Method and system for optimizing voice recognition and information searching based on talkgroup activities

• US 10,666,808 B2
• Filed: 09/21/2016
• Issued: 05/26/2020
• Est. Priority Date: 09/21/2016
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Motorola Solutions, Inc.
• Inventors: Musik, Marta Tatiana, Kaplita, Grzegorz, Wojcik, Wojciech T.
• Primary Examiner(s): Trinh, Tan H
• Application Number:
  US16/333,188
• Publication Number:
  US 20190222698A1
• Time in Patent Office: 1,343 Days
• Field of Search: 455518, 455519, 455509, 455458, 370316, 704244, 704231
• CPC Class Codes: G06F 16/638 Presentation of query results
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G10L 15/08 Speech classification or search
• 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
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2044 Group features, e.g. closed user group
• CPC Class Codes: H04M 3/56 Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities video conference systems H04N7/15
• CPC Class Codes: H04W 4/10 Push-to-Talk [PTT] or Push-On-Call services

Abstract

A method and system for optimizing voice recognition and information searching. The method includes determining context data associated with a particular talkgroup (140) that includes a plurality of communications devices (120) and creating a list of talkgroup-specific keywords associated with the context data, the list of talkgroup-specific keywords including a first characteristic for each talkgroup-specific keyword. The method also includes receiving, from a first communications device (120A) of the plurality of communications devices (120), audio data associated with a user of the first communications device (120A) and processing the audio data to generate an initial output term. The method further includes determining a second characteristic of the initial output term and determining whether the first characteristic of a talkgroup-specific keyword from the list of talkgroup-specific keywords matches the second characteristic of the initial output term. The method also includes outputting the keyword when the first characteristic matches the second characteristic.

Claims

1. A method of operating a call controller including an electronic processor for improving voice recognition and information searching within a talkgroup, the method comprising:

determining, using the electronic processor, context data associated with the talkgroup that includes a plurality of communications devices;

creating, using the electronic processor, a list of talkgroup-specific keywords associated with the context data, the list of talkgroup-specific keywords including a first characteristic for each talkgroup-specific keyword;

assigning a rank to each talkgroup-specific keyword in the list of talkgroup-specific keywords based on a type of context data, from which each talkgroup-specific keyword in the list of talkgroup-specific keywords is extracted;

receiving, at the electronic processor from a first communications device of the plurality of communications devices, audio data associated with a user of the first communications device;

processing, using the electronic processor, the audio data to generate an initial output term;

determining, using the electronic processor, a second characteristic of the initial output term;

determining, using the electronic processor, that a first characteristic of a talkgroup-specific keyword from the list of talkgroup-specific keywords matches the second characteristic of the initial output term;

determining, using the electronic processor, that the first characteristic of a second talkgroup-specific keyword from the list of talkgroup-specific keywords matches the second characteristic of the initial output term, the second talkgroup-specific keyword having a higher rank than the talkgroup-specific keyword; and

outputting, using the electronic processor, the second talkgroup-specific keyword.

2. The method of claim 1, wherein the context data associated with the talkgroup includes at least one selected from a group consisting of prior voice communication in the particular talkgroup, prior status updates from a computer-aided dispatcher, presence of equipment in a personal area network of a talkgroup participant, usage of equipment, data from sensors of a talkgroup participant, and one or more locations of the plurality of communications devices.

3. The method of claim 1, further comprising:

determining, using the electronic processor, second context data associated with the talkgroup; and

adjusting the rank for each talkgroup-specific keyword in the list of talkgroup-specific keywords based on the context data and the second context data.

4. The method of claim 1, wherein the audio data includes one selected from a group consisting of a voice command and a search term.

5. A method of operating a call controller including an electronic processor for improving voice recognition and information searching within a talkgroup, the method comprising:

determining, using the electronic processor, context data associated with the talkgroup that includes a plurality of communications devices;

creating, using the electronic processor, a list of talkgroup-specific keywords associated with the context data, the list of talkgroup-specific keywords including a first characteristic for each talkgroup-specific keyword;

receiving, at the electronic processor from a first communications device of the plurality of communications devices, audio data associated with a user of the first communications device;

processing, using the electronic processor, the audio data to generate an initial output term;

determining, using the electronic processor, a second characteristic of the initial output term, wherein determining the second characteristic of the initial output term includes determining, using the electronic processor, a second list of keywords ranked by probability based on natural language processing of the audio data;

determining whether the list of talkgroup-specific keywords includes at least one keyword from the second list of keywords; and

outputting, using the electronic processor, the at least one keyword from the second list of keywords when the list of talkgroup-specific keywords includes the at least one keyword from the second list of keywords.

6. The method of claim 5, wherein the context data associated with the talkgroup includes at least one selected from a group consisting of prior voice communication in the particular talkgroup, prior status updates from a computer-aided dispatcher, presence of equipment in a personal area network of a talkgroup participant, usage of equipment, data from sensors of a talkgroup participant, and one or more locations of the plurality of communications devices.

7. The method of claim 5, wherein the audio data includes one selected from a group consisting of a voice command and a search term.

8. A system for optimizing voice recognition and information searching, comprising:

a plurality of communications devices forming a talkgroup; and

a call controller communicating with the plurality of communications devices forming the talkgroup and including an electronic processor, the electronic processor configured to;

determine context data associated with the talkgroup that includes the plurality of communications devices;

create a list of talkgroup-specific keywords associated with the context data, the list of talkgroup-specific keywords including a first characteristic for each talkgroup-specific keyword;

assign a rank to each talkgroup-specific keyword in the list of talkgroup-specific keywords based on a type of context data, from which each talkgroup-specific keyword in the list of talkgroup-specific keywords is extracted;

receive, from a first communications device of the plurality of communications devices, audio data associated with a user of the first communications device;

process the audio data to generate an initial output term;

determine a second characteristic of the initial output term;

determine that a first characteristic of a talkgroup-specific keyword from the list of talkgroup-specific keywords matches the second characteristic of the initial output term;

determine that the first characteristic of a second talkgroup-specific keyword from the list of talkgroup-specific keywords matches the second characteristic of the initial output term, the second talkgroup-specific keyword having a higher rank than the talkgroup-specific keyword; and

output the second talkgroup-specific keyword.

9. The system of claim 8, wherein the context data associated with the talkgroup includes at least one selected from a group consisting of prior voice communication in the talkgroup, prior status updates from a computer-aided dispatcher, presence of equipment in a personal area network of a talkgroup participant, data from sensors of a talkgroup participant, and one or more locations of the plurality of communications devices.

10. The system of claim 8, wherein the electronic processor is further configured to:

determine second context data from the talkgroup; and

adjusting the rank for each talkgroup-specific keyword in the list of talkgroup-specific keywords based on the context data and the second context data.

11. The system of claim 8, wherein the audio data includes one selected from a group consisting of a voice command and a search term.

12. A system for optimizing voice recognition and information searching, comprising:

a plurality of communications devices forming a talkgroup; and

a call controller communicating with the plurality of communications devices forming the talkgroup and including an electronic processor, the electronic processor configured to;

determine context data associated with the talkgroup that includes the plurality of communications devices;

create a list of talkgroup-specific keywords associated with the context data, the list of talkgroup-specific keywords including a first characteristic for each talkgroup-specific keyword;

receive, from a first communications device of the plurality of communications devices, audio data associated with a user of the first communications device;

process the audio data to generate an initial output term;

determine a second characteristic of the initial output term, wherein determining the second characteristic of the initial output term includes determining a second list of keywords ranked by probability based on natural language processing of the audio data;

determine whether the list of talkgroup-specific keywords includes at least one keyword from the second list of keywords; and

output the at least one keyword from the second list of keywords when the list of talkgroup-specific keywords includes the at least one keyword from the second list of keywords.

13. The system of claim 12, wherein the context data associated with the talkgroup includes at least one selected from a group consisting of prior voice communication in the talkgroup, prior status updates from a computer-aided dispatcher, presence of equipment in a personal area network of a talkgroup participant, data from sensors of a talkgroup participant, and one or more locations of the plurality of communications devices.

14. The system of claim 12, wherein the audio data includes one selected from a group consisting of a voice command and a search term.