System and method for intelligent troubleshooting of in-service customer experience issues in communication networks

• US 9,026,851 B2
• Filed: 01/29/2013
• Issued: 05/05/2015
• Est. Priority Date: 09/05/2012
• Status: Active Grant

• Current Assignee: Wipro Limited
• Original Assignee: Wipro Limited
• Inventors: Mondal, Subhas Chandra, Ghosh, Sudipta, Nair, Manoj K.
• Primary Examiner(s): Iqbal, Nadeem
• Application Number:
  US13/752,632
• Publication Number:
  US 20140068348A1
• Time in Patent Office: 826 Days
• US Class Current: 714/26
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/10 Services
• CPC Class Codes: H04L 41/0631 using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 43/12 Network monitoring probes

Abstract

The present disclosure relates to methods and systems for improving customer experience through real time troubleshooting in relation to customer experience management. In one embodiment, a proactive customer experience management method is disclosed, comprising: obtaining a performance-indicating alert (PA); identifying relevant alerts from the alert database in absence of possible fault condition from the PA; determining a possible problem condition from the PA and identified relevant alerts; raising trace trigger for gathering relevant trace data; determining specific problem condition and relevant cause, based on gathered trace data and relevant data from PM/FM, CDR, OSS systems; determining appropriate recommendation for resolution of the determined specific problem condition; updating a user interface dashboard using the determination of the root cause of the possible problem and the recommendation for resolution of the possible problem; and updating new knowledge into a knowledge base with problem-context, resolution, relevant adjustments to alerts, thresholds and rules.

Claims

1. A computer-implemented method for proactive customer experience management in a communication network, comprising:

a) obtaining a performance-indicating alert (PA) from at least one probe;

b) identifying relevant alerts from an alert database in absence of possible fault condition from the PA;

c) determining a possible problem condition from the PA and the identified relevant alerts;

d) raising trace trigger for gathering relevant trace data;

e) determining specific problem condition and relevant cause, based on gathered trace data and relevant data from PM/FM, CDR and OSS systems;

f) determining appropriate recommendation for resolution of the determined specific problem condition;

g) recalculating a probe alert threshold value for triggering the performance-indicating probe alert;

h) providing the recalculated probe alert threshold value for modifying a configuration of a performance-indicating probe;

i) updating a user interface dashboard using the determination of a root cause of the possible problem and the recommendation for resolution of the possible problem; and

j) updating new knowledge into a knowledge base with problem-context, resolution, relevant adjustments to alerts, thresholds and rules.

2. The method of claim 1, wherein the relevant alerts are identified from the alert database using a rules engine applying pre-defined rules.

3. The method of claim 1, wherein the possible problem condition is determined using an analytic engine operating on the PA and the identified relevant alerts.

4. The method of claim 1, wherein the trace trigger is configured to trigger gathering probe data through a Probe-Data-Interface for a limited duration specified in the trace trigger.

5. The method of claim 3, wherein the specific problem condition and relevant cause are determined using the analytic engine and information from a historical database.

6. The method of claim 1, wherein the appropriate recommendation for resolution of the determined specific problem condition is retrieved from the knowledge base.

7. The method of claim 1, wherein the performance-indicating probe alert is obtained from at least one of:

an external hardware probe operatively connected at a network interface;

an end-user device;

a service application server; and

a communication network component.

8. The method of claim 1, wherein the possible problem condition includes degradation of an end-user service quality indicator.

9. The method of claim 8, wherein the degradation included in the possible problem condition is a future degradation of the end-user service quality indicator.

10. The method of claim 1, wherein the root cause analysis utilizes historical aggregated performance data to determine the root cause of the possible problem.

11. The method of claim 1, wherein the recalculation utilizes the aggregated performance data and the recommendation for resolution of the root cause of the possible problem.

12. The method of claim 1, further comprising:

updating the knowledge base using the aggregated performance data and the root cause of the possible problem.

13. The method of claim 1, further comprising:

triggering, based on the root cause analysis, the gathering of the trace data via the selective trace trigger.

14. A proactive communication network customer experience management system, comprising:

a hardware processor; and

a memory device operatively connected to the hardware processor and storing instructions executable by the hardware processor for;

a) obtaining a performance-indicating alert (PA) from at least one probe;

b) identifying relevant alerts from a alert database in absence of possible fault condition from the PA;

c) determining a possible problem condition from the PA and the identified relevant alerts;

d) raising trace trigger for gathering relevant trace data;

e) determining specific problem condition and relevant cause, based on gathered trace data and relevant data from PM/FM, CDR and OSS systems;

f) determining appropriate recommendation for resolution of the determined specific problem condition;

g) recalculating a probe alert threshold value for triggering the performance-indicating probe alert;

h) providing the recalculated probe alert threshold value for modifying a configuration of a performance-indicating probe;

i) updating a user interface dashboard using the determination of a root cause of the possible problem and the recommendation for resolution of the possible problem; and

j) updating new knowledge into a knowledge base with problem-context, resolution, relevant adjustments to alerts, thresholds and rules.

15. A non-transitory computer-readable storage medium storing computer-executable instructions for communication network customer experience management, the instructions being executable by a computer for:

a) obtaining a performance-indicating alert (PA) from at least one probe;

b) identifying relevant alerts from a alert database in absence of possible fault condition from the PA;

c) determining a possible problem condition from the PA and the identified relevant alerts;

d) raising trace trigger for gathering relevant trace data;

e) determining specific problem condition and relevant cause, based on gathered trace data and relevant data from PM/FM, CDR and OSS systems;

f) determining appropriate recommendation for resolution of the determined specific problem condition;

g) recalculating a probe alert threshold value for triggering the performance-indicating probe alert;

h) providing the recalculated probe alert threshold value for modifying a configuration of a performance-indicating probe;

i) updating a user interface dashboard using the determination of a root cause of the possible problem and the recommendation for resolution of the possible problem; and

j) updating new knowledge into a knowledge base with problem-context, resolution, relevant adjustments to alerts, thresholds and rules.