SYNCHRONIZED TRANSCRIPTION RULES HANDLING

• US 20100125450A1
• Filed: 10/27/2009
• Published: 05/20/2010
• Est. Priority Date: 10/27/2008
• Status: Abandoned Application

• Current Assignee: MModal IP LLC (3M Company)
• Original Assignee: Spheris Incorporated (3M Company)
• Inventors: Smith, Doug, Michaelangelo, Nixon, Graham, Dennis, Appley, Paula
• Application Number:
  US12/606,823
• Publication Number:
  US 20100125450A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/226 Validation
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G10L 15/063 Training
• 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

Abstract

Methods, systems, and software are disclosed for providing rule handling functionality in a distributed transcription environment. Some embodiments provide client-server workflow management for providing and supporting distributed transcription services. Other embodiments provide audio-to-text synchronization to support certain transcription functionality. Still other embodiments provide logging functionality to support quality, personnel, billing, and/or other enterprise tasks. And other embodiments provide functionality to support rule generation, editing, validation, and/or execution.

Claims

1. A method for rules handling in a distributed transcription system, the method comprising:

receiving a transcription assignment at a computer-implemented transcription environment, the transcription assignment comprising;

dictation data comprising audio information dictated by an author into a dictation interface, the author being associated with a context designation; and

a transcription rule set being one of a plurality of transcription rule sets stored in a rules data store and generated for application to the dictation data as a function of the context designation;

receiving transcription data at the computer-implemented transcription environment from a transcriptionist via a transcription interface, the transcription data comprising textual representations of corresponding portions of the dictation data, the textual representations being at least partially synchronized with the corresponding portions of the dictation data;

identifying a rule violation by applying the transcription rule set to the transcription data using the computer-implemented transcription environment, the rule violation being associated with a textual representation and substantially synchronized with the corresponding portion of the dictation data; and

displaying an indication of the rule violation to the transcriptionist via the computer-implemented transcription environment.

2. The method of claim 1, further comprising:

receiving an interaction with the computer-implemented transcription environment from the transcriptionist indicating a selection of the rule violation;

in response to receiving the interaction, configuring playback of the audio information from a position associated with the corresponding portion of the dictation data substantially synchronized with the rule violation.

3. The method of claim 1, wherein the transcription assignment is received at the computer-implemented transcription environment from a workflow management server over a communications network, the workflow management server being communicatively coupled with the rules data store and configured to:

receive the dictation data from the author, the author being one of a plurality of authors in communication with the workflow management server over the communications network;

identify the transcription rule set from the rules data store for application to the dictation data;

generate the transcription assignment, such that the transcription assignment comprises the dictation data and the transcription rule set and is formatted for use in the computer-implemented transcription environment;

assign the transcription assignment to the transcriptionist, the transcriptionist being one of a plurality of transcriptionists in communication with the workflow management server over the communications network; and

communicate the transcription assignment over the communications network to the transcriptionist for use in the computer-implemented transcription environment.

4. The method of claim 1, wherein the context designation comprises context tags that indicate a context for the transcription assignment, each context tag being associated with a plurality of transcription rules.

5. The method of claim 4, wherein each context tag indicates at least one of an organization identifier, a site identifier, a location identifier, a work type identifier, an author identifier, an author type identifier, an author role identifier, a work role identifier, a dictation interface identifier, or a transcriptionist identifier.

6. The method of claim 4, wherein:

each context tag is further associated with inheritance rules; and

the transcription rule set is generated for application to the dictation data as a function of the context designation by;

building a rule list comprising the plurality of transcription rules associated with the context tags as a function of the inheritance rules; and

when any of the plurality of transcription rules in the rules list conflicts with any other of the plurality of transcription rules in the rules list, culling the rules list to resolve rule conflicts.

7. The method of claim 4, further comprising:

determining the context designation by identifying the context tags associated with the dictation data, wherein at least some of the context tags are identified by analyzing the dictation data.

8. The method of claim 4, further comprising:

determining the context designation by identifying the context tags associated with the dictation data, wherein at least some of the context tags are associated with prompts provided to the author substantially when the dictation data is dictated by the author.

9. The method of claim 1, wherein receiving transcription data at the computer-implemented transcription environment from the transcriptionist comprises:

playing the audio information comprised by the dictation data from the computer-implemented transcription environment to the transcriptionist;

receiving the transcription data during playback of the audio information, such that at least some of the textual representations are received via the transcription interface substantially as the respective corresponding portions of the dictation data are being played to the transcriptionist.

10. The method of claim 1, further comprising:

providing a transcription template to the transcriptionist configured to receive the transcription data from the transcriptionist via the transcription interface, the transcription template being generated at least according to the set of transcription rules.

11. The method of claim 1, wherein identifying the rule violation by applying the transcription rule set to the transcription data using the computer-implemented transcription environment comprises:

applying the transcription rule set to the transcription data substantially while receiving the transcription data from the transcriptionist via the transcription interface, such that identifying the rule violation occurs substantially in real time while receiving the transcription data.

12. The method of claim 1, further comprising:

receiving an instruction to validate the transcription data,

wherein identifying the rule violation occurs substantially in response to receiving the instruction.

13. The method of claim 1, wherein the set of transcription rules comprises:

an information rule configured to trigger a rule violation as a function of an association between the dictation data and a context tag associated with the information rule, regardless of the transcription data received from the transcriptionist, a triggering of the information rule indicating information relating to a handling instruction associated with the dictation data;

a warning rule configured to trigger a rule violation as a function of applying the warning rule to the transcription data received from the transcriptionist, a triggering of the warning rule indicating a possible error in the transcription data; and

an error rule configured to trigger a rule violation as a function of applying the error rule to the transcription data received from the transcriptionist, a triggering of the error rule indicating a definite error in the transcription data.

14. The method of claim 1, further comprising:

receiving a submission instruction from the transcriptionist at the computer-implemented transcription environment that a transcription product comprising the transcription data received from the transcriptionist is complete; and

validating the transcription product automatically in response to receiving the submission instruction, validating the transcription product comprising identifying the rule violation.

15. The method of claim 14, further comprising:

when validating the transcription product comprises identifying triggering of an error rule indicating a definite error in the transcription data, preventing submission of the transcription product while the rule violation persists.

16. The method of claim 14, further comprising:

substantially upon completion of validating the transcription product, generating a log characterizing performance of at least one of the transcription environment or the transcriptionist.

17. The method of claim 16, further comprising:

receiving the log associated with the transcription assignment at a workflow management server, the log being one of a plurality of logs associated with a plurality of transcription assignments, the workflow management server being configured to adjust a workflow metric as a function of the plurality of logs and to assign transcription assignments to one or more of a plurality of transcriptionists as a function of the workflow metric.

18. The method of claim 1, wherein the transcriptionist is a computer-implemented speech recognition application.

19. A system for rules handling in a distributed transcription system, the system comprising:

a transcription module, configured to;

receive a transcription assignment, the transcription assignment comprising;

dictation data comprising audio information dictated by an author into a dictation interface, the author being associated with a context designation; and

a transcription rule set being one of a plurality of transcription rule sets stored in a rules data store and generated for application to the dictation data as a function of the context designation;

receive transcription data via a computer-implemented transcription environment from a transcriptionist via a transcription interface, the transcription data comprising textual representations of corresponding portions of the dictation data, the textual representations being at least partially synchronized with the corresponding portions of the dictation data; and

generate a draft transcription product comprising the transcription data; and

a validation module, communicatively coupled with the transcription module, and configured to validate the draft transcription product to generate a validated transcription product by;

identifying rule violations by applying the transcription rule set to the transcription data, each rule violation being associated with a textual representation and substantially synchronized with the corresponding portion of the dictation data; and

resolving each rule violation.

20. The system of claim 19, wherein resolving each rule violation comprises:

providing an indication of the rule violation to the transcriptionist; and

receiving a resolution instruction from the transcriptionist at the validation module.

21. The system of claim 20, wherein resolving each rule violation further comprises:

receiving an interaction with the computer-implemented transcription environment from the transcriptionist indicating a selection of the rule violation;

in response to receiving the interaction, configuring playback of the audio information from a position associated with the corresponding portion of the dictation data substantially synchronized with the rule violation.

22. The system of claim 19, wherein the transcription module is communicatively coupled with a workflow management server over a communications network and receives the transcription assignment from the workflow management server.

23. The system of claim 22, wherein the workflow management server is configured to:

receive the dictation data from the author, the author being one of a plurality of authors in communication with the workflow management server over the communications network;

identify the transcription rule set from the rules data store for application to the dictation data;

generate the transcription assignment, such that the transcription assignment comprises the dictation data and the transcription rule set and is formatted for use in the computer-implemented transcription environment;

assign the transcription assignment to the transcriptionist, the transcriptionist being one of a plurality of transcriptionists in communication with the workflow management server over the communications network; and

communicate the transcription assignment over the communications network to the transcriptionist for use in the computer-implemented transcription environment.

24. The system of claim 19, wherein:

the context designation comprises context tags that indicate a context for the transcription assignment, each context tag being associated with a plurality of transcription rules and inheritance rules; and

the transcription rule set is generated for application to the dictation data as a function of the context designation by;

building a rule list comprising the plurality of transcription rules associated with the context tags as a function of the inheritance rules; and

when any of the plurality of transcription rules in the rules list conflicts with any other of the plurality of transcription rules in the rules list, culling the rules list to resolve rule conflicts.

25. The system of claim 19, wherein the transcription module is configured to provide the computer-implemented transcription environment such that receiving transcription data at the computer-implemented transcription environment from the transcriptionist comprises:

playing the audio information comprised by the dictation data from the computer-implemented transcription environment to the transcriptionist; and

receiving the transcription data during playback of the audio information, such that at least some of the textual representations are received via the transcription interface substantially as the respective corresponding portions of the dictation data are being played to the transcriptionist.

26. The system of claim 19, wherein the transcription module is configured to provide a transcription template configured to receive the transcription data from the transcriptionist via the transcription interface, the transcription template being generated at least according to the set of transcription rules.

27. The system of claim 19, wherein the validation module is configured to apply the transcription rule set to the transcription data substantially while the transcription module receives the transcription data from the transcriptionist, such that validating the draft transcription product occurs substantially in real time while receiving the transcription data.

28. The system of claim 19, wherein the validation module is configured to receive an instruction to validate the transcription data, wherein validating the draft transcription product occurs substantially in response to receiving the instruction.

29. The system of claim 19, further comprising:

a delivery module, communicatively coupled with the validation module, and configured to output a final transcription product according to the validated transcription product and according to a formatting scheme associated with the context designation.

30. The system of claim 29, wherein the delivery module is configured to:

determine whether the draft transcription product has been validated to generate the validated transcription product; and

when the draft transcription product has not been validated to generate the validated transcription product, prevent output of the final transcription product.

31. The system of claim 19, further comprising:

a logging module, communicatively coupled with the validation module, and configured to generate a log substantially upon completion of validating the draft transcription product, the log characterizing performance of at least one of the transcription environment or the transcriptionist.

32. A machine-readable medium for rules handling in a transcription environment, the machine-readable medium having instructions stored thereon which, when executed by a machine, cause the machine to perform steps comprising:

receiving a transcription assignment at a computer-implemented transcription environment, the transcription assignment comprising;

dictation data comprising audio information dictated by an author into a dictation interface, the author being associated with a context designation; and

a transcription rule set being one of a plurality of transcription rule sets stored in a rules data store and generated for application to the dictation data as a function of the context designation;

receiving transcription data at the computer-implemented transcription environment from a transcriptionist via a transcription interface, the transcription data comprising textual representations of corresponding portions of the dictation data, the textual representations being at least partially synchronized with the corresponding portions of the dictation data; and

identifying a rule violation by applying the transcription rule set to the transcription data using the computer-implemented transcription environment, the rule violation being associated with a textual representation and substantially synchronized with the corresponding portion of the dictation data.

33. The machine-readable medium of claim 32, the instructions stored thereon, when executed by a machine, causing the machine to perform steps further comprising:

displaying an indication of the rule violation to the transcriptionist via the computer-implemented transcription environment;

receiving an interaction with the computer-implemented transcription environment from the transcriptionist indicating a selection of the rule violation; and

in response to receiving the interaction, configuring playback of the audio information from a position associated with the corresponding portion of the dictation data substantially synchronized with the rule violation.

34. The machine-readable medium of claim 32, wherein the context designation comprises context tags that indicate a context for the transcription assignment, each context tag being associated with a plurality of transcription rules, the transcription rule set being derived from the plurality of transcription rules.

35. The machine-readable medium of claim 34, the instructions stored thereon, when executed by a machine, causing the machine to perform steps further comprising:

deriving the transcription rule set from the plurality of transcription rules by;

building a rule list comprising the plurality of transcription rules associated with the context tags as a function of a set of inheritance rules; and

when any of the plurality of transcription rules in the rules list conflicts with any other of the plurality of transcription rules in the rules list, culling the rules list to resolve rule conflicts.

36. The machine-readable medium of claim 32, the instructions stored thereon, when executed by a machine, causing the machine to perform steps further comprising:

providing a transcription template to the transcriptionist configured to receive the transcription data from the transcriptionist via the transcription interface, the transcription template being generated at least according to the set of transcription rules.

37. The machine-readable medium of claim 32, wherein identifying the rule violation by applying the transcription rule set to the transcription data using the computer-implemented transcription environment comprises:

applying the transcription rule set to the transcription data substantially while receiving the transcription data from the transcriptionist via the transcription interface, such that identifying the rule violation occurs substantially in real time while receiving the transcription data.

38. The machine-readable medium of claim 32, the instructions stored thereon, when executed by a machine, causing the machine to perform steps further comprising:

receiving an instruction to validate the transcription data,

wherein identifying the rule violation occurs substantially in response to receiving the instruction.

39. The machine-readable medium of claim 32, the instructions stored thereon, when executed by a machine, causing the machine to perform steps further comprising:

receiving a submission instruction from the transcriptionist at the computer-implemented transcription environment that a transcription product comprising the transcription data received from the transcriptionist is complete; and

validating the transcription product automatically in response to receiving the submission instruction, validating the transcription product comprising identifying the rule violation.

40. The machine-readable medium of claim 39, the instructions stored thereon, when executed by a machine, causing the machine to perform steps further comprising:

when validating the transcription product comprises identifying triggering of an error rule indicating a definite error in the transcription data, preventing submission of the transcription product while the rule violation persists.