Determining desirability value using sale format of item listing

• US 9,323,832 B2
• Filed: 12/31/2008
• Issued: 04/26/2016
• Est. Priority Date: 06/18/2008
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Sundaresan, Neelakantan
• Primary Examiner(s): Cao, Phuong Thao
• Application Number:
  US12/347,258
• Publication Number:
  US 20090319511A1
• Time in Patent Office: 2,673 Days
• Field of Search: 707/769, 707/748
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: Y10S 707/99937 Sorting

Abstract

Some example embodiments illustrate a system and method to sort a search result using sale format information. The system and method include providing a desirability index including multiple desirability values. Each desirability value may be associated with a keyword and indicate an accumulative frequency of the keyword being in an item listing selected throughout multiple user transactions. The system and method include identifying a search result including item listings in response to a query from a user device. The system and method include accessing, for each item listing, the desirability index and getting a desirability value for each keyword included in the item listing. The system and method include calculating a relevancy value using the desirability values for the keywords of a given item listing. The system and method further include sorting the item listings according their relevancy values and returning the sorted item listings to the user device.

Claims

1. A method comprising:

providing a user device with a first search result including one or more item listings in response to a first query received from the user device, each item listing including a plurality of keywords and being associated with a sale format;

tracking a plurality of transactions performed on the one or more item listings via the user device;

assigning, using one or more processors, for each transaction, a first numerical value to one or more keywords included in a selected item listing and a second numerical value to one or more keywords included in non-selected item listings, the first numerical value being determined based upon the sale format associated with the selected item listing, the assigning including determining the first numerical value based at least in part on whether the sale format associated with the selected item listing is a fixed price sale or a non-fixed price sale; and

building a desirability index using one or more numerical values including the first and second numerical values, the desirability index including a desirability value for each keyword, the desirability value being determined based on one or more first numerical values assigned to the keyword, and the desirability value indicating an accumulative frequency of a corresponding keyword being selected throughout the plurality of transactions;

wherein the desirability index is accessed to sort item listings in a second search result identified in response to a second query.

2. The method of claim 1, wherein the first numerical value is a positive value upon determination of the sale format being an auction sale.

3. The method of claim 1, wherein the first numerical value is zero or a negative value upon determination of the sale format being the fixed price sale.

4. The method of claim 1, wherein each item listing is further associated with a remaining listing period and wherein the first numerical value is determined based upon the remaining listing period associated with the selected item listing.

5. The method of claim 4, wherein the first numerical value is a positive value upon determination of the remaining listing period being equal to or shorter than a specified period.

6. The method of claim 4, wherein the first numerical value is zero or a negative value upon determination of the remaining listing period being longer than a specified period.

7. The method of claim 1, wherein each item listing is further associated with a number of bids and wherein the first numerical value is determined based upon the number of bids associated with the selected item listing.

8. The method of claim 7, wherein the first numerical value is a positive value upon determination of the number of bids being equal to or larger than a specified number.

9. The method of claim 7, wherein the first numerical value is zero or a negative value upon determination of the number of bids being less than a specified number.

10. The method of claim 1, wherein the first numerical value is not assigned to a keyword upon determination of the keyword being included in the first query.

11. The method of claim 1, wherein the first numerical value is zero or a negative value upon determination of the sale format being an auction sale.

12. The method of claim 1, wherein the first numerical value is a positive value upon determination of the sale format being the fixed price sale.

13. The method of claim 1, wherein the non-fixed price sale comprises an auction.

14. The method of claim 1, wherein the determining of the first numerical value for assigning comprising assigning a first value as the first numerical value based at least in part on determining that the sale format associated with the selected item listing is the fixed price sale, and assigning a second value different from the first value as the first numerical value based at least in part on determining that the sale format is the non-fixed price sale.

15. The method of claim 1, wherein the desirability value is determined differently based at least in part on whether the sale format is the non-fixed price sale or the fixed price sale.

16. A method comprising:

providing, using one or more processors, a desirability index including a plurality of desirability values, the desirability index being built such that each desirability value is associated with a keyword, is determined according to a numerical value assigned to a selected item listing having the keyword based upon a sale format associated with the selected item listing, and indicates an accumulative frequency of the keyword being included in a first set of one or more item listings selected throughout a number of user transactions, the assigning of the numerical value comprising determining the numerical value based at least in part on whether the sale format associated with the selected item listing is a fixed price sale or a non-fixed price sale;

identifying, using the one or more processors, a search result including a second set of one or more item listings in response to a query from a user device, each item listing including a plurality of keywords;

accessing, using the one or more processors, for each item listing, the desirability index and obtaining a desirability value for each keyword included in the item listing;

calculating, using the one or more processors, a relevancy value for each item listing, the relevancy value being an accumulation of the desirability values for the keywords included in the item listing; and

sorting, using the one or more processors, the item listings in the search result according to the relevancy values for the item listings and returning the sorted item listings to the user device.

17. The method of claim 16, wherein the desirability values for the keywords are not accumulated to calculate the relevancy value upon determination of the keywords being included in the query.

18. The method of claim 16, wherein the desirability values for the keywords are not accumulated to calculate the relevancy value upon determination of the desirability values being modified prior to a specified temporal range.

19. The method of claim 16, wherein the specified temporal range is received from the user device.

20. An apparatus comprising:

at least one hardware processor to run a search engine, the search engine configured to provide a user device with a first search result including one or more item listings in response to a first query received from the user device, each item listing including a plurality of keywords and being associated with a sale format; and

a tracking engine, executed by the at least one hardware processor, to track a plurality of transactions performed on the item listings via the user device, and to assign, for each transaction, a first numerical value to one or more keywords included in a selected item listing and a second numerical value to one or more keywords included in non-selected item listings, the first numerical value being determined based upon the sale format associated with the selected item listing, the assigning comprising determining the first numerical value based at least in part on whether the sale format associated with the selected item listing is a fixed price sale or a non-fixed price sale, the tracking engine configured to build a desirability index using one or more numerical values including the first and second numerical values, the desirability index including a desirability value for each keyword, the desirability value being determined based on one or more first numerical values assigned to the keyword, and the desirability value indicating an accumulative frequency of a corresponding keyword being selected throughout the plurality of transactions;

wherein the desirability index is accessed to sort item listings in a second search result identified in response to a second query.

21. The apparatus of claim 20, wherein the first numerical value is a positive value upon determination of the sale format being an auction sale.

22. The apparatus of claim 20, wherein the first numerical value is zero or a negative value upon determination of the sale format being the fixed price sale.

23. The apparatus of claim 20, wherein each item listing is further associated with a remaining listing period and wherein the tracking engine determines the first numerical value based upon the remaining listing period associated with the selected item listing.

24. The apparatus of claim 20, wherein each item listing is further associated with a number of bids and wherein the tracking engine determines the first numerical value based upon the number of bids associated with the selected item listing.

25. The apparatus of claim 20, wherein the first numerical value is zero or a negative value upon determination of the sale format being an auction sale.

26. The apparatus of claim 20, wherein the first numerical value is a positive value upon determination of the sale format being the fixed price sale.

27. An apparatus comprising:

a desirability index including a plurality of desirability values, each desirability value being associated with a keyword, being determined according to a numerical value assigned to a selected item listing having the keyword based upon a sale format associated with the selected item listing, and indicating an accumulative frequency of the keyword being included in a first set of one or more item listings selected throughout a number of user transactions, the assigning of the numerical value comprising determining the numerical value based at least in part on whether the sale format associated with the selected item listing is a fixed price sale or a non-fixed price sale;

at least one hardware processor to run a search engine, the search engine configured to identify a search result including a second set of one or more item listings in response to a query from a user device, each item listing including a plurality of keywords; and

a lookup engine, executed by the at least one hardware processor, to access, for each item listing, the desirability index and obtain a desirability value for each keyword included in the item listing and to calculate a relevancy value for each item listing, the relevancy value being an accumulation of the desirability values for the keywords included in the item listing;

wherein the search engine is configured to sort the item listings in the search result according to the relevancy values for the item listings and return the sorted item listings to the user device.

28. The apparatus of claim 27, wherein the lookup engine does not accumulate the desirability values for the keywords to calculate the relevancy value upon determination of the desirability values being modified prior to a specified temporal range.

29. The apparatus of claim 27, wherein the lookup engine receives a specified temporal range from the user device.

30. A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors cause the one or more processors to perform operations comprising:

providing a user device with a first search result including one or more item listings in response to a first query received from the user device, each item listing including a plurality of keywords and being associated with a sale format;

tracking a plurality of transactions performed on the one or more item listings via the user device;

assigning, for each transaction, a first numerical value to one or more keywords included in a selected item listing and a second numerical value to one or more keywords included in non-selected item listings, the first numerical value being determined based upon the sale format associated with the selected item listing, the assigning including determining the first numerical value based at least in part on whether the sale format associated with the selected item listing is a fixed price sale or a non-fixed price sale; and

building a desirability index using one or more numerical values including the first and second numerical values, the desirability index including a desirability value for each of the keyword, the desirability value being determined based on one or more first numerical values assigned to the keyword, and the desirability value indicating an accumulative frequency of a corresponding keyword being selected throughout the plurality of transactions;

wherein the desirability index is accessed to sort item listings in a second search result identified in response to a second query.

31. A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors cause the one or more processors to perform operations comprising:

providing a desirability index including a plurality of desirability values, the desirability index being built such that each desirability value is associated with a keyword, is determined according to a numerical value assigned to a selected item listing having the keyword based upon a sale format associated with the selected item listing, and indicates an accumulative frequency of the keyword being included in a first set of one or more item listings selected throughout a number of user transactions, the assigning of the numerical value comprising determining the numerical value based at least in part on whether the sale format associated with the selected item listing is a fixed price sale or a non-fixed price sale;

identifying a search result including a second set of one or more item listings in response to a query from a user device, each item listing including a plurality of keywords;

accessing, for each item listing, the desirability index and obtaining a desirability value for each keyword included in the item listing;

calculating a relevancy value for each item listing, the relevancy value being an accumulation of the desirability values for the keywords included in the item listing; and

sorting the item listings in the search result according to the relevancy values for the item listings and returning the sorted item listings to the user device.