Dynamic definitive image service

• US 9,910,867 B2
• Filed: 08/18/2016
• Issued: 03/06/2018
• Est. Priority Date: 12/30/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Hamilton, Justin, Ma, Troy, Wu, Kun, Lang, Bing, Sheng, Xiaowei, Vemuluru, Avinash, Borza, Paul
• Primary Examiner(s): Mackes, Kris
• Assistant Examiner(s): Nguyen, Merilyn
• Application Number:
  US15/240,926
• Publication Number:
  US 20160357786A1
• Time in Patent Office: 565 Days
• CPC Class Codes: G06F 16/20 of structured data, e.g. relational data
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• 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 16/5846 using extracted text
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information

Abstract

A representative image system is described herein that provides a representative image for any given search query. Upon receiving a search for a term (or terms), the system accesses an inverted index to identify images associated with that term. The system then receives a ranked list of images. The ranked list includes image identifiers, and once an item in the list is selected the system can use the associated image identifier to retrieve the image from a thumbnail or other server. If an editor has overridden the default image for the present search query, then the system returns the image identifier for the overridden image, which can be used to access the image from the thumbnail or other server. Thus, the representative image system provides a reliable and universal mechanism for retrieving representative images for any given topic dynamically in real time.

Claims

1. A computer system providing a dynamic definitive image service, the system having a processor and a memory, the memory having components executing on the processor and comprising:

an image request component that receives a query from a user for a definitive image that is representative of a topic of the query;

an image mapping component that maps one or more terms of the query to one or more images stored in an image data store for those of the one or more images that are related to the one or more terms;

an image ranking component that ranks the one or more images according to a relative likelihood of being the definitive image for the topic of the query, the image ranking component outputting a ranked definitive image;

an editorial override component that allows a human editor to replace the ranked definitive image selected by the image ranking component with an editor-chosen definitive image;

an image selection component providing as output the definitive image selected from the ranked definitive image and the editor-chosen definitive image;

a retrieval component that retrieves an image binary associated with the definitive image selected by the image selection component; and

an image response component that responds to the query with the retrieved image binary.

2. The system of claim 1, wherein the image ranking component ranks the one or more images based on relevance of each of the one or more images to the one or more terms and a quality of each of the one or more images.

3. The system of claim 1, wherein data regarding the one or more images comprises a plurality of image binaries.

4. The system of claim 3, wherein the image data store includes one or more remote data stores.

5. The system of claim 1, wherein the image request component operates on top of a search engine that services requests for definitive images in addition to requests for images or other types of searches already handled by the search engine.

6. The system of claim 1, wherein the image mapping component maintains an inverted index of the one or more images stored in the image data store, and wherein the image mapping component maps the one or more terms of the query to the one or more images according to the inverted index.

7. The system of claim 6 wherein the inverted index is shared between a search engine service for finding multiple images and a search engine service for finding a single definitive image.

8. The system of claim 1, wherein the image ranking component applies a neural net ranker that factors in information on an authoritativeness of a source of the one or more images and a quality of the one or more images.

9. The system of claim 8, wherein the image ranking component determines the one or more images representative of the topic.

10. A computer-implemented method comprising each of the following as implemented by a processor of a computer:

storing data regarding a plurality of images in an image data store;

receiving, from a user, a query for a definitive image representative of a topic of the query;

identifying one or more of the plurality of images that are related to the topic from the data regarding the plurality of images in the image data store;

ranking each of the one or more of the plurality of images with a relative likelihood score of being the definitive image;

supplying an editorial override allowing a human editor the ability to designate the definitive image irrespective of the ranking;

selecting the definitive image according to the relative likelihood score of the one or more of the plurality of images and according to the editorial override;

retrieving an image binary associated with the selected definitive image; and

sending the retrieved image binary to the user in response to the query.

11. The method of claim 10, wherein ranking each of the one or more of the plurality of images with a relative likelihood score comprises ranking the one or more of the plurality of images based on relevance of an image to a query term and a quality of the respective one of the one or more of the plurality of images.

12. The method of claim 10, wherein the data regarding the one or more of the plurality of images comprises a plurality of image binaries.

13. The method of claim 12, wherein the data regarding the one or more of the plurality of images comprises a plurality of references to image binaries stored in remote data stores.

14. The method of claim 10, wherein the query comprises information indicating a requested quality level of a definitive image.

15. The method of claim 10, wherein ranking each of the one or more of the plurality of images with a relative likelihood score of being the definitive image comprises ranking each of the one or more of the plurality of images according to a corresponding image resolution and authority information associated with a respective one of the one or more of the plurality of images.

16. Computer readable media encoded with computer readable instructions which, when executed by a processor on a computing system, carry out a method for providing a definitive image, the method comprising:

storing data regarding a plurality of images in an image data store;

receiving a request during a query for the definitive image that is representative of a topic of the query;

identifying one or more of the plurality of images that are related to the topic of the query from the data regarding the one or more of the plurality of images in the image data store;

ranking each of the one or more of the plurality of images with a relative likelihood score of being the definitive image;

supplying an editorial override allowing a human editor the ability to designate the definitive image irrespective of the ranking;

selecting the definitive image according to the relative likelihood score of the one or more of the plurality of images and according to the editorial override;

retrieving an image binary associated with the selected definitive image; and

sending the retrieved image binary in response to the request.

17. The computer-readable media of claim 16, wherein ranking each of the one or more of the plurality of images with a relative likelihood score comprises ranking each of the one or more of the plurality of images based on relevance of an image to a query term and a quality of the respective one of the one or more of the plurality of images.

18. The computer-readable media of claim 16, wherein the request comprises information indicating a requested quality level of the requested definitive image.

19. The computer-readable media of claim 16, wherein ranking each of the one or more of the plurality of images with a relative likelihood score comprises ranking each of the one or more of the plurality of images according to a corresponding image resolution and authority information associated with a respective one of the one or more of the plurality of images.