Method and system for identifying keywords for use in placing keyword-targeted advertisements

• US 7,752,200 B2
• Filed: 08/09/2004
• Issued: 07/06/2010
• Est. Priority Date: 08/09/2004
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Scholl, Nathaniel B., DeNeui, Alexander W.
• Primary Examiner(s): Rones; Charles
• Assistant Examiner(s): Khoshnoodi; Fariborz
• Application Number:
  US10/914,722
• Publication Number:
  US 20060041536A1
• Time in Patent Office: 2,157 Days
• Field of Search: 707/3, 707/1, 709/203
• US Class Current: 707/730
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search

Abstract

A method and system for identifying search terms for placing advertisements along with search results is provided. The advertisement system selects a description of an item that is to be advertised. The advertisement system then retrieves documents that match the selected description. The advertisement system generates a score for each word of the retrieved documents that indicates relatedness of the word to the item to be advertised. After generating the scores for the words, the advertisement system identifies phrases of the words within the documents that are related to the item. The advertisement system then generates search terms for the item to be advertised from the identified phrases. The advertisement system submits the search terms and an advertisement to a search engines service for placement of a paid-for advertisement for the item.

Claims

1. A computer-implemented method for identifying search terms for advertising an item, the method comprising:

identifying the item proposed for advertising;

submitting a description of the item to a search engine service;

receiving search results provided by the search engine service corresponding to the description of the item;

analyzing web pages corresponding to the received search results to identify phrases of words within the web pages that are related to the item, the identifying of the phrases including generating a first score for at least some of the words of the web pages and generating a second score for phrases based at least in part on the first score of said at least some of the words within the phrases;

the first score being generated based at least in part on a relative value of;

a first average frequency of the word in the web pages, said first average frequency based at least in part upon a first frequency of the word for a plurality of the web pages corresponding to the received search results;

a second average frequency of the word in a general corpus of web pages, said second average frequency based at least in part upon a second frequency of the word for the general corpus of web pages;

the relative value of the first average frequency with respect to the second average frequency indicating a level of relevance of the word to the item; and

deriving search terms for advertising the item from the identified phrases of the search results based at least in part upon the second score for each of the identified phrases.

2. The method of claim 1, further comprising retrieving the description from an item catalog.

3. The method of claim 2 wherein the description is a title of the item that is stored in the item catalog.

4. The method of claim 3 wherein the generating of a first score for a word of the web pages is further based at least in part on a number of the web pages that contain the word.

5. The method of claim 1 wherein the generating of a first score for a word of the web pages is based at least in part on a number of the web pages that contain the word.

6. The method of claim 1 wherein the identifying of a phrase includes selecting words with top scores, locating each selected word within the web pages as a part of a phrase, and extending each phrase by words proximate to the phrase based at least in part on the first score for said at least some of the words.

7. The method of claim 6 wherein a phrase is only extended by words that have an associated first score indicating relatedness to the item.

8. The method of claim 1 wherein relatedness of a phrase to the item is determined to be high based at least in part on a number of occurrences of the phrase within the retrieved web pages.

9. The method of claim 1 wherein a word that is similar to another word already in a phrase is not added to that phrase.

10. The method of claim 1 wherein a phrase is ended when a word that is similar to a word already in the phrase is encountered.

11. The method of claim 1 wherein noise words are ignored.

12. The method of claim 1 wherein words that generally score highly according to a corresponding first score, regardless of the selected description, are ignored.

13. The method of claim 1 wherein retrieved web pages that are similar to other retrieved web pages are ignored.

14. The method of claim 1 wherein the identifying and deriving are repeated for a previously identified phrase rather than the selected description.

15. A computer system for identifying search terms for advertising an item, comprising:

a processor;

a computer-readable storage medium including instructions that, when executed by the processor, provide;

a component that submits a description of the item to a search engine service and receives search results provided by the search engine service corresponding to the description of the item;

a component that analyzes documents corresponding to the received search results to identify phrases of words within the documents that are related to the item, the identifying including generating a first score for at least some of the words of the documents and generating a second score for phrases based at least in part on the first score of said at least some of the words within the phrases;

the first score being generated based at least in part on a relative value of;

a first average frequency of the word in the web pages, based at least in part upon a first frequency of the word for a plurality of the web pages corresponding to the received search results;

a second average frequency of the word in a general corpus of web pages, based at least in part upon a second frequency of the word for the general corpus of web pages;

the relative value of the first average frequency with respect to the second average frequency indicating a level of relevance of the word to the item; and

a component that derives, from the identified phrases of the search results, search terms for advertising the item based at least in part upon the second score for each of the identified phrases.

16. The computer system of claim 15 including a component that submits the derived search terms along with an advertisement for the item to a search engine service for advertising the item when a search matching the derived search terms is submitted.

17. The computer system of claim 15 wherein the generating of a first score for a word of the documents is further based at least in part on a number of documents of the document store that contain the word.

18. The computer system of claim 15 wherein the component that identifies a phrase selects words with top scores, locates each selected word within the documents as a part of a phrase, and extends each phrase by words proximate to the phrase based at least in part on the first score of each of the words proximate to the phrase.

19. The computer system of claim 18 wherein a phrase is only extended by words having an associated first score indicating relatedness to the item.

20. A computer program product embedded in a computer-readable storage medium for identifying search terms for advertising an item, comprising:

program code for identifying the item proposed for advertising;

program code for submitting a description of the item to a search engine service;

program code for receiving search results provided by the search engine service corresponding to the description of the item;

program code for analyzing web pages corresponding to the received search results to identify phrases of words within the web pages that are related to the item, the identifying including generating a first score for at least some of the words of the web pages and generating a second score for phrases based at least in part on the first score of said at least some of the words within the phrases;

the first score being generated based at least in part on a relative value of;

a first average frequency of the word in the web pages, based at least in part upon a first frequency of the word for a plurality of the web pages corresponding to the received search results;

a second average frequency of the word in a general corpus of web pages, based at least in part upon a second frequency of the word for the general corpus of web pages;

the relative value of the first average frequency with respect to the second average frequency indicating a level of relevance of the word to the item; and

program code for deriving search terms for advertising the item from the identified phrases of the search results based at least in part upon the second score for each of the identified phrases.