CN-122001740-A - Fault diagnosis method, fault diagnosis device, electronic equipment, storage medium and product

CN122001740ACN 122001740 ACN122001740 ACN 122001740ACN-122001740-A

Abstract

The application provides a fault diagnosis method, a fault diagnosis device, an electronic device, a computer readable storage medium and a computer program product; the method comprises the steps of obtaining equipment fault description information provided by a user, determining a plurality of first fault labels and fault probabilities corresponding to the first fault labels based on the equipment fault description information, and generating a target fault diagnosis result based on the first fault labels and the fault probabilities corresponding to the first fault labels, wherein the target fault diagnosis result comprises user information of the user and the target fault labels.

Inventors

LUO ZHIDAN
LIU WEI
ZHOU XIAOFENG

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: 20260121

Claims (10)

1. A fault diagnosis method, the method comprising: Acquiring equipment fault description information provided by a user; Determining a plurality of first fault labels and fault probabilities corresponding to each first fault label based on the equipment fault description information; And generating a target fault diagnosis result based on each first fault label and the fault probability corresponding to each first fault label, wherein the target fault diagnosis result comprises user information of the user and the target fault label.
2. The method of claim 1, wherein the determining a plurality of first failure tags based on the device failure description information comprises: inputting the fault description information into a pre-training language model to obtain a plurality of fault text vectors output by the pre-training language model; Inputting a plurality of fault text vectors into an unsupervised learning clustering model to obtain an initial clustering result and a plurality of initial categories which are output by the unsupervised learning clustering model, wherein the initial clustering result comprises a plurality of initial clustering centers; establishing each probability density model for a plurality of data points in a target range of each initial cluster center based on a Gaussian mixture model, wherein each probability density model represents the distribution condition of a plurality of data points in a sub-cluster; and carrying out sub-cluster combination based on a plurality of probability density models corresponding to the initial cluster centers to obtain a final cluster result and a plurality of first fault labels, wherein the final cluster result comprises a plurality of final cluster centers and cluster-like numbers.
3. The method of claim 1, wherein each of the first failure tags corresponds to a failure probability that is a confidence rating for each of the first failure tags.
4. A method according to any one of claims 1 to 3, wherein generating a target fault diagnosis result based on each of the first fault tags and a fault probability corresponding to each of the first fault tags comprises: If the maximum fault probability in the fault probabilities corresponding to the plurality of first fault tags is larger than or equal to a first threshold value, determining that the fault tag corresponding to the maximum fault probability is the target fault tag; and generating the target fault diagnosis result based on the target fault label.
5. A method according to any one of claims 1 to 3, wherein generating a target fault diagnosis result based on each of the first fault tags and a fault probability corresponding to each of the first fault tags comprises: if the maximum fault probability in the fault probabilities corresponding to the plurality of first fault tags is smaller than a first threshold value, selecting a plurality of candidate fault tags from the plurality of first fault tags, wherein the fault probability corresponding to the plurality of candidate fault tags is larger than a second threshold value and smaller than the first threshold value; acquiring candidate fault characteristics corresponding to each candidate fault label; Acquiring confirmed fault characteristics from the equipment fault description information; removing the confirmed fault features from the candidate fault features to obtain a plurality of primary screening fault features; acquiring target fault characteristics selected by the user from a plurality of primary screening fault characteristics; determining a plurality of second fault labels and fault probabilities corresponding to each second fault label based on the target fault characteristics and the equipment fault description information; and generating the target fault diagnosis result based on the plurality of second fault labels and the fault probability corresponding to each second fault label.
6. The method of claim 5, wherein generating the target fault diagnosis result based on the plurality of second fault tags and the fault probability corresponding to each of the second fault tags comprises: Taking a fault label corresponding to the maximum fault probability in the fault probabilities corresponding to the plurality of second fault labels as the target fault label; and generating the target fault diagnosis result based on the target fault label.
7. A fault diagnosis apparatus characterized by comprising: the acquisition unit is used for acquiring equipment fault description information provided by a user; The processing unit is used for determining a plurality of first fault labels and fault probabilities corresponding to each first fault label based on the equipment fault description information; The processing unit is used for generating a target fault diagnosis result based on each first fault label and the fault probability corresponding to each first fault label, wherein the target fault diagnosis result comprises user information of the user and the target fault label.
8. An electronic device comprising a communication interface and a processor, wherein, The communication interface is used for acquiring equipment fault description information provided by a user; The processor is used for determining a plurality of first fault labels and fault probabilities corresponding to the first fault labels based on the equipment fault description information, generating a target fault diagnosis result based on the first fault labels and the fault probabilities corresponding to the first fault labels, and the target fault diagnosis result comprises user information of the user and the target fault labels.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Description

Fault diagnosis method, fault diagnosis device, electronic equipment, storage medium and product Technical Field The present application relates to computer technology, and more particularly, to a fault diagnosis method, a fault diagnosis apparatus, an electronic device, a computer-readable storage medium, and a computer program product. Background In a communication network, with the continuous expansion of service types and the improvement of equipment complexity, the probability of faults of various service platforms, communication equipment and terminal equipment is increased. In order to ensure the stability and continuity of communication service, the rapid and accurate diagnosis of faults becomes a key link in operation and maintenance management. In the related art, fault diagnosis generally depends on the experience judgment of a technician. After the user reports the fault information, the technician of the operator can judge the fault type according to the user description or the system log and other information and combine the experience of the user, and the processing proposal is provided. The related manual experience diagnosis mode is strong in subjectivity, different technicians can make different judgments on the same problem, and unified evaluation standards are difficult to form. Meanwhile, due to the lack of systematic quantization indexes, diagnosis results are difficult to objectively measure and optimize. Disclosure of Invention The embodiment of the application provides a fault diagnosis method, a fault diagnosis device, an electronic device, a computer readable storage medium and a computer program product. The technical scheme of the embodiment of the application is realized as follows: the embodiment of the application provides a fault diagnosis method, which comprises the following steps: Acquiring equipment fault description information provided by a user; Determining a plurality of first fault labels and fault probabilities corresponding to each first fault label based on the equipment fault description information; And generating a target fault diagnosis result based on each first fault label and the fault probability corresponding to each first fault label, wherein the target fault diagnosis result comprises user information of the user and the target fault label. An embodiment of the present application provides a fault diagnosis apparatus, including: the acquisition unit is used for acquiring equipment fault description information provided by a user; The processing unit is used for determining a plurality of first fault labels and fault probabilities corresponding to each first fault label based on the equipment fault description information; The processing unit is used for generating a target fault diagnosis result based on each first fault label and the fault probability corresponding to each first fault label, wherein the target fault diagnosis result comprises user information of the user and the target fault label. The embodiment of the application provides an electronic device, which comprises a communication interface and a processor, wherein, The communication interface is used for acquiring equipment fault description information provided by a user; The processor is used for determining a plurality of first fault labels and fault probabilities corresponding to the first fault labels based on the equipment fault description information, generating a target fault diagnosis result based on the first fault labels and the fault probabilities corresponding to the first fault labels, and the target fault diagnosis result comprises user information of the user and the target fault labels. The embodiment of the application provides a computer readable storage medium, which stores a computer program or computer executable instructions for realizing the fault diagnosis method provided by the embodiment of the application when being executed by a processor. The embodiment of the application provides a computer program product, which comprises a computer program or a computer executable instruction, and the computer program or the computer executable instruction realize the fault diagnosis method provided by the embodiment of the application when being executed by a processor. The method and the device have the advantages that firstly, equipment fault description information provided by a user is obtained, secondly, a plurality of first fault labels and corresponding fault probabilities thereof are determined based on the information, and finally, a fault diagnosis result comprising the user information and the target fault labels is generated. On the one hand, the fault labels are determined based on the fault description information, and on the other hand, the fault labels are screened by combining the fault probability, so that the most probable target fault label can be reasonably selected, the reliability and the automation degree of fault diagnosis are improved, the manu