Document extension in dictation-based document generation workflow

• US 9,996,510 B2
• Filed: 02/26/2016
• Issued: 06/12/2018
• Est. Priority Date: 06/19/2011
• Status: Active Grant

• Current Assignee: 3M Health Information Systems (3M Company)
• Original Assignee: MModal IP LLC (3M Company)
• Inventors: Koll, Detlef, Fritsch, Juergen, Finke, Michael
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US15/055,069
• Publication Number:
  US 20160179770A1
• Time in Patent Office: 837 Days
• Field of Search: 715201, 715209, 715277, 715817, 715825, 704235, 704 10
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/143 Markup, e.g. Standard Generalized Markup Language [SGML] or Document Type Definition [DTD]
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

An automatic speech recognizer is used to produce a structured document representing the contents of human speech. A best practice is applied to the structured document to produce a conclusion, such as a conclusion that required information is missing from the structured document. Content is inserted into the structured document based on the conclusion, thereby producing a modified document. The inserted content may be obtained by prompting a human user for the content and receiving input representing the content from the human user.

Claims

1. A computer-implemented method performed by at least one computer processor, the method comprising:

(A) applying automatic speech recognition to an audio signal to produce a structured document representing contents of the audio signal;

(B) determining whether the structured document includes an indication of compliance for each of a plurality of best practices to produce a conclusion, the plurality of best practices related to at least one action required to be taken before completion of the structured document, at least one of the plurality of best practices including at least one of a heuristic and a procedure for drawing a conclusion about whether the structured document fails to comply with a standard applicable to the structured document; and

(C) inserting content into the structured document, based on the conclusion, to produce a modified structured document, wherein inserting further comprises;

(C)(1) obtaining the content from a data source without human input; and

(C)(2) inserting the content into the structured document.

2. The method of claim 1, wherein (B) further comprises:

identifying a type of the structured document;

identifying one of the plurality of best practices associated with the identified type; and

determining whether the structured document includes an indication of compliance with the identified one of the plurality of best practices to produce the conclusion.

3. The method of claim 2, further comprising determining whether the structured document includes an indication of compliance with a universal best practice.

4. The method of claim 1, wherein (B) further comprises:

analyzing a data source relating to an event to which the structured document relates; and

identifying the best practice based on the analysis of the data source.

5. The method of claim 1, further comprising producing a conclusion that information is missing from the structured document.

6. The method of claim 1, wherein (C) comprises:

(C)(1) obtaining a version of the content from a data source without human input; and

(C)(2) inserting the version of the content into the structured document with an indication that the version of the content is an estimate of the content.

7. The method of claim 1, wherein (C) comprises:

(C) inserting, into the structured document, an indication that the content is missing.

8. The method of claim 1, wherein (C) comprises:

(C)(1) obtaining the content from a data source without human input; and

(C)(2) inserting the content into the structured document with an indication that the content was automatically generated.

9. The method of claim 8, further comprising inserting, into the structured document, a request for review of the automatically generated content.

10. The method of claim 1, wherein (A) comprises applying automatic speech recognition to a first portion of the audio signal to produce a structured document representing contents of the first portion of the audio signal, during generation of a second portion of the audio signal.

11. A non-transitory computer readable medium having instructions stored thereon, wherein the instructions are executable by at least one computer processor to perform a method, the method comprising:

(A) applying automatic speech recognition to an audio signal to produce a structured document representing contents of the audio signal;

(B) determining whether the structured document includes an indication of compliance for each of a plurality of best practices to produce a conclusion, the plurality of best practices related to at least one action required to be taken before completion of the structured document, at least one of the plurality of best practices including at least one of a heuristic and a procedure for drawing a conclusion about whether the structured document fails to comply with a standard applicable to the structured document; and

(C) inserting content into the structured document, based on the conclusion, to produce a modified structured document, wherein inserting further comprises;

(C)(1) obtaining the content from a data source without human input; and

(C)(2) inserting the content into the structured document.

12. The computer readable medium of claim 11, wherein (B) further comprises:

identifying a type of the structured document;

identifying a best practice associated with the identified type; and

determining whether the structured document includes an indication of compliance with the identified best practice to produce the conclusion.

13. The computer readable medium of claim 12, further comprising determining whether the structured document includes an indication of compliance with a universal best practice.

14. The computer readable medium of claim 11, wherein (B) further comprises:

analyzing a data source relating to an event to which the structured document relates; and

identifying the best practice based on the analysis of the data source.

15. The computer readable medium of claim 11, further comprising producing a conclusion that information is missing from the structured document.

16. The computer readable medium of claim 11, wherein (C) comprises:

(C)(1) obtaining a version of the content from a data source without human input; and

(C)(2) inserting the version of the content into the structured document with an indication that the version of the content is an estimate of the content.

17. The computer readable medium of claim 11, wherein (C) comprises:

(C) inserting, into the structured document, an indication that the content is missing.

18. The computer readable medium of claim 11, wherein (C) comprises:

(C)(1) obtaining the content from a data source without human input; and

(C)(2) inserting the content into the structured document with an indication that the content was automatically generated.

19. The computer readable medium of claim 18, wherein the method further comprises inserting, into the structured document, a request for review of the automatically generated content.

20. The computer readable medium of claim 11, wherein (A) comprises applying automatic speech recognition to a first portion of the audio signal to produce a structured document representing contents of the first portion of the audio signal, during generation of a second portion of the audio signal.