Adaptive search refinement

• US 9,990,589 B2
• Filed: 07/07/2015
• Issued: 06/05/2018
• Est. Priority Date: 07/07/2015
• Status: Expired due to Fees

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Gabbai, Jonathan, Tenniswood, James, Chakravarti, Nandita
• Primary Examiner(s): Dang, Thanh-Ha
• Application Number:
  US14/793,342
• Publication Number:
  US 20170011136A1
• Time in Patent Office: 1,064 Days
• Field of Search: 707722
• CPC Class Codes: G06F 16/2425 Iterative querying; Query formulation based on the results of a preceding query
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/26 Visual data mining; Browsing structured data
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 3/048 Interaction techniques based on graphical user interfaces [GUI]
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 30/0641 Shopping interfaces

Abstract

A computer-implemented method for adaptive search refinement is provided. The method may include obtaining an indication of user engagement with an online marketplace and in response to obtaining the indication, providing visually guided search refinement to construct a search query for searching the online marketplace. Providing the visually guided search refinement may include providing search refinement options, obtaining an indication of the approval or disapproval of one or more of the search refinement options, and repeating providing the search refinement options and receiving the indication. For each iteration of providing the plurality of search refinement options, at least some of the search refinement options may be different and determined based on previously received indications of both approval and disapproval. The method for adaptive search refinement may further include providing search results based on the search query.

Claims

1. A computer-implemented method for adaptive search refinement, the method comprising:

obtaining a first search query;

comparing a level of specificity of the first search query to a search threshold; and

when the level of specificity is below the search threshold, providing visually guided search refinement to construct a second search query, the visually guided search refinement provided instead of search results for the first search query, wherein providing the visually guided search refinement includes;

providing a plurality of search refinement options, each of the search refinement options including an image visually illustrating a search refinement category and being configured to be both selectively approved and selectively disapproved;

obtaining an indication of the approval or the disapproval of one or more of the plurality of search refinement options; and

repeating providing the plurality of search refinement options and receiving the indication, wherein for each iteration of providing the plurality of search refinement options, at least some of the plurality of search refinement options are different and determined based on previously received indications of both approval and disapproval; and

providing search results based on the second search query.

2. The computer-implemented method of claim 1, wherein the plurality of search refinement options is determined based on a non-absolute interpretation and an absolute interpretation of the previously received indications of approval and disapproval.

3. The computer-implemented method of claim 2, wherein a degree of the non-absolute interpretation of the previously received indications of approval, non-approval, and disapproval is based on a number of approvals, non-approvals, and disapprovals for search refinement options in a same search refinement category.

4. The computer-implemented method of claim 1, wherein the level of specificity of the first search query is based on a word count of the first search query or a number of different categories in which products which are found in the search results for the first search query are categorized.

5. The computer-implemented method of claim 1, wherein the providing the plurality of search refinement options and receiving the indication is repeated until a level of specificity of the second search query is above the search threshold.

6. The computer-implemented method of claim 5, further comprising:

obtaining a search results display request; and

in response to the search results display request, providing the search results based on the second search query before the level of specificity of the second search query is above the search threshold.

7. The computer-implemented method of claim 6, further comprising:

obtaining a visually guided search refinement request; and

in response to the visually guided search refinement request, providing the visually guided search refinement after providing the search results based on the second search query.

8. The computer-implemented method of claim 1, wherein providing the visually guided search refinement further includes providing one or more goods options with the plurality of search refinement options, each of the goods options including an image visually illustrating a particular good and being configured to be approved or disapproved, wherein each iteration of providing the plurality of search refinement options is further based on the previously received indications of approval or disapproval of the one or more goods options.

9. The computer-implemented method of claim 8, wherein the search results include the goods options with received indications of approval.

10. A computer-implemented method for adaptive search refinement, the method comprising:

obtaining an indication of user engagement with an online marketplace;

in response to obtaining the indication, providing visually guided search refinement to construct a search query for searching the online marketplace, wherein providing the visually guided search refinement includes;

providing a plurality of search refinement options, one or more of the search refinement options including an image visually illustrating a search refinement category and being configured to be approved or disapproved;

obtaining an indication of the approval or disapproval of one or more of the plurality of search refinement options; and

repeating providing the plurality of search refinement options and receiving the indication, wherein for each iteration of providing the plurality of search refinement options, at least some of the plurality of search refinement options are different and determined based on previously received indications of both approval and disapproval; and

providing search results based on the search query.

11. The computer-implemented method of claim 10, wherein the plurality of search refinement options is determined based on a non-absolute interpretation and an absolute interpretation of the previously received indications of approval and disapproval.

12. The computer-implemented method of claim 11, wherein a degree of the non-absolute interpretation of the previously received indications of both approval and disapproval is based on a number of approvals and disapprovals for search refinement options in a same search refinement category.

13. The computer-implemented method of claim 10, wherein the providing the plurality of search refinement options and receiving the indication is repeated until an output of a preference machine learning model indicates a product preference above a product preference threshold.

14. The computer-implemented method of claim 13, wherein the output of the preference machine learning model is based on a past history of a current user, the previously received indications of both approval and disapproval, and interactions with the online marketplace by one or more other previous users.

15. The computer-implemented method of claim 14, further comprising:

obtaining a search results display request; and

in response to the search results display request, providing the search results based on the search query before the output of the preference machine learning model is above the product preference threshold.

16. The computer-implemented method of claim 15, further comprising:

obtaining a visually guided search refinement request; and

in response to the visually guided search refinement request, providing the visually guided search refinement after providing the search results based on the search query.

17. The computer-implemented method of claim 10, wherein providing the visually guided search refinement further includes providing one or more goods options with the plurality of search refinement options, each of the goods options including an image visually illustrating a particular good and being configured to be approved or disapproved, wherein each iteration of providing the plurality of search refinement options is further based on the previously received indications of approval or disapproval of the one or more goods options.

18. The computer-implemented method of claim 17, wherein the search results include the goods options with received indications of approval.

19. One or more non-transitory computer-readable media configured to store instructions that when executed by one or more processing systems performs operations that perform a computer-implemented method, the method comprising:

obtaining an indication of user engagement with an online marketplace;

in response to obtaining the indication, providing visually guided search refinement to construct a search query for searching the online marketplace, wherein providing the visually guided search refinement includes;

providing a plurality of search refinement options, one or more of the search refinement options including an image visually illustrating a search refinement category and being configured to be approved or disapproved;

obtaining an indication of the approval or disapproval of one or more of the plurality of search refinement options; and

repeating providing the plurality of search refinement options and receiving the indication, wherein for each iteration of providing the plurality of search refinement options, at least some of the plurality of search refinement options are different and determined based on previously received indications of both approval and disapproval; and

providing search results based on the search query.

20. The one or more non-transitory computer-readable media of claim 19, wherein the plurality of search refinement options is determined based on a non-absolute interpretation and an absolute interpretation of the previously received indications of approval and disapproval.