METHOD AND SYSTEM FOR PEER DETECTION

• US 20160350294A1
• Filed: 05/31/2015
• Published: 12/01/2016
• Est. Priority Date: 05/31/2015
• Status: Active Grant

• Current Assignee: Thomson Reuters Enterprise Centre GmbH (The Woodbridge Co. Ltd.)
• Original Assignee: Thomson Reuters Global Resources
• Inventors: Nefedov, Nikolai, Waerniers, Jan, Suvorova, Ekaterina, Ulicny, Brian
• Granted Patent: US 10,019,442 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3323 using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

The present invention provides a method and system delivering graph-based metric to measure a similarity between weighted sets of classifications codes (presented as nodes) defined on hierarchical taxonomy trees. The suggested method is applied to find company peers in a particular domain, e.g., the IP domain based on a company patent portfolio. The suggested method may be applied to other domains that include hierarchical classifications such as trademarks, legal documents, scientific papers, lawsuits etc.

Claims

1. A computer-based system for processing a user query to detect a set of peers and generate a graphical representation of detected peers responsive to the query, the system comprising:

a peer detection search engine executed by a computer in communication with at least one database, the peer detection search engine being adapted to receive a peer query and, based at least in part on the peer query, to search at least one corpus of documents contained in the at least one database, the peer detection search engine comprising;

a feature extraction module adapted to extract data from files contained in the at least one corpus of documents, the extracted data related to content associated with documents;

a portfolio comparison module adapted to determine a set of similarity scores based at least in part on a set of the extracted data; and

a graphical interface generation module adapted to transform the set of similarity scores and generate and present on a remote user display a graphical representation of the transformed set of similarity scores for visual perception by a human user associated with the remote user display.

2. The system of claim 1, wherein the extracted data includes a hierarchical set of features and the portfolio comparison module is adapted to determine the set of similarity scores based on a set of weights assigned, respectively, to the hierarchical set of features.

3. The system of claim 1, wherein the extracted data includes a hierarchical set of features and the portfolio comparison module is adapted to determine the set of similarity scores based on a set of weights assigned, respectively, to the hierarchical set of features and to generate a set of feature vectors.

4. The system of claim 1 further comprises a set of database object files, each object file comprising entity data, extracted data, classification code data, and a set of similarity scores.

5. The system of claim 1, wherein the extracted data includes a set of patent features and the peer detection search engine is further adapted to determine a first set of peer candidates, the portfolio comparison module is further adapted to generate for each of the first set of peer candidates a set of feature scores associated with the set of patent features.

6. The system of claim 5, wherein, the portfolio comparison module is further adapted to rank the set of peer candidates based at least in part on the set of feature scores.

7. The system of claim 5, wherein one or more of the set of feature scores is normalized.

8. The system of claim 5, wherein the set of patent features comprises one or more from the group consisting of:

fields of a patent;

patent title;

patent abstract;

patent IPC code;

patent references;

patent claims;

rank-c, representing the lowest rank of any claim of a patent in the first set of candidate patents;

sim(c,c), representing a highest similarity score between the query and claims in a patent in the first set of candidate patents;

sim(c,cs), representing a similarity score between the query and all the claims of a patent in the first set of candidate patents;

sim(c,title), representing a similarity score between the query and the title of a patent in the first set of candidate patents;

sim(c,abstract), representing a similarity score between the query and the abstract of a patent in the first set of candidate patents;

sim(key,key), representing a similarity score between key concepts of the query and a patent in the first set of patents;

sim(key,title), representing a similarity score between the key concept of the query and the title of a patent in the first set of patents;

sim(key,abstract), representing a similarity score between the key concept of the query and the abstract of a patent in the first set of patents; and

IPC-overlap, representing a number of overlapping IPC codes between IPC codes of a patent in the first set of patents and the IPC codes of an initial high-ranking set of patents in the first set of patents.

9. The system of claim 5, wherein the set of patent features includes IPC-overlap, representing the number of the overlapping IPC codes between the IPC codes of a patent in the first set of patent documents, the system further adapted to compute IPC-overlap including code adapted to define the overlap score between two IPC codes, divide each IPC code to a plurality of levels based on IPC code structure, and wherein a first level overlap between two IPC codes results in a first score and a second level overlap between two IPC codes results in a second score.

10. The system of claim 1, wherein the portfolio comparison module is further adapted to determine a first set of similarity scores by calculating aggregated code data.

11. The system of claim 1, wherein the portfolio comparison module is further adapted to determine a first set of similarity scores by determining a minimum path distance via root on a taxonomy tree between nodes at one or more hierarchical levels.

12. The system of claim 1, wherein the portfolio comparison module is further adapted to determine a first set of similarity scores based on a number of shared hierarchy levels or a number of shared nodes excluding root.

13. The system of claim 1, wherein the portfolio comparison module is further adapted to determine a first set of similarity scores based on stopping computations at a lowest matching level of shared nodes or shared hierarchy levels on a taxonomy tree.

14. The system of claim 1, wherein the portfolio comparison module is further adapted to determine a first set of normalized similarity scores between at least two nodes at a given hierarchy level on a taxonomy tree.

15. The system of claim 1, wherein the portfolio comparison module is further adapted to determine a first set of similarity scores based at least in part on a weighted path length from root to node on a taxonomy tree.

16. The system of claim 1, wherein the portfolio comparison module is further adapted to determine portfolio concentration score data representing a measure of an identified company'"'"'s concentration of resources in one or more technology domains.

17. The system of claim 16, wherein the determined portfolio concentration score data represents a measure of the identified company'"'"'s activities based on patent classifications.

18. The system of claim 17, wherein the determined portfolio concentration score data is transformed into a two-dimensional company characterization metric.

19. The system of claim 18, wherein the two-dimensional company characterization metric includes a first portfolio concentration metric and a second portfolio volume metric.

20. The system of claim 16, wherein the portfolio comparison module is further adapted to determine a pair-wise similarity between nodes by mapping nodes from a set of portfolios to an underlying classification tree.

21. The system of claim 1, wherein the portfolio comparison module is further adapted to determine a second set of similarity scores by performing a direct comparison of selected portfolio data.

22. The system of claim 21, wherein the portfolio comparison module is further adapted to perform the direct comparison by comparing a first set of patent data associated with a first patent portfolio with a second set of patent data associated with a second patent portfolio.

23. The system of claim 22, wherein at least one of the first patent portfolio and the second patent portfolio are determined based on a prior determined set of similarity scores calculated using a set of patent features.

24. (canceled)

25. (canceled)

26. (canceled)

27. (canceled)

28. (canceled)

29. (canceled)

30. (canceled)

31. (canceled)

32. (canceled)

33. (canceled)

34. (canceled)

35. (canceled)

36. (canceled)

37. (canceled)

38. (canceled)

39. (canceled)

40. (canceled)

41. (canceled)

42. (canceled)

43. (canceled)

44. (canceled)

45. (canceled)

46. (canceled)