Systems and methods for automatic item classification

• US 8,805,838 B1
• Filed: 12/22/2009
• Issued: 08/12/2014
• Est. Priority Date: 12/22/2009
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Khoshnevisan, Cyrus, Kansal, Abhishek, Nguyen, Lam D., Touloumtzis, Michael Paul
• Primary Examiner(s): TIMBLIN, ROBERT M
• Application Number:
  US12/645,420
• Time in Patent Office: 1,694 Days
• Field of Search: 707/737, 707/740, 707/778
• US Class Current: 707/737
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/901 Indexing; Data structures therefor; Storage structures for retrieval from the web G06F16/951

Abstract

An item categorization service is described that automatically categorizes items of interest to a user. The user may possess an item that they wish to offer for sale using a network-based service. The user may submit item information to the item categorization service to categorize the item of interest. Upon receipt, the categorization service may assess the relevance of the item information to hierarchically organized categories maintained by the network-based service. Categories having the highest relevance may be identified as first category candidates. The deepest common ancestor of the first category candidates may be identified the first category. One or more categories, representing sub-categories of the first category, may be identified and subjected to relevance assessment. Those sub-categories having the highest relevance may be identified as second category candidates. The deepest common ancestor of the second category candidates may be identified as a second category for the item of interest.

Claims

1. A system for categorizing items, the system comprising:

a network-based service configured to;

receive a request to categorize an item of interest, the request including item information regarding the item of interest; and

transmit the request to an item categorization service;

a data store configured to store categories for items, wherein at least a portion of the categories are hierarchically organized with respect to one another; and

the item categorization service in communication with the data store and the network-based service, the item categorization service configured to;

assign a first category to the item of interest by;

determining a plurality of first category candidates based at least in part upon an assessment of the relevance of the item information with one or more first categories stored by the data store; and

assigning, as the first category for the item of interest, a first common ancestor of the hierarchically organized first category candidates, the first common ancestor comprising a category that is hierarchically superior to any remaining first category candidates; and

assign a second category to the item of interest by;

determining a plurality of second category candidates based at least in part upon an assessment of the relevance of the item information with one or more second categories stored by the data store; and

assigning, as the second category for the item of interest, a second common ancestor of the hierarchically organized second category candidates, the second common ancestor comprising a category that is hierarchically superior to any remaining second category candidates.

2. The system of claim 1, wherein the item categorization service is further configured to transmit updated item information, including the assigned first and second categories, to the network-based service.

3. The system of claim 1, wherein the common ancestor of the respective first and second category candidates comprises the deepest common ancestor of the respective first and second category candidates, wherein the deepest common ancestor comprises the deepest category in the hierarchically organized categories that is common to the respective first and second category candidates.

4. The system of claim 1, wherein the first and second categories are represented, at least in part, by one or more category attributes and respective category attribute values.

5. The system of claim 4, wherein each of the second category candidates comprises a selected category attribute and respective category attribute value of the first category.

6. A system for categorizing items, the system comprising:

a data store that stores a plurality of hierarchically organized categories for items, each of the hierarchically organized categories represented by at least one category attribute and corresponding category attribute value; and

an item categorization service in communication with the data store, the item categorization service configured to;

receive item information for an item of interest, the item information comprising at least one item attribute and a corresponding item attribute value for the item of interest;

assign a first category for the item of interest from first categories of the hierarchically organized categories stored by the data store;

identify a category attribute of the assigned first category;

obtain at least one second category that comprises the identified category attribute and corresponding category attribute value;

determine one or more second category candidates based at least in part upon an assessment of the relevance of the item information with the at least one second category; and

assign one of the second category candidates as a second category for the item of interest based at least in part upon the hierarchical positions of the one or more second category candidates with respect to one another such that at least one of the remaining second category candidates is a sub-category of the second category.

7. The system of claim 6, wherein assigning the first category for the item of interest from the first categories comprises assessing the relevance of the at least one category attribute and corresponding category attribute value of each of the first categories to the received at least one item attribute and corresponding item attribute value.

8. The system of claim 7, wherein assigning the first category for the item of interest from the first categories further comprises identifying a selected number of the first categories having the highest assessed relevance value as first category candidates.

9. The system of claim 8, wherein assigning the first category for the item of interest from the first categories further comprises selecting a deepest common ancestor of the hierarchically organized first category candidates, wherein the deepest common ancestor comprises the deepest category in the hierarchically organized categories that is common to all of the hierarchically organized first category candidates.

10. The system of claim 6, wherein at least one of the first categories does not comprise the identified category attribute of the assigned first category.

11. The system of claim 6, wherein assessing the relevance of the item information with the at least one second category comprises assessing the relevance of the at least one second category attribute and corresponding category attribute value of the at least one second category to the received at least one item attribute and corresponding item attribute value.

12. The system of claim 6, wherein the item categorization service is further configured to update the item information for the item of interest with the assigned first category and the assigned second category and transmit the updated item information for storage.

13. The system of claim 6, wherein the category attribute of the assigned first category is identified from one or more rules stored by the data store.

14. The system of claim 6, wherein assigning the second category for the item of interest further comprises selecting a deepest common ancestor of the hierarchically organized second category candidates, wherein the deepest common ancestor comprises the deepest category in the hierarchically organized categories that is common to all of the hierarchically organized second category candidates.

15. A computer-implemented method for categorizing items, the method comprising:

under control of one or more configured computer systems;

receiving item information for an item of interest, the item information comprising one or more item attributes and respective item attribute values for the item of interest;

assigning a primary category describing an item of interest, the primary category selected from a first search index comprising one or more hierarchically organized first categories having first attributes and respective first attribute values;

identifying a category attribute describing the assigned primary category;

obtaining a second search index comprising one or more hierarchically organized second categories, wherein each of the second categories includes the identified category attribute of the primary category;

determining one or more secondary category candidates based at least in part upon an assessment of the relevance of the item information with each of the one or more hierarchically organized second categories; and

assigning one of the second category candidates as a secondary category describing the item of interest based at least in part upon the hierarchical positions of the secondary category candidates with respect to one another such that at least one of the remaining second category candidates is a sub-category of the second category.

16. The computer-implemented method of claim 15, wherein assigning the primary category describing the item of interest from the first search index comprises assessing the relevance of at least one of the category attributes and respective category attribute values of respective first categories to the received item attributes and item attribute values.

17. The computer-implemented method of claim 16, wherein assigning the primary category describing the item of interest from the first search index further comprises identifying a selected number of the first categories having the highest assessed relevance value as first category candidates.

18. The computer-implemented method of claim 17, wherein assigning the primary category describing the item of interest from the first search index further comprises selecting a deepest common ancestor of the hierarchically organized first category candidates as the primary category, wherein the deepest common ancestor comprises the deepest category in the hierarchically organized first categories that is common to the hierarchically organized first category candidates.

19. The computer-implemented method of claim 15, wherein at least one of the first categories included in the first search index does not comprise the identified category attribute.

20. The computer-implemented method of claim 15, wherein assessing the relevance of the item information with respective second categories comprises assessing the relevance of at least one of the category attributes and respective category attribute values of respective second categories to the received item attributes and item attribute values.

21. The computer-implemented method of claim 15, further comprising updating the item information with the assigned primary category and the assigned secondary category and transmitting the updated item information for storage.

22. A computer-readable medium having instructions stored thereon, wherein the instructions, when executed by a computing apparatus, cause the computing apparatus to:

receive item information for an item of interest, the item information comprising one or more item attributes and corresponding item attribute values for the item of interest;

assign a first category for the item of interest from hierarchically organized first categories stored by a data store;

identify a category attribute of the assigned first category;

obtain one or more hierarchically organized second categories that comprise the identified category attribute and a corresponding category attribute value;

determine one or more second category candidates based at least in part upon an assessment of the relevance of the item information with each of the second categories; and

assign one of the second category candidates a second category for the item of interest based at least in part upon the hierarchical positions of the second category candidates with respect to one another such that at least one of the remaining second category candidates is a sub-category of the second category.

23. The computer-readable medium of claim 22, wherein assigning the first category for the item of interest from the first categories comprises assessing the relevance of at least one of the category attributes and category attribute values of respective first categories to the received item attributes and item attribute values.

24. The computer-readable medium of claim 22, wherein assigning the first category for the item of interest from the first categories further comprises identifying a selected number of the first categories having the highest assessed relevance value as first category candidates.

25. The computer-readable medium of claim 24, wherein assigning the first category for the item of interest from the hierarchically organized first categories further comprises selecting a deepest common ancestor of the first category candidates, wherein the deepest common ancestor comprises the deepest category in the hierarchically organized first categories that is common to the first category candidates.

26. The computer-readable medium of claim 22, wherein at least one of the first categories does not comprise the identified category attribute of the assigned first category.

27. The computer-readable medium of claim 22, wherein assessing the relevance of the item information with each of the second categories comprises assessing the relevance of at least one of the second category attributes and category attribute values of the second categories to the received item attributes and item attribute values.

28. The computer-readable medium of claim 22, further comprising updating the item information with the assigned first category and the assigned second category and transmitting the updated item information for storage.