Ranking keywords for product types with manual curation

Patent metadata

Field	Value
Publication number	US-9064230-B2
Application number	US-201313756482-A
Country	US
Kind code	B2
Filing date	Jan 31, 2013
Priority date	Jan 31, 2013
Publication date	Jun 23, 2015
Grant date	Jun 23, 2015

Abstract

The present disclosure extends to methods, systems, and computer program products for automatically determining key words within item information with product types, and classifying new items within product types within a merchant's database.

First claim

The invention claimed is:

1. A computer implemented method for categorizing new product items within a merchant's database of product offerings, comprising:
a computer receiving new product item information;
the computer receiving a keyword list and keyword scores for product types within the merchant's database;
wherein the keyword scores are determined by:
the computer receiving a plurality of item information for items within a first product type;
the computer creating a list of words that appear within the plurality of item information within the first product type;
the computer selecting a keyword from the list of words that appear within the plurality of item information within the first product type;
the computer determining a first value of how many times the keyword appears in the plurality of item information within the first product type;
the computer determining a second value by dividing the first value of how many times the keyword appears in the plurality of item information by a count of how many items are represented in the first product type;
the computer determining a third value of how many times the keyword appears in other product types within the merchant's database;
the computer determining a fourth value by dividing the first value of how many times the keyword appears in the first product type by the third value of how many times the keyword appears in the other product types within the merchant's database;
the computer determining a fifth value by dividing the first value of how many times the keyword appears in the first product type by a largest number of times the keyword appears in one of the other product types within the merchant's database; and
the computer providing a score for the keyword using the first value, the second value, the third value, the fourth value, and the fifth value;

the computer, for the product types within the merchant's database, creating product type totals by adding keyword scores for words from within the new product item information that match keywords from the keyword list for the other product types within the merchant's database;
the computer classifying a classification for a new product item of the new product items as a product type for the product types within the merchant database producing a highest product type total; and
the computer updating the merchant's database with the classification for the new product item.

2. The method according to claim 1 , further comprising: presenting over a network the keyword list to a user for review and curation.

3. The method according to claim 1 , wherein the keyword list is comprised of words from the list of words that appear within the plurality of item information for items within the first product type having largest scores of the keyword scores relative to other words from the list of words that appear within the plurality of item information for items within the first product type.

4. The method according to claim 3 , further comprising: presenting over a network the keyword list to a user for review and curation.

5. The method according to claim 1 , wherein the plurality of item information comprises a title of items within the first product type.

6. The method according to claim 1 , wherein the plurality of item information comprises a description for items within the first product type.

7. The method according to claim 2 , wherein keywords are removed from the keyword list after curation.

8. A system for categorizing new product items within a merchant's database of product offerings comprising:
a computer having one or more processors and one or more memory devices operably coupled to the one or more processors and storing executable and operational data, the executable and operational data programmed to cause the one or more processors to:
receive new product item information;
receive a keyword list and keyword scores for product types within the merchant's database;
wherein the keyword scores are determined by:
receiving a plurality of item information for items within a first product type;
creating a list of words that appear within the plurality of item information within the first product type;
selecting a keyword from the list of words that appear within the plurality of item information within the first product type;
determining a first value of how many times the keyword appears in the plurality of item information within the first product type;
determining a second value by dividing the first value of how many times the keyword appears in the plurality of item information by a count of how many items are represented in the first product type;
determining a third value of how many times the keyword appears in other product types within the merchant's database;
determining a fourth value by dividing the first value of how many times the keyword appears in the first product type by the third value of how many times the keyword appears in all of the other product types within the merchant's database;
determining a fifth value by dividing the first value of how many times the keyword appears in the first product type by a largest number of times the keyword appears in one of the other product types within the merchant's database; and
providing a score for the keyword using the first value, the second value, the third value, the fourth value, and the fifth value;

add keyword scores for words from within the new product item information that match keywords from the keyword list for the other product types within the merchant's database to create product type totals;
classify a classification for a new product item of the new product items as a product type for the product types producing a highest product type total; and
update the merchant's database with the classification for the new product item.

9. The system according to claim 8 , further comprising: presenting over a network the keyword list to a user for review and curation.

10. The system according to claim 8 , wherein the keyword list is comprised of words from the list of words that appear within the plurality of item information for the first product type having largest scores of the keyword scores relative to other words from the list of words that appear within the plurality of item information for the first product type.

11. The system according to claim 10 , further comprising: presenting over a network the keyword list to a user for review and curation.

12. The system according to claim 8 , wherein the plurality of item information comprises a title of items within the first product type.

13. The system according to claim 8 , wherein the plurality of item information comprises a description for items within the first product type.

14. The system according to claim 9 , wherein keywords are removed from the keyword list after curation.

Assignees

• Wal Mart Stores Inc

Inventors

• Garera Nikesh Lucky
• Rampalli Narasimhan
• Ravikant Dintyala Venkata Subrahmanya
• Subramaniam Srikanth
• Sun Chong
• Yalin Heather Dawn

Classifications

• G06Q10/101

  Collaborative creation, e.g. joint development of products or services · CPC title

• G06Q10/087 Primary

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title