Ranking product information

• US 9,886,517 B2
• Filed: 12/03/2011
• Issued: 02/06/2018
• Est. Priority Date: 12/07/2010
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Chen, Chao, Feng, Jinghua
• Primary Examiner(s): Pham, Tuan A
• Assistant Examiner(s): Gurmu, Muluemebet
• Application Number:
  US13/310,731
• Publication Number:
  US 20120143883A1
• Time in Patent Office: 2,257 Days
• Field of Search: 707751
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

Ranking product information is disclosed, including: determining, for each of a plurality of pieces of product information, a category grading value and a plurality of attribute grading values associated with that piece of product information; determining a plurality of user demand values corresponding to the plurality of pieces of product information based at least in part on the category grading value and at least one of the plurality of attribute grading values associated with each of the plurality of pieces of product information; and ranking the plurality of pieces of product information based at least in part on the corresponding plurality of user demand values.

Claims

1. A method for ranking product information, comprising:

obtaining a category and a plurality of attributes corresponding to a piece of product information of a plurality of pieces of product information;

determining a category grading value associated with the category corresponding to the piece of product information and a plurality of attribute grading values corresponding to respective ones of the plurality of attributes corresponding to the piece of product information, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are obtained from storage, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are determined based at least in part on historical search data, and wherein the historical search data comprises one or more of click logs and impression logs;

determining, using a processor, a plurality of user demand values corresponding to the plurality of pieces of product information based at least in part on the category grading value and at least one of the plurality of attribute grading values associated with each of the plurality of pieces of product information, wherein the user demand values are based at least in part on an impression log that records a number of times a piece of product information is displayed and on a click log that records a number of times a piece of product information that has been displayed has been clicked, wherein determining the plurality of user demand values includes determining a user demand value corresponding to the piece of product information, wherein determining the user demand value corresponding to the piece of product information includes;

determining at least a subset of the plurality of attributes that meet a condition based at least in part on a respective plurality of attribute grading values, wherein the condition is associated with a selected attribute grading value from the plurality of attribute grading values; and

determining the user demand value corresponding to the piece of product information based at least in part on the category grading value, the determined at least the subset of the plurality of attributes, a weighting associated with category, and a weighting associated with the at least the subset of the plurality of attributes; and

ranking the plurality of pieces of product information based at least in part on the corresponding plurality of user demand values.

2. The method of claim 1, further comprising receiving a search query comprising one or more query words.

3. The method of claim 2, wherein the plurality of pieces of product information is determined as results in response to the one or more query words.

4. The method of claim 1, further comprising displaying the ranked plurality of pieces of product information, wherein the plurality of pieces of product information is displayed starting with one of the plurality of pieces of product information associated with a highest user demand value.

5. The method of claim 1 wherein the historical search data comprises click-through rates corresponding to pieces of product information.

6. The method of claim 1, wherein the condition comprises being associated with a highest attribute grading value and wherein the user demand value corresponding to the piece of product information is determined based at least in part on a function of the category grading value corresponding to the piece of product information, a number of attributes associated with the determined at least the subset of the plurality of attributes that meet the condition, and a total number of attributes associated with the plurality of attributes.

14. The method of claim 1, wherein the selected attribute grading value comprises a highest attribute grading value from the plurality of attribute grading values and the condition further comprises being associated with the highest attribute grading value.

15. The method of claim 1, wherein the impression log records a number of times a piece of product information is displayed in connection with a search result for a past search.

16. The method of claim 1, wherein a number of clicks associated with a particular piece of product information that exceed a threshold click value is excluded in the determination of the user demand value.

17. The method of claim 1, wherein:

the category is assigned one of a plurality of category grading values based at least in part on;

a comparison between a plurality of category thresholds and the number of times pieces of product information is displayed, and

a comparison between the plurality of category thresholds and the number of times a piece of product information that has been displayed has been clicked, and

the plurality of attributes are respectively assigned one of a plurality of attribute grading values based at least in part on;

a comparison between a plurality of attribute thresholds and a number of times pieces of product information associated with a corresponding one of the plurality of attributes is displayed, and

a comparison between plurality of attribute thresholds the number of times a piece of product information associated with a corresponding one of the plurality of attributes that has been displayed has been clicked.

18. The method of claim 1, wherein the category describes a classification of product information, and wherein the plurality of attributes comprises one or more brands associated with the plurality of pieces of product information.

19. The method of claim 1, wherein the category grading value and at least one of the plurality of the attribute grading values are determined separately.

20. The method of claim 1, wherein the user demand value corresponding to the piece of product information is based at least in part on a summation of a first weighted value corresponding to the category and one or more second weighted values corresponding to the at least the subset of the plurality of attributes.

7. A system for ranking product information, comprising:

a processor configured to;

obtain a category and a plurality of attributes corresponding to a piece of product information of a plurality of pieces of product information;

determine a category grading value associated with the category corresponding to the piece of product information and a plurality of attribute grading values corresponding to respective ones of the plurality of attributes corresponding to the piece of product information, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are obtained from storage, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are determined based at least in part on historical search data, and wherein the historical search data comprises one or more of click logs and impression logs;

determine a plurality of user demand values corresponding to the plurality of pieces of product information based at least in part on the category grading value and at least one of the plurality of attribute grading values associated with each of the plurality of pieces of product information, wherein determining the plurality of user demand values includes determining a user demand value corresponding to the piece of product information, wherein the user demand values are based at least in part on an impression log that records a number of times a piece of product information is displayed and on a click log that records a number of times a piece of product information that has been displayed has been clicked, wherein determining the user demand value corresponding to the piece of product information includes;

determining at least a subset of the plurality of attributes that meet a condition based at least in part on a respective plurality of attribute grading values, wherein the condition is associated with a selected attribute grading value from the plurality of attribute grading values; and

determining the user demand value corresponding to the piece of product information based at least in part on the category grading value, the determined at least the subset of the plurality of attributes, a weighting associated with category, and a weighting associated with the at least the subset of the plurality of attributes; and

rank the plurality of pieces of product information based at least in part on the corresponding plurality of user demand values; and

a memory coupled to the processor and configured to provide the processor with instructions.

8. The system of claim 7, wherein the processor is further configured to receive a search query comprising one or more query words.

9. The system of claim 8, wherein the plurality of pieces of product information is determined as results in response to the one or more query words.

10. The system of claim 7, wherein the processor is further configured to display the ranked plurality of pieces of product information, wherein the plurality of pieces of product information is displayed starting with one of the plurality of pieces of product information associated with a highest user demand value.

11. The system of claim 7, wherein the historical search data comprises click-through rates corresponding to pieces of product information.

12. A computer program product for ranking product information, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

obtaining a category and a plurality of attributes corresponding to a piece of product information of a plurality of pieces of product information;

determining a category grading value associated with the category corresponding to the piece of product information and a plurality of attribute grading values corresponding to respective ones of the plurality of attributes corresponding to the piece of product information, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are obtained from storage, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are determined based at least in part on historical search data, and wherein the historical search data comprises one or more of click logs and impression logs;

determining a plurality of user demand values corresponding to the plurality of pieces of product information based at least in part on the category grading value and at least one of the plurality of attribute grading values associated with each of the plurality of pieces of product information, wherein determining the plurality of user demand values includes determining a user demand value corresponding to the piece of product information, wherein the user demand values are based at least in part on an impression log that records a number of times a piece of product information is displayed and on a click log that records a number of times a piece of product information that has been displayed has been clicked, wherein determining the user demand value corresponding to the piece of product information includes;

determining at least a subset of the plurality of attributes that meet a condition based at least in part on a respective plurality of attribute grading values, wherein the condition is associated with a selected attribute grading value from the plurality of attribute grading values; and

determining the user demand value corresponding to the piece of product information based at least in part on the category grading value, the determined at least the subset of the plurality of attributes, a weighting associated with category, and a weighting associated with the at least the subset of the plurality of attributes; and

ranking the plurality of pieces of product information based at least in part on the corresponding plurality of user demand values.

13. A computer program product for ranking product information, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

obtaining a category and a plurality of attributes corresponding to a piece of product information of a plurality of pieces of product information;

determining a category grading value associated with the category corresponding to the piece of product information and a plurality of attribute grading values corresponding to respective ones of the plurality of attributes corresponding to the piece of product information, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are obtained from storage, wherein the category grading value and the plurality of attribute grading values associated with the piece of product information are determined based at least in part on historical search data, and wherein the historical search data comprises one or more of click logs and impression logs;

determining a plurality of user demand values corresponding to the plurality of pieces of product information based at least in part on the category grading value and at least one of the plurality of attribute grading values associated with each of the plurality of pieces of product information, wherein determining the plurality of user demand values includes determining a user demand value corresponding to the piece of product information, wherein the user demand values are based at least in part on an impression log that records a number of times a piece of product information is displayed and on a click log that records a number of times a piece of product information that has been displayed has been clicked, wherein determining the user demand value corresponding to the piece of product information includes;

determining at least a subset of the plurality of attributes that meet a condition based at least in part on a respective plurality of attribute grading values, wherein the condition is associated with a selected attribute grading value from the plurality of attribute grading values; and

determining the user demand value corresponding to the piece of product information based at least in part on the category grading value, the determined at least the subset of the plurality of attributes, a weighting associated with category, and a weighting associated with the at least the subset of the plurality of attributes; and

ranking the plurality of pieces of product information based at least in part on the corresponding plurality of user demand values.