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

• US 5,950,194 A
• Filed: 08/31/1998
• Issued: 09/07/1999
• 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): Lintz, Paul R.
• Assistant Examiner(s): Alam, Hosain T.
• Application Number:
  US09/144,591
• Time in Patent Office: 372 Days
• Field of Search: 707/1-6, 707/104, 704/9, 704/246, 704/251, 704/257, 704/231, 704/270, 345/329, 345/338, 345/339, 345/348
• US Class Current: 704/251
• 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 computing system used during a proceeding in which real-time transcript of spoken words is generated, said computing system comprising:

a screen;

a processing circuit communicatively coupled to said screen;

said processing circuit producing in real-time an index that corresponds to the spoken words from real-time transcript as it is generated; and

said processing circuit using the index to support real-time searching.

2. The computing system of claim 1 wherein said processing circuit causes the display on said screen of an indication of a number of hits in response to a search request made during generation of the real-time transcript.

3. The computing system of claim 1 wherein said processing circuit directs the display on said screen of text for a non-searching reason, and further comprising a user interface for permitting an attorney to manually select at least a portion of the text displayed for the non-searching reason and to initiate a search by said processing circuit of the real-time transcript generated using the selected text.

4. The computing system of claim 1 wherein the real-time searching gives higher priority to words of low occurrence.

5. The computing system of claim 1 wherein the real-time searching screens words of high occurrence.

6. The computing system of claim 1 further comprising:

a transcription system that generates the real-time transcript;

an attorney terminal communicatively coupled to the transcription system to receive the real-time transcript as it is generated, said attorney terminal comprising the screen, the processing circuit, and a user interface that accepts a search request;

said processing circuit responding to the search request during generation of the real-time transcript by referencing the index;

said processing circuit utilizing the referencing of the index to identify a portion of the real-time transcript; and

said processing circuit directing the display on said screen of the identified portion of the real-time transcript.

7. The computing system of claim 6 wherein said processing circuit directs display on said screen of an indication of a number of hits determined from the referencing of the index.

8. A computing system used during a proceeding in which a transcript representative of spoken words is generated in real-time, said computing system comprising:

a transcription system that generates transcript in real time;

an attorney terminal communicatively coupled to the transcription system to receive the transcript, said attorney terminal comprising a screen, a processing circuit, and a user interface that accepts a first search request during generation of the transcript in real-time; and

said processing circuit directing, during generation of the transcript in real-time, display on said screen of at least a portion of the transcript corresponding to results of the first search request.

9. The computing system of claim 8 wherein said processing circuit generates an index that corresponds to the spoken words of the transcript in real-time.

10. The computing system of claim 9 wherein said processing circuit utilizes the index to identify an indication of a number of hits prior to displaying the at least portion of the transcript corresponding to the results of the first search request.

11. The computing system of claim 8 wherein said processing circuit directs the display on said screen of text for a non-searching reason, and said user interface for permitting an attorney to manually select at least a portion of the text displayed for the non-searching reason as a second search request.

12. A method performed by a computing system during a transcription proceeding, the method comprising:

converting representations of spoken words to a textual format in real time;

adding occurrence indications for at least a portion of the spoken words in the textual format to an index in real-time; and

referencing the index to identify at least one of the occurrence indications in performing a search in real-time during the transcription proceeding.

13. The method of claim 12 further comprising displaying on a screen the at least one occurrence indication in response to the search.

14. The method of claim 13 further comprising selectively displaying on the screen, subsequent to the displaying on the screen of the at least one occurrence indication, at least one of the spoken words in the textual format that corresponds to the at least one occurrence indication.

15. The method of claim 12 further comprising treating those of the spoken words in the textual format that occur relatively less frequently with relatively higher significance in performing the search.

16. The method of claim 12 further comprising screening those of the spoken words in the textual format occurring relatively more frequently while performing the search.

17. A method performed by a computing system during a transcription proceeding, the method comprising:

converting representations of a first occurrence of a spoken word to a textual format in real time;

indicating an occurrence of the spoken word in the textual format in an index in real-time;

converting representations of subsequent occurrences of the spoken word to the textual format in real-time;

indicating the subsequent occurrences of the spoken word in the textual format in the index in real-time.

18. The method of claim 17 further comprising using the index in performing a search during generation of the transcript in real-time.

19. The method of claim 18 further comprising displaying on a screen a number of hits by referencing the index in response to the search.

20. The method of claim 19 further comprising selectively displaying on the screen, subsequent to the displaying of the number of hits, search results.

21. The method of claim 17 further comprising considering a number of occurrences of the spoken word in the textual format in performing a search.