A method and device for detecting performance faults based on support vector machines
A support vector machine and performance technology, applied in the computer field, can solve problems such as low prediction efficiency and accuracy, ignore outliers, etc., to achieve the effect of improving prediction efficiency and prediction accuracy, reducing selection time, and reducing search space
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0056] This embodiment provides a method for detecting performance faults based on support vector machines, please refer to figure 1 , the method includes:
[0057] Step S1: Vectorize the performance log data generated by the system.
[0058] Specifically, for a piece of original performance log data, it contains many log items, such as a large amount of operating information of the system, which can reflect whether the operating state of the system is healthy or not, and also contains some information that is not related to system performance. Items, these items are confused in the record items of the log, there are text and value. Generally speaking, the original log contains three types of log attribute items: text log data items, numerical system performance-related log attribute items, and numerical system performance-independent attribute items. The main function of log vectorization is to remove text-type log data items and numerical log attribute items related to sys...
Embodiment 2
[0123] This embodiment provides a device for detecting performance faults based on support vector machines, please refer to Image 6 , the device consists of:
[0124] A log vectorization module 201, configured to vectorize the performance log data generated by the system;
[0125] The log tagging module 202 is used to add tags to the log data after vectorization processing to obtain a training data set;
[0126] The kernel function selection module 203 is used to select the kernel function by mixing Gaussian kernel and linear kernel direct product;
[0127] Parameter and penalty factor selection module 204, for selecting the parameter and penalty factor of kernel function based on bilinear pattern search method;
[0128] A model building module 205, configured to construct a prediction model based on a support vector machine according to the kernel function, parameters of the kernel function, and a penalty factor, and use the training data set to train the prediction model;...
Embodiment 3
[0149] See Figure 7 , based on the same inventive concept, the present application also provides a computer-readable storage medium 300, on which a computer program 311 is stored. When the program is executed, the method as described in the first embodiment is implemented.
[0150] Since the computer-readable storage medium introduced in the third embodiment of the present invention is a computer device used to implement the support vector machine-based performance fault detection method in the first embodiment of the present invention, based on the method introduced in the first embodiment of the present invention, Those skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, so details will not be repeated here. All computer-readable storage media used in the method in Embodiment 1 of the present invention fall within the scope of protection intended by the present invention.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More