Identification of anomalies in air traffic control communications

Patent metadata

Field	Value
Publication number	US-11783817-B2
Application number	US-202117333443-A
Country	US
Kind code	B2
Filing date	May 28, 2021
Priority date	May 28, 2021
Publication date	Oct 10, 2023
Grant date	Oct 10, 2023

Abstract

A processor may identify an anomaly in one or more communications. A processor may monitor the one or more communications for an utterance. A processor may perform natural language processing (NLP) on the utterance. A processor may generate an understanding of the utterance using natural language understanding (NLU). A processor may detect the anomaly from the understanding of the utterance. A processor may execute a response, responsive to detecting the anomaly.

First claim

What is claimed is:

1. A method for identifying an anomaly in one or more communications:
monitoring, by a processor, the one or more communications for an utterance;
performing natural language processing (NLP) of the utterance;
generating an understanding of the utterance using natural language understanding (NLU);
obtaining aircraft and engine operating parameters and context information;
identifying a target rule of one or more rules associated with the understanding of the utterance;
comparing a target associated with the target rule to the aircraft and engine operating parameters;
detecting the anomaly based on comparing the target to the one or more aircraft and engine operating parameters and context information; and
executing a response, responsive to detecting the anomaly.

2. The method of claim 1 , wherein detecting the anomaly from the understanding of the utterance includes:
comparing the utterance against one or more established alert rules.

3. The method of claim 2 , wherein one or more alert rules further includes checking at least one scope policy, at least one anomaly policy, and at least one response policy.

4. The method of claim 1 , wherein detecting the anomaly further includes:
determining if a timer exceeds a maximum allotted time; and
identifying an anomaly has occurred in the utterance.

5. The method of claim 1 , wherein detecting the anomaly includes:
determining if a trigger in the utterance has occurred; and
determining if the target associated with the trigger has occurred in the utterance.

6. The method of claim 5 , further including:
determining a confidence score for the trigger; and
determining if the confidence score of the trigger exceeds a minimum threshold.

7. The method of claim 5 , further including:
determining a confidence score for the target; and
determining if the confidence score of the target exceeds a minimum threshold.

8. The method of claim 1 , further comprising:
analyzing the one or more communications;
identifying one or more partial utterances in the one or more communications; and
updating a communication register by replacing each of the one or more partial utterances with an associated full utterance.

9. A system for identifying an anomaly in one or more communications, the system comprising:
a memory; and
a processor in communication with the memory, the processor being configured to perform operations comprising:
monitoring the one or more communications for an utterance;
performing natural language processing (NLP) of the utterance;
generating an understanding of the utterance using natural language understanding (NLU);
obtaining aircraft and engine operating parameters and context information;
identifying a target rule of one or more rules associated with the understanding of the utterance;
comparing a target associated with the target rule to the aircraft and engine operating parameters;
detecting the anomaly based on comparing the target to the one or more aircraft and engine operating parameters and context information; and
executing a response, responsive to detecting the anomaly.

10. The system of claim 9 , wherein detecting the anomaly from the understanding of the utterance includes:
comparing the utterance against one or more established alert rules.

11. The system of claim 10 , wherein one or more alert rules further includes checking at least one scope policy, at least one anomaly policy, and at least one response policy.

12. The system of claim 9 , wherein detecting the anomaly further includes:
determining if a timer exceeds a maximum allotted time; and
identifying an anomaly has occurred in the utterance.

13. The system of claim 9 , wherein detecting the anomaly includes:
determining if a trigger in the utterance has occurred; and
determining if the target associated with the trigger has occurred in the utterance.

14. The system of claim 13 , further including:
determining a confidence score for the trigger; and
determining if the confidence score of the trigger exceeds a minimum threshold.

15. The system of claim 13 , further including:
determining a confidence score for the target; and
determining if the confidence score of the target exceeds a minimum threshold.

16. A computer program product for removing an anomaly in a collection of material, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processors to perform a function, the function comprising:
monitoring the one or more communications for an utterance;
performing natural language processing (NLP) of the utterance;
generating an understanding of the utterance using natural language understanding (NLU);
obtaining aircraft and engine operating parameters and context information;
identifying a target rule of one or more rules associated with the understanding of the utterance;
comparing a target associated with the target rule to the aircraft and engine operating parameters;
detecting the anomaly based on comparing the target to the one or more aircraft and engine operating parameters and context information; and
executing a response, responsive to detecting the anomaly.

17. The computer program product of claim 16 , wherein detecting the anomaly from the understanding of the utterance includes:
comparing the utterance against one or more established alert rules.

18. The computer program product of claim 16 , wherein detecting the anomaly further includes:
determining if a timer exceeds a maximum allotted time; and
identifying an anomaly has occurred in the utterance.

19. The computer program product of claim 16 , wherein detecting the anomaly includes:
determining if a trigger in the utterance has occurred; and
determining if the target associated with the trigger has occurred in the utterance.

20. The computer program product of claim 19 , further including:
determining a confidence score for the trigger; and
determining if the confidence score of the trigger exceeds a minimum threshold.

Assignees

• IBM

Inventors

• Tkaczyk Gregory M J H
• Katz Edward Graham
• Quimby John S

Classifications

• G10L15/1822 Primary

  Parsing for meaning understanding · CPC title

• G10L15/10

  using distance or distortion measures between unknown speech and reference templates · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06F40/279

  Recognition of textual entities · CPC title

• G06F40/295

  Named entity recognition · CPC title