IP Library Granted Patent US 12,332,734
Granted Patent B2
US 12,332,734 · App. 18/359,350 · Granted Jun 17, 2025

Disentangled graph learning for incremental causal discovery and root cause analysis

Inventors: Zhengzhang Chen (Princeton Junction, NJ); Haifeng Chen (West Windsor, NJ); Liang Tong (Lawrenceville, NJ); Dongjie Wang (Orlando, FL)
Assignee: NEC Corporation
G06F11/079G06F11/0709G06F11/076G06F11/3447
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 12,332,734
App. No.
18/359,350
Granted
Jun 17, 2025
Kind
B2
Abstract

A computer-implemented method for locating root causes is provided. The method includes detecting a trigger point from entity metrics data and key performance indicator (KPI) data, generating a learned causal graph by fusing a state-invariant causal graph with a state-dependent causal graph, and locating the root causes by employing a random walk-based technique to estimate a probability score for each of the entity metrics data by starting from a KPI node.

Claims (31)

1. A computer-implemented method for locating root causes, the method comprising:

detecting a trigger point from entity metrics data and key performance indicator (KPI) data;

generating a learned causal graph by fusing a state-invariant causal graph with a state-dependent causal graph; and

locating the root causes by employing a random walk-based technique to estimate a probability score for each of the entity metrics data by starting from a KPI node.

2. The computer-implemented method of claim 1 , wherein the trigger point detection involves constructing an initial system state space by using a time-lagged trajectory matrix.

3. The computer-implemented method of claim 2 , wherein the time-lagged trajectory matrix leverages non-linear kernel-based matrix decomposition to learn a robust subspace.

4. The computer-implemented method of claim 1 , wherein a disentangle graph learning-based incremental causal discovery framework is employed to generate the learned causal graph.

5. The computer-implemented method of claim 1 , wherein a prediction layer is used to predict future time-series data on the learned causal graph.

6. The computer-implemented method of claim 1 , wherein, when the learned causal graph and a root cause list converge, a root causes report for system recovery is generated.

7. The computer-implemented method of claim 1 , wherein the learned causal graph is input into a root cause analysis algorithm to output top pods as the root causes of system failures.

8. A computer program product for locating root causes, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

detecting a trigger point from entity metrics data and key performance indicator (KPI) data;

generating a learned causal graph by fusing a state-invariant causal graph with a state-dependent causal graph; and

locating the root causes by employing a random walk-based technique to estimate a probability score for each of the entity metrics data by starting from a KPI node.

9. The computer program product of claim 8 , wherein the trigger point detection involves constructing an initial system state space by using a time-lagged trajectory matrix.

10. The computer program product of claim 9 , wherein the time-lagged trajectory matrix leverages non-linear kernel-based matrix decomposition to learn a robust subspace.

11. The computer program product of claim 8 , wherein a disentangle graph learning-based incremental causal discovery framework is employed to generate the learned causal graph.

12. The computer program product of claim 8 , wherein a prediction layer is used to predict future time-series data on the learned causal graph.

13. The computer program product of claim 8 , wherein, when the learned causal graph and a root cause list converge, a root causes report for system recovery is generated.

14. The computer program product of claim 8 , wherein the learned causal graph is input into a root cause analysis algorithm to output top pods as the root causes of system failures.

15. A computer processing system for locating root causes, comprising:

a memory device for storing program code; and

a processor device, operatively coupled to the memory device, for running the program code to:

detect a trigger point from entity metrics data and key performance indicator (KPI) data;

generate a learned causal graph by fusing a state-invariant causal graph with a state-dependent causal graph; and

locate the root causes by employing a random walk-based technique to estimate a probability score for each of the entity metrics data by starting from a KPI node.

16. The computer processing system of claim 15 , wherein the trigger point detection involves constructing an initial system state space by using a time-lagged trajectory matrix.

17. The computer processing system of claim 16 , wherein the time-lagged trajectory matrix leverages non-linear kernel-based matrix decomposition to learn a robust subspace.

18. The computer processing system of claim 15 , wherein a disentangle graph learning-based incremental causal discovery framework is employed to generate the learned causal graph.

19. The computer processing system of claim 15 , wherein a prediction layer is used to predict future time-series data on the learned causal graph.

20. The computer processing system of claim 15 , wherein, when the learned causal graph and a root cause list converge, a root causes report for system recovery is generated.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 13, 2025
From: NEC LABORATORIES AMERICA, INC.
To: NEC CORPORATION
Reel/Frame 071095/0825 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 26, 2023
From: CHEN, ZHENGZHANG; CHEN, HAIFENG; TONG, LIANG; WANG, DONGJIE
To: NEC LABORATORIES AMERICA, INC.
Reel/Frame 064390/0146 →
Continuity (3)
Provisional Application 63442155 · Jan 31, 2023
Provisional Application 63397955 · Aug 15, 2022
Related Publication 20240061740A1 · Feb 22, 2024
References Cited (10)
US 20220076135A1 · Chen et al. · 2022 [cited by applicant]
US 20220382614A1 · Chen et al. · 2022 [cited by applicant]
US 20230069074A1 · Chen et al. · 2023 [cited by applicant]
Ikram et al., “Root cause analysis of failures in microservices through causal discovery”, 2022, Advances in Neural Information Processing Systems, 35, pp. 31158-31170. (Year: 2022). [cited by examiner]
Wang et al., “Incremental causal graph learning for online root cause analysis”, Aug. 6-10, 2023, Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining (pp. 2269-2278). (Year: 2023). [cited by examiner]
Li, H., Wang, X., Zhang, Z., Yuan, Z., Li, H., & Zhu, W. (Dec. 6, 2021). Disentangled contrastive learning on graphs. Advances in Neural Information Processing Systems, 34, 21872-21884. [cited by applicant]
Wang, D., Chen, Z., Ni, J., Tong, L., Wang, Z., Fu, Y., & Chen, H. (Feb. 3, 2023). Hierarchical graph neural networks for causal discovery and root cause localization. arXiv preprint arXiv:2302.01987. [cited by applicant]
Cheng, W., Zhang, K., Chen, H., Jiang, G., Chen, Z., & Wang, W. (Aug. 13, 2016). Ranking causal anomalies via temporal and dynamical analysis on vanishing correlations. In Proceedings of the 22nd ACM SIGKDD Internationa… [cited by applicant]
Luo, C., Chen, Z., Tang, L. A., Shrivastava, A., Li, Z., Chen, H., & Ye, J. (Jul. 19, 2018). TINET: learning invariant networks via knowledge transfer. In Proceedings of the 24th ACM SIGKDD International Conference on K… [cited by applicant]
Li, Y., Chen, Z., Zha, D., Du, M., Ni, J., Zhang, D., . . . & Hu, X. (Aug. 14, 2022). Towards learning disentangled representations for time series. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discover… [cited by applicant]