System and method for using text analytics to identify a set of related documents from a source document

• US 20070112748A1
• Filed: 11/17/2005
• Published: 05/17/2007
• Est. Priority Date: 11/17/2005
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Martin, David, Rhodes, James, Hennessy, Richard, Boyer, Stephen, Cooper, James, Kanungo, Tapas, Spangler, W., Weintraub, Herschel, Angell, Robert, Kreulen, Jeffrey
• Granted Patent: US 9,495,349 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/237 Lexical tools

Abstract

A system and method for processing a document to generate a set of related documents. A system is provided that includes a textual analytics system that analyzes unstructured data contained in a source document and extracts a set of structured information about the source document; and a compare system that identifies a set of related documents by comparing the set of structured information with metadata indexed from a set of publications.

Claims

1. A document processing system, comprising:

a textual analytics system that analyzes unstructured data contained in a source document and extracts a set of structured information about the source document; and

a compare system that identifies a set of related documents by comparing the set of structured information with metadata indexed from a set of publications.

2. The document processing system of claim 1, wherein the set of structured information comprises key words associated with a technology field.

3. The document processing system of claim 1, wherein the set of structured information comprises a list of chemical abstract numbers.

4. The document processing system of claim 1, wherein the set of structured information comprises a list of SMILES (simplified molecular input line entry specification) strings.

5. The document processing system of claim 1, wherein the source document comprises a patent document and the set of related documents comprise technical references.

6. The document processing system of claim 1, wherein the source document comprises a medical record and the set of related documents comprise technical references.

7. The document processing system of claim 1, further comprising an annotation system for annotating the source document with metadata associated with the set of related documents.

8. The document processing system of claim 7, further comprising:

a database of annotated documents; and

a data mining system for mining the database of annotated documents.

9. The document processing system of claim 1, wherein the metadata is contained in a database of MedLine abstracts.

10. The document processing system of claim 1, further comprising an aggregation and ranking system for prioritizing the set of related documents.

11. A computer program product stored on a computer readable medium for processing a content source, comprising:

program code configured for analyzing unstructured data contained in the content source and for extracting a set of structured information about the content source; and

program code configured for identifying a set of related documents by comparing the set of structured information with metadata indexed from a set of publications.

12. The computer program product of claim 11, wherein the set of structured information comprises key words associated with a technology field.

13. The computer program product of claim 11, wherein the set of structured information comprises a list of chemical abstract numbers.

14. The computer program product of claim 11, wherein the set of structured information comprises a list of SMILES (simplified molecular input line entry specification) strings.

15. The computer program product of claim 11, wherein the content source comprises a patent document and the set of related documents comprise technical references.

16. The computer program product of claim 11, wherein the content source is selected from the group consisting of:

a medical record, a Web page, a multimedia input, a technical reference, and a publication.

17. The computer program product of claim 11, further comprising program code configured for annotating the content source with metadata associated with the set of related documents.

18. The computer program product of claim 17, further comprising:

program code configured for storing an annotated content source in a database of annotated documents; and

program code configured for data mining the database of annotated content sources.

19. The computer program product of claim 11, wherein the metadata is contained in a database of MedLine abstracts.

20. The computer program product of claim 11, further comprising program code configured for prioritizing the set of related documents.

21. A method of processing a source document, comprising:

analyzing unstructured data contained in the source document;

extracting a set of structured information about the source document; and

identifying a set of related documents by comparing the set of structured information with metadata indexed from a set of publications.

22. The method of claim 21, wherein the set of structured information comprises information selected from the group consisting of:

key words associated with a technology field, a list of chemical abstract numbers, and a list of SMILES (simplified molecular input line entry specification) strings.

23. The method of claim 21, wherein the source document comprises a document selected from the group consisting of:

a patent document, a Web page, a medical record, a technical reference, and a publication.

24. The method of claim 21, further comprising the step of annotating the source document with metadata associated with the set of related documents.

25. The method of claim 21, wherein the metadata is contained in a database of MedLine abstracts.

26. The method of claim 21, further comprising the step of prioritizing the set of related documents.

27. A method for deploying an application for processing a document, comprising:

providing a computer infrastructure being operable to;

analyze unstructured data contained in the content source and for extracting a set of structured information about the content source; and

identify a set of related documents by comparing the set of structured information with metadata indexed from a set of publications.