Product recommendation in a network-based commerce system

• US 20050125240A9
• Filed: 09/18/2003
• Published: 06/09/2005
• Est. Priority Date: 10/21/2002
• Status: Abandoned Application

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Monier, Louis M., Speiser, Leonard Robert, Posner, Nicholas David, Lai, Jannie
• Application Number:
  US10/666,681
• Publication Number:
  US 20040078214A1
• Time in Patent Office: Days
• US Class Current: 705/27
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A method and system of providing listing recommendations to users of a network-based commerce system including a plurality of listings arranged in a plurality of divisions is described. The method includes identifying a division of the plurality of divisions based on user interaction with the network-based commerce system, and identifying at least one frequently used search term associated with the division. A link is provided to the user to listings associated with the frequently used search term. The search terms may be ranked by retrieving frequently used search terms from a first memory location and determining a number of listings in each division associated with each frequently used search term. Each frequently used search term may then be ranked based on the number of listings in each division.

Claims

1. A method of ranking search terms used in a network-based commerce system including a plurality of listings arranged in divisions, the method including:

retrieving frequently used search terms from a first memory location;

determining a number of listings in each division associated with each frequently used search term; and

ranking each frequently used search term based on the number of listings in each division.

2. The method of claim 1, which includes periodically adding new listings and removing terminated listings prior to determining the number of listings in each division associated with each frequently used search term so that the ranking is dependent upon supply and demand for the listings.

3. The method of claim 1, in which the divisions are categories, the method including ranking the frequently used search terms within each category.

4. The method of claim 1, which includes storing the ranked frequently used search terms in a second memory location in one of ascending and descending order, the frequently used search terms being identified from search terms used by a plurality of users of the network-based commerce system.

5. The method of claim 1, which includes determining if the frequently used search terms meet at least one predetermined criterion.

6. The method of claim 5, wherein the predetermined criterion is a minimum number of occurrences of listings in a division associated with the frequently used search term.

7. The method of claim 6, wherein the minimum number of occurrences of listings in a division is provided by a user selectable numeric value.

8. The method of claim 5, wherein the predetermined criterion is a minimum word length used in the search term.

9. The method of claim 5, wherein the predetermined criterion is that the frequently used search term does not correspond to a name of a division in the form of a category.

10. The method of claim 1, in which determining a number of listings in each division associated with each frequently used search term includes searching a database including the listings using each frequently used search term.

11. The method of claim 1, in which the frequently used search terms are sourced from a plurality of web sites.

12. The method of claim 11, wherein the web sites are located in a plurality of different countries, the method including identifying the frequently used search term according one of country, geography, language, and type of listing associated with the frequently used search term.

13. The method of claim 1, which includes determining if the frequently used search terms meet at least one predetermined criterion, the method including:

comparing the frequently used search terms against a list of reference words;

determining if any word of each frequently used search term corresponds to a word in the list of reference words; and

storing the frequently used search terms which do not include a word in the list of reference words for subsequent use.

14. The method of claim 13, which includes periodically updating the list of reference words.

15. A method of providing listing recommendations to users of a network-based commerce system including a plurality of listings arranged in a plurality of divisions, the method including:

identifying a division of the plurality of divisions based on user interaction with the network-based commerce system;

identifying at least one frequently used search term associated with the division; and

providing a link to the user to listings associated with the frequently used search term.

16. The method of claim 15, which includes communicating a web page to the user including a hyperlink to the listings associated with the frequently used search term.

17. The method of claim 15, in which the listings associated with the frequently used search term are listings that would be located if the user conducted a search of the network-based commerce system using the frequently used search terms.

18. The method of claim 15, wherein the predetermined number of frequently used search terms are ranked in one of an ascending and descending order according to a number of occurrences of listings in a division associated with the search term.

19. The method of claim 18, which includes periodically adding new listings and removing terminated listings prior to determining the number of listings in each division associated with each frequently used search term so that the ranking is dependent upon supply and demand for the listings.

20. The method of claim 15, which includes searching the network-based commerce system using at least one frequently used search term when the user selects the link.

21. The method of claim 15, wherein the frequently used search terms are displayed according to rank in one of an ascending and descending order.

22. The method of claim 15, wherein frequently used search terms are assigned to each of the plurality of divisions, the divisions being defined by categories.

23. A machine-readable medium embodying a sequence of instructions that, when executed by a machine, cause the machine to:

retrieve frequently used search terms from a first memory location of a network-based commerce system including a plurality of listings arranged in divisions;

determine a number of listings in each division associated with each frequently used search term; and

rank each frequently used search term based on the number of listings in each division.

24. The machine-readable medium of claim 23, wherein periodically new listings are added and terminated listings are removed prior to determining the number of listings in each division associated with each frequently used search term so that the ranking is dependent upon supply and demand for the listings.

25. The machine-readable medium of claim 23, wherein the divisions are categories and the frequently used search terms are ranked within each category.

26. The machine-readable medium of claim 23, wherein the frequently used search terms are sourced from a plurality of web sites located in a plurality of different countries.

27. A machine-readable medium embodying a sequence of instructions that, when executed by a machine, cause the machine to:

identify a division of a plurality of divisions based on user interaction with a network-based commerce system;

identify at least one frequently used search term associated with the division; and

provide a link to the user to listings associated with the frequently used search term thereby to provide listing recommendations a user.

28. The machine-readable medium of claim 27, wherein periodically new listings are added and terminated listings are removed prior to determining the number of listings in each division associated with each frequently used search term so that the ranking is dependent upon supply and demand for the listings.

29. A method of ranking search terms used in searching a database including a plurality of entries arranged in divisions, the method including:

retrieving frequently used search terms from a first memory location;

determining a number of entries in each division associated with each frequently used search term; and

ranking each frequently used search term based on the number of entries in each division.

30. A system to rank search terms used in a network-based commerce system including a plurality of listings arranged in divisions, the system including:

a frequently used search term retrieval module to retrieve frequently used search terms from a first memory location of the network-based commerce system;

a determination module to determine a number of listings in each division associated with each frequently used search term; and

a ranking module to rank each frequently used search term based on the number of listings in each division.

31. The system of claim 30, wherein periodically new listings are added and terminated listings are removed prior to determining the number of listings in each division associated with each frequently used search term so that the ranking is dependent upon supply and demand for the listings.

32. A system to provide listing recommendations to users of a network-based commerce system including a plurality of listings arranged in a plurality of divisions, the system including:

a division identification module to identify a division of a plurality of divisions based on user interaction with a network-based commerce system;

a frequently used search term identification module to identify at least one frequently used search term associated with the division; and

a display module to provide a link to the user to listings associated with the frequently used search term thereby to provide listing recommendations a user.

33. The system of claim 32, wherein periodically new listings are added and terminated listings are removed prior to determining the number of listings in each division associated with each frequently used search term so that the ranking is dependent upon supply and demand for the listings.

34. A system to provide listing recommendations to users of a network-based commerce system including a plurality of listings arranged in a plurality of divisions, the system including:

means to identify a division of a plurality of divisions based on user interaction with a network-based commerce system;

means to identify at least one frequently used search term associated with the division; and

means to provide a link to the user to listings associated with the frequently used search term thereby to provide listing recommendations a user.