Method and fault detection device for automatic fault detection and analysis in video conferencing systems

Patent metadata

Field	Value
Publication number	US-9977707-B1
Application number	US-201715474087-A
Country	US
Kind code	B1
Filing date	Mar 30, 2017
Priority date	Mar 30, 2017
Publication date	May 22, 2018
Grant date	May 22, 2018

Abstract

This disclosure relates to a method and device for detecting and analyzing faults in video conferencing systems. The method includes extracting a diagnostic log that includes unstructured textual information for at least one video conference session from a video conferencing system. The method further includes converting the diagnostic log into a uniform time zone diagnostic log that includes structured textual information. The method includes collecting Quality of Service (QoS) metrics associated with the at least one video conference session and event parameters associated with at least one live event within the at least one video conference session. The method includes processing the uniform time zone diagnostic log, the QoS metrics, and the event parameters based on at least one of a plurality of analytics rules stored in an analytics rule database. The method further includes performing at least one predefined action based on a result of the processing.

First claim

What is claimed is:

1. A method for detecting and analyzing faults in video conferencing systems, the method comprising:
extracting, by a fault detection device, a diagnostic log for at least one video conference session from a video conferencing system, wherein the diagnostic log comprises unstructured textual information;
converting, by the fault detection device, the diagnostic log into a uniform time zone diagnostic log comprising structured textual information;
collecting, by the fault detection device, Quality of Service (QoS) metrics associated with the at least one video conference session and event parameters associated with at least one live event within the at least one video conference session;
processing, by the fault detection device, the uniform time zone diagnostic log, the QoS metrics, and the event parameters based on at least one of a plurality of analytics rules stored in an analytics rule database, wherein the plurality of analytics rules in the analytics rule database are created based on machine learning performed on the uniform time zone diagnostic log, the QoS metrics, and the event parameters; and
performing, by the fault detection device, at least one predefined action based on a result of the processing.

2. The method of claim 1 , wherein the diagnostic log is converted into the uniform time zone diagnostic log based on at least one of logging time of each participant, time zone of the video conferencing system, time zone of each participant, or relevant day light savings, and wherein the uniform time zone diagnostic log comprises a plurality of fields comprising at least one of a severity classification of error messages, time stamp of each error message, or actual verbose description of an error message or an event.

3. The method of claim 1 , wherein the QoS metrics comprises at least one of a video QoS, an audio QoS, or a network QoS.

4. The method of claim 3 , wherein the video QoS comprises at least one of frame rates, video freeze, or video blackouts, the audio QoS comprises at least one of audio bitrate, audio artifacts, or silence detection, and the network QoS comprises at least one of network bandwidth, packet latency, or packet loss.

5. The method of claim 1 , wherein the event parameters comprise at least one of screen co-ordinates of a video freeze, a duration of the video freeze, a duration of an audio freeze, a duration of video quality deterioration, and a duration of audio quality deterioration.

6. The method of claim 1 , wherein the at least one predefined action comprises at least one of: generating key performance indicators associated with the at least one video conference session, generating an alert or warning, or generating a summary report for the at least one video conference session, or sending a notification.

7. The method of claim 1 further comprising updating one or more analytics rules of the plurality of analytics rules stored in the analytics rule database in response to the performed machine learning.

8. The method of claim 1 further comprising creating the analytics rule database comprising the plurality of analytics rules based on analysis of at least one historical video conference session.

9. A fault detection device comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
extract a diagnostic log for at least one video conference session from a video conferencing system, wherein the diagnostic log comprises unstructured textual information;
convert the diagnostic log into a uniform time zone diagnostic log comprising structured textual information;
collect Quality of Service (QoS) metrics associated with the at least one video conference session and event parameters associated with at least one live event within the at least one video conference session;
process the uniform time zone diagnostic log, the QoS metrics, and the event parameters based on at least one of a plurality of analytics rules stored in an analytics rule database, wherein the plurality of analytics rules in the analytics rule database are created based on machine learning performed on the uniform time zone diagnostic log, the QoS metrics, and the event parameters; and
perform at least one predefined action based on a result of the processing.

10. The fault detection device of claim 9 , wherein the diagnostic log is converted into the uniform time zone diagnostic log based on at least one of logging time of each participant, time zone of the video conferencing system, time zone of each participant, or relevant day light savings, and wherein the uniform time zone diagnostic log comprises a plurality of fields comprising at least one of a severity classification of error messages, time stamp of each error message, or actual verbose description of an error message or an event.

11. The fault detection device of claim 9 , wherein the QoS metrics comprises at least one of a video QoS, an audio QoS, or a network QoS.

12. The fault detection device of claim 11 , wherein the video QoS comprises at least one of frame rates, video freeze, or video blackouts, the audio QoS comprises at least one of audio bitrate, audio artifacts, or silence detection, and the network QoS comprises at least one of network bandwidth, packet latency, or packet loss.

13. The fault detection device of claim 9 , wherein the event parameters comprise at least one of screen co-ordinates of the video freeze, a duration of the video freeze, a duration of an audio freeze, a duration of video quality deterioration, and a duration of audio quality deterioration.

14. The fault detection device of claim 9 , wherein the at least one predefined action comprises at least one of: generating key performance indicators associated with the at least one video conference session, generating an alert or warning, or generating a summary report for the at least one video conference session, or sending a notification.

15. The fault detection device of claim 9 , wherein the processor instructions further cause the processor to update one or more analytics rules of the plurality of analytics rules stored in the analytics rule database in response to the performed machine learning.

16. The fault detection device of claim 9 , wherein the processor instructions further cause the processor to create the analytics rule database comprising the plurality of analytics rules based on analysis of at least one historical video conference session.

17. A non-transitory computer-readable storage medium having stored thereon, a set of computer-executable instructions causing a computer comprising one or more processors to perform steps comprising:
extracting, by a fault detection device, a diagnostic log for at least one video conference session from a video conferencing system, wherein the diagnostic log comprises unstructured textual information;
converting, by the fault detection device, the diagnostic log into a uniform time zone diagnostic log comprising structured textual information;
collecting, by the fault detection device, Quality of Service (QoS) metrics associated with the at least one video conference session and event parameters associated with at least one live event within the at least one video conference session;
processing, by the fault detection device, the uniform time zone diagnostic log, the QoS metrics, and the event parameters based on at least one of a plurality of analytics rules stored in an analytics rule database, wherein the plurality of analytics rules in the ana

Assignees

• Wipro Ltd

Inventors

• Nagabushanam Sudhakar Getamaneni

Classifications

• H04N7/15

  Conference systems · CPC title

• G06F11/0751

  Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06) · CPC title

• G06F11/0736

  in functional embedded systems, i.e. in a data processing system designed as a combination of hardware and software dedicated to performing a certain function (testing or monitoring of automated control systems G05B23/02) · CPC title

• G06N99/005

  Physics · mapped topic

• G06F11/079 Primary

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title