Apparatus and method for queuing jobs in a distributed dictation/transcription system

• US 9,240,185 B2
• Filed: 04/01/2013
• Issued: 01/19/2016
• Est. Priority Date: 12/21/2007
• Status: Active Grant

• Current Assignee: nVoq, Inc.
• Original Assignee: nVoq, Inc.
• Inventors: Boes, Kirstin, Riggs, Curtis, Ford, Jon
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US13/854,850
• Publication Number:
  US 20140067389A1
• Time in Patent Office: 1,023 Days
• Field of Search: 704/235
• US Class Current: 1/1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/285 Memory allocation or algorithm optimisation to reduce hardware requirements
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A distributed dictation/transcription system is provided. The system provides a client station, dictation manager, and dictation server connected such that the dictation manager can select a dictation server to transcribe audio from the client station. The dictation manager has a data port to at least receive and transmit audio, and receive and transmit data or text. A job queue at the dictation manager holds the audio to be provided to the dictation servers. When the dictation manager identifies an available dictation server, the dictation manager reviews all jobs in the queue. If a job in the queue has a user profile that has been previously uploaded to the available dictation server, the dictation manager transmits the audio to the dictation server.

Claims

1. A dictation manager adapted to have a connection to at least one client station and at least one dictation server where the dictation manager, comprising:

at least one data port to receive audio signals from a client station and to transmit the received audio signals to a dictation server, to receive textual data from the dictation server where the textual data comprises data from the audio signal transformed into textual data by the dictation server;

a dictation server selector to identify an available dictation server to which the dictation manager can transmit the received audio signal;

at least one memory containing a user profile and data regarding whether a user profile has been loaded to the available dictation server;

a job queue to store a plurality of audio files waiting to be transcribed by the dictation server;

wherein when the dictation server selector identifies the available dictation server, the dictation server determines if the user profile loaded to the available dictation server matches any of the user profiles associated with the audio files waiting to be transcribed in the job queue; and

wherein if it is determined that an audio file in the job queue has the same user profile as the user profile loaded to the available dictation server, the dictation manager sends the audio file to the dictation server with the same user profile.

2. The dictation manager of claim 1 wherein the dictation manager advances the audio file with the matching user profile in the job queue over at least one audio file that has been pending longer than the audio file with the matching user profile.

3. The dictation manager of claim 1 wherein the dictation manager determines whether another of the audio files in the job queue has a higher priority than the audio file with matching user profile and advances the audio file with the higher priority over the audio file with the matching user profile.

4. The dictation manager of claim 3 wherein audio files pending in the job queue over a predetermined length of time have a higher priority than the audio file with the matching user profile.

5. The dictation manager of claim 3 wherein the priority is set by an administrator.

6. A method of queuing audio files in a processor that are to be transmitted to a dictation server for transcription by the dictation server to a textual file, the method performed using at least one processor associated with a dictation manager, the method comprising the steps of:

receiving at least one audio file generated by a user at a client station;

storing the at least one audio file in a job queue;

identifying at least one audio file user profile stored in a memory of the dictation manager associated with the user of the received audio signal;

identifying at least one available dictation server;

determining whether the at least one available dictation server has a loaded user profile and whether the at least one audio file user profile matches the loaded user profile; and

transmitting the at least one audio file with the matching user profile in the job queue to the available dictation server if the loaded user profile matches the at least one audio file user profile.

7. The method of claim 6 wherein if none of the at least one audio file user profiles match the loaded user profile, identify a next audio file in the job queue and transmit a new user profile and the next audio file to the available dictation server.

8. The method of claim 6 wherein prior to transmitting the at least one audio file with the matching user profile in the job queue to the available dictation server if the loaded user profile matches the at least one audio file user profile, determining whether another audio file in the job queue has a higher priority than the audio file with the matching user profile.

9. The method of claim 8 wherein the another audio file with the higher priority is transmitted to the available dictation server.

10. The method of claim 8 wherein the higher priority for the another audio file is determined based on a length of time the another audio file has been pending.

11. The method of claim 8 wherein the higher priority for the another audio file is set by an administrator.