System and method for adaptive multi-cultural searching and matching of personal names

• US 20050273468A1
• Filed: 07/26/2005
• Published: 12/08/2005
• Est. Priority Date: 03/25/1998
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: Language Analysis Systems, Inc. (International Business Machines Corporation)
• Inventors: McCallum-Bayliss, Heather, Shaefer, Leonard Arthur Jr., Lutz, Richard D., Hermansen, John Christian
• Application Number:
  US11/188,979
• Publication Number:
  US 20050273468A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/33 Querying
• CPC Class Codes: G06F 16/90344 by using string matching techniques
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

An automated name searching system incorporates an automatic name classifier and a multi-path architecture in which different algorithms are applied based on cultural identity of the query name. The name classifier operates with a preemptive list, analysis of morphological elements, length, and linguistic rules. A name regularizer produces a character based computational representation of the name. A pronunciation equivalent representation such as an IPA language representation, and language specific rules to generate name searching keys, are used in a first pass to eliminate database entries which are obviously not matches for the query name. The methods can also be implemented as a callable set of library routines including an intelligent preprocessor and a name evaluator that produces a score comparing a query name and database name, based on a variety of user-adjustable parameters. The user-controlled parameters permit tuning of the search methodologies for specific custom applications.

Claims

1-18. -18. (canceled)

19. A method of providing an indication of whether an input name belongs to a particular culture, the method comprising:

accessing an input name;

accessing a classifying algorithm that is based on linguistic analysis of names in a particular culture;

accessing another classifying algorithm, the other classifying algorithm being based on linguistic analysis of names in another culture;

processing the input name using the classifying algorithm;

processing the input name using the other classifying algorithm;

providing an indication of whether the input name belongs to the particular culture based on the processing of the input name using the classifying algorithm; and

providing an indication of whether the input name belongs to the other culture based on the processing of the input name using the other classifying algorithm.

20. The method of claim 19 further comprising:

accessing a second classifying algorithm that is based on linguistic analysis of names in the particular culture; and

processing the input name using the second classifying algorithm.

21. The method of claim 20 wherein providing the indication is further based on the processing of the input name using the second classifying algorithm.

22. The method of claim 20 wherein the classifying algorithm and the second classifying algorithm each relate to independent linguistic features.

23. The method of claim 20 wherein:

processing the input name using the classifying algorithm comprises producing a result,

processing the input name using the second classifying algorithm comprises producing a second result, and

the method further comprises accumulating and weighing the result and the second result.

24. The method of claim 23 wherein accumulating and weighing the result and the second result comprises applying an order of precedence to the result and the second result.

25. The method of claim 19 wherein processing the input name using the classifying algorithm comprises producing a result.

26. The method of claim 25 wherein processing the input name using the classifying algorithm further comprises generating a confidence level for the result.

27. The method of claim 19 wherein providing the indication of whether the input name belongs to the particular culture comprises providing an indication of whether the input name belongs to a particular language.

28. The method of claim 19 wherein the classifying algorithm is orthographic based, and processing the input name comprises analyzing characters in the input name.

29. The method of claim 28 wherein processing the input name comprises analyzing an affix in the input name.

30. The method of claim 19 wherein processing the input name comprises comparing digrams in the input name to digrams present in names from the particular culture.

31. The method of claim 30 wherein processing the input name further comprises computing a likelihood that the input name belongs to the particular culture based on digram distribution statistics for names from the particular culture.

32. The method claim 31 wherein computing the likelihood is further based on digram position within the input name.

33. The method of claim 19 wherein the classifying algorithm is element based, and processing the input name comprises analyzing elements in the input name.

34. The method of claim 33 wherein processing the input name comprises analyzing a title in the input name.

35. The method of claim 33 wherein processing the input name comprises analyzing a qualifier in the input name.

36. The method of claim 19 wherein the classifying algorithm is semantic based, and processing the input name comprises analyzing meaning in the input name.

37. The method of claim 19 wherein the classifying algorithm is phonologically based, and processing the input name comprises analyzing a sound in the input name.

38. The method of claim 19 wherein the classifying algorithm is syntactic based, and processing the input name comprises analyzing an order of elements in the input name.

39. The method of claim 19 wherein providing the indication of whether the input name belongs to the particular culture comprises providing a non-binary indication of a degree to which the input name belongs to the particular culture.

40. The method of claim 19 wherein:

the input name is a full name including a given name and a surname,

accessing the input name comprises accessing the full name, and

processing the input name comprises processing the full name.

41. The method of claim 19 wherein:

the input name is a partial name,

accessing the input name comprises accessing the partial name, and

processing the input name comprises processing the partial name.

42. The method of claim 19 wherein processing the input name comprises comparing the input name to a high-frequency name in the particular culture.

43. The method of claim 19 wherein processing the input name comprises comparing a length of the input name to lengths of names in the particular culture.

44. The method of claim 19 wherein processing the input name comprises comparing the input name to a string of characters that occurs in names in the particular culture.

45. The method of claim 44 wherein the string of characters comprises a morpheme in the particular culture, and processing the input name comprises comparing the input name to the morpheme.

46. The method of claim 19 wherein providing the indication comprises providing a likelihood that the input name belongs to the particular culture.

47. The method of claim 19 wherein:

providing the indication of whether the input name belongs to the particular culture comprises providing an indication that the input name does belong to the particular culture, and

providing the indication of whether the input name belongs to the other culture comprises providing an indication that the input name does belong to the other culture.

48. The method of claim 19 wherein providing the indication comprises providing the indication to a user.

49. The method of claim 19 wherein providing the indication comprises providing the indication to another algorithm.

50. The method of claim 19 wherein accessing the classifying algorithm comprises accessing the classifying algorithm from among multiple algorithms, the multiple algorithms each being based on linguistic analysis of names in a different culture such that no two algorithms are based on the same culture.

51. The method of claim 19 wherein providing the indication comprises providing an indication that the input name belongs to the particular culture, and the method further comprises:

accessing a stored name of the particular culture;

selecting a comparing algorithm that is based on names in the particular culture;

comparing the input name and the stored name using the comparing algorithm; and

providing an indication of whether the input name matches the stored name based on the comparing of the input name and the stored name.

52. The method of claim 51 wherein selecting the comparing algorithm comprises selecting the comparing algorithm from among multiple comparing algorithms, each comparing algorithm being based on names in a different culture such that no two comparing algorithms are based on the same culture.

53. A method of providing an indication of whether an input name belongs to a particular culture, the method comprising:

accessing an input name;

accessing a classifying algorithm that is based on linguistic analysis of names in a particular culture, wherein the classifying algorithm is semantic based;

processing the input name using the classifying algorithm, the processing including analyzing meaning in the input name; and

providing an indication of whether the input name belongs to the particular culture based on the processing of the input name using the classifying algorithm.

54. A method of providing an indication of whether an input name belongs to a particular culture, the method comprising:

accessing an input name;

accessing a classifying algorithm that is based on linguistic analysis of names in a particular culture, wherein the classifying algorithm is phonologically based;

processing the input name using the classifying algorithm, the processing including analyzing a sound in the input name; and

providing an indication of whether the input name belongs to the particular culture based on the processing of the input name using the classifying algorithm.

55. A method of providing an indication of whether an input name belongs to a particular culture, the method comprising:

accessing an input name;

accessing a classifying algorithm that is based on linguistic analysis of names in a particular culture, wherein the classifying algorithm is based on morphemes;

processing the input name using the classifying algorithm, the processing including comparing the input name to a morpheme from the particular culture; and

providing an indication of whether the input name belongs to the particular culture based on the processing of the input name using the classifying algorithm.

56. An apparatus comprising a computer readable medium having instructions stored thereon that when executed by a machine result in at least the following:

accessing an input name;

accessing a classifying algorithm that is based on linguistic analysis of names in a particular culture;

accessing another classifying algorithm, the other classifying algorithm being based on linguistic analysis of names in another culture;

processing the input name using the classifying algorithm;

processing the input name using the other classifying algorithm;

providing an indication of whether the input name belongs to the particular culture based on the processing of the input name using the classifying algorithm; and

providing an indication of whether the input name belongs to the other culture based on the processing of the input name using the other classifying algorithm.