Methods and systems for assessing excessive accessory listings in search results

Patent metadata

Field	Value
Publication number	US-9384278-B2
Application number	US-201113082226-A
Country	US
Kind code	B2
Filing date	Apr 7, 2011
Priority date	Apr 7, 2011
Publication date	Jul 5, 2016
Grant date	Jul 5, 2016

Abstract

A system and method for assessing excessive accessory listings in search results includes a processor-implemented textual mining module that parses a data field of a document and generates at least one token from the data field. A processor-implemented scoring module calculates a score for the at least one token, with the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications. The processor-implemented scoring module also calculates a score for the document based on the at least one token score, with the document score representing a probability of the document being in one of the two binary classifications. A processor-implemented decision tree module inputs the document score and document attribute values into a decision tree and generates an output representing a refined score based on the document score and at least one of the document attribute values.

First claim

What is claimed is:

1. A system, comprising:
a processor-implemented textual mining module configured to parse a data field of a document and generate at least one token from the data field;
a processor-implemented scoring module configured to:
calculate a score for the at least one token, the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications; and
calculate a score for the document based on the at least one token score, the document score representing a probability of the document being in one of the two binary classifications; and

a processor-implemented decision tree module configured to generate an output representing a refined score for the document based on the document score and at least one document attribute value.

2. The system of claim 1 , wherein the processor-implemented scoring module uses a naive Bayes classifier to calculate the scores of the at least one token.

3. The system of claim 1 , wherein the document is an item listing of an item offered for sale, and wherein the two binary classifications are products and product accessories.

4. The system of claim 1 , wherein the processor-implemented scoring module is configured to calculate the at least one token score by determining a first number of occurrences of the at least one token in a first binary classification in a set of item listings and a second number of occurrences of the at least one token in a second binary classification in the set of item listings and by obtaining a ratio of the first number of occurrences to a sum of the first number of occurrences and the second number of occurrences.

5. The system of claim 4 , wherein the processor-implemented scoring module is further configured to calculate the at least one token score by normalizing the ratio to derive the at least one token score.

6. The system of claim 4 , wherein the processor-implemented scoring module is configured to calculate the document score by adding together the first number of occurrences for the at least one token and dividing the added first number of occurrences for the at least one token by the sum of the first number of occurrences and the second number of occurrences.

7. The system of claim 3 , wherein the at least one document attribute value includes at least one of quantity of the item, price of the item, median price of the item, product sales rank, shipping cost, return policy, seller feedback score, and item location.

8. A computer-implemented method, comprising:
parsing, by at least one processor, a data field of a document and generating at least one token from the data field;
calculating, by the at least one processor, a score for the at least one token, the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications;
calculating, by the at least one processor, a score for the document based on the at least one token score, the document score representing a probability of the document being in one of the two binary classifications;
inputting the document score and document attribute values into a decision tree; and
generating an output using the decision tree, the output representing a refined score for the document based on the document score and at least one of the document attribute values.

9. The computer-implemented method of claim 8 , wherein the calculating of the at least one token score uses a naive Bayes classifier.

10. The computer-implemented method of claim 8 , wherein the document is an item listing of an item offered for sale, and wherein the two binary classifications are products and product accessories.

11. The computer-implemented method of claim 8 , wherein the calculating of the at least one token score comprises:
determining a first number of occurrences of the at least one token in a first binary classification in a set of item listings and a second number of occurrences of the at least one token in a second binary classification in the set of item listings; and calculating a ratio of the first number of occurrences to a sum of the first number of occurrences and the second number of occurrences.

12. The computer-implemented method of claim 11 , wherein the calculating of the at least one token score further comprises normalizing the ratio to derive the at least one token score.

13. The computer-implemented method of claim 11 , wherein the calculating of the document score comprises:
adding together the first number of occurrences for the at least one token; and
dividing the added first number of occurrences for the at least one token by the sum of the first number of occurrences and the second number of occurrences.

14. The computer-implemented method of claim 8 , wherein the document attribute values include at least one of quantity of the item, price of the item, median price of the item, product sales rank, shipping cost, return policy, seller feedback score, and item location.

15. A non-transitory machine-readable storage medium storing a set of instructions that, when executed by at least one processor, causes the at least one processor to perform operations comprising:
parsing a data field of a document and generating at least one token from the data field;
calculating a score for the at least one token, the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications;
calculating a score for the document based on the at least one token score, the document score representing a probability of the document being in one of the two binary classifications;
inputting the document score and document attribute values into a decision tree; and
generating an output using the decision tree, the output representing a refined score for the document based on the document score and at least one of the document attribute values.

16. The machine-readable storage medium of claim 15 , wherein the calculating of the at least one token score uses a naive Bayes classifier.

17. The machine-readable storage medium of claim 15 , wherein the document is an item listing of an item offered for sale, and wherein the two binary classifications are products and product accessories.

18. The machine-readable storage medium of claim 15 , wherein the calculating of the at least one token score comprises:
determining a first number of occurrences of the at least one token in a first binary classification in a set of item listings and a second number of occurrences of the at least one token in a second binary classification in the set of item listings; and calculating a ratio of the first number of occurrences to a sum of the first number of occurrences and the second number of occurrences.

19. The machine-readable storage medium of claim 18 , wherein the calculating of the at least one token score further comprises normalizing the ratio to derive the at least one token score.

20. The machine-readable storage medium of claim 18 , wherein the calculating of the document score comprises:
adding together the first number of occurrences for the at least one token; and
dividing the added first number of occurrences for the at least one token by the sum of the first number of occurrences and the second number of occurrences.

21. The machine-readable storage medium of claim 15 , wherein the document attribute values include at least one of quantity of the item, price of the item, median price of the item, product sales rank, shi

Assignees

• Yuan Ted Tao
• Mathieson Michael
• Kulkarni Parashuram
• Ebay Inc

Inventors

• Yuan Ted Tao
• Mathieson Michael
• Kulkarni Parashuram

Classifications

• G06F17/30864 Primary

  Physics · mapped topic

• G06F16/951 Primary

  Indexing; Web crawling techniques · CPC title

• G06F16/24578 Primary

  using ranking · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/9538

  Presentation of query results · CPC title