An electronic equipment automatic test method and system based on machine learning

Abstract

The invention provides an electronic equipment automatic test method and system based on machine learning. The automatic test method for the electronic equipment based on machine learning comprises the following steps: acquiring test data of the electronic equipment, and extracting a characteristic component of the test data; wherein the test data comprises serialized waveform data and non-serialized video and image data; performing principal component analysis on the test data, determining the correlation of different characteristic components, and generating characteristic vectors; and inputting the feature vector into a preset fault diagnosis model, and outputting a prediction result of the electronic test fault.

Description

technical field [0001] The disclosure belongs to the field of electronic testing, in particular to a method and system for automatic testing of electronic equipment based on machine learning. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] Automatic testing is the current mainstream technology in the field of electronic testing. It collects, enters and displays data in the form of the client, integrates and analyzes data on the server, and uses threshold judgment or expert system as the basis for decision-making. Automatic testing gathers a large number of test resources, including test instruments, testers, and test data, to meet the centralized realization and decision-making of test requirements. Among them, the realization of test requirements is mainly based on systematic and platform-based data collection, and decision-making and j...

AI Technical Summary

Problems solved by technology

Compared with the traditional manual test, the automatic test has improved the test ability. Combined with the development and introduction of network technology, the ability to collect and share a large amount of data has been improved to a certain extent; combined with statistical methods and fault analysis modeling, it has certain advantages. Data analysis and processing capabilities. Although automatic testing is widely used in the field of electronic testing, with the improvement of electronic testing requirements for intelligence, sharing, precision, efficiency, and speed, automatic testing has gradually failed to meet modern electronic intelligence. testing needs

[0004] Traditional automatic testing mostly emphasizes reducing manpower consumption and improving automation in the testing process, which has the following disadvantages: First, automatic testing technology often adopts a centralized testing method, and all links in testing technology are easily subject to geographical restrictions. Although technology can achieve a certain degree of data sharing, the intelligent data processing capability is still limited and the data processing efficiency is low; Insufficient mining capabilities; thirdly, the current automatic testing field is not closely integrated with machine learning. During the execution of automatic testing, after collecting data according to the test resource configuration and process, the diagnosis and prediction results can be obtained through simple preprocessing and machine learning algorithms.

In this process, data collection based on testing and decision-making based on machine learning often run independently, and the integration of intelligent testing has not been realized; fourth, the current level of intelligence in automatic testing is relatively low, and most of them rely on human experience to develop automatic testing processes , and then carry out the test behavior. Such automatic testing cannot update the test resource configuration and process based on real-time test results combined with intelligently inferred decisions, nor can it accurately improve the consumption of test resources for the data collected by specific tests.

Images