RUN-TIME UTILIZATION OF CONTEXTUAL PREFERENCES FOR A SEARCH INTERFACE

• US 20160125498A1
• Filed: 05/19/2015
• Published: 05/05/2016
• Est. Priority Date: 11/04/2014
• Status: Abandoned Application

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Setty, Rakesh, Somaiya, Manas Haribhai, Mukherjee, Rajyashree
• Application Number:
  US14/716,662
• Publication Number:
  US 20160125498A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/25 Integrating or interfacing systems involving database management systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 30/0627 using item specifications

Abstract

The present disclosure is directed to apparatuses, systems, and methods for enhancing search results based on a user'"'"'s interaction history with a publication system (e.g., an electronic marketplace). As described herein, embodiments may infer various refinements for search queries; these refinements are based, at least in part, on the user'"'"'s previous interactions with the search platform (e.g., from one or more previous sessions) of the publication system. In other words, as the user continuously interacts with the search platform of the publication system across multiple sessions, one or more of refinements may be inferred to help make the search results more relevant to the user.

Claims

1. A system comprising:

a parsing engine to;

receive a user activity log for user activities related to a plurality of item listings published via a publication system and monitored during a plurality of data communication sessions between the user and the publication system, each data communication session to comprise a time period of user interactions with the publication system via a client device; and

parse the user activity log to determine one or more user preferences for one or more user contexts;

an aggregation engine to aggregate the one or more user preferences and the one or more user contexts;

a storage engine to store the aggregated user preferences and user contexts;

a recommendation engine to;

query the storage engine for the stored aggregated user preferences and user contexts; and

determine one or more user preferences for a current user context; and

a processing engine to;

process one or more user activities during a current communication session with the user and the publication system; and

provide item listings to be displayed for the user via a client device used during the current session based, at least in part, on the determined one or more user preferences for the current user context.

2. The system of claim 1, wherein the one or more user activities during the current communication session includes a search query submission for an item offered for sale and listed via the publication system, wherein the provided item listings to be displayed for the user comprise a plurality of item listings to satisfy the search query, wherein the one or more user preferences comprises a determined at least one filter value associated with an item listing attribute, and wherein the processing engine is to further:

narrow a scope the plurality of item listings to satisfy the search query based, at least in part, on the determined at least one filter value.

3. The system of claim 2, wherein the processing engine is to further provide a plurality of selectable filter values to the client machine for display, wherein each filter value, alone or in combination, is to narrow the scope of the plurality of search results into a second plurality of search results, and wherein selectable filter values associated with the determined at least one filter value are displayed as selected filter values.

4. The system of claim 1, wherein the user activities stored in the user activities log comprise at least one of a user selection of a listing, a user bid on a listing, a user purchase of a listing, or an addition of a listing to a user watch list.

5. The system of claim 1, wherein the parsing engine is to further:

determine a confidence score associated with each of the determined one or more user preferences;

wherein the aggregation engine is to further aggregate one or more user preferences associated with a confidence score exceeding a threshold value.

6. The system of claim 1, wherein the processing engine is to further store the one or more user activities during the current communication session with the user and the publication system for the parsing engine to receive in real time.

7. The system of claim 6, wherein the parsing engine is to parse the user activity log in response to detecting an update to the user activity log.

8. A method comprising:

monitoring user activities related to a plurality of item listings at a publication system during a plurality of data communication sessions between the user and the publication system, each data communication session to comprise a time period of user interactions with the publication system via a client device;

determining at least one filter value from the monitored user activities, wherein each filter value is associated with an item listing attribute;

receiving a first search query for an item offered for sale through the publication system from a client device during a current data communication session;

identifying a first plurality of item listings, from a plurality of offered items, satisfying the received first search query;

narrowing the scope of the first plurality of item listings into a second plurality of item listings based, at least in part, on the determined at least one filter value; and

sending the second plurality of item listings for display to the client device used during the current data communication session.

9. The method of claim 8, wherein user actions include at least one of a user selection of a listing, a user bid on a listing, a user purchase of a listing, or an addition of a listing to a user watch list.

10. The method of claim 8, wherein the plurality of item listings comprise query results for a plurality of search queries previously submitted by the user during the plurality of data communication sessions.

11. The method of claim 8, wherein sending the second plurality of item listings for display is in response to receiving a user input request to display the second plurality of item listings.

12. The method of claim 8, further comprising:

sending a plurality of selectable filter values for display, wherein each filter value, alone or in combination, is to narrow the scope of the first plurality of search results into a second plurality of search results, wherein selectable filter values associated with the determined at least one filter value are displayed as selected filter values.

13. The method of claim 8, wherein the item listing attribute comprises a physical attribute of the item.

14. The method of claim 8, wherein the item listing attribute comprises a listing attribute identifying the listing as a fixed price listing or an auction-based listing.

15. The method of claim 8, wherein the plurality of data communication sessions between the user and the publication system comprise data communication sessions authenticated via a user login identifier (ID).

16. The method of claim 15, wherein the plurality of data communication sessions between the user and the publication system comprise data communication sessions which are further authenticated via a cookie stored on the client device used during the current communication session.

17. A non-transitory machine-useable storage medium embodying instructions which, when executed by a machine, cause the machine to perform a process including operations to:

monitor user activities related to a plurality of item listings at a publication system during a plurality of data communication sessions between the user and the publication system, each data communication session to comprise a time period of user interactions with the publication system via a client device;

determine at least one filter value from the monitored user activities, wherein each filter value is associated with an item listing attribute;

receive a first search query for an item offered for sale through the publication system from a client device during a current data communication session;

identify a first plurality of item listings, from a plurality of offered items, satisfying the received first search query;

narrow the scope of the first plurality of item listings into a second plurality of item listings based, at least in part, on the determined at least one filter value; and

send the second plurality of item listings for display to the client device used during the current data communication session.

18. The non-transitory machine-useable storage medium of claim 17, wherein user actions include at least one of a user selection of a listing, a user bid on a listing, a user purchase of a listing, or an addition of a listing to a user watch list.

19. The non-transitory machine-useable storage medium of claim 18, wherein the plurality of item listings comprise query results for a plurality of search queries previously submitted by the user during the plurality of data communication sessions.

20. The non-transitory machine-useable storage medium of claim 17, wherein sending the second plurality of item listings for display is in response to receiving a user input request to display the second plurality of item listings.