COMPUTER-IMPLEMENTED PATENT PORTFOLIO ANALYSIS METHOD AND APPARATUS

• US 20120109642A1
• Filed: 01/09/2012
• Published: 05/03/2012
• Est. Priority Date: 02/05/1999
• Status: Active Grant

• Current Assignee: Ontologics Incorporated
• Original Assignee: Gregory A. Stobbs, John V. Biernacki
• Inventors: STOBBS, Gregory A., Biernacki, John V.
• Granted Patent: US 9,710,457 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis
• CPC Class Codes: G06Q 50/184 Intellectual property management
• CPC Class Codes: Y10S 707/934 Analyzing patent activity

Abstract

A computer-implemented apparatus and method for performing patent portfolio analysis. The patent portfolio analysis apparatus and method clusters a group of patents based upon one or more techniques. The clustering techniques include linguistic clustering techniques (e.g., eigenvector analysis), claim meaning, and patent classification techniques. Different aspects of the clusters are analyzed, including financial, claim breadth, and assignee patent comparisons. Moreover, patents and/or their clusters are linked to the Internet in order to determine what products might be covered by the claims of the patents or whether materials on the Internet might render patent claims invalid.

Claims

1. A computer-implemented patent portfolio analysis method comprising:

providing user-prescribed categories which were specified by a user;

retrieving a corpus of patent information from a database, wherein the patent information is information from multiple patent documents;

analyzing said patent information to generate a category model corresponding to at least one of said user-prescribed categories; and

applying said model against said patent information to select from said patent information a subset that fits said model and storing said subset in association with a label corresponding to said at least one of said user-prescribed categories in a computer-readable dataset,

wherein said patent information includes textual information to be analyzed and wherein said analyzing step includes;

defining an eigenspace representing a training population of training textual information;

representing at least a portion of said training textual information in said eigenspace and associating a predefined category with each training textual information in said eigenspace; and

projecting the textual information to be analyzed into said eigenspace and associating with said projected textual information the predefined category of the training textual information to which said projected textual information is closest within the eigenspace.