INFORMATION RETRIEVAL BY NATURAL LANGUAGE QUERYING

• US 20030078766A1
• Filed: 09/17/1999
• Published: 04/24/2003
• Est. Priority Date: 09/17/1999
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Spanlink Communications Incorporated (ConvergeOne Holdings, Inc.)
• Inventors: ISRAEL, DAVID J., MARTIN, DAVID L., APPELT, DOUGLAS E., BEAR, JOHN S, HOBBS, JERRY ROBERT, TYSON, WILLIAM MABRY, RAVICHANDRAN, GOPALAN, KAMEYAMA, MEGUMI, ARNOLD, JAMES FREDRICK, STICKEL, MARK EDWARD, MYERS, KAREN LOUIS
• Granted Patent: US 6,601,026 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A natural language information querying system includes an indexing facility configured to automatically generate indices of updated textual sources based on one or more predefined grammars and a database coupled to the indexing facility to store the indices for subsequent searching.

Claims

1. A system for providing information in response to a natural language query, comprising:

an information extraction engine adapted to index an updated text source based on a predefined grammar;

a database coupled to the information extraction engine to store the index output; and

a natural language query engine coupled to the database to search the index for the text corpus in response to the natural language query.

2. The system of claim 1, further comprising a data acquisition unit coupled to the information extraction engine to automatically update the text corpus.

3. The system of claim 2, wherein the data acquisition unit receives data from a web crawler, a news service, or a search engine.

4. The system of claim 1, wherein the grammar is associated with a topic.

5. The system of claim 1, wherein the grammar is based on events and relationships associated with a topic.

6. The system of claim 1, wherein the grammar comprises pattern-action rules.

7. The system of claim 1, wherein the grammar comprises one or more rules to specify a proper noun, a complex word, a phrase, or a domain event.

8. The system of claim 1, wherein the grammar comprises one or more rules for merging partial information from different parts of a document.

9. The system of claim 1, further comprising searching the index for the text corpus using natural language querying.

10. The system of claim 9, wherein the natural language querying is based on a query grammar.

11. The system of claim 10, wherein the query grammar is associated with a topic.

12. The system of claim 10, wherein the query grammar is represented as pattern-action rules.

13. The system of claim 1, further comprising a query reply generator coupled to the natural language query engine to format the output of the search.

14. The system of claim 13, wherein the query reply generator creates a summary of the output for a group of documents.

15. The system of claim 13, wherein the query reply generator quotes a relevant portion of each located document in a summary.

16. The system of claim 13, wherein the query reply generator annotates the output by group in a summary.

17. The system of claim 13, wherein the query reply generator highlights a relevant portion in each located document.

18. The system of claim 1, further comprising a network coupled to the natural language query system.

19. The system of claim 18, wherein the network comprises the Internet.

20. The system of claim 18, further comprising one or more clients coupled to the natural language query engine.

21. The system of claim 20, wherein each client is a mobile computer.

22. The system of claim 20, wherein the client is a handheld computer adapted to transmit a natural language query to the natural language query engine and to receive a distilled natural language response from the natural language query engine.

23. The system of claim 20, wherein the client has a speech recognition engine adapted to convert user speech to the natural language query.

24. The system of claim 20, wherein the client has a text-to-speech engine adapted to convert the result of the search to speech.

25. The system of claim 1, wherein the text corpus is generated through computer recognition of spoken language.

26. The system of claim 1, further comprising:

a multimedia data source having a sound stream and a corresponding video stream; and

,

a speech recognizer coupled to the multimedia data source and the data acquisition unit, the speech recognizer converting the sound stream to a text stream and delivering the text stream to the data acquisition unit.

27. The system of claim 26, wherein the multimedia data source comprises one of a digital video disk, a videotape, a television transmission source, and a cable transmission source.

28. The system of claim 21, wherein the client has a pen input engine adapted to convert user handwritings to the natural language query.

29. A natural language information querying system, comprising:

an indexing facility configured to automatically generate indices of updated versions of the textual information based on a predefined grammar; and

a database coupled to the indexing facility to store the indices.

30. The system of claim 29, further comprising a query engine coupled to the database to respond to the natural language query.

31. A method for providing information in response to a natural language query, comprising:

extracting information from an updated text source based on a predefined grammar; and

creating a stored indexed text corpus adapted to permit natural language querying.

32. The method of claim 31, further comprising searching the stored indexed text corpus based on the natural language query.

33. The method of claim 31, wherein the information extracting step further comprises creating templates conforming to one or more events and relationships associated with a topic.

34. The method of claim 31, further comprising updating the text corpus by applying a speech recognizer to a multimedia stream.

35. The method of claim 31, further comprising creating a summary for each group of documents.

36. The method of claim 31, further comprising quoting a relevant portion of each located document in a summary.

37. The method of claim 31, further comprising annotating the output by group in a summary.

38. The method of claim 31, wherein the stored indexed text corpus resides on a server, further comprising:

sending the natural language query from a handheld computer; and

receiving a natural language response from the server and forwarding the response to a user.

39. The method of claim 31, further comprising converting the response to speech using a text-to-speech unit.

40. The method of claim 31, further comprising receiving the natural language query using a speech recognizer.

41. The method of claim 31, further comprising receiving the natural language query using a handwriting recognizer.

42. The method of claim 31, wherein the query and the text corpus relate to locating competitive intelligence information.

43. The method of claim 31, wherein the query and the text corpus relate to locating litigation support information.

44. The method of claim 31, wherein the query and the text corpus relate to locating products on-line.

45. The method of claim 31, wherein the query and the text corpus relate to locating medical information.

46. The method of claim 31, wherein the query and the text corpus relate to locating legal information.

47. The method of claim 31, wherein the query and the text corpus relate to locating electronic commerce information.

48. The method of claim 31, wherein the query and the text corpus relate to locating educational information.

49. The method of claim 31, wherein the query and the text corpus relate to locating financial information.

50. The method of claim 31, wherein the query and the text corpus relate to locating investment information.

51. The method of claim 31, wherein the query and the text corpus relate to locating information for a vertical market application.