity.

8. The method of claim 1, wherein the at least one signal further comprises an indication of an area of focus.

9. The method of claim 1, wherein the at least one signal further comprises one of:

a current user location and a determined user market for the user.

10. The method of claim 1, wherein identifying at least one geo-entity of intent comprises:

determining a plurality of potential geo-entities of intent;

identifying at least one geo-location for each of the plurality of potential geo-entities of intent;

clustering each of the plurality of potential geo-entities of intent into a geo-chain hierarchy; and

filtering, based on a machine learned ranking of the clustered potential geo-entities of intent, at least one of the potential geo-entities of intent having a lower rank in the geo-chain hierarchy than at least one other potential geo-entities of intent.

11. The method of claim 3, wherein identifying at least one geo-entity of intent further comprises:

measuring, in pixels, a first distance from a first candidate text string to a second candidate text string closest to the first candidate text string;

measuring, in pixels, a second distance from the first candidate text string to a third candidate text string that is second closest to the first candidate text string;

calculating an average geodesic distance for the first and second distances; and

filtering at least one potential geo-entity of intent having a larger average geodesic distance for the first and second distances relative to at least one other potential geo-entity of intent.

12. The method of claim 3, further comprising determining a viewport size for the interactive map to replace the static image, the determining comprising:

determining a pixel distance from a first candidate text string corresponding to a first potential geo-entity of intent to a second candidate text string corresponding to second potential geo-entity of intent;

geocoding the first potential geo-entity of intent and the second potential geo-entity of intent;

determining, based on the geocoding, a geodesic distance from the first potential geo-entity of intent and the second potential geo-entity of intent;

determining that a ratio between the determined pixel distance and the determined geodesic distance exceeds a threshold value; and

adjusting the size of the interactive map for display.

13. The method of claim 11, further comprising:

measuring, in pixels, a distance from each of a plurality of potential geo-entities of intent to each side of the static image; and

computing, based on the measuring of the distance from each of the plurality of potential geo-entities of intent to each side of the static image, longitude and latitude coordinates to display for the interactive map.

14. A computer-readable storage device having computer-executable instructions, that when executed by a processor, assist with converting a static image into an interactive map, the computer-executable instructions executable by the processor for:

inspecting the static image;

determining whether the static image meets a map identification threshold value;

evaluating at least one signal associated with the static image, the at least one signal including text extracted from the static image;

identifying, based on the evaluation of the at least one signal, at least one geo-entity of intent; and

replacing the static image with an interactive map corresponding to at least one of the identified geo-entities of intent.

15. The computer-readable storage device of claim 14, wherein the evaluation of the at least one signal further comprises analyzing a font size of a plurality of candidate text strings from the extracted text and filtering out at least one of the candidate text strings determined to have a smaller font size relative to at least one other candidate text string of the plurality of candidate text strings.

16. The computer-readable storage device of claim 14, wherein identifying at least one geo-entity of intent comprises:

determining a plurality of potential geo-entities of intent;

identifying a geo-location for each of the plurality of potential geo-entities of intent;

clustering each of the plurality of potential geo-entities of intent into a geo-chain hierarchy; and

filtering at least one of the potential geo-entities of intent having a lower rank in the geo-chain hierarchy than at least one other potential geo-entity of intent.

17. The computer-readable storage device of claim 15, wherein identifying at least one geo-entity of intent further comprises:

measuring, in pixels, a first distance from a first candidate text string to a second candidate text string closest to the first candidate text string;

measuring, in pixels, a second distance from the first candidate text string to a third candidate text string that is second closest to the first candidate text string;

calculating an average geodesic distance for the first and second distances; and

filtering at least one potential geo-entity of intent having a larger average geodesic distance for the first and second distances relative to at least one other potential geo-entity of intent.

18. A system for assisting with converting a static image into an interactive map, comprising:

a memory for storing executable program code; and

a processor, functionally coupled to the memory, the processor being responsive to computer-executable instructions contained in the program code and operative to;

inspect the static image;

determine whether the static image meets a map identification threshold value;

evaluate at least one signal associated with the static image, the at least one signal including text extracted from the static image;

identify, based on the evaluation of the at least one signal, at least one geo-entity of intent; and

replace the static image with an interactive map corresponding to at least one of the identified geo-entities of intent.

19. The system of claim 18, wherein the evaluation of the at least one signal further comprises analyzing a font size of a plurality of candidate text strings from the extracted text and filtering at least one of the candidate text strings determined to have a smaller font size relative to at least one other candidate text string of the plurality of candidate text strings.

20. The system of claim 18, wherein identifying at least one geo-entity of intent comprises:

determining a plurality of potential geo-entities of intent;

identifying at least one geo-location for each of the plurality of potential geo-entities of intent;

clustering each of the plurality of potential geo-entities of intent into a geo-chain hierarchy; and

filtering at least one of the potential geo-entities of intent having a lower rank in the geo-chain hierarchy than at least one other potential geo-entities of intent.