IP Library Granted Patent US 11,720,947
Granted Patent B2
US 11,720,947 · App. 16/655,935 · Granted Aug 8, 2023

Method, media, and system for generating diverse search results for presenting to a user

Inventors: Saratchandra Indrakanti (Pleasanton, CA); Manojkumar Rangasamy Kannadasan (Freemont, CA); Rajyashree Mukherjee (San Carlos, CA); Svetlana Strunjas (Menlo Park, CA); Shubhangi Tandon (San Jose, CA)
Assignee: EBAY INC.
G06Q30/0625G06F16/248G06F16/24578
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,720,947
App. No.
16/655,935
Filed
Oct 17, 2019
Granted
Aug 8, 2023
Kind
B2
Art Unit
3684
USPC
705/26.62
Abstract

A search engine provides diverse search results in response to a search query using a trained diversity ranker. The diverse results may be generated by determining ranking positions of at least some search results based on delta feature values that are dependent on higher-ranked results. Delta feature values indicate a degree or magnitude of difference between a particular result and other results with respect to a particular feature, such as price, category, or shipping type. In providing the ranked results for presentation to a user at a computing device, a diversity feature indicator for at least some results may be generated. The diversity feature is a feature that distinguishes a given result from other results. As such, the diversity feature indicator represents that diversity feature for the particular result being different from other results and distinguishes the diversity feature from other features in the particular result.

Claims (37)

1. A computer-implemented method for providing a visualization of diverse search results, the computer-implemented method comprising:

receiving a search query at a search engine;

identifying a set of item listings based on the search query;

ranking item listings within the set of item listings based at least partly on one or more delta feature values for at least a subset of item listings, the one or more delta feature values being dependent on higher-ranked item listings within the set of item listings;

providing for display the ranking of item listings as search results for the search query; and

based upon a hover interaction with a particular item listing of the item listings, providing a diversity feature indicator for the particular item listing of the item listings within the ranking of item listings that disappears when a cursor is moved away from the particular item listing of the item listings, wherein the diversity feature indicator visually represents a diversity feature for the particular item listing being different than higher-ranked item listings and visually distinguishes the diversity feature from other features identified in the particular item listing, and further wherein the diversity feature indicator includes a pop-up message displayed within a user interface corresponding to the search engine, the pop-up message explaining how the particular item listing is different from other item listings.

2. The computer-implemented method of claim 1 , further comprising identifying the diversity feature for the particular item listing based on a set of delta feature values indicating a degree of difference in feature values between the particular item listing and other item listings within the set of item listings.

3. The computer-implemented method of claim 2 , wherein identifying the diversity feature for the particular item listing comprises determining an impact value for each delta feature value within the set of delta feature values, the impact value measuring an amount of influence that the delta feature value had on ranking the particular item listing.

4. The computer-implemented method of claim 3 , wherein the diversity feature is identified for the particular item listing based on having the highest impact value relative to other delta feature values for that particular item listing.

5. The computer-implemented method of claim 1 , wherein the diversity feature indicator comprises a textual feature indicator that is formatted differently than indicators for corresponding features in other item listings and other features in the particular item listing.

6. The computer-implemented method of claim 1 , wherein the diversity feature indicator comprises an icon or image that is displayed with a textual indicator of the diversity feature.

7. The computer-implemented method of claim 1 , wherein diversity feature indicators for different item listings represent different features.

8. The computer-implemented method of claim 1 , wherein features corresponding to the one or more delta feature values comprise shipping type, price, and item category.

9. The computer-implemented method of claim 1 , wherein ranking the item listings within the set of item listings comprises determining one or more feature values independently of other item listings and determining the one or more delta feature values for at least a subset of item listings based on feature values of higher-ranked item listings.

10. The computer-implemented method of claim 9 , wherein, for each item listing within the subset of item listings, the one or more feature values determined independently are combined with the one or more delta feature values.

11. One or more computer storage media having computer-executable instructions embodied thereon that, when executed by one or more processors, cause the one or more processors to perform a method for providing diverse search results, the method comprising

receiving a search query at a search engine;

identifying a set of item listings based on the search query;

providing for display a ranking of item listings as search results for the search query; and

based upon a hover interaction with a particular item listing of the item listings, providing a diversity feature indicator for the particular item listing of the item listings within the ranking of item listings that disappears when a cursor is moved away from the particular item listing of the item listings, wherein the diversity feature indicator visually represents a diversity feature for the particular item listing being different than higher-ranked item listings and visually distinguishes the diversity feature from other features identified in the particular item listing, and further wherein the diversity feature indicator includes a pop-up message displayed within a user interface corresponding to the search engine, the pop-up message explaining how the particular item listing is different from other item listings.

12. The computer storage media of claim 11 , wherein the method further comprises determining the ranking of item listings based at least partly on one or more delta feature values for at least a first subset of item listings, the one or more delta feature values being dependent on higher-ranked item listings within the set of item listings, wherein the particular item listing is within the first subset.

13. The computer storage media of claim 12 , wherein a second subset of item listings are not presented with diversity feature indicators.

14. The computer storage media of claim 13 , wherein the second subset of item listings are ranked higher than the first subset of item listings.

15. The computer storage media of claim 14 , wherein the second subset of item listings are not ranked based on delta feature values.

16. A search system for providing diverse results, the system comprising:

one or more processors; and

one or more computer storage media storing computer-useable instructions that, when used by the one or more processors, cause the one or more processors to:

receive a search query at a search engine;

identify a set of item listings based on the search query;

for at least a subset of item listings, determine delta feature values for one or more features of the subset of item listings, each delta feature value indicating a degree of difference between an item listing and other item listings within the set of item listings with respect to a feature;

rank item listings within the set of item listings based at least partly on the delta feature values; and

provide for display the ranking of item listings as search results for the search query; and

based upon a hover interaction with a particular item listing of the item listings, provide a diversity feature indicator for the particular item listing of the item listings within the ranking of item listings that disappears when a cursor is moved away from the particular item listing of the item listings, wherein the diversity feature indicator visually represents a diversity feature for the particular item listing being different than higher-ranked item listings and visually distinguishes the diversity feature from other features identified in the particular item listing, and further wherein the diversity feature indicator includes a pop-up message displayed within a user interface corresponding to the search engine, the pop-up message explaining how the particular item listing is different from other item listings.

17. The search system of claim 16 , wherein the diversity feature indicator represents the diversity feature for the particular item listing being different from only a portion of higher-ranked item listings.

18. The search system of claim 16 , wherein identifying the diversity feature for the particular item listing comprises determining an impact value for each delta feature value, the impact value measuring an amount of influence that the delta feature value had on ranking the particular item listing.

19. The search system of claim 16 , wherein each diversity feature indicator is a visual indicator.

20. The search system of claim 19 , wherein diversity feature indicators for different item listings visually represent different features.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 13, 2019
From: INDRAKANTI, SARATCHANDRA; KANNADASAN, MANOJKUMAR RANGASAMY; MUKHERJEE, RAJYASHREE; STRUNJAS, SVETLANA; TANDON, SHUBHANGI
To: EBAY INC.
Reel/Frame 050987/0930 →
Continuity (1)
Related Publication 20210118034A1 · Apr 22, 2021