Method and system for probabilistically quantifying and visualizing relevance between two or more citationally or contextually related data objects

• US 8,131,701 B2
• Filed: 03/29/2010
• Issued: 03/06/2012
• Est. Priority Date: 09/27/2005
• Status: Active Grant

• Current Assignee: PatentRatings, LLC
• Original Assignee: PatentRatings, LLC
• Inventors: Barney, Jonathan A.
• Primary Examiner(s): Jami, Hares
• Application Number:
  US12/749,381
• Publication Number:
  US 20110072024A1
• Time in Patent Office: 708 Days
• Field of Search: 707/705, 707/722, 707/726, 707/728, 707/731, 707/999.1, 707/912, 707/923, 707/930, 707/937
• US Class Current: 707/705
• CPC Class Codes: G06F 16/14 Details of searching files based on file metadata
• CPC Class Codes: G06F 16/2228 Indexing structures
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/26 Visual data mining; Browsing structured data
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/3346 using probabilistic model
• CPC Class Codes: G06F 16/34 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/382 using citations hypermedia G06F16/94
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 2216/11 Patent retrieval
• CPC Class Codes: Y10S 707/912 Applications of a database
• CPC Class Codes: Y10S 707/923 Intellectual property
• CPC Class Codes: Y10S 707/93 intellectual property analysis
• CPC Class Codes: Y10S 707/933 Citation analysis
• CPC Class Codes: Y10S 707/937 intellectual property searching

Abstract

In one embodiment the present invention provides a novel method for probabilistically quantifying a degree of relevance between two or more citationally or contextually related data objects, such as patent documents, non-patent documents, web pages, personal and corporate contacts information, product information, consumer to behavior, technical or scientific information, address information, and the like. In another embodiment the present invention provides a novel method for visualizing and displaying relevance between two or more citationally or contextually related data objects. In another embodiment the present invention provides a novel search input/output interface that utilizes an iterative self-organizing mapping (“SOM”) technique to automatically generate a visual map of relevant patents and/or other related documents desired to be explored, searched or analyzed. In another embodiment the present invention provides a novel search input/output interface that displays and/or communicates search input criteria and corresponding search results in a way that facilitates intuitive understanding and visualization of the logical relationships between two or more related concepts being searched.

Claims

1. A computer-implemented method for probabilistically quantifying a likelihood or probability that a direct citational relationship exists between a first document and a second document based on one or more observed indirect citational relationships occurring between said first document and said second document, the method comprising:

determining by a computer system said one or more indirect citational relationships between said first document and said second document;

analyzing by the computer system said one or more indirect citational relationships to determine one or more generational citation counts between said first and second documents at generations higher than said direct first generation citational relationship;

applying by the computer system a probability transform function to said one or more determined generational citation counts to determine or probabilistically quantify a relative event probability that said first document directly cites said second document or said second document directly cites said first document;

calculating by the computer system a probability value based on the relative event probability that said first document directly cites said second document or said second document directly cites said first document,

wherein the applying a probability transform function comprises providing said one or more determined generational citation counts as input predictor variables to a multi-variate regression model, said model being selected and adjusted to determine a relative event probability that said first document directly cites said second document or said second document directly cites said first document based on said one or more determined generational citation counts,

wherein the computer system comprises at least a processor and a storage device.

2. The computer-implemented method of claim 1, wherein the determining said one or more indirect citational relationships comprises using computer database logic to extend multiple generations of citations from each said first and second document to identify one or more shared or overlapping citations to one or more commonly cited documents.

3. The computer-implemented method of claim 1, wherein the analyzing said one or more indirect citational relationships comprises determining for each said indirect citational relationship the number of citation links or generations separating said first document from said second document and counting or aggregating said indirect citational relationships according to said determined number of citation links or generations.

4. The computer-implemented method of claim 3, wherein the analyzing said one or more indirect citational relationships further comprises weighting or normalizing each said indirect citational relationship.

5. The computer-implemented method of claim 3, wherein the analyzing said one or more indirect citational relationships further comprises weighting said generational citation counts in accordance with one or more citation credits, said citation credits being determined such that a total citation credit for each said first or second document is divided from generation to generation substantially inversely proportionally to the total number of citations occurring at each generation.

6. The computer-implemented method of claim 1, wherein said multi-variate regression model is further selected and adjusted to determine a relative event probability that said first document directly cites said second document or said second document directly cites said first document based on one or more additional measurable or discernable relationships that may exist between said first document and said second document and wherein the applying a probability transform function further comprises providing said one or more additional measurable or discernable relationships as input predictor variables to said multi-variate regression model.

7. The computer-implemented method of claim 1, further comprising generating a search result set comprising two or more documents having one or more indirect citational relationships to said first or second documents and using said determined likelihood or probability of direct citation to rank or order said search result set.

8. The computer-implemented method of claim 1, further comprising using said first document to generate a first search result set comprising two or more documents having one or more indirect citational relationships to said first document and using said determined likelihood or probability of direct citation to rank or order said first search result set.

9. The computer-implemented method of claim 8, further comprising selecting from said first search result set at least one additional document, using said first document and said at least one additional document to generate a second search result set comprising two or more documents having one or more indirect citational relationships to either said first document or said at least one additional document, and using said determined likelihood or probability of direct citation to rank or order said second search result set.

10. The computer-implemented method of claim 1, further comprising the further step of using said determined likelihood or probability of direct citation to identify or qualify patent assets or groups of patent assets desired to be purchased or sold through private negotiated transactions, public sales or public auctions.

11. The computer-implemented method of claim 1, further comprising using said determined likelihood or probability of direct citation to identify logical clusters of similar or related documents.

12. The computer-implemented method of claim 1, wherein at least said first or second document comprises a patent, and further comprising rating, ranking or valuing said patent based at least in part on said determined likelihood or probability of direct citation.

13. A computer-implemented method for rating or ranking the relative quality or value of a first patent document based at least in part on determining a relative probability that a direct citational relationship exists between said first patent document and a second patent document, the method comprising:

determining by a computer system one or more indirect citational relationships that may exist between said first patent document and said second patent document;

analyzing by the computer system said one or more indirect citational relationships by determining for each said indirect citational relationship the number of citation links or generations separating said first patent document from said second patent document and counting or aggregating said indirect citational relationships into generational citation counts according to said determined number of citation links or generations;

applying by the computer system a probability transform function to said one or more determined generational citation counts to determine or quantify the relative probability that said first patent document directly cites said second patent document or said second patent document directly cites said first patent document;

wherein the applying a probability transform function comprises providing said one or more determined generational citation counts as input predictor variables to a multi-variable event prediction model, said model being selected and adjusted to determine a relative event probability that said first document directly cites said second document or said second document directly cites said first document based on said one or more determined generational citation counts; and

providing by the computer system said determined relative probability to a computer-implemented patent rating system and causing said computer-implemented patent rating system to thereby rate or rank the relative quality or value of said first patent document based at least in part on said determined relative probability,

wherein the computer system comprises at least a processor and a storage device.

14. The computer-implemented method of claim 13, wherein the determining said one or more indirect citational relationships comprises using computer database logic to extend multiple generations of citations from each said first and second patent document to identify one or more shared or overlapping citations to one or more commonly cited documents.

15. The computer-implemented method of claim 13 wherein the analyzing said one or more indirect citational relationships further comprises weighting or normalizing each said indirect citational relationship.

16. The computer-implemented method of claim 15, wherein the analyzing said one or more indirect citational relationships further comprises weighting said generational citation counts in accordance with one or more citation credits, said citation credits being determined such that a total citation credit for each said first or second patent document is divided from generation to generation substantially inversely proportionally to the total number of citations occurring at each generation.

17. The computer-implemented method of claim 13, wherein the applying a probability transform function comprises providing said one or more determined generational citation counts as input predictor variables to a multi-variate regression model, said model being selected and adjusted to determine a relative event probability that said first patent document directly cites said second patent document or said second patent document directly cites said first patent document based on said one or more determined generational citation counts.

18. The computer-implemented method of claim 13, wherein the providing said determined relative probability comprises providing said determined relative probability as an input predictor variable to a multi-variate regression model, said model being selected and adjusted to determine a relative rating, ranking or value of said first patent document based at least in part on said determined relative probability and other selected metrics relative to said first and second patent documents.

19. The computer-implemented method of claim 13, further comprising generating a search result set comprising two or more documents having one or more indirect citational relationships to said first or second patent documents and using said determined relative probability to rank or order said search result set.

20. The computer-implemented method of claim 13, further comprising using said determined relative probability to identify or qualify patent assets or groups of patent assets desired to be purchased or sold through private negotiated transactions, public sales or public auctions.

21. The computer-implemented method of claim 13, further comprising using said determined relative probability to identify logical clusters of similar or related patent documents.