Search engine using sales and revenue to weight search results

• US 6,631,372 B1
• Filed: 02/12/1999
• Issued: 10/07/2003
• Est. Priority Date: 02/13/1998
• Status: Expired due to Term

• Current Assignee: Oath Inc. (Verizon Communications Inc.)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Graham, Paul
• Primary Examiner(s): Robinson, Greta
• Assistant Examiner(s): Le, Debbie M.
• Application Number:
  US09/249,828
• Time in Patent Office: 1,698 Days
• Field of Search: 707/1-5, 707/6, 705/26, 705/37, 705/14
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A search engine selects one or more search hits from among a plurality of hits, wherein a hit is a reference to a page or a site, based on a user interest, comprising an input module for accepting a query from a user, the query representing an interest of the user; a tracking module for tracking the user'"'"'s navigation through the plurality of pages, including at least a destination purchase page, the destination purchase page being a page from which the user makes a purchase; a sales module which records associations between purchases and queries where the associations are provided, at least in part by an output of the tracking module; and a search module, which takes as its inputs at least a query and sales associations of that query provided by the sales module, and which outputs one or more search hits based on at least the query and the sales associations of that query. In some systems, instead of using sales data to alter the weights of the search results, merchant bidding is used to alter the weights of the search results, or a combination of the two is used.

Claims

1. A search engine for generating a list of hits in response to a query, wherein a hit is a reference to a page or site, the search engine comprising:

a search module configured to receive from a user a current query containing a current search term and further configured to generate a current list of hits based on the current query and a set of purchasing interaction associations, the set of purchasing interaction associations based on a set of previous queries;

a tracking module configured to track user navigation to a target page or site from the current list of hits, to detect a purchasing interaction of the user with the target page or site, and to generate a purchasing interaction record; and

a sales module configured to communicate with the search module and the tracking module, the sales module configured to receive the purchasing interaction record from the tracking module and further configured to add to the set of purchasing interaction associations an association between the purchasing interaction record and the current query.

2. The search engine of claim 1, wherein the current search term comprises a word.

3. The search engine of claim 1, wherein the current search term comprises a plurality of words.

4. The search engine of claim 1, wherein the current search term comprises a selection from a pick list.

5. The search engine of claim 1, wherein each query in the set of previous queries includes the current search term.

6. The search engine of claim 1, wherein the purchasing interaction includes viewing goods or services offered at the target page or site.

7. The search engine of claim 1, wherein the purchasing interaction includes making a purchase.

8. The search engine of claim 7, wherein the purchasing interaction record includes a price of the purchase.

9. The search engine of claim 1, wherein the purchasing interaction includes declining to make a purchase.

10. The search engine of claim 1, wherein a hit comprises an encoded URL configured to provide extra information.

11. The search engine of claim 10, wherein the extra information includes a representation of the current query.

12. The search engine of claim 1, wherein the search module comprises:

an input module configured to receive the current query; and

a ranking module configured to determine an order for the current list of hits based on at least a first weighting and a second weighting, wherein the first weighing is based on occurrences of the current search term in the page or site referenced by the hit and the second weighting is based on purchasing interaction associations of the page or site referenced by the hit.

13. The search engine of claim 12, wherein the second weighting comprises an estimate of an amount of revenue generated by an average user visiting the page or site referenced by the hit, determined from the set of purchasing interaction associations.

14. The search engine of claim 13, wherein the estimate is based on average sales per capita for the page referenced by the hit, determined from the set of purchasing interaction associations.

15. The search engine of claim 14, wherein the estimate is further based on multiplying the average sales per capita by a commission percentage payable to an entity operating the search engine.

16. The search engine of claim 12, wherein the second weighting includes a time of the purchasing interaction association.

17. The search engine of claim 12, wherein the ranking module is furt her configured to randomly reorder a subset of the current list of hits after determining the order.

18. The search engine of claim 12, wherein the ranking module is further configured to adjust the order of the current list of hits when the current query matches a reserved query, the reserved query being reserved by an entity operating one of the pages referenced on the list of hits.

31. The system of claim 1, wherein the search module is further configured to identify hits for inclusion in the current list of hits based on the current search term and to order the identified hits based on associations between the current search term and previous purchases made at pages or sites referenced by the identified hits, the associations being included in the set of purchasing interaction associations.

19. A method for operating a search engine, comprising:

receiving a first user query;

providing a first list of hits based on the first user query, each hit being a reference to a page or site;

tracking user navigation from the first list of hits to a target page or site;

detecting a purchasing interaction of the user with the target page or site;

recording an association between the purchasing interaction and the first user query;

receiving a second user query; and

providing a second list of hits based on the second user query and the recorded purchasing interaction association.

20. The method of claim 19, wherein each of the first query and the second query includes a matching search term.

21. The method of claim 19, wherein each hit comprises an encoded URL configured to carry extra information.

22. The method of claim 21, wherein the extra information includes a representation of the first query.

23. The method of claim 22, wherein recording an association between the purchasing interaction and the first user query comprises using the extra information to identify the first query.

24. The method of claim 21, wherein tracking user navigation comprises receiving the encoded URL when the page or site is selected.

25. The method of claim 19, wherein detecting a purchasing interaction comprises detecting at least one of the following user actions:

viewing goods or services offered at the target page or site;

making a purchase of goods or services; and

declining to make a purchase of goods or services.

26. The method of claim 19, wherein providing a second list of hits based on the second user query and the recorded purchasing interaction association comprises:

generating a first weighting for each of a plurality of candidate pages or sites based on occurrences therein of a search term contained in the second user query;

generating a second weighting for each of the plurality of candidate pages or sites based on a set of purchasing interaction associations including at least the recorded purchasing interaction association; and

ordering the plurality of candidate pages or sites based on at least the first weighting and the second weighting.

27. The method of claim 26, wherein generating a second weighting comprises estimating an amount of revenue generated by an average user visiting the candidate page or site.

28. The method of claim 27, wherein generating a second weighting further comprises multiplying the estimated amount of revenue by a commission percentage payable to an entity operating the search engine.

29. The method of claim 26, further comprising:

adjusting the ordering of the plurality of candidate pages or sites when the second query matches a reserved query, the reserved query being reserved by an entity operating one of the plurality of candidate pages or sites.

30. The method of claim 26, further comprising:

randomly reordering a subset of the plurality of candidate pages or sites after ordering the plurality of candidate pages or sites.

32. A method for operating a search engine, comprising:

receiving a first user query;

providing a first list of hits based on the first user query, each hit being a reference to a page or site;

tracking user navigation from the first list of hits to a target page or site;

detecting a purchasing interaction of the user with the target page or site;

recording an association between the purchasing interaction and the first user query;

receiving a second user query; and

providing a second list of hits based on the second user query and the recorded purchasing interaction association,

wherein providing the second list of hits includes;

identifying pages or sites that include a search term of the second user query, including the target page or site; and

ranking the identified pages or sites based on recorded associations between purchasing interactions and the search term of the second user query.