Product placement engine and method

• US 20050065909A1
• Filed: 08/05/2004
• Published: 03/24/2005
• Est. Priority Date: 08/05/2003
• Status: Active Grant

• Current Assignee: CBS Interactive Inc. (Paramount Global (f/k/a ViacomCBS Inc.))
• Original Assignee: CBS Interactive Inc. (Paramount Global (f/k/a ViacomCBS Inc.))
• Inventors: Musgrove, Timothy A., Walsh, Robin Hiroko
• Granted Patent: US 7,505,969 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0629 for generating comparisons
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation

Abstract

A product placement engine and method for automatically identifying products for association with a document, the engine including a parser, an analysis module adapted to determine word scores and to adjust the word scores of the words by predetermined weightings, a keyword constructor module adapted to construct a keyword query search string using words having the highest word scores, a search engine adapted to search a products database having product records to identify products satisfying the keyword query search string and assign product scores, and a post processing module adapted to identify word matches in each of the product records and the document and update the product score.

Claims

1. A method of automatically identifying products for association with a document comprising the steps of:

providing a products database having product records containing information regarding an associated product;

parsing a document;

determining word scores of the words in the document based on the frequency of the words in the document;

adjusting the word scores of the words by predetermined weightings corresponding to the use of each word in the document;

constructing a keyword query search string using words having the highest word scores;

searching the product records of the products database to identify products satisfying the keyword query search string;

assigning product scores to the identified products based on matches to the keyword query search string;

parsing the product records to identify word matches in each of the product records and the document;

updating the product score by processing the adjusted word scores corresponding to the matched word with the product score of the product for which word matched; and

selecting products from the identified products that have the highest updated product scores.

2. A product placement engine for automatically identifying products for association with a document comprising:

a parser adapted to parsing a document;

an analysis module adapted to determine word scores of the words in the document based on the frequency of the words in the document, and to adjust the word scores of the words by predetermined weightings corresponding to the use of each word in the document;

a keyword constructor module adapted to construct a keyword query search string using words having the highest word scores;

a search engine adapted to search a products database having product records containing information regarding an associated product to identify products satisfying the keyword query search string and assign product scores to the identified products based on matches to the keyword query search string; and

a post processing module adapted to identify word matches in each of the product records and the document and update the product score by processing the adjusted word scores corresponding to the matched word with the product score of the product for which word matched.

3. A computer readable medium for automatically identifying products for association with a document comprising:

instructions for parsing a document;

instructions for determining word scores of the words in the document based on the frequency of the words in the document;

instructions for adjusting the word scores of the words by predetermined weightings corresponding to the use of each word in the document;

instructions for constructing a keyword query search string using words having the highest word scores;

instructions for searching a products database having product records containing information regarding an associated product to identify products satisfying the keyword query search string;

instructions for assigning product scores to the identified products based on matches to the keyword query search string;

instructions for parsing the product records to identify word matches in each of the product records and the document;

instructions for updating the product score by processing the adjusted word scores corresponding to the matched word with the product score of the product for which word matched; and

instructions for selecting products from the identified products that have the highest updated product scores.