Generating a recommendation

• US 10,074,127 B2
• Filed: 10/16/2015
• Issued: 09/11/2018
• Est. Priority Date: 04/17/2002
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Poon, Alex Dai-Shun, Maltzman, Reed, Taylor, Jeffrey
• Primary Examiner(s): Pond, Robert M
• Application Number:
  US14/885,298
• Publication Number:
  US 20160042435A1
• Time in Patent Office: 1,061 Days
• Field of Search: 705 26, 705 27
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

A method and an apparatus for communicating a recommended item to a user are described. The method comprises determining that the user has a level of commitment to an item offered for sale, and, in response to this determination, communicating information concerning a recommended item to the user over a network. The recommended item is identified based on a set of longest words in a description of the item offered for sale.

Claims

1. A system comprising:

a memory having instructions embodied thereon; and

one or more processors configured to execute the instructions and perform operations comprising;

incrementing a commitment evaluation value associated with a first item described on an item page based on a determination that the item page was requested by a remote client device;

generating a recommendation of a second item for communication to the remote client device based on another determination that the incremented commitment evaluation value exceeds a defined commitment value threshold associated with the first item, the recommendation being generated by;

parsing a set of words from a first description of the first item based at least in part on a comparison of determined word lengths in the first description to a defined word length threshold, and

selecting the second item to include in the recommendation based on a determination that a second description of the second item also includes the parsed set of words.

2. The system of claim 1, wherein the set of words is parsed based further in part on a defined word count threshold.

3. The system of claim 1, wherein the set of words is parsed from the first description based further in part on a determination that the defined word length threshold exceeds each word length in the determined word lengths.

4. The system of claim 3, wherein the set of words is parsed from the first description based further in part on a determined maximum word length of the determined word lengths.

5. The system of claim 1, wherein

the generated recommendation is communicated to the remote client device based on stored seller preference data associated with the first item.

6. The system of claim 1, wherein the commitment evaluation value corresponds to a number of times the item page has been requested by the remote client device.

7. The system of claim 1, wherein the generated recommendation is communicated to the remote client device in response to a subsequent log-in from the remote client device.

8. A computer-implemented method comprising:

incrementing a commitment evaluation value associated with a first item described on an item page based on a determination that the item page was requested by a remote client device;

parsing a set of words from the first item description based at least in part on a determination that the incremented commitment evaluation value exceeds a defined commitment value threshold associated with the first item and that a defined word length threshold exceeds a determined length of each word in a plurality of words included in the first item description;

searching for the parsed set of words in at least a second description corresponding to a second item;

selecting the second item as a recommended item based on a determination that the second item includes the parsed set of words; and

generating a recommendation that includes the recommended item for communication to the remote client device based on the selection.

9. The computer-implemented method of claim 8, wherein the set of words is parsed from the first item description based further in part on a determined longest word length for the plurality of words included in the first item description.

10. The computer-implemented method of claim 9, wherein each word in the parsed set of words has a number of characters that corresponds to the determined longest word length.

11. The computer-implemented method of claim 8, wherein the set of words is parsed from the first item description based further in part on a defined word count threshold.

12. The computer-implemented method of claim 8, wherein

the generated recommendation is communicated to the remote client device based on a determination that seller preference data associated with the first item includes an authorization to communicate the recommendation.

13. The computer-implemented method of claim 8, wherein the commitment evaluation value corresponds to a number of times the item page has been requested by the remote client device.

14. The computer-implemented method of claim 8, wherein the generated recommendation is communicated to the remote client device in response to a link corresponding to the generated recommendation being activated by the remote client device.

15. A non-transitory machine-readable medium having instructions embodied thereon, which, when executed by one or more processors, cause the one or more processors to perform operations comprising:

incrementing a commitment evaluation value associated with a first item described on an item page based on a determination that the item page was requested by a remote client device;

parsing a set of words from the first item description based at least in part on a determination that the incremented commitment evaluation value exceeds a defined commitment value threshold associated with the first item, and that each word in the parsed set of words has a corresponding word length that is at least as long as a determined longest word length for a plurality of words included in the first item description;

selecting a second item as a recommended item based on a determination that a second description corresponding to the second item includes the parsed set of words; and

generating a recommendation that includes the recommended item for communication to the remote client device based on the selection.

16. The non-transitory machine-readable medium of claim 15, wherein the set of words is parsed from the first item description based further in part on a comparison of the determined longest word length to a defined word length threshold.

17. The non-transitory machine-readable medium of claim 16, wherein each word in the parsed set of words has a corresponding word length that is equal to the determined longest word length based on the comparison indicating that the defined word length threshold is greater than the determined longest word length.

18. The non-transitory machine-readable medium of claim 15, wherein the commitment evaluation value corresponds to a number of times that the item page has been requested by the remote client device.

19. The non-transitory machine-readable medium of claim 15, wherein the set of words is parsed based further in part on the determination that the item page was requested by the remote client device.

20. The non-transitory machine-readable medium of claim 15, wherein the generated recommendation is communicated to the remote client device via an email message associated with the remote client device.