Search

CN-121996449-A - Fault diagnosis method and device, electronic equipment, storage medium and product

CN121996449ACN 121996449 ACN121996449 ACN 121996449ACN-121996449-A

Abstract

The disclosure relates to the field of computer technology, and in particular, provides a fault diagnosis method and device, electronic equipment, a storage medium and a product. The method and the device for diagnosing the faults of the vehicle comprise the steps of obtaining real-time abnormal alarm data in an application system, and processing the abnormal alarm data by utilizing a fault diagnosis model deployed on line to obtain a diagnosis result output by the fault diagnosis model, wherein the fault diagnosis model is used for diagnosing the faults based on the correlation degree between the abnormal alarm data and historical alarm events, and the correlation degree is related to event content and event time. In summary, the technical scheme provided by the disclosure can utilize a large model technology based on correlation comparison, so that the fault diagnosis efficiency and accuracy can be effectively improved.

Inventors

  • PANG JUNLING

Assignees

  • 中移(苏州)软件技术有限公司
  • 中国移动通信集团有限公司

Dates

Publication Date
20260508
Application Date
20250908

Claims (12)

  1. 1. A fault diagnosis method, characterized by comprising: Acquiring real-time abnormal alarm data in an application system; Processing the abnormal alarm data by using an on-line deployed fault diagnosis model to obtain a diagnosis result output by the fault diagnosis model; The fault diagnosis model is used for carrying out fault diagnosis based on the correlation degree between the abnormal alarm data and the historical alarm event, wherein the correlation degree is related to event content and event time.
  2. 2. The method according to claim 1, wherein the correlation is positively correlated with a spatial similarity between the event content, the spatial similarity being used to characterize a degree of textual and/or semantic similarity between data content; The correlation is positively correlated with a time weight between the event times, which is negatively correlated with the degree of time difference.
  3. 3. The method according to claim 1, wherein the fault diagnosis model is specifically for: acquiring the correlation degree between the abnormal alarm data and each historical alarm event; determining similar historical events of the abnormal alarm data based on the correlation degree; And determining the diagnosis result of the abnormal alarm data by taking the fault root cause of the similar historical event as a reference.
  4. 4. The method according to claim 1, wherein the method further comprises: the method comprises the steps of acquiring historical alarm data, wherein the historical alarm data comprises a historical alarm event and a fault root cause; The historical alarm data is used as a training sample to train a fault diagnosis model; The fault diagnosis model is deployed on a wire.
  5. 5. The method according to claim 1, wherein the method further comprises: obtaining auditing data of a user on the diagnosis result; And performing online optimization on the fault diagnosis model based on the diagnosis result, the auditing data and the abnormal alarm data.
  6. 6. The method according to claim 1, wherein the method further comprises: visually displaying the diagnosis result on a display interface; The diagnosis result at least comprises a fault root cause, and also comprises at least one of event information of similar historical events, a fault processing method and confidence.
  7. 7. The method according to any one of claims 1-6, wherein the anomaly alert data comprises at least one of monitoring data, base data; the monitoring data come from a monitoring device and comprise at least one of an application log, an index and a call chain; the basic data is from the application system and comprises at least one of configuration data, a fault work order and a change work order.
  8. 8. The method of any of claims 1-6, wherein the application system comprises a cloud application system; the diagnosis result comprises at least one of software abnormality, network abnormality and system abnormality.
  9. 9. A fault diagnosis apparatus characterized by comprising: the acquisition unit is used for acquiring real-time abnormal alarm data in the application system; the processing unit is used for processing the abnormal alarm data by utilizing the fault diagnosis model deployed on line to obtain a diagnosis result output by the fault diagnosis model; The fault diagnosis model is used for carrying out fault diagnosis based on the correlation degree between the abnormal alarm data and the historical alarm event, wherein the correlation degree is related to event content and event time.
  10. 10. An electronic device comprising a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any one of claims 1-8.
  11. 11. A computer readable storage medium having stored thereon a computer program/instruction which, when executed by a processor, implements the method according to any of claims 1-8.
  12. 12. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the method of any of claims 1-8.

Description

Fault diagnosis method and device, electronic equipment, storage medium and product Technical Field The present disclosure relates to the field of computer technologies, and in particular, to a fault diagnosis method and apparatus, an electronic device, a storage medium, and a product. Background Currently, in the related art, fault diagnosis is generally realized by adopting rule arrangement or an unsupervised intelligent diagnosis algorithm. The rule arrangement is to form a tree structure and a mechanism for automatically diagnosing single faults from top to bottom and from the table to the inside by carrying out standardized arrangement on atomic capacity, precipitate expert experience and improve the precision and efficiency of fault treatment, but the fault diagnosis mode needs to pre-comb scenes and problems, has huge workload and can not diagnose new fault types which are not combed. The unsupervised intelligent diagnosis algorithm automatically identifies and realizes fault diagnosis through the algorithm under the condition of no pre-marked data, but the unsupervised intelligent diagnosis algorithm lacks marked data, so that the accuracy of a diagnosis result is poor, and particularly, larger errors and defects can occur during prediction, and the unsupervised intelligent diagnosis algorithm is sensitive to small disturbance of input data, so that the result is unstable. With the development of cloud computing and big data technology, the complexity of an application system is increasing, and when the application system fails, it is particularly important to quickly and accurately locate the failure cause. However, the fault diagnosis method in the related art has problems of low diagnosis efficiency and poor accuracy. Disclosure of Invention The present disclosure has been made in view of the above-described problems. The disclosure provides a fault diagnosis method and device, electronic equipment, storage medium and product, which are used for improving fault diagnosis efficiency and accuracy. According to one aspect of the present disclosure, there is provided a fault diagnosis method including: Acquiring real-time abnormal alarm data in an application system; Processing the abnormal alarm data by using an on-line deployed fault diagnosis model to obtain a diagnosis result output by the fault diagnosis model; The fault diagnosis model is used for carrying out fault diagnosis based on the correlation degree between the abnormal alarm data and the historical alarm event, wherein the correlation degree is related to event content and event time. According to another aspect of the present disclosure, there is provided a fault diagnosis apparatus including: the acquisition unit is used for acquiring real-time abnormal alarm data in the application system; the processing unit is used for processing the abnormal alarm data by utilizing the fault diagnosis model deployed on line to obtain a diagnosis result output by the fault diagnosis model; The fault diagnosis model is used for carrying out fault diagnosis based on the correlation degree between the abnormal alarm data and the historical alarm event, wherein the correlation degree is related to event content and event time. According to another aspect of the present disclosure, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to implement a method as described in any of the embodiments above. According to another aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program/instruction which, when executed by a processor, implements a method as described in any of the embodiments above. According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program/instruction which, when executed by a processor, implements a method as described in any of the embodiments above. As will be described in detail below, according to the fault diagnosis method and apparatus, electronic device, storage medium and product of the embodiments of the present disclosure, rapid diagnosis processing of abnormal alarm data is achieved through an on-line deployed fault diagnosis model, and correlation between current abnormal alarm data and historical alarm events can be evaluated from two dimensions of event content and event time, and fault diagnosis is performed based on the correlation, which means that the fault diagnosis model can output a diagnosis result corresponding to the current abnormal alarm data more rapidly and more accurately by referring to a processing experience of the historical alarm event with reference to the historical alarm event with higher correlation. In other words, the technical scheme provided by the disclosure can effectively improve the fault diagnosis efficiency and accuracy by using a large model technol