Down-line transcription system having real-time generation of transcript and searching thereof

• US 6,026,395 A
• Filed: 07/01/1999
• Issued: 02/15/2000
• Est. Priority Date: 03/24/1993
• Status: Expired due to Term

• Current Assignee: Engate LLC
• Original Assignee: Engate, Inc.
• Inventors: Jarvis, Lawrence M., Bennett, James D.
• Primary Examiner(s): Alam, Hosain T.
• Application Number:
  US09/345,910
• Time in Patent Office: 229 Days
• Field of Search: 707/1-4, 707/10, 707/100-102, 704/4-5, 704/7, 704/200, 704/201, 704/270, 345/326
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2428 Query predicate definition using graphical user interfaces, including menus and forms G06F16/2423 takes precedence
• CPC Class Codes: G06F 16/319 Inverted lists
• CPC Class Codes: G06F 16/332 Query formulation
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: H04L 65/1101 Session protocols
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355
• CPC Class Codes: H04L 9/40 Network security protocols
• CPC Class Codes: H04M 11/10 with dictation recording and playback systems
• CPC Class Codes: H04N 7/15 Conference systems
• CPC Class Codes: Y10S 707/917 Text
• CPC Class Codes: Y10S 707/925 Drafting an application
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A context sensitive searching front-end is disclosed for use in a deposition or trial proceeding wherein a computer aided transcription terminal provides real-time transcribed text down-line to attorney terminals. The terminals may thereafter use the transcribed text and any other text currently being displayed to formulate searches with little or no typing interaction required. Other text which may be used as a basis for searching includes communications from other attorney terminals, from artificial intelligence objection messages, and personal notes. Searching may be conducted on natural language or boolean front-ends which provide virtually instant feed-back as to the value of a search formulation before and after any "searching" actually occurs. Graphing of search results, including individual search word contribution, is provided for modification and selection of the documents to be reviewed. Library selection for searching is provided by analyzing the context from which the search originated, and from the actual words selected for searching. A database structure is also disclosed for providing backward referencing into the actual locations of search words without having to search the text files.

Claims

1. A method performed by a computing system during a proceeding in which a transcript representative of spoken words is generated in real-time, the method comprising:

generating, by a transcription system, a transcript in real time;

communicating the transcript to a terminal;

storing the transcript;

accepting, by a user interface at the terminal during generation of the transcript, a first search request;

identifying, by the terminal, at least a portion of the stored transcript corresponding to the first search request; and

displaying, by the terminal during generation of the transcript, the at least a portion of the transcript identified.

2. The method of claim 1 further comprising generating an index that corresponds to the spoken words of the transcript in real-time.

3. The method of claim 2 further comprising utilizing the index to identify an indication of a number of hits prior to the displaying the at least a portion of the transcript identified.

4. The method of claim 1 further comprising displaying at the terminal the text for viewing in real time and accepting by the user interface a selection of at least a portion of the displayed text as a second search request.

5. The method claim 1 further comprising screening words of high occurrence during the identifying.

6. The method claim 1 further comprising giving higher priority to words of low occurrence during the identifying.

7. A method performed by a computing system during a proceeding in which a transcript representative of spoken words is generated in real-time, the method comprising:

generating a transcript in real time;

storing the transcript;

accepting, during generation of the transcript, a user input representative of a first search request;

identifying at least a portion of the stored transcript corresponding to the first search request; and

displaying, during generation of the transcript, the at least a portion of the transcript identified.

8. The method of claim 7 further comprising generating an index that corresponds to the spoken words of the transcript in real-time.

9. The method of claim 8 further comprising utilizing the index to identify an indication of a number of hits prior to the displaying the at least a portion of the transcript identified.

10. The method of claim 7 further comprising displaying the text for viewing in real time and accepting a user input selecting at least a portion of the displayed text as a second search request.

11. The method claim 7 further comprising screening words of high occurrence during the identifying.

12. The method claim 7 further comprising giving higher priority to words of low occurrence during the identifying.

13. A method performed by a computing system during a proceeding in which a transcript representative of spoken words is generated in real-time, the method comprising:

generating a transcript in real time;

storing the transcript;

accepting, during generation of the transcript, a user input representative of a first search request; and

displaying, during generation of the transcript and after access the user input, at least a portion of the transcript corresponding to results of the first search request.

14. The method of claim 13 further comprising generating an index that corresponds to the spoken words of the transcript in real-time.

15. The method of claim 14 further comprising utilizing the index to identify an indication of a number of hits prior to the displaying the at least a portion of the transcript corresponding to results of the first search request.

16. The method of claim 13 further comprising displaying the text for viewing in real time and accepting a user input selecting at least a portion of the displayed text as a second search request.

17. The method claim 13 further comprising screening words of high occurrence during searching.

18. The method claim 13 further comprising giving higher priority to words of low occurrence during searching.