Natural language based search engine and methods of use therefor

• US 20060224566A1
• Filed: 03/31/2005
• Published: 10/05/2006
• Est. Priority Date: 03/31/2005
• Status: Abandoned Application

• Current Assignee: Jiles Incorporated
• Original Assignee: Jiles Incorporated
• Inventors: Quiroga, Martin A., Flowers, John S., DeSanto, John A., Fischer, Gordon H.
• Application Number:
  US11/096,118
• Publication Number:
  US 20060224566A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

There is provided a search engine or other electronic search application that receives an inputted query in natural language. The search engine then analyzes the query in accordance with the syntactic relationships of the natural language in which it was presented, and generates a result to the query as output. The outputted result is typically an answer, in the form of a sentence or a phrase, along with the document from which the sentence or phrase is taken, including a hypertext link for the document.

Claims

1. A method for analyzing a query, comprising:

receiving a query in natural language; and

providing at least one response to the query in accordance with the relationships of the words to each other in natural language, of the query.

2. The method of claim 1, wherein providing the at least one response to the query includes, providing at least one representation of a corpus, the corpus including text in natural language, based on the relationships of words to each other in natural language.

3. The method of claim 2, wherein providing the at least one response to the query includes, creating relational components of the query in accordance with the relationships of the words to each other in the natural language of the query.

4. The method of claim 3, wherein providing the at least one response to the query includes, matching the relational components of the query to a portion of the representation of corpus.

5. The method of claim 4, wherein the matching includes, isolating the portion of the representation of the corpus.

6. The method of claim 5, wherein the at least one response to the query includes at least one sentence from the text of the corpus corresponding to the isolated portion of the representation of the corpus.

7. A search engine comprising:

a first component configured for receiving a query in natural language; and

a second component configured for providing at least one response to the query in accordance with the relationships of the words to each other in natural language, of the query.

8. The search engine of claim 7, wherein the second component includes a first module configured for providing at least one representation of a corpus, the corpus including text in natural language, based on the relationships of words to each other in natural language.

9. The search engine of claim 8, wherein the second component includes a second module configured for creating relational components of the query in accordance with the relationships of the words to each other in the natural language of the query.

10. The search engine of claim 9, wherein the second module is additionally configured for, matching the relational components of the query to a portion of the representation of corpus.

11. The search engine of claim 10, wherein the second module is additionally configured for isolating the portion of the representation of the corpus.

12. The search engine of claim 11, wherein the first module is additionally configured for providing at least one sentence from the text of the corpus corresponding to the isolated portion of the representation of the corpus.

13. A method for isolating data from a corpus, comprising:

processing at least a portion of the corpus into at least one first collection of syntactic relationships;

processing at least one query into at least one second collection of syntactic relationships; and

,

comparing the at least one second collection of syntactic relationships to the at least one first collection of syntactic relationships.

14. The method of claim 13, additionally comprising:

receiving at least one inputted query.

15. The method of claim 13, wherein processing at least a portion of the corpus includes, receiving feeds and isolating documents from the feeds.

16. The method of claim 15, wherein processing at least a portion of the corpus includes, isolating individual sentences from the documents.

17. The method of claim 16, wherein processing the corpus includes, parsing each sentence into at least one syntactic relationship.

18. The method of claim 17, wherein processing the corpus includes, ordering the at least one syntactic relationship into the at least one first collection of syntactic relationships.

19. The method of claim 18, wherein at least one syntactic relationship includes,

a plurality of syntactic relationships;

and,

ordering the at least one syntactic relationship includes, ordering the plurality of syntactic relationships into the at least one first collection of syntactic relationships.

20. The method of claim 19, wherein the at least one first collection of syntactic relationships includes, a plurality of first collections of syntactic relationships.

21. The method of claim 13, wherein comparing includes, matching the at least one second collection of syntactic relationships to the at least one first collection of syntactic relationships, and, if there is a match, isolating the at least one first collection of syntactic relationships.

22. The method of claim 21, additionally comprising:

providing a response to the at least one query by providing the sentence corresponding to the at least one first collection of syntactic relationships.

23. The method of claim 22, wherein providing the response includes, providing access to the document from which the sentence corresponding to the at least one set of syntactic relationships was isolated.

24. A method for providing at least one response to at least one query in natural language, comprising:

populating a data store by obtaining documents from at least a portion of a corpus, isolating sentences from the documents, parsing the sentences into linked pairs of words in accordance with predetermined relationships, assigning concept identifiers to each word of the linked pair of words, assigning concept link identifiers to each pair of concept identifiers corresponding to each linked pair of words, and, combining the concept link identifiers for each sentence into a statement;

receiving an inputted query in natural language;

parsing the query into linked pairs of words in accordance with predetermined relationships, assigning concept identifiers to each word of the linked pair of words, assigning concept link identifiers to each pair of concept identifiers corresponding to each linked pair of words, and, combining the concept link identifiers into a query statement;

analyzing the query statement and the statements in the data store for matches between concept link identifiers;

isolating statements in the data store having at least one concept link identifier that matches at least one concept link identifier in the query statement; and

,

providing at least one sentence corresponding to at least one isolated statement in the data store as a response to the natural language query.

25. The method of claim 24, additionally comprising:

providing access to at least one document from which the at least one sentence, corresponding to the at least one matched statement, was isolated.

26. The method of claim 24, wherein the predetermined relationships are defined by a parser.

27. The method of claim 24, wherein isolating statements in the data store includes, isolating statements in the data store having the greatest number of concept links that match the greatest number of concept links in the query statement.

28. The method of claim 24, wherein assigning concept identifiers to each word of the query includes, performing a lookup in the data store for the concept identifier matching the word from the query.

29. The method of claim 28, wherein assigning concept link identifiers includes, performing a lookup in the data store for paired concept identifiers matching the paired concept identifiers from the query.

30. A method for analyzing a query to a search engine, comprising:

creating related pairs of words in the query;

assigning concept identifiers to the each of the words in each of the related pairs of words;

creating pairs of concept identifiers by applying the assigned concept identifiers to each word in the related pairs of words;

assigning concept link identifiers to each pair of concept identifiers; and

,

combining all of the concept link identifiers into a query statement.

31. The method of claim 30, wherein all of the concept link identifiers of the query statement define a master set, where N is the number of concept link identifiers in the master set;

and,

creating a power set from the master set including, creating a plurality of subsets from the master set, the plurality of subsets defining members of the power set, the power set including at least one member of N concept link identifiers and at least N members of one concept link identifier.

32. The method of claim 30, wherein the creating related pairs of words includes, parsing the query in a parser.

33. The method of claim 31, additionally comprising:

analyzing a plurality of stored statements, the stored statements formed of a plurality of concept link identifiers, with the members of the power set, the analysis including, determining matches of the concept link identifiers in the stored statements with all of the concept link identifiers in each member of the power set.

34. The method of claim 33, additionally comprising:

isolating stored statements with concept link identifiers that match all of the concept link identifiers in a member of the power set.

35. The method of claim 34, wherein the stored statements with the greatest number of concept links, matching all of the concept links in the member of the power set with the greatest number of concept links, are assigned the highest rank.

36. The method of claim 35, wherein at least one stored statement of the highest rank is isolated.

37. The method of claim 36, wherein the at least one isolated stored statement is determined to be a response to the query.

38. The method of claim 37, wherein the at least one isolated stored statement corresponds to at least one sentence of a document, and, the at least one sentence is returned to a predetermined location.

39. The method of claim 38, wherein access to the document that included the at least one sentence is provided at the predetermined location in association with the returned sentence.

40. A method for analyzing a query to a search engine, placed in natural language, comprising:

creating related pairs of words from the natural language of the query;

assigning concept identifiers to the each of the words in each of the related pairs of words;

creating pairs of concept identifiers by applying the assigned concept identifiers to each word in the related pairs of words;

assigning concept link identifiers to each pair of concept identifiers; and

,

combining all of the concept link identifiers into a query statement.

41. The method of claim 40, wherein all of the concept link identifiers of the query statement define a master set, where N is the number of concept link identifiers in the master set;

and,

creating a power set from the master set including, creating a plurality of subsets from the master set, the plurality of subsets defining members of the power set, the power set including at least one member of N concept link identifiers and at least N members of one concept link identifier.

42. The method of claim 40, wherein the creating related pairs of words includes, parsing the query in a parser.

43. The method of claim 41, additionally comprising:

analyzing a plurality of stored statements, the stored statements formed of a plurality of concept link identifiers, with the members of the power set, the analysis including, determining matches of the concept link identifiers in the stored statements with all of the concept link identifiers in each member of the power set.

44. The method of claim 41, additionally comprising:

isolating stored statements with concept link identifiers that match all of the concept link identifiers in a member of the power set.

45. The method of claim 44, wherein the stored statements with the greatest number of concept links, matching all of the concept links in the member of the power set with the greatest number of concept links, are assigned the highest rank.

46. The method of claim 45, wherein at least one stored statement of the highest rank is isolated.

47. The method of claim 46, wherein the at least one isolated stored statement is determined to be a response to the query.

48. The method of claim 47, wherein the at least one isolated stored statement corresponds to at least one sentence of a document, and, the at least one sentence in natural language and the at least one sentence is returned to a predetermined location.

49. The method of claim 48, wherein access to the document that included the at least one sentence is provided at the predetermined location in association with the returned sentence.

50. A method for identifying a document from syntactic relationships:

electronically maintaining a document database identifying documents;

electronically maintaining a sentences database identifying sentences of each of the documents;

electronically maintaining a syntactic relationships database identifying collections of syntactic relationships between pairs of words formed from the words of each of the sentences; and

,

electronically linking the document database, the sentences database and the syntactic relationships data base, such that when at least one collection of syntactic relationships is isolated, the corresponding sentence in the sentence database is isolated, and the corresponding document in the document database is isolated from the isolated sentence in the sentence database.

51. The method of claim 50, wherein the collections of syntactic relationships define statements.

52. The method of claim 51, wherein the statements include concept link identifiers, the concept link identifiers based on pairs of concept identifiers.

53. The method of claim 52, wherein each word of each pair of words includes a corresponding concept identifier.

54. An architecture for isolating data from a corpus, comprising:

at least one data storage unit including at least one database;

a database population module in communication with the at least one data storage unit, the database population module configured for;

processing at least a portion of the corpus into at least one first collection of syntactic relationships; and

,

storing the at least one first collection of syntactic relationships in the at least one data storage unit; and

,

an answer module in communication with the at least one data storage unit, the answer module configured for;

processing at least one query into at least one second collection of syntactic relationships; and

,

comparing the at least one second collection of syntactic relationships to the at least one first collection of syntactic relationships.

55. The architecture of claim 54, additionally comprising:

a graphical user interface in communication with the answer module for receiving at least one inputted query.

56. The architecture of claim 54, wherein the database population module includes, at least one retrieval module configured for receiving feeds, and, at least one feed module, in communication with the at least one retrieval module, the at least one feed module configured for isolating documents from the feeds.

57. The architecture of claim 56, wherein the database population module includes, at least one document module in communication with the at least on feed module, the at least one document module configured for isolating individual sentences from the documents.

58. The architecture of claim 57, wherein the database population module includes, at least one sentence module in communication with the at least one document module, that at least one sentence module configured for;

parsing each sentence into at least one syntactic relationship; and

ordering the at least one syntactic relationship into the at least one first collection of syntactic relationships.

59. The architecture of claim 58, wherein the answer module configured for comparing the at least one second collection of syntactic relationships to the at least one first collection of syntactic relationships is additionally configured for;

matching the at least one second collection of syntactic relationships to the at least one first collection of syntactic relationships; and

,

if there is a match, isolating the at least one first collection of syntactic relationships.

60. The architecture of claim 59, wherein the answer module is additionally configured for providing a response to the at least one query by providing the sentence corresponding to the at least one first collection of syntactic relationships, from the at least one data storage unit.