System and method for providing automatic high-value listing feeds for online computer users

• US 10,311,488 B2
• Filed: 08/17/2015
• Issued: 06/04/2019
• Est. Priority Date: 08/25/2011
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Liu, Shaobo, Tang, Tom (Xiaofeng)
• Primary Examiner(s): Richardson, James E
• Assistant Examiner(s): Khakhar, Nirav K
• Application Number:
  US14/828,012
• Publication Number:
  US 20160042410A1
• Time in Patent Office: 1,387 Days
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0276 Advertisement creation

Abstract

A system and method for providing automatic high-value listing feeds for online computer users is disclosed. A particular embodiment includes obtaining publisher information corresponding to a plurality of publisher content items from a plurality of publisher sites; obtaining merchant information including value information corresponding to the plurality of publisher content items; using a processor, the publisher information, and the merchant information to generate a set of high-value feeds for transfer to the plurality of publisher sites, the set of high-value feeds each being ranked corresponding to a quality score computed for each listing item of each high-value feed; and transferring the set of high-value feeds to corresponding publisher sites of the plurality of publisher sites.

Claims

1. A computer-implemented method comprising:

obtaining publisher information corresponding to a plurality of publisher content items from a plurality of publisher sites, the publisher information comprising a plurality of user queries and a plurality of keywords corresponding to the plurality of publisher content items;

obtaining merchant information including value information corresponding to the plurality of publisher content items;

generating a merchant data set using the merchant information, the merchant data set comprising information related to relationships between products or items appearing in particular publisher content items, identifiers of publisher sites corresponding to the particular publisher content items, merchant bids corresponding to the products or items, and a merchant or seller associated with each merchant bid;

generating, by a processor, a set of high-value feeds based on the publisher information and the merchant information, wherein generating the set of high-value feeds comprises;

allocating relative profits to each user query based on at least one of a sum of clicks or a sum of bids for each user query determined from the merchant data set;

selecting a set of user queries satisfying a threshold profitability; and

determining, using at least in part the set of user queries selected, a quality score for each listing item corresponding to a keyword from the plurality of keywords, wherein the set of high-value feeds comprises listing items selected using qualities scores; and

transmitting the set of high-value feeds to corresponding publisher sites of the plurality of publisher sites.

2. The computer-implemented method of claim 1, further comprising generating a publisher data set using the publisher information, the publisher data set comprising information related to relationships between products or items appearing in particular publisher content items and identifiers of publisher sites corresponding to the particular publisher content items.

3. The computer-implemented method of claim 1, wherein obtaining the publisher information includes providing an application programming interface (API) for the plurality of publisher sites.

4. The computer-implemented method of claim 1, wherein generating the set of high-value feeds further comprises performing a keyword cleansing operation to pre-process the publisher information.

5. The computer-implemented method of claim 1, wherein generating the set of high-value feeds further comprises obtaining a revenue value associated with each listing item of each high-value feed.

6. The computer-implemented method of claim 1, wherein generating the set of high-value feeds further comprises matching keywords against content in a set of listings.

7. The computer-implemented method of claim 1, wherein generating the set of high-value feeds further comprises ranking the listing items in the set of listing items based on the quality scores and restricting a pre-determined portion of the ranked listing items from being in the set of high-value feeds.

8. The computer-implemented method of claim 7, wherein the pre-determined portion of the ranked listing items comprises listing items that do not satisfy a minimum quality score threshold.

9. A system comprising:

at least one processor; and

a non-transitory computer-readable medium storing executable instructions that, when executed, cause the at least one processor to perform operations comprising;

obtaining publisher information corresponding to a plurality of publisher content items from a plurality of publisher sites, the publisher information comprising a plurality of user queries and a plurality of keywords corresponding to the plurality of publisher content items;

obtaining merchant information including value information corresponding to the plurality of publisher content items;

generating a merchant data set using the merchant information, the merchant data set comprising information related to relationships between products or items appearing in particular publisher content items, identifiers of publisher sites corresponding to the particular publisher content items, merchant bids corresponding to the products or items, and a merchant or seller associated with each merchant bid;

generating a set of high-value feeds based on the publisher information and the merchant information, wherein generating the set of high-value feeds comprises;

allocating relative profits to each user query based on at least one of a sum of clicks or a sum of bids for each user query determined from the merchant data set;

selecting a set of user queries satisfying a threshold profitability; and

determining, using at least in part the set of user queries selected, a quality score for each listing item corresponding to a keyword from the plurality of keywords, wherein the set of high-value feeds comprises listing items selected using qualities scores; and

transmitting the set of high-value feeds to corresponding publisher sites of the plurality of publisher sites.

10. The system of claim 9, wherein the operations further comprise generating a publisher data set using the publisher information, the publisher data set comprising information related to relationships between products or items appearing in particular publisher content items and identifiers of publisher sites corresponding to the particular publisher content items.

11. The system of claim 9, wherein obtaining the publisher information includes providing an application programming interface (API) for the plurality of publisher sites.

12. The system of claim 9, wherein generating the set of high-value feeds further comprises performing a keyword cleansing operation to pre-process the publisher information.

13. The system of claim 9, wherein generating the set of high-value feeds further comprises obtaining a revenue value associated with each listing item of each high-value feed.

14. The system of claim 9, wherein generating the set of high-value feeds further comprises matching keywords against content in a set of listings.

15. The system of claim 9, wherein generating the set of high-value feeds further comprises ranking the listing items in the set of listing items based on the quality scores and restricting a pre-determined portion of the ranked listing items from being in the set of high-value feeds.

16. A non-transitory computer-readable medium storing executable instructions that, when executed, cause at least one processor to perform operations comprising:

obtaining publisher information corresponding to a plurality of publisher content items from a plurality of publisher sites, the publisher information comprising a plurality of user queries and a plurality of keywords corresponding to the plurality of publisher content items;

obtaining merchant information including value information corresponding to the plurality of publisher content items;

generating a merchant data set using the merchant information, the merchant data set comprising information related to relationships between products or items appearing in particular publisher content items, identifiers of publisher sites corresponding to the particular publisher content items, merchant bids corresponding to the products or items, and a merchant or seller associated with each merchant bid;

generating a set of high-value feeds based on the publisher information and the merchant information, wherein generating the set of high-value feeds comprises;

allocating relative profits to each user query based on at least one of a sum of clicks or a sum of bids for each user query determined from the merchant data set;

selecting a set of user queries satisfying a threshold profitability; and

determining, using at least in part the set of user queries selected, a quality score for each listing item corresponding to a keyword from the plurality of keywords, wherein the set of high-value feeds comprises listing items selected using qualities scores; and

transmitting the set of high-value feeds to corresponding publisher sites of the plurality of publisher sites.

17. The computer-readable medium of claim 16, wherein the operations further comprise generating a publisher data set using the publisher information, the publisher data set comprising information related to relationships between products or items appearing in particular publisher content items and identifiers of publisher sites corresponding to the particular publisher content items.

18. The computer-readable medium of claim 16, wherein obtaining the publisher information includes providing an application programming interface (API) for the plurality of publisher sites.

19. The computer-readable medium of claim 16, wherein generating the set of high-value feeds further comprises performing a keyword cleansing operation to pre-process the publisher information.

20. The computer-readable medium of claim 16, wherein generating the set of high-value feeds further comprises obtaining a revenue value associated with each listing item of each high-value feed.