Determining relevancy and desirability of terms

• US 8,200,683 B2
• Filed: 06/30/2009
• Issued: 06/12/2012
• Est. Priority Date: 06/09/2006
• Status: Expired due to Fees

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Gupta, Raghav, Xu, Sichun
• Primary Examiner(s): Vo, Tim T.
• Assistant Examiner(s): Fan, Shiow-Jy
• Application Number:
  US12/495,663
• Publication Number:
  US 20100017398A1
• Time in Patent Office: 1,078 Days
• Field of Search: 707/758, 707/748, 707/752, 707/999.005, 707/999.007, 707/E17.014
• US Class Current: 707/758
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries

Abstract

A system and method to sort search results based upon a desirability value is illustrated. This desirability value may be based upon the difference between a demand value and a supply value. Demand may be based upon user activity such as click-throughs, purchases, price, or location. Supply may be based upon a supply of keywords that may be the number of times a word is used in search or item title. The system and method may include receiving a search query, associating a first numerical value with a keyword that is a part of the search query, tracking user activity associated with the keyword, associating a second numerical value with the keyword based upon the user activity, finding a difference value between the first and second numerical values, associating this difference value with the keyword, sorting keywords based upon the difference values, and returning the search results of the sorting.

Claims

1. A computer-implemented method comprising:

processing, using a hardware processor, a search query specifying one or more keywords to identify listings satisfying the search query, each listing from the identified listings describing an item or service offered for sale and including a title and a price;

organizing the identified listings based on a composite relevance score assigned to each listing from the identified listings, the composite relevance score derived as a sum of relevance scores respectively associated with each keyword from the one or more keywords appearing in a listing from the identified listings, each relevance score representing a customer desirability measure for a keyword in the listing, the customer desirability measure determined based on a calculated difference between a measure of customer demand and supply for the keyword, the measure of customer demand for the keyword is expressed as the percentage of listings that i) are selected by a user over a period of time, and ii) have titles including words that match keywords specified in the query, and the measure of supply for the keyword is expressed as the percentage of listings satisfying the search query that include the keyword; and

displaying the organized listings.

2. The computer-implemented method of claim 1, wherein organizing the identified listings includes sorting the identified listings in descending order of the respective composite relevance scores assigned to the identified listings.

3. The computer-implemented method of claim 1, wherein the composite relevance score is derived as the sum of relevance scores associated with each keyword appearing in the title of a respective identified listing.

4. The computer-implemented method of claim 1, wherein the measure of customer demand for the keyword in the title of the listing is expressed as the percentage of all search queries received over a period of time that include the keyword.

5. The computer-implemented method of claim 1, wherein the measure of customer demand for the keyword in the title of the listing is derived by tracking user activity associated with listings including the keyword in the title.

6. The computer-implemented method of claim 4, wherein the user activity includes a user selection of a listing, a user bid on a listing, a user purchase of a listing, or addition of the listing to a user watch list.

7. A system comprising:

at least one processor operable to execute;

a search engine to process a search query specifying one or more keywords to identify listings satisfying the search query, each listing from the identified listings describing an item or service offered for sale and including a title and a price;

a sorting engine to organize the identified listings based on a composite relevance score assigned to each listing from the identified listings, the composite relevance score derived as a sum of relevance scores respectively associated with each keyword from the one or more keywords appearing in a listing from the identified listings, each relevance score representing a customer desirability measure for a keyword in the listing, the customer desirability measure determined based on a calculated difference between a measure of customer demand and supply for the keyword;

a relevance engine to derive the measure of customer demand for the keyword as the percentage of listings that i) are selected by a user over a period of time, and ii) have titles including words that match keywords specified in the search query;

a keyword engine to derive the measure of supply for the keyword as the percentage of listings satisfying the search query that include the keyword; and

an output module to display the organized listings.

8. The system of claim 7, wherein the sorting engine is to sort the listings from the identified listings in descending order of the respective composite relevance score assigned to each listing from the identified listings.

9. The system of claim 7, further comprising a relevance engine to derive the composite relevance score as the sum of relevance scores associated with each keyword appearing in the title of a listing from the identified listings.

10. The system of claim 7, further comprising a relevance engine to derive the measure of demand for the keyword in the title of the listing as the percentage of all search queries received over a period of time that include the keyword.

11. The system of claim 7, further comprising a relevance engine to derive the measure of customer demand for the keyword in the title of the listing by utilizing data from a tracking engine configured to track user activity associated with listings including the keyword in the title.

12. The system of claim 11, wherein the tracking engine is to track user activity including a user selection of a listing, a user bid on a listing, a user purchase of a listing, or addition of the listing to a user watch list.

13. A non-transitory computer-readable medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a method, comprising:

processing a search query specifying one or more keywords to identify listings satisfying the search query, each listing from the identified listings describing an item or service offered for sale and including a title and a price;

organizing the identified listings based on a composite relevance score assigned to each listing from the identified listings, the composite relevance score derived as a sum of relevance scores respectively associated with each keyword from the one or more keywords appearing in a listing from the identified listings, each relevance score representing a customer desirability measure for a keyword in the listing, the customer desirability measure determined based on a calculated difference between a measure of customer demand and supply for the keyword, the measure of customer demand for the keyword is expressed as the percentage of listings that i) are selected by a user over a period of time, and ii) have titles including words that match keywords specified in the query, and the measure of supply for the keyword is expressed as the percentage of listings satisfying the search query that include the keyword; and

displaying the organized listings.

14. The computer-readable medium of claim 13, wherein organizing the identified listings includes sorting the identified listings in descending order of the composite relevance score assigned to each listing.

15. The computer-readable medium of claim 13, wherein the composite relevance score is derived as the sum of relevance scores associated with each keyword appearing in the title of a listing.