IP Library Granted Patent US 10,061,637
Granted Patent B1
US 10,061,637 · App. 15/410,623 · Granted Aug 28, 2018

System, method, and computer program for automatic root cause analysis

Inventors: Dan Halbersberg (Tel Aviv, IL); Vivi Miranda (Raanana, IL); Eitan Gal (Tel-Aviv, IL)
Assignee: AMDOCS DEVELOPMENT LIMITED
G06F11/079G06F11/0751G06F11/0787
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,061,637
App. No.
15/410,623
Granted
Aug 28, 2018
Kind
B1
Abstract

A system, method, and computer program product are provided for automatic root cause analysis. In operation, a root cause analysis system identifies at least one event associated with one or more records for which to perform a root cause analysis. The root cause analysis system performs a root cause analysis of the event by automatically generating a decision tree based on all records in the current time-window such that each leaf in the decision tree represents the probabilities for class labels of a target variable and each branch in the decision tree represents a feature that leads to a corresponding class label probability. The root cause analysis system automatically generates the decision tree by automatically selecting at each step the feature that maximizes information gain based on a current subset of data. The root cause analysis system then classifies which conditioned feature is a causal factor and which is a root cause of the event by using a conditional entropy equation on each branch leading to the tree leaf. The root cause analysis is repeatedly performed on sequential time-window sets of records gathered, per a sufficiently small time window for near-real-time root cause detection, yet sufficiently large records set for statistical significance.

Claims (32)

1. A method, comprising:

identifying, by a root cause analysis system, at least one event associated with one or more records for which to perform a root cause analysis; and

performing, by the root cause analysis system, a root cause analysis of the at least one event by automatically generating a decision tree based on all records in a current time-window;

wherein each leaf in the decision tree represents probabilities for class labels of a target variable and each branch in the decision tree represents a feature that leads to a corresponding class label;

wherein automatically generating the decision tree includes automatically selecting, at each step, the feature that maximizes information gain based on a current subset of data and classifying which conditioned feature along each path is a causal factor and which is a root cause by using a conditional entropy equation.

2. The method of claim 1 , wherein the at least one event includes a defect.

3. The method of claim 1 , wherein the at least one event includes a fault.

4. The method of claim 1 , wherein the at least one event is associated with customer churn.

5. The method of claim 1 , wherein the at least one event is associated with process quality assurance and optimization.

6. The method of claim 1 , wherein the at least one event is associated with a failure in order activation.

7. The method of claim 1 , wherein the one or more records include call detail records (CDRs).

8. The method of claim 1 , wherein the current time window may be in seconds, minutes, or hours.

9. A computer program product embodied on a non-transitory computer readable medium, comprising computer code for:

identifying, by a root cause analysis system, at least one event associated with one or more records for which to perform a root cause analysis; and

performing, by the root cause analysis system, a root cause analysis of the at least one event by automatically generating a decision tree based on all records in a current time-window;

wherein each leaf in the decision tree represents probabilities for class labels of a target variable and each branch in the decision tree represents a feature that leads to a corresponding class label;

wherein automatically generating the decision tree includes automatically selecting, at each step, the feature that maximizes information gain based on a current subset of data and classifying which conditioned feature along each path is a causal factor and which is a root cause by using a conditional entropy equation.

10. The computer program product of claim 9 , wherein the at least one event includes a defect.

11. The computer program product of claim 9 , wherein the at least one event includes a fault.

12. The computer program product of claim 9 , wherein the at least one event is associated with customer churn.

13. The computer program product of claim 9 , wherein the at least one event is associated with process quality assurance and optimization.

14. The computer program product of claim 9 , wherein the at least one event is associated with a failure in order activation.

15. The computer program product of claim 9 , wherein the one or more records include call detail records (CDRs).

16. The computer program product of claim 9 , wherein the current time window may be in seconds, minutes, or hours.

17. A root cause analysis system, comprising one or more processors operable for:

identifying, by the root cause analysis system, at least one event associated with one or more records for which to perform a root cause analysis; and

performing, by the root cause analysis system, a root cause analysis of the at least one event by automatically generating a decision tree based on all records in a current time-window;

wherein each leaf in the decision tree represents probabilities for class labels of a target variable and each branch in the decision tree represents a feature that leads to a corresponding class label;

wherein automatically generating the decision tree includes automatically selecting, at each step, the feature that maximizes information gain based on a current subset of data and classifying which conditioned feature along each path is a causal factor and which is a root cause by using a conditional entropy equation.

18. The system of claim 17 , wherein the at least one event includes a defect.

19. The system of claim 17 , wherein the at least one event includes a fault.

20. The system of claim 17 , wherein the at least one event is associated with customer churn.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 16, 2018
From: HALBERSBERG, DAN; MIRANDA, VIVI; GAL, EITAN
To: AMDOCS DEVELOPMENT LIMITED
Reel/Frame 044630/0994 →
Cited By (12)
US 51,007 US 12,194,849 US 12,246,594 US 12,280,663 US 12,286,011 US 12,287,217 US 12,320,657 US 12,498,234 US 12,516,946 US 12,566,074 US 12,566,658 US 12,578,199