IP Library › Granted Patent US 10,742,799
Granted Patent B2
US 10,742,799 · App. 16/284,066 · Granted Aug 11, 2020

Automated speech-to-text processing and analysis of call data apparatuses, methods and systems

Inventors: Elliott Broidy (Los Angeles, CA); James Sexton (Los Angeles, CA); Christian Wensel (Irvine, CA); Brennan Karrer (Irvine, CA)
Assignee: LEO Technologies, LLC
H04M3/2218G06F16/64G06F16/685G06F16/687G10L15/26
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,742,799
App. No.
16/284,066
Granted
Aug 11, 2020
Kind
B2
Abstract

The present invention discloses a system, apparatus, and method that obtains audio and metadata information from voice calls, generates textual transcripts from those calls, and makes the resulting data searchable via a user interface. The system converts audio data from one or more sources (such as a telecommunications provider) into searchable usable text transcripts. One use of which is law enforcement and intelligence work. Another use relates to call centers to improve quality and track customer service history. Searches can be performed for callers, callees, keywords, and/or other information in calls across the system. The system can also generate automatic alerts based on callers, callees, keywords, phone numbers, and/or other information. Further the system generates and provides analytic information on the use of the phone system, the semantic content of the calls, and the connections between callers and phone numbers called, which can aid analysts in detecting patterns of behavior, and in looking for patterns of equipment use or failure.

Claims (82)

1. A method of providing a user interface for accessing information related to telephone calls initiated from and/or received at a correctional facility, comprising:

receiving a plurality of audio files corresponding to a plurality of telephone calls from one or more telephones at said correctional facility;

translating each audio file into a transcript that is text-searchable;

associating metadata with each transcript, said metadata including an ID that identifies a person at the correctional facility, a phone number associated with a third party, and a call duration;

storing each of the plurality transcripts and associated metadata in a database;

providing said user interface on a display of a computer that has access to said database, said user interface displaying a call list of calls, each call in the call list having access to associated metadata; and

displaying a side-by-side transcript of a conversation between the person and the third party of the call, and associated metadata.

2. The method of claim 1 , wherein said receiving comprises receiving said plurality of audio files and associated metadata corresponding to said plurality of telephone calls from said one or more telephones at said correctional facility.

3. The method of claim 1 , further comprising:

recording said plurality of telephone calls from said one or more telephones at said correctional facility; and

creating said audio file for each of said plurality of telephone calls.

4. The method of claim 1 , wherein said metadata further includes a call time.

5. The method of claim 1 , wherein said step of providing said user interface further comprises providing a search field for receiving one or more search terms and displays said call list based at least in part on said one or more search terms.

6. The method of claim 1 , wherein said step of providing said user interface further comprises displaying a transcript of a call and associated metadata.

7. The method of claim 6 , wherein said step of providing said user interface further comprises displaying a link to an audio file of the transcript and user controls for fast forwarding or rewinding through the audio file, said transcript highlighting text corresponding to the audio file being played back.

8. The method of claim 1 , wherein said step of providing said user interface further comprises displaying an audio bar for playing back the audio corresponding to the transcript.

9. The method of claim 1 , wherein said correctional facility comprises one of a jail, prison, and detention center.

10. The method of claim 1 further comprising applying data analytics to said database, wherein information related to said data analytics is accessible via said user interface.

11. The method of claim 1 further comprising:

accessing the database to obtain said metadata from a plurality of telephones at said correctional facility;

adding the total number of telephone calls from the plurality of telephones;

storing said total number of telephone calls in one or more entries in said database; and

displaying on the user interface said total number of telephone calls.

12. The method of claim 11 wherein said displaying comprises displaying on the user interface said total number of telephone calls grouped by one or both of location and time.

13. The method of claim 11 further comprising:

storing said total number of telephone calls in one or more entries in said database.

14. The method of claim 11 further comprising:

adding the duration of the telephone calls from the plurality of telephones;

storing said total duration in one or more entries in said database; and

displaying on the user interface said total duration.

15. The method of claim 14 wherein said displaying on the user interface said total duration comprises displaying on the user interface said total duration grouped by one or both of location and time.

16. The method of claim 14 further comprising:

storing said total duration in one or more entries in said database.

17. The method of claim 1 further comprising:

accessing the database to obtain said metadata from a plurality of telephones at said facility;

adding the total number of telephone calls by each person at said correctional facility; and

displaying on the user interface said total number of telephone calls for one or more selected persons.

18. The method of claim 1 further comprising:

storing a total number of telephone calls by each person in said database.

19. The method of claim 18 further comprising:

adding the total duration of telephone calls by each person at said correctional facility; and

displaying on the user interface said total duration of telephone calls for one or more selected persons.

20. The method of claim 19 further comprising:

displaying on the user interface the phone number(s) called by one or more selected persons.

21. The method of claim 1 further comprising:

creating an index of words from each transcript of a selected person at the correctional facility;

storing said index of words in said database associated with said selected person;

updating said index for each new transcript of said selected person;

providing access to said index on said user interface to allow searching of a particular word or words; and

displaying the particular word or words on said user interface.

22. The method of claim 21 further comprising:

generating an alert when said particular word or words match one or more predefined words.

23. The method of claim 21 further comprising:

detecting a new word from said one or more transcripts;

for each said new word detected, updating a lexicon in said database with one or both of said new word and a synonym of said new word.

24. The method of claim 1 further comprising:

detecting whether said phone numbers from said plurality of metadata matches a phone number of witness or victim;

providing an alert in response to said detecting.

25. An Apparatus for providing a user interface for accessing information related to telephone calls at a correctional facility, comprising:

a display unit;

a memory including one or more instructions; and

a processor coupled to said display and memory, said processor executing said one or more instructions to:

access a database containing a plurality of transcripts and associated metadata, each transcript and associated metadata based on an audio file of a telephone call from a telephone at said correctional facility between a person and a third party; and

cause the display unit to display a user interface for displaying a side-by-side transcript of a conversation between the person and the third party of the call, and associated metadata.

26. A system, comprising:

one or more databases;

a call processing computer having a processor and memory, said processor executing one or more software modules located in said memory to:

receive a plurality of audio files corresponding to a plurality of telephone calls from one or more telephones at a correctional facility;

receive a plurality of transcripts corresponding to the plurality of audio files, each of said plurality of transcripts being text-searchable;

associate metadata with each transcript, said metadata including an ID that identifies a person at the facility and a phone number associated with a third party; and

store each of the plurality transcripts and associated metadata in said one or more databases; and

a computer having a processor, memory, and display unit, said computer having access to said one or more databases, said computer having one or more software modules to provide a user interface to display a side-by-side transcript of a conversation between the person and the third party of the call, and associated metadata on said display unit.

27. The system of claim 26 wherein said call processing computer and said computer are the same computer.

28. The system of claim 26 wherein said call processing computer comprises a plurality of call processing computers each having a processor and memory, said plurality of call processing computers working in concert to execute said one or more software modules to:

receive said plurality of audio files corresponding to said plurality of telephone calls from said one or more telephones at said correctional facility;

receive said plurality of transcripts corresponding to the plurality of audio files, each of said plurality of transcripts being text-searchable;

associate metadata with each transcript, said metadata including said caller ID that identifies said person at the facility and said phone number associated with said third party; and

store each of the plurality transcripts and associated metadata in said one or more databases.

29. The system of claim 26 wherein said processor of said call processing computer executing said one or more software modules to:

record said plurality of telephone calls from said one or more telephone at said;

create said plurality of audio files for each of said plurality of telephone calls; and

provide said plurality of audio files for transcription.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 13, 2020
From: CIRCINUS, LLC
To: LEO TECHNOLOGIES, LLC
Reel/Frame 052651/0467 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 25, 2019
From: BROIDY, ELLIOTT; SEXTON, JAMES; WENSEL, CHRISTIAN; KARRER, BRENNAN
To: CIRCINUS, LLC
Reel/Frame 048422/0901 →
Continuity (2)
Provisional Application 62635774 · Feb 27, 2018
Related Publication 20190268465A1 · Aug 29, 2019
Cited By (1)
US 12,244,762