Claims:WE CLAIM

1. A method of 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 even parameters based on at least one of a plurality of analytics rules stored in an analytics rule database; 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 performing machine learning on the uniform time zone diagnostic log and the QoS metrics for incremental learning and training.
8. The method of claim 7 further comprising updating the analytics rule database with new analytics rule in response to performing the machine learning.
9. 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.
10. A fault detection device for detecting and analyzing faults in a video conferencing system, the fault detection device comprises:
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 even parameters based on at least one of a plurality of analytics rules stored in an analytics rule database; and
perform at least one predefined action based on a result of the processing.
11.The fault detection device of claim 10, 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.
12. The fault detection device of claim 10, wherein the QoS metrics comprises at least one of a video QoS, an audio QoS, or a network QoS.
13. The fault detection device of claim 12, 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.
14. The fault detection device of claim 10, 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.
15. The fault detection device of claim 10, 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.
16. The fault detection device of claim 10, wherein the processor instructions further cause the processor to perform machine learning on the uniform time zone diagnostic log and the QoS metrics for incremental learning and training.
17. The fault detection device of claim 16, wherein the processor instructions further cause the processor to update the analytics rule database with new analytics rule in response to performing the machine learning.
18. The fault detection device of claim 10, 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.

Dated this 30th day of March 2017

Swetha SN
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
This disclosure relates generally to video conferencing and more particularly to a method and fault detection device for automatic fault detection and analysis in video conferencing systems.