Granted Patent B2

US 12,748,803 · App. 17/479,172 · Granted Sep 29, 2026

Inventors: Swaminathan Balasubramanian (Troy, MI); Radha Mohan De (Howrah, IN); Mamnoon Jamil (Voorhees, NJ); Jian Wu (Mansfield, TX); Cheranellore Vasudevan (Bastrop, TX)

Assignee: International Business Machines Corporation

G06F16/53G06F16/58

Abstract

Claims (63)

1 . A computer-implemented method of performing an electronic search, the computer-implemented method comprising:

receiving, using a processor, a composite electronic image comprising a plurality of electronically identifiable objects, wherein the composite electronic image is associated with a user;

segmenting, using the processor, the composite electronic image into sub-images by providing at least one of the sub-images for each of the plurality of electronically identifiable objects; and

using the processor to perform personalized sub-image search operations on each of the sub-images without relying on the user taking action, the personalized sub-image search operations comprising:

deciding, by the processor, a sub-image-to-be-searched from among the sub-images;

associating the sub-image-to-be-searched with personalized metadata of the user; and

searching, based at least in part on the personalized metadata of the user, a database to return a set of search images.

2 . The computer-implemented method of claim 1 , wherein the personalized metadata of the user comprises:

a description of a relevance of the sub-image-to-be-searched to the user;

a relative size of the sub-image-to-be-searched to the composite image; and

a relative position of the sub-image-to-be-searched within the composite image.

3 . The computer-implemented method of claim 2 , wherein the personalized metadata of the user is derived from a corpus of information about the user.

4 . The computer-implemented method of claim 1 , wherein the personalized sub-image search operations further comprise:

assigning a relevance level to the sub-image-to-be-searched;

wherein the relevance level comprises a relevance of the sub-image-to-be-searched to the user; and

ranking the sub-image-to-be-searched against the sub-images based at least in part on the relevance level.

5 . The computer-implemented method of claim 1 , wherein the personalized sub-image search operations further comprise:

presenting results of the personalized sub-image search operations to the user; and

receiving feedback from the user on the results of the personalized sub-image search operations.

6 . The computer-implemented method of claim 5 further comprising repeating the personalized sub-image search operations for the sub-image-to-be-searched based on the feedback.

7 . The computer-implemented method of claim 4 , wherein the processor comprises a classifier trained to:

generate the personalized metadata of the user based on the corpus of information about the user; and

determine the relevance of the sub-image-to-be-searched to the user based at least in part on the corpus of information about the user.

8 . A computer system for performing an electronic search, the computer system comprising a memory communicatively coupled to a processor, the processor configured to perform processor operations comprising:

receiving a composite electronic image comprising a plurality of electronically identifiable objects, wherein the composite electronic image is associated with a user;

segmenting the composite electronic image into sub-images by providing at least one of the sub-images for each of the plurality of electronically identifiable objects; and

performing personalized sub-image search operations on each of the sub-images without relying on the user taking action, the personalized sub-image search operations comprising:

deciding, by the processor, a sub-image-to-be-searched from among the sub-images;

using the processor to perform a cognitive task comprising determining a level of relevance of the sub-image-to-be-searched to the user, incorporating the level of relevance of the sub-image-to-be-searched to the user into metadata of the sub-image-to-be-searched to create personalized metadata of the user, and associating the sub-image-to-be-searched with the personalized metadata of the user; and

searching, based at least in part on the personalized metadata of the user, a database to return a set of search images.

9 . The computer system of claim 8 , wherein the personalized metadata of the user comprises a description of a relevance of the sub-image-to-be-searched to the user.

10 . The computer system of claim 9 , wherein the personalized metadata of the user is derived from a corpus of information about the user.

11 . The computer system of claim 8 , wherein the personalized sub-image search operations further comprise:

assigning a relevance level to the sub-image-to-be-searched;

wherein the relevance level comprises the relevance of the sub-image-to-be-searched to the user; and

ranking the sub-image-to-be-searched against the sub-images based at least in part on the relevance level.

12 . The computer system of claim 8 , wherein the personalized sub-image search operations further comprise:

presenting results of the personalized sub-image search operations to the user; and

receiving feedback from the user on the results of the personalized sub-image search operations.

13 . The computer system of claim 12 , wherein the processor operations further comprise repeating the personalized sub-image search operations for the sub-image-to-be-searched based on the feedback.

14 . The computer system of claim 11 , wherein the processor comprises a classifier trained to:

generate the personalized metadata of the user based on the corpus of information about the user; and

determine the relevance of the sub-image-to-be-searched to the user based at least in part on the corpus of information about the user.

15 . A computer program product for performing an electronic search, the computer program product comprising a computer readable program stored on a computer readable storage medium, wherein the computer readable program, when executed on a processor, causes the processor to perform a method comprising:

receiving a composite electronic image comprising a plurality of electronically identifiable objects, wherein the composite electronic image is associated with a user;

segmenting the composite electronic image into sub-images by providing at least one of the sub-images for each of the plurality of electronically identifiable objects; and

performing personalized sub-image search operations on each of the sub-images without relying on the user taking action, the personalized sub-image search operations comprising:

deciding, by the processor, a sub-image-to-be-searched from among the sub-images;

associating the sub-image-to-be-searched with personalized metadata of the user; and

searching, based at least in part on the personalized metadata of the user, a database to return a set of search images.

16 . The computer program product of claim 15 , wherein the personalized metadata of the user comprises a description of a relevance of the sub-image-to-be-searched to the user.

17 . The computer program product of claim 16 , wherein the personalized metadata of the user is derived from a corpus of information about the user.

18 . The computer program product of claim 15 , wherein the personalized sub-image search operations further comprise:

assigning a relevance level to the sub-image-to-be-searched;

wherein the relevance level comprises the relevance of the sub-image-to-be-searched to the user; and

ranking the sub-image-to-be-searched against the sub-images based at least in part on the relevance level.

19 . The computer program product of claim 15 , wherein the personalized sub-image search operations further comprise:

presenting results of the personalized sub-image search operations to the user; and

receiving feedback from the user on the results of the personalized sub-image search operations;

wherein the processor operations further comprise repeating the personalized sub-image search operations for the sub-image-to-be-searched based on the feedback.

20 . The computer program product of claim 18 , wherein the processor comprises a classifier trained to:

generate the personalized metadata of the user based on the corpus of information about the user; and

determine a relevance of the sub-image-to-be-searched to the user based at least in part on the corpus of information about the user.

Assignments (1)

Continuity (1)

References Cited (103)