Verification of extracted data

• US 8,321,199 B2
• Filed: 04/30/2010
• Issued: 11/27/2012
• Est. Priority Date: 06/22/2006
• Status: Active Grant

• Current Assignee: 3M Health Information Systems (3M Company)
• Original Assignee: Multimodal Technologies Incorporated (3M Company)
• Inventors: Koll, Detlef, Finke, Michael
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US12/771,193
• Publication Number:
  US 20100211869A1
• Time in Patent Office: 942 Days
• Field of Search: 704 1- 10, 704/235, 704/257, 704/231
• US Class Current: 704/9
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 19/00 Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis in musical instruments G10H
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

Facts are extracted from speech and recorded in a document using codings. Each coding represents an extracted fact and includes a code and a datum. The code may represent a type of the extracted fact and the datum may represent a value of the extracted fact. The datum in a coding is rendered based on a specified feature of the coding. For example, the datum may be rendered as boldface text to indicate that the coding has been designated as an “allergy.” In this way, the specified feature of the coding (e.g., “allergy”-ness) is used to modify the manner in which the datum is rendered. A user inspects the rendering and provides, based on the rendering, an indication of whether the coding was accurately designated as having the specified feature. A record of the user'"'"'s indication may be stored, such as within the coding itself.

Claims

1. A method performed by at least one computer processor executing computer program instructions tangibly stored on at least one non-transitory computer-readable medium, the method comprising:

(A) identifying a document including a first coding having a first feature encoding a first concept, the first coding being associated with a first code;

(B) rendering the first coding on an output device to have a visual characteristic that is based on the first feature, without rendering the first code;

(C) receiving, via an input device, a first indication from a user of whether the rendering is accurate;

(D) identifying, based on the first indication received from the user, a verification status of the first coding, wherein the verification status of the first coding indicates whether the first code represents the first concept, comprising;

(D)(1) if the first indication indicates that the rendering is accurate, then identifying a verification status of the first coding indicating that the first coding is accurate; and

(D)(2) otherwise, identifying a verification status of the first coding indicating that the first coding is inaccurate; and

(E) if the verification status of the first coding indicates that the first coding is inaccurate, then modifying the first feature of the first coding to produce a modified first feature and storing a non-transitory record of the modified first feature.

2. The method of claim 1, wherein the first feature comprises a specified relationship between the first coding and a second coding, and wherein (E) comprises modifying the relationship between the first coding and the second coding.

3. The method of claim 2, wherein the second coding includes the first coding, wherein the first feature comprises inclusion of the first coding in the second coding, and wherein (E) comprises removing the first coding from the second coding.

4. The method of claim 2, wherein the first and second codings are disjoint and wherein the first feature is represented by a first feature identifier in the document.

5. The method of claim 2, wherein (E) comprises severing the specified relationship.

6. The method of claim 1, further comprising:

(F) identifying, based on the first indication received from the user, a verification status of a second coding.

7. The method of claim 6, further comprising:

(G) storing, in the document, a record indicating that the verification status of the second coding was identified based on the verification status of the first coding.

8. The method of claim 1, wherein (C) comprises receiving first input by the user indicating whether the rendering is accurate.

9. The method of claim 1, wherein (C) comprises identifying lack of input by the user in response to rendering the first coding.

10. The method of claim 1, wherein a second coding includes the first coding and a third coding, the third coding being associated with a third code, and wherein (B) does not include rendering the third code.

11. The method of claim 1, wherein the first data comprises first text, and wherein (D) comprises identifying a verification status of the first coding, wherein the verification status of the first coding indicates whether the first text describes the first concept.

12. The method of claim 1, further comprising:

(F) storing, in the document, a record of the verification status of the first coding.

13. The method of claim 12, wherein (F) comprises storing the record in the first coding.

14. The method of claim 1, wherein (D) comprises determining whether the first code represents a concept having the first feature.

15. The method of claim 1, wherein the visual characteristic comprises a text formatting characteristic.

16. The method of claim 15, wherein the visual characteristic comprises boldface.

17. A non-transitory computer readable medium comprising computer program instructions tangibly stored on the computer readable medium, wherein the computer program instructions are executable by at least one computer processor to perform a method, the method comprising:

(A) identifying a document including a first coding having a first feature encoding a first concept, the first coding being associated with a first code;

(B) rendering the first coding on an output device to have a visual characteristic that is based on the first feature, without rendering the first code;

(C) receiving a first indication, via an input device, from a user of whether the rendering is accurate;

(D) identifying, based on the first indication received from the user, a verification status of the first coding, wherein the verification status of the first coding indicates whether the first code represents the first concept, comprising;

(D)(1) if the first indication indicates that the rendering is accurate, then identifying a verification status of the first coding indicating that the first coding is accurate; and

(D)(2) otherwise, identifying a verification status of the first coding indicating that the first coding is inaccurate; and

(E) if the verification status of the first coding indicates that the first coding is inaccurate, then modifying the first feature of the first coding to produce a modified first feature and storing a non-transitory record of the modified first feature.

18. The computer readable medium of claim 17, wherein the first feature comprises a specified relationship between the first coding and a second coding, and wherein (E) comprises modifying the relationship between the first coding and the second coding.

19. The computer readable medium of claim 18, wherein the second coding includes the first coding, wherein the first feature comprises inclusion of the first coding in the second coding, and wherein (E) comprises removing the first coding from the second coding.

20. The computer readable medium of claim 18, wherein the first and second codings are disjoint and wherein the first feature is represented by a first feature identifier in the document.

21. The computer readable medium of claim 18, wherein (E) comprises severing the specified relationship.

22. The computer readable medium of claim 17, wherein the method further comprises:

(F) identifying, based on the first indication received from the user, a verification status of a second coding.

23. The computer readable medium of claim 22, wherein the method further comprises:

(G) storing, in the document, a record indicating that the verification status of the second coding was identified based on the verification status of the first coding.

24. The computer readable medium of claim 17, wherein (C) comprises receiving first input by the user indicating whether the rendering is accurate.

25. The computer readable medium of claim 17, wherein (C) comprises identifying lack of input by the user in response to rendering the first coding.

26. The computer readable medium of claim 17, wherein a second coding includes the first coding and a third coding, the third coding being associated with a third code, and wherein (B) does not include rendering the third code.

27. The computer readable medium of claim 17, wherein the first data comprises first text, and wherein (D) comprises identifying a verification status of the first coding, wherein the verification status of the first coding indicates whether the first text describes the first concept.

28. The computer readable medium of claim 17, wherein the method further comprises:

(G) storing, in the document, a record of the verification status of the first coding.

29. The computer readable medium of claim 28, wherein (F) comprises storing the record in the first coding.

30. The computer readable medium of claim 17, wherein (D) comprises determining whether the first code represents a concept having the first feature.

31. The computer readable medium of claim 17, wherein the visual characteristic comprises a text formatting characteristic.

32. The computer readable medium of claim 31, wherein the visual characteristic comprises boldface.

33. A method performed by at least one computer processor executing computer program instructions tangibly stored on at least one non-transitory computer-readable medium, the method comprising:

(A) identifying a document including a first coding having a first feature, the first coding being associated with a first code, the first code having first data;

(B) rendering the first data on an output device based on the first feature;

(C) receiving, via an input device, a first indication from a user of a verification status of the rendering; and

(D) identifying, based on the verification status of the rendering, a verification status of the first feature, comprising;

(D)(1) if the verification status of the rendering indicates that the rendering is accurate, then identifying a verification status of the first feature indicating that the first feature is accurate; and

(D)(2) otherwise, identifying a verification status of the first feature indicating that the first feature is inaccurate;

(E) identifying, based on the verification status of the first feature, a verification status of the first coding; and

(F) storing, in a non-transitory computer-readable medium, a record of the verification status of the first coding.

34. The method of claim 33, wherein the first feature comprises a specified relationship with a second coding, and wherein (D) comprises determining whether the specified relationship is accurate.

35. The method of claim 34, wherein the second coding includes the first coding, wherein the first feature comprises inclusion of the first coding in the second coding, and wherein (D) comprises determining that inclusion of the first coding within the second coding is accurate.

36. The method of claim 34, wherein the first and second codings are disjoint and wherein the first feature is represented by a first feature identifier in the document.

37. The method of claim 34, further comprising:

(G) severing the specified relationship if the specified relationship is determined not to be accurate.

38. The method of claim 34, wherein the second coding is associated with a second code, the second code having second data, and wherein (B) comprises rendering the first data based on the second data.

39. The method of claim 38, wherein (B) does not include rendering the second code.

40. The method of claim 33, further comprising:

(E) identifying, based on the verification status of the first feature, a verification status of a second feature of a second coding.

41. The method of claim 40, further comprising:

(F) storing, in the document, a record indicating that the verification status of the second feature was identified based on the verification status of the first feature.

42. The method of claim 33, wherein (B) comprises:

(B)(1) selecting a visual characteristic based on the first feature;

(B)(2) rendering the first data based on the first feature to produce a rendering of the first data, whereby the rendering has the selected visual characteristic.

43. The method of claim 42, wherein the visual characteristic comprises a text formatting characteristic.

44. The method of claim 43, wherein the visual characteristic comprises boldface.

45. The method of claim 33, wherein (C) comprises receiving first input by the user indicating the verification status of the rendering.

46. The method of claim 45, wherein (D) comprises identifying a verification status of the first feature indicating that the first feature is inaccurate.

47. The method of claim 33, wherein (C) comprises identifying lack of input by the user in response to rendering the first data.

48. The method of claim 33, wherein (D) comprises identifying a verification status of the first feature indicating that the first feature is accurate.

49. The method of claim 33, wherein (B) does not include rendering the first code.

50. The method of claim 33, wherein a second coding includes the first coding and a third coding, the third coding being associated with a third code, the third code having third data, and wherein (B) does not include rendering the third code or the third data.

51. The method of claim 33, wherein the first data comprises first text.

52. The method of claim 51, further comprising:

(E) before (A), using an automatic speech recognizer to recognize an audio stream representing speech and thereby to produce the first text.

53. The method of claim 51, wherein the document further includes second text not included in the first coding.

54. The method of claim 51, wherein the first indication comprises input specifying a modification to the first text.

55. The method of claim 54, wherein the first indication comprises input specifying a modification to a text formatting characteristic of the first text.

56. The method of claim 51, wherein (D) comprises identifying a verification status of the feature indicating whether the first text describes a concept having the first feature.

57. The method of claim 33, wherein (C) further comprises receiving a second indication by the user indicating a verification status of the first data.

58. The method of claim 33, wherein (F) comprises storing the record of the verification status of the first coding in the document.

59. The method of claim 58, wherein (E) comprises storing the record in the first coding in the document.

60. The method of claim 33, wherein (D) comprises determining whether the first data represents a concept having the first feature.

61. A non-transitory computer readable medium comprising computer program instructions tangibly stored on the computer readable medium, wherein the computer program instructions are executable by at least one computer processor to perform a method, the method comprising:

(A) identifying a document including a first coding having a first feature, the first coding being associated with a first code, the first code having first data;

(B) rendering the first data on an output device based on the first feature;

(C) receiving, via an input device, a first indication from a user of a verification status of the rendering; and

(D) identifying, based on the verification status of the rendering, a verification status of the first feature, comprising;

(D)(1) if the verification status of the rendering indicates that the rendering is accurate, then identifying a verification status of the first feature indicating that the first feature is accurate; and

(D)(2) otherwise, identifying a verification status of the first feature indicating that the first feature is inaccurate;

(E) identifying, based on the verification status of the first feature, a verification status of the first coding; and

(F) storing, in a non-transitory computer-readable medium, a record of the verification status of the first coding.

62. The computer readable medium of claim 61, wherein the first feature comprises a specified relationship with a second coding, and wherein (D) comprises determining whether the specified relationship is accurate.

63. The computer readable medium of claim 62, wherein the second coding includes the first coding, wherein the first feature comprises inclusion of the first coding in the second coding, and wherein (D) comprises determining that inclusion of the first coding within the second coding is accurate.

64. The computer readable medium of claim 62, wherein the first and second codings are disjoint and wherein the first feature is represented by a first feature identifier in the document.

65. The computer readable medium of claim 62, wherein the method further comprises:

(G) severing the specified relationship if the specified relationship is determined not to be accurate.

66. The computer readable medium of claim 62, wherein the second coding is associated with a second code, the second code having second data, and wherein (B) comprises rendering the first data based on the second data.

67. The computer readable medium of claim 62, wherein (B) does not include rendering the second code.

68. The computer readable medium of claim 61, further comprising:

(G) identifying, based on the verification status of the first feature, a verification status of a second feature of a second coding.

69. The computer readable medium of claim 68, wherein the method further comprises:

(H) storing, in the document, a record indicating that the verification status of the second feature was identified based on the verification status of the first feature.

70. The computer readable medium of claim 61, wherein (B) comprises:

(B)(1) selecting a visual characteristic based on the first feature;

(B)(2) rendering the first data based on the first feature to produce a rendering of the first data, whereby the rendering has the selected visual characteristic.

71. The computer readable medium of claim 70, wherein the visual characteristic comprises a text formatting characteristic.

72. The computer readable medium of claim 71, wherein the visual characteristic comprises boldface.

73. The computer readable medium of claim 61, wherein (C) comprises receiving first input by the user indicating the verification status of the rendering.

74. The computer readable medium of claim 73, wherein (D) comprises identifying a verification status of the first feature indicating that the first feature is inaccurate.

75. The computer readable medium of claim 61, wherein (C) comprises identifying lack of input by the user in response to rendering the first data.

76. The computer readable medium of claim 61, wherein (D) comprises identifying a verification status of the first feature indicating that the first feature is accurate.

77. The computer readable medium of claim 61, wherein (B) does not include rendering the first code.

78. The computer readable medium of claim 61, wherein a second coding includes the first coding and a third coding, the third coding being associated with a third code, the third code having third data, and wherein (B) does not include rendering the third code or the third data.

79. The computer readable medium of claim 61, wherein the first data comprises first text.

80. The computer readable medium of claim 79, wherein the method further comprises:

(F) before (A), using an automatic speech recognizer to recognize an audio stream representing speech and thereby to produce the first text.

81. The computer readable medium of claim 79, wherein the document further includes second text not included in the first coding.

82. The computer readable medium of claim 79, wherein the first indication comprises input specifying a modification to the first text.

83. The computer readable medium of claim 82, wherein the first indication comprises input specifying a modification to a text formatting characteristic of the first text.

84. The computer readable medium of claim 79, wherein (D) comprises identifying a verification status of the feature indicating whether the first text describes a concept having the first feature.

85. The computer readable medium of claim 61, wherein (C) further comprises receiving a second indication by the user indicating a verification status of the first data.

86. The computer readable medium of claim 61, wherein (F) comprises storing the record of the verification status of the first coding in the document.

87. The computer readable medium of claim 86, wherein (E) comprises storing the record in the first coding in the document.

88. The computer readable medium of claim 61, wherein (D) comprises determining whether the first data represents a concept having the first feature.