Anomaly detection method and device, terminal and storage medium

1. An anomaly detection method, comprising:

generating at least one clustering set of objects based on configuration data and performance indicator data of the objects;

determining an algorithm configuration parameter corresponding to each clustering set based on a preset anomaly detection algorithm and the performance indicator data corresponding to the objects in the clustering set; and

determining, based on the algorithm configuration parameter, abnormal performance indicator data of the objects in the corresponding clustering set, so as to determine abnormal objects based on the abnormal performance indicator data.

2. The method of claim 1 , wherein the objects comprise function modules for constructing a wireless communication network system.

3. The method of claim 1 , wherein the generating at least one clustering set of objects based on configuration data and performance indicator data of the objects comprises:

generating at least one clustering set of the objects based on configuration data, performance indicator data and operation state data of the objects.

4. The method of claim 3 , wherein the operation state data comprises one or more of service quality data, measurement report, call tracing data, signaling tracing data, and user complaint data.

5. The method of claim 3 , wherein the generating at least one clustering set of the objects based on configuration data, performance indicator data and operation state data of the objects comprises:

acquiring the configuration data of the objects, and clustering the objects based on the configuration data to generate a first clustering set of the objects;

acquiring the performance indicator data of the objects, and clustering the objects based on the performance indicator data to generate a second clustering set of the objects;

acquiring the operation state data of the objects, and clustering the objects based on the operation state data to generate a third clustering set of the objects; and

performing logical operations on the first clustering set, the second clustering set and the third clustering set based on a preset rule to obtain at least one clustering set of the objects.

6. The method of claim 1 , wherein the determining an algorithm configuration parameter corresponding to each clustering set based on a preset anomaly detection algorithm and the performance indicator data corresponding to the objects in the clustering set comprises:

training the preset anomaly detection algorithm based on the performance indicator data of the objects in each clustering set to obtain the algorithm configuration parameter corresponding to each clustering set.

7. The method of claim 1 , wherein the determining, based on the algorithm configuration parameter, abnormal performance indicator data of the objects in the corresponding clustering set comprises:

acquiring target performance indicator data corresponding to the objects in the clustering set to be detected;

determining a target algorithm configuration parameter corresponding to the clustering set to be detected; and

performing anomaly detection on the target performance indicator data based on the preset anomaly detection algorithm and the target algorithm configuration parameter, and determining abnormal performance indicator data in the target performance indicator data based on anomaly detection results.

8. The method of claim 1 , further comprising:

after the determining an abnormal object based on the abnormal performance indicator data,

generating, a set of abnormal objects to be determined based on the abnormal objects;

acquiring a logical dependency between the objects in the wireless communication network system, wherein the logical dependency is determined based on the configuration data;

determining a logical causality between the abnormal objects in the set of abnormal objects to be determined based on the logical dependency between the objects; and

adjusting the set of abnormal objects to be determined based on the logical causality to obtain a set of abnormal objects.

9. A device, comprising:

a memory, and one or more processors, wherein the memory is configured to store one or more programs; and

the one or more programs, when executed by the one or more processors, cause the one or more processors to perform an anomaly detection method comprising:

generating at least one clustering set of objects based on configuration data and performance indicator data of the objects;

determining an algorithm configuration parameter corresponding to each clustering set based on a preset anomaly detection algorithm and the performance indicator data corresponding to the objects in the clustering set; and

determining, based on the algorithm configuration parameter, abnormal performance indicator data of the objects in the corresponding clustering set, so as to determine abnormal objects based on the abnormal performance indicator data.

10. The device of claim 9 , wherein the objects comprise function modules for constructing a wireless communication network system.

11. The device of claim 9 , wherein the generating at least one clustering set of objects based on configuration data and performance indicator data of the objects comprises:

generating at least one clustering set of the objects based on configuration data, performance indicator data and operation state data of the objects.

12. The device of claim 11 , wherein the operation state data comprises one or more of service quality data, measurement report, call tracing data, signaling tracing data, and user complaint data.

13. The device of claim 11 , wherein the generating at least one clustering set of the objects based on configuration data, performance indicator data and operation state data of the objects comprises:

acquiring the configuration data of the objects, and clustering the objects based on the configuration data to generate a first clustering set of the objects;

acquiring the performance indicator data of the objects, and clustering the objects based on the performance indicator data to generate a second clustering set of the objects;

acquiring the operation state data of the objects, and clustering the objects based on the operation state data to generate a third clustering set of the objects; and

performing logical operations on the first clustering set, the second clustering set and the third clustering set based on a preset rule to obtain at least one clustering set of the objects.

14. The device of claim 9 , wherein the determining an algorithm configuration parameter corresponding to each clustering set based on a preset anomaly detection algorithm and the performance indicator data corresponding to the objects in the clustering set comprises:

training the preset anomaly detection algorithm based on the performance indicator data of the objects in each clustering set to obtain the algorithm configuration parameter corresponding to each clustering set.

15. The device of claim 9 , wherein the determining, based on the algorithm configuration parameter, abnormal performance indicator data of the objects in the corresponding clustering set comprises:

acquiring target performance indicator data corresponding to the objects in the clustering set to be detected;

determining a target algorithm configuration parameter corresponding to the clustering set to be detected; and

performing anomaly detection on the target performance indicator data based on the preset anomaly detection algorithm and the target algorithm configuration parameter, and determining abnormal performance indicator data in the target performance indicator data based on anomaly detection results.

16. The device of claim 9 , wherein the one or more programs, when executed by the one or more processors, further cause the one or more processors to perform steps of:

after the determining an abnormal object based on the abnormal performance indicator data,

generating, a set of abnormal objects to be determined based on the abnormal objects;

acquiring a logical dependency between the objects in the wireless communication network system, wherein the logical dependency is determined based on the configuration data;

determining a logical causality between the abnormal objects in the set of abnormal objects to be determined based on the logical dependency between the objects; and

adjusting the set of abnormal objects to be determined based on the logical causality to obtain a set of abnormal objects.

17. A non-transitory storage medium storing a computer program, wherein the computer program, when executed by a processor, causes the processor to perform an anomaly detection method comprising:

generating at least one clustering set of objects based on configuration data and performance indicator data of the objects;

determining an algorithm configuration parameter corresponding to each clustering set based on a preset anomaly detection algorithm and the performance indicator data corresponding to the objects in the clustering set; and

determining, based on the algorithm configuration parameter, abnormal performance indicator data of the objects in the corresponding clustering set, so as to determine abnormal objects based on the abnormal performance indicator data.

18. The non-transitory storage medium of claim 17 , wherein the objects comprise function modules for constructing a wireless communication network system.

19. The non-transitory storage medium of claim 17 , wherein the generating at least one clustering set of objects based on configuration data and performance indicator data of the objects comprises:

generating at least one clustering set of the objects based on configuration data, performance indicator data and operation state data of the objects.

20. The non-transitory storage medium of claim 19 , wherein the operation state data comprises one or more of service quality data, measurement report, call tracing data, signaling tracing data, and user complaint data.

21. The non-transitory storage medium of claim 19 , wherein the generating at least one clustering set of the objects based on configuration data, performance indicator data and operation state data of the objects comprises:

acquiring the configuration data of the objects, and clustering the objects based on the configuration data to generate a first clustering set of the objects;

acquiring the performance indicator data of the objects, and clustering the objects based on the performance indicator data to generate a second clustering set of the objects;

acquiring the operation state data of the objects, and clustering the objects based on the operation state data to generate a third clustering set of the objects; and

performing logical operations on the first clustering set, the second clustering set and the third clustering set based on a preset rule to obtain at least one clustering set of the objects.

22. The non-transitory storage medium of claim 17 , wherein the determining an algorithm configuration parameter corresponding to each clustering set based on a preset anomaly detection algorithm and the performance indicator data corresponding to the objects in the clustering set comprises:

training the preset anomaly detection algorithm based on the performance indicator data of the objects in each clustering set to obtain the algorithm configuration parameter corresponding to each clustering set.

23. The non-transitory storage medium of claim 17 , wherein the determining, based on the algorithm configuration parameter, abnormal performance indicator data of the objects in the corresponding clustering set comprises:

acquiring target performance indicator data corresponding to the objects in the clustering set to be detected;

determining a target algorithm configuration parameter corresponding to the clustering set to be detected; and

performing anomaly detection on the target performance indicator data based on the preset anomaly detection algorithm and the target algorithm configuration parameter, and determining abnormal performance indicator data in the target performance indicator data based on anomaly detection results.

24. The non-transitory storage medium of claim 17 , wherein the computer program, when executed by a processor, further causes the processor to perform steps of:

after the determining an abnormal object based on the abnormal performance indicator data,

generating, a set of abnormal objects to be determined based on the abnormal objects;

acquiring a logical dependency between the objects in the wireless communication network system, wherein the logical dependency is determined based on the configuration data;

determining a logical causality between the abnormal objects in the set of abnormal objects to be determined based on the logical dependency between the objects; and

adjusting the set of abnormal objects to be determined based on the logical causality to obtain a set of abnormal objects.