Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Memory testing method based on naive Bayes classifier

A Bayesian classifier and memory testing technology, which is applied in faulty hardware testing methods, instruments, and faulty computer hardware detection, can solve problems such as predicting the yield rate of mass production on the production line, and the high yield rate of the production line. , achieving significant progress, reliable design principles, and outstanding substantive features

Active Publication Date: 2019-09-06
SUZHOU LANGCHAO INTELLIGENT TECH CO LTD
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The above-mentioned existing memory introduction test of the existing technology ignores the relationship between each test item, and it is impossible to predict the yield rate of mass production of the production line based on the test results of the test items. It often happens that the introduction test of new memory meets various test items Requirements, but the defect that the yield rate of the production line remains high, the present invention provides a memory testing method based on a naive Bayesian classifier to solve the above technical problems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Memory testing method based on naive Bayes classifier
  • Memory testing method based on naive Bayes classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] like figure 1 As shown, the present invention provides a kind of memory testing method based on Naive Bayesian classifier, comprises the steps:

[0039] S1. Select the memory introduction test item; the memory introduction test item includes RMT test, utilization rate test, performance test and golden finger thickness test;

[0040] S2. Generate training data according to the production line yield corresponding to the test results of the memory-introduced test items;

[0041] S3. Use the training data to train and classify the Naive Bayesian classifier;

[0042] S4. Use the trained naive Bayesian classifier to predict the production line yield of the memory to be introduced;

[0043] S5. Determine whether to import the memory to be imported according to the predicted yield rate of the production line.

Embodiment 2

[0045] like figure 2 As shown, the present invention provides a kind of memory testing method based on Naive Bayesian classifier, comprises the steps:

[0046] S1. Select the memory import test item;

[0047] S2. Generate training data according to the production line yield corresponding to the test results of the memory-introduced test items; the specific steps are as follows:

[0048] S21. Obtain the test result of each memory introduction test item;

[0049] S22. Parameterize the test results of introducing each memory into the test item; the specific steps are as follows:

[0050] S221. Obtain the test standard of each memory introduction test item;

[0051] S222. Take the difference between the test result of each memory introduction test item and its corresponding test standard;

[0052] S23. Parameterize the yield rate of the production line; there are two parameters for the yield rate of the production line, which are less than the standard yield threshold F and g...

Embodiment 3

[0062] The present invention provides a kind of memory test method based on Naive Bayesian classifier, comprises the following steps:

[0063] S1. Select the memory introduction test item; the memory introduction test item includes RMT test, utilization rate test, performance test and golden finger thickness test. The reason for these four test items is that the test results of these four test items can be standardized. Can ignore the influence of mutation factor, can improve the accuracy of the present invention;

[0064] S2. Generate training data according to the production line yield corresponding to the test results of the memory-introduced test items; the specific steps are as follows:

[0065] S21. Obtain the test result of each memory introduction test item;

[0066] S22. Parameterize the test results of introducing each memory into the test item; the specific steps are as follows:

[0067] S221. Obtain the test standard of each memory introduction test item;

[006...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a memory test method based on a naive Bayes classifier. The memory test method comprises the following steps: S1, selecting a memory introduction test item; s2, generating training data according to a production line yield corresponding to a test result of the memory introduction test item; s3, using the training data to train and classify the naive Bayes classifier; s4, carrying out production line yield prediction on the to-be-introduced memory by adopting the trained naive Bayes classifier; and S5, judging whether to introduce the to-be-introduced memory or not according to the predicted yield of the production line. According to the invention, a test item selection basis, a parameterization processing method and a naive Bayes and test item combination mode are adopted, an existing memory introduction test item is combined with a naive Bayes classifier artificial intelligence algorithm, the yield of a to-be-introduced memory production line is predicted, whether the to-be-introduced memory is good or bad is judged, and a controllable calculation support is provided for a component engineer.

Description

technical field [0001] The invention belongs to the field of server testing, and in particular relates to a memory testing method based on a naive Bayesian classifier. Background technique [0002] Memory is one of the important components of the server. Sufficient testing and experiments in the early stage will help improve the overall stability of the server. And most of the server errors come from storage components. Memory is the bridge to communicate with CPU. All programs in the computer run in the memory, so the performance of the memory has a great impact on the computer. Memory (Memory), also known as internal memory, is used to temporarily store computing data in the CPU and exchange data with external memories such as hard disks. As long as the computer is running, the CPU will transfer the data that needs to be calculated to the memory for calculation. After the calculation is completed, the CPU will send the result out. The operation of the memory also deter...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F11/22G06K9/62
CPCG06F11/2273G06F18/24155G06F18/214
Inventor 刘波
Owner SUZHOU LANGCHAO INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products