An intelligent solid state hard disk quality detection method, system, device and medium

Abstract

The present application relates to an intelligent solid-state hard disk quality detection method, system, device and medium, including obtaining test requirement data of a solid-state hard disk to be detected, extracting feature point data in the test requirement data from the test requirement data using a feature extraction algorithm to obtain requirement feature point data; obtaining environmental data, transmitting the requirement feature point data and environmental data to a pre-trained detection model for comparison and analysis to obtain a test adjustment plan; performing a virtual environment test according to the test adjustment plan to obtain a virtual environment test result; when the virtual environment test result does not meet expectations, obtaining difference information from the virtual environment test result, modifying the test adjustment plan accordingly according to the difference information to obtain an optimized adjustment plan, and adjusting the test process and parameter configuration of the solid-state hard disk to be detected according to the optimized adjustment plan. The present application has the effect of improving the accuracy of solid-state hard disk quality detection.

Description

Technical Field

[0001] The present application relates to the technical field of computer hardware testing, and in particular to an intelligent solid-state hard disk quality detection method, system, device and medium. Background Art

[0002] At present, on the production line of solid-state drives, manual inspection or traditional automatic inspection systems are usually used to complete product quality inspection. With the improvement of solid-state drive performance and technological progress, the quality inspection standards for hard drives are also constantly improving, and the existing quality inspection methods often cannot meet the growing demand. The traditional manual inspection method relies on visual inspection and instrument assistance. This method is not only time-consuming but also easily affected by human factors, resulting in a high rate of missed detection; in addition, there are traditional automated inspection equipment based on fixed program settings. Although this type of equipment can reduce manpower investment to a certain extent, it has poor flexibility and is difficult to achieve adaptive adjustment when faced with diverse testing needs.

[0003] The above-mentioned existing technical solutions have the following defects: the current automated testing equipment for solid-state drives is difficult to achieve adaptive adjustment when facing diverse testing requirements, and there is a problem of low accuracy when testing the quality of solid-state drives, so there is room for improvement. Summary of the invention

[0004] In order to improve the accuracy of solid-state hard disk quality detection, the present application provides an intelligent solid-state hard disk quality detection method, system, device and medium.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0006] An intelligent solid state hard disk quality detection method, the intelligent solid state hard disk quality detection method comprising:

[0007] Acquire test requirement data of the solid state drive to be tested, and extract feature point data in the test requirement data from the test requirement data using a feature extraction algorithm to obtain requirement feature point data;

[0008] Acquire environmental data, transmit the demand feature point data and the environmental data to a pre-trained detection model for comparison and analysis, and obtain a test adjustment plan;

[0009] Perform a virtual environment test according to the test adjustment plan to obtain a virtual environment test result;

[0010] When the virtual environment test results do not meet expectations, difference information is obtained from the virtual environment test results, the test adjustment plan is modified accordingly according to the difference information to obtain an optimized adjustment plan, and the test process and parameter configuration of the solid-state hard drive to be tested are adjusted according to the optimized adjustment plan.

[0011] By adopting the above technical solutions, by obtaining test demand data, the specific goals and standards of solid-state drive detection are clarified, ensuring that the detection process is targeted and systematic, and using feature extraction algorithms to extract key feature points from test demand data, simplify data dimensions, highlight important information, and improve data processing efficiency; by obtaining environmental data, the impact of the external environment on the performance of solid-state drives is considered to ensure the comprehensiveness and practical applicability of the detection results, and the demand feature point data is combined with environmental data to provide richer information input, and enhance the analysis ability and prediction accuracy of the detection model; through virtual environment testing, actual usage scenarios are simulated, potential problems are discovered in advance, and risks and costs in actual testing are reduced. The virtual environment test results are obtained, the effectiveness of the detection plan is quickly fed back, and the iterative optimization of the detection process is promoted; by obtaining difference information, deficiencies and problems in the detection process are accurately identified, and the formulation of subsequent optimization measures is guided. The test adjustment plan is modified according to the difference information to ensure that the adjustment plan is more in line with actual needs and improve the effectiveness of the detection plan. The optimized adjustment plan is applied to the test process and parameter configuration, and the detection system is continuously improved to improve the accuracy and efficiency of the overall detection.

[0012] In a preferred example, the present application may be further configured as follows: the test requirement data of the solid state drive to be tested is obtained, and feature point data in the test requirement data is extracted from the test requirement data using a feature extraction algorithm, and the requirement feature point data is obtained, including:

[0013] Acquire test items that a user needs to test on the solid-state hard disk to be detected through a user interface, statistically integrate data of the test items, and obtain test requirement data of the solid-state hard disk to be detected;

[0014] The test demand data is clustered and analyzed using a k-means algorithm to obtain the demand feature point data.

[0015] By adopting the above technical solution, test items are obtained through the user interface to ensure the accuracy of test requirements and comprehensive coverage of user needs, improve the pertinence of the test plan, statistically integrate test item data, systematically organize and analyze test requirements, simplify the data processing process, and improve the efficiency of data management; use the k-means algorithm for cluster analysis to effectively group test requirement data, identify feature points of different categories, improve the interpretability of data, obtain requirement feature point data, extract key features, reduce data dimensions, highlight important information, and improve the efficiency of subsequent analysis and model training.

[0016] In a preferred example, the present application may be further configured as follows: before obtaining environmental data, transmitting the demand feature point data and the environmental data to a pre-trained detection model for comparison and analysis, and obtaining a test adjustment plan, the intelligent solid-state hard disk quality detection method further includes:

[0017] Collect historical test data and actual failure cases of the solid-state hard disk to be tested under different environments, pre-process and annotate the historical test data and actual failure cases to obtain a training set;

[0018] Using the training set to perform forward propagation and back propagation training on a detection model built based on a convolutional neural network and a recurrent neural network, to obtain a detection model after propagation training;

[0019] The genetic algorithm is used to optimize the parameters of the detection model after the propagation training to obtain the pre-trained detection model.

[0020] By adopting the above technical solutions, historical test data and actual failure cases under different environments are collected to ensure the diversity and comprehensiveness of the data, improve the adaptability of the model in various practical application scenarios, preprocess and annotate the data, clean the noise and error information in the data, improve the data quality, and ensure the accuracy and reliability of the training set; through the combination of convolutional neural network (CNN) and recurrent neural network (RNN), the advantages of CNN in extracting spatial features and RNN in processing time series data are fully utilized to improve the comprehensive analysis ability of the model, and the forward propagation and back propagation training methods are adopted to optimize the weights and parameters of the model to improve the accuracy and generalization ability of the model; through genetic algorithm, parameter optimization is performed, and the hyperparameters of the model are automatically searched and adjusted to find the optimal parameter combination and improve the performance of the model.

[0021] In a preferred example, the present application can be further configured as follows: the environmental data is acquired, and the demand feature point data and the environmental data are transmitted to a pre-trained detection model for comparison and analysis, and the test adjustment scheme is obtained, including:

[0022] The environmental sensor detects the data of the external environment of the solid state drive to be detected in real time to obtain the environmental data;

[0023] The demand feature point data and the environmental data are normalized to obtain normalized data, and the normalized data are compared and analyzed with the data in the pre-trained detection model to obtain the test adjustment plan.

[0024] By adopting the above technical solution, the external environment data of the solid-state hard disk is detected in real time through environmental sensors, and key environmental parameters such as temperature, humidity, vibration, etc. can be obtained in time to ensure the comprehensiveness and accuracy of monitoring. The acquisition of real-time environmental data is helpful to dynamically monitor the operating status of the hard disk and promptly discover the potential impact of environmental changes on the performance and life of the hard disk, thereby improving the timeliness and effectiveness of fault warning; by normalizing the demand feature point data and environmental data, the impact of different data dimensions and dimensions is eliminated, the consistency and comparability of the data are improved, and the accuracy of subsequent analysis is enhanced. The normalized data is compared and analyzed with the pre-trained detection model, which can accurately match the current hard disk operating status with the historical failure mode and identify potential failure risks.

[0025] In a preferred example, the present application may be further configured as follows: performing a virtual environment test according to the test adjustment scheme to obtain a virtual environment test result includes:

[0026] Input the test adjustment plan into the virtualization platform, perform multi-dimensional simulation tests according to the test adjustment plan, and obtain simulation test logs and error information;

[0027] The simulation test log and error information are analyzed by a log analysis tool to obtain the virtual environment test result.

[0028] By adopting the above technical solution and inputting the test adjustment plan into the virtualization platform, different test conditions and scenarios can be accurately reproduced in a controlled virtual environment, ensuring the comprehensiveness and repeatability of the test, and conducting multi-dimensional simulation tests. Stress testing, performance evaluation and fault simulation can be performed on solid-state drives from multiple angles and levels to fully identify potential problems. Log analysis tools can be used to systematically analyze the logs and error information generated by the simulation test, which can quickly extract key data and abnormal patterns, improve the efficiency of problem discovery, and automated processing during the analysis process reduces the impact of human errors and subjective judgments, thereby improving the accuracy and consistency of test results.

[0029] In a preferred example, the present application can be further configured as follows: the intelligent solid state hard disk quality detection method further includes:

[0030] Feeding back the virtual environment test results and the optimized adjustment scheme to the pre-trained detection model, and continuously learning and updating the pre-trained detection model according to the virtual environment test results and the optimized adjustment scheme;

[0031] Based on the distributed test architecture, the test nodes of the solid-state drive to be tested are coordinated to improve the test efficiency and flexibility;

[0032] During the test, the operating status of the solid-state hard disk to be tested is monitored in real time. If the operating status reaches a preset operating threshold, an alarm signal is generated and automatically sent to the user end.

[0033] By adopting the above technical solution, by feeding back the virtual environment test results and the optimized adjustment plan to the pre-trained detection model, the detection model can continuously absorb the latest test data and optimization strategies, improve the adaptability and accuracy of the model, and continuously learn and update the detection model according to the virtual environment test results and the optimized adjustment plan, which helps the model to timely capture and reflect the latest performance and failure mode of the solid-state drive in different environments, and enhance the accuracy of fault prediction; based on the distributed test architecture, it is possible to simultaneously schedule multiple test nodes to process the detection tasks in parallel, greatly improve the overall test efficiency, shorten the detection cycle, coordinate multiple test nodes to perform quality inspection in parallel, enhance the processing capacity and scalability of the system, and flexibly respond to large-scale solid-state drive detection needs and adapt to test scenarios of different scales and complexities; by real-time monitoring of the operating status of the solid-state drive to be detected, it is possible to instantly grasp the performance and health of the hard disk, ensure the transparency and timeliness of the detection process, and generate an alarm signal when the operating status reaches the preset operating threshold, which can quickly identify potential fault risks, prevent the problem from expanding, ensure the stable operation of the system, and automatically send an alarm signal to the user end, ensuring that relevant personnel can obtain alarm information in the first time, take countermeasures in time, shorten the fault response time, and reduce the risk of system downtime or data loss.

[0034] The second object of the invention is achieved by the following technical solutions:

[0035] An intelligent solid-state hard disk quality detection system, the intelligent solid-state hard disk quality detection system comprising:

[0036] The requirement acquisition module is used to acquire the test requirement data of the solid state drive to be detected, and extract the feature point data in the test requirement data from the test requirement data by using a feature extraction algorithm to obtain the requirement feature point data;

[0037] A model analysis module is used to obtain environmental data, transmit the demand feature point data and the environmental data to a pre-trained detection model for comparison and analysis, and obtain a test adjustment plan;

[0038] A virtual testing module, used to perform a virtual environment test according to the test adjustment scheme to obtain a virtual environment test result;

[0039] The scheme adjustment module is used to obtain difference information from the virtual environment test results when the virtual environment test results do not meet expectations, modify the test adjustment scheme accordingly according to the difference information to obtain an optimized adjustment scheme, and adjust the test process and parameter configuration of the solid-state hard disk to be tested according to the optimized adjustment scheme.

[0040] By adopting the above technical solutions, by obtaining test demand data, the specific goals and standards of solid-state drive detection are clarified, ensuring that the detection process is targeted and systematic, and using feature extraction algorithms to extract key feature points from test demand data, simplify data dimensions, highlight important information, and improve data processing efficiency; by obtaining environmental data, the impact of the external environment on the performance of solid-state drives is considered to ensure the comprehensiveness and practical applicability of the detection results, and the demand feature point data is combined with environmental data to provide richer information input, and enhance the analysis ability and prediction accuracy of the detection model; through virtual environment testing, actual usage scenarios are simulated, potential problems are discovered in advance, and risks and costs in actual testing are reduced. The virtual environment test results are obtained, the effectiveness of the detection plan is quickly fed back, and the iterative optimization of the detection process is promoted; by obtaining difference information, deficiencies and problems in the detection process are accurately identified, and the formulation of subsequent optimization measures is guided. The test adjustment plan is modified according to the difference information to ensure that the adjustment plan is more in line with actual needs and improve the effectiveness of the detection plan. The optimized adjustment plan is applied to the test process and parameter configuration, and the detection system is continuously improved to improve the accuracy and efficiency of the overall detection.

[0041] The third objective of the present application is achieved through the following technical solutions:

[0042] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned intelligent solid-state hard disk quality detection method are implemented.

[0043] The fourth objective of the present application is achieved through the following technical solutions:

[0044] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent solid-state hard disk quality detection method.

[0045] In summary, the present application includes at least one of the following beneficial technical effects:

[0046] 1. By obtaining test demand data, clarify the specific goals and standards of SSD testing, ensure that the testing process is targeted and systematic, use feature extraction algorithms to extract key feature points from test demand data, simplify data dimensions, highlight important information, and improve data processing efficiency; by obtaining environmental data, consider the impact of the external environment on SSD performance, ensure the comprehensiveness and practical applicability of the test results, combine demand feature point data with environmental data, provide richer information input, and enhance the analysis ability and prediction accuracy of the detection model;

[0047] 2. Through virtual environment testing, simulate actual usage scenarios, discover potential problems in advance, reduce risks and costs in actual testing, obtain virtual environment test results, quickly feedback the effectiveness of the detection plan, and promote iterative optimization of the detection process; by obtaining difference information, accurately identify deficiencies and problems in the detection process, guide the formulation of subsequent optimization measures, modify the test adjustment plan according to the difference information, ensure that the adjustment plan is more in line with actual needs, improve the effectiveness of the detection plan, apply the optimized adjustment plan to the test process and parameter configuration, continuously improve the detection system, and improve the accuracy and efficiency of the overall detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of an intelligent solid state hard disk quality detection method in one embodiment of the present application;

[0049] Figure 2 This is a flowchart for implementing step S10 in an intelligent solid state hard disk quality detection method in an embodiment of the present application;

[0050] Figure 3 This is a flowchart of an intelligent solid state hard disk quality detection method in an embodiment of the present application;

[0051] Figure 4 This is a flowchart for implementing step S20 in an intelligent solid state hard disk quality detection method in an embodiment of the present application;

[0052] Figure 5 It is a flowchart for implementing step S30 in an intelligent solid state hard disk quality detection method in one embodiment of the present application;

[0053] Figure 6 This is a flowchart of an intelligent solid state hard disk quality detection method in an embodiment of the present application;

[0054] Figure 7It is a principle block diagram of an intelligent solid state hard disk quality detection system in one embodiment of the present application;

[0055] Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The present application is further described in detail below in conjunction with the accompanying drawings.

[0057] In one embodiment, if Figure 1 As shown, the present application discloses an intelligent solid state hard disk quality detection method, which specifically includes the following steps:

[0058] S10: Acquire test requirement data of the solid state drive to be tested, and extract feature point data in the test requirement data from the test requirement data using a feature extraction algorithm to obtain requirement feature point data.

[0059] Specifically, the test requirement data of the solid-state drive to be tested is obtained through the user interface, such as the performance indicators, usage scenarios, expected service life, etc. of the solid-state drive, and the feature point data in the test requirement data is extracted from the test requirement data using a feature extraction algorithm. The feature extraction algorithm can identify key information points from a large amount of test requirement data. After being processed by the feature extraction algorithm, the obtained requirement feature point data is a refined representation of the solid-state drive test requirements, such as the key performance parameters of the solid-state drive, the requirements of the usage environment, and factors that may affect the performance and life of the hard drive.

[0060] S20: Acquire environmental data, and transmit the demand feature point data and environmental data to a pre-trained detection model for comparison and analysis to obtain a test adjustment plan.

[0061] Specifically, relevant data of the current environment are collected. These data may include temperature, humidity, air pressure, dust concentration, etc., because these environmental factors may affect the performance and test results of the SSD. The demand feature point data and real-time environmental data of the SSD are input into a pre-trained detection model. The detection model compares and analyzes the input demand feature point data and environmental data. Through the comparison and analysis, the model can evaluate whether the performance of the SSD in the current environment meets expectations and identify any potential problems or deviations. Based on the results of the comparison and analysis, the model generates a test adjustment plan, such as adjusting test parameters, changing the test environment, or adopting a specific test strategy.

[0062] S30: Perform a virtual environment test according to the test adjustment plan to obtain a virtual environment test result.

[0063] Specifically, software simulation or virtualization technology is used to create a virtual test environment that is similar to the real environment. This virtual environment can simulate various operating conditions, workloads and environmental factors, such as temperature, humidity, vibration, etc., and perform solid-state drive tests in the virtual environment, including performance tests, stability tests, life tests, etc. These tests can be automated or semi-automated, relying on pre-set test scripts to execute. After the test is completed, the test data is collected and analyzed, including key parameters such as performance indicators, error rates, and response times of the solid-state drives. The collected data is integrated to obtain the virtual environment test results.

[0064] S40: When the virtual environment test result does not meet expectations, obtain difference information from the virtual environment test result, modify the test adjustment plan accordingly according to the difference information to obtain an optimized adjustment plan, and adjust the test process and parameter configuration of the solid state drive to be tested according to the optimized adjustment plan.

[0065] Specifically, when the virtual environment test is completed, if the test results show that the performance, stability or other key indicators of the solid-state drive do not meet the predetermined goals or standards, this indicates that the test results do not meet expectations. The virtual environment test results are analyzed to identify the differences with the expected goals. This may include deviations in performance indicators, abnormal error rates, extended response times, etc. Based on the difference information obtained, the original test adjustment plan is reviewed and modified, such as changing test conditions, adjusting test parameters, optimizing test processes, or enhancing test coverage. After modification and optimization, a new test adjustment plan is obtained, which takes into account the difference information in the test results and makes targeted adjustments. The optimized adjustment plan is implemented to adjust the test process of the solid-state drive, including the order of tests, the selection of test cases, the setting of the test environment, etc. At the same time, parameter configurations are updated, such as workload, power supply conditions, temperature range, etc.

[0066] By adopting the above technical solutions, by obtaining test demand data, the specific goals and standards of solid-state drive detection are clarified, ensuring that the detection process is targeted and systematic, and using feature extraction algorithms to extract key feature points from test demand data, simplify data dimensions, highlight important information, and improve data processing efficiency; by obtaining environmental data, the impact of the external environment on the performance of solid-state drives is considered to ensure the comprehensiveness and practical applicability of the detection results, and the demand feature point data is combined with environmental data to provide richer information input, and enhance the analysis ability and prediction accuracy of the detection model; through virtual environment testing, actual usage scenarios are simulated, potential problems are discovered in advance, and risks and costs in actual testing are reduced. The virtual environment test results are obtained, the effectiveness of the detection plan is quickly fed back, and the iterative optimization of the detection process is promoted; by obtaining difference information, deficiencies and problems in the detection process are accurately identified, and the formulation of subsequent optimization measures is guided. The test adjustment plan is modified according to the difference information to ensure that the adjustment plan is more in line with actual needs and improve the effectiveness of the detection plan. The optimized adjustment plan is applied to the test process and parameter configuration, and the detection system is continuously improved to improve the accuracy and efficiency of the overall detection.

[0067] In one embodiment, if Figure 2 As shown, in step S10, the test requirement data of the solid state drive to be tested is obtained, and feature point data in the test requirement data is extracted from the test requirement data using a feature extraction algorithm to obtain the requirement feature point data, which specifically includes:

[0068] S11: obtaining test items that the user needs to test on the solid-state hard disk to be tested through the user interface, statistically integrating the data of the test items, and obtaining test requirement data of the solid-state hard disk to be tested.

[0069] Specifically, a user interface is provided to allow users to input or select the test items they wish to perform on the SSD. The system collects the test item data selected by the user and organizes and integrates the data. This may include recording the type of test item, the frequency of the test, the duration of the test, etc. The integrated test item data is converted into test requirement data for the SSD to be tested. These data will be used to develop a test plan and configure a test environment.

[0070] S12: Use the k-means algorithm to perform cluster analysis on the test demand data to obtain demand feature point data.

[0071] Specifically, the K-means clustering algorithm is used to analyze the SSD test requirement data, and key feature points are extracted from the SSD test requirement data. These feature points include key parameters and performance indicators of the test items. After clustering analysis by the K-means algorithm, the demand feature point data obtained is a refined representation of the SSD test requirements. These data points represent the key information in the test requirements and can be used for further analysis and decision support.

[0072] In one embodiment, if Figure 3 As shown, before step S20, that is, obtaining environmental data, transmitting the demand feature point data and the environmental data to a pre-trained detection model for comparison and analysis, and obtaining a test adjustment plan, the intelligent solid-state hard disk quality detection method also includes:

[0073] S201: Collect historical test data and actual failure cases of solid-state hard disks to be tested in different environments, pre-process and annotate the historical test data and actual failure cases, and obtain a training set.

[0074] Specifically, historical test data and actual failure cases of the solid-state drives to be tested are collected under different environmental conditions, including test results under different temperature, humidity, operating pressure and other conditions, as well as detailed records of various failures. The collected historical test data and failure cases are preprocessed, including data cleaning, noise removal, missing value filling, feature extraction, etc. At the same time, the data is labeled, that is, it is determined whether each data point represents a failure, and the type of failure. The preprocessed and labeled data are organized into a training set, which will be used to train the machine learning model. The training set provides a learning basis for the model, so that the model can learn how to identify the failure mode of the solid-state drive through these data.

[0075] S202: Perform forward propagation and back propagation training on the detection model constructed based on the convolutional neural network and the recurrent neural network using the training set to obtain the detection model after propagation training.

[0076] Specifically, a hybrid model including convolutional neural network and recurrent neural network is designed to detect the performance and failure of solid-state drives. The detection model is trained using preprocessed and labeled training sets. Through training, the model learns the data patterns in normal and abnormal states. In the forward propagation stage, the input data is passed through the network layer by layer. Each layer performs weighted summation on the data and applies an activation function to finally generate an output result. In the back-propagation stage, the error between the output result and the actual label is calculated and the error is passed back to the network. The weights and biases in the network are updated using the gradient descent algorithm to reduce the prediction error. After multiple iterations of training, the parameters of the model are optimized to obtain a trained detection model.

[0077] S203: Optimize the parameters of the detection model after propagation training using a genetic algorithm to obtain a pre-trained detection model.

[0078] Specifically, a genetic algorithm is used to optimize the parameters of the detection model after propagation training. The optimal solution to the problem is searched by simulating biological genetic mechanisms such as natural selection, crossover, and mutation. By iteratively improving the parameter combination, a better model parameter setting can be found, and finally a detection model optimized by a genetic algorithm, that is, a pre-trained detection model, is obtained.

[0079] In one embodiment, if Figure 4 As shown, in step S20, the environmental data is obtained, and the demand feature point data and the environmental data are transmitted to the pre-trained detection model for comparison and analysis to obtain a test adjustment plan, which specifically includes:

[0080] S21: Using an environmental sensor to detect data of the external environment of the solid state drive to be detected in real time to obtain environmental data.

[0081] Specifically, environmental sensors are deployed to monitor the environmental conditions during SSD testing or operation in real time. These sensors include but are not limited to temperature sensors, humidity sensors, air pressure sensors, etc., which can detect environmental parameters such as temperature, humidity, and air pressure. The data collected by the sensors are recorded to form an environmental data set, which includes continuous numerical readings, such as changes in temperature over time, or instantaneous measurements, such as the humidity level at a certain moment.

[0082] S22: Normalize the demand feature point data and the environmental data to obtain normalized data, and compare and analyze the normalized data with the data in the pre-trained detection model to obtain a test adjustment plan.

[0083] Specifically, the collected demand feature point data and environmental data are normalized to fall within a specific range, such as 0 to 1 or -1 to 1. The normalized data is compared and analyzed with the data in the pre-trained detection model. Through the comparison and analysis, the difference between the current SSD test requirements and the data during model training can be identified. Based on the results of the comparison and analysis, a test adjustment plan is generated, including suggestions such as modifying test parameters, adjusting the test environment or optimizing the test process, so as to optimize the SSD test process and improve the accuracy and efficiency of the test.

[0084] In one embodiment, if Figure 5 As shown, in step S30, a virtual environment test is performed according to the test adjustment scheme to obtain a virtual environment test result, which specifically includes:

[0085] S31: Input the test adjustment plan into the virtualization platform, perform multi-dimensional simulation tests according to the test adjustment plan, and obtain simulation test logs and error information.

[0086] Specifically, the test adjustment plan formulated according to the actual test requirements and environmental data is input into the virtualization platform. The virtualization platform can simulate the real hardware environment and allow testing without physical hardware. Multi-dimensional simulation tests are performed on the virtualization platform, which may include performance testing, stress testing, compatibility testing, etc. During the simulation test, the system will record detailed test logs, including the steps, time and results of the test execution. At the same time, it will also capture and record any errors or exceptions that occur, namely the simulation test logs and error information.

[0087] S32: Analyze the simulation test log and error information through a log analysis tool to obtain a virtual environment test result.

[0088] Specifically, a specialized log analysis tool is used to process and analyze the log data and error information collected during the simulation test. Based on the detailed reports and analysis results provided by the log analysis tool, testers can identify problems found in the test and formulate adjustment plans accordingly. By comprehensively considering the log analysis results and the test adjustment plan, testers can obtain comprehensive test results about the test environment, that is, the virtual environment test results.

[0089] In one embodiment, if Figure 6 As shown, the intelligent solid state hard disk quality detection method also includes:

[0090] S50: Feedback the virtual environment test results and the optimized adjustment plan to the pre-trained detection model, and continuously learn and update the pre-trained detection model according to the virtual environment test results and the optimized adjustment plan.

[0091] Specifically, the results obtained from the virtual environment test and the optimization adjustment plan formulated according to the test results are input into the pre-trained detection model, and the test data and the adjustment plan are used as new training samples for further training or fine-tuning the model. The pre-trained model is continuously learned and updated using the virtual environment test results and the optimized adjustment plan. The model continuously adjusts its parameters when receiving new data. In this way, the model can learn new test scenarios and adjustment strategies, thereby improving its adaptability and accuracy in practical applications.

[0092] S60: Based on the distributed test architecture, it coordinates the test nodes of the SSD to be tested to improve the test efficiency and flexibility.

[0093] Specifically, through a central control system or test management platform, the test tasks distributed on different nodes are coordinated. These nodes can simultaneously perform various tests on the solid-state drives, such as performance tests, durability tests, compatibility tests, etc. Each node is responsible for a part of the test tasks, thereby achieving parallel processing and improving test coverage and diversity.

[0094] S70: During the test, the operating status of the solid state drive to be tested is monitored in real time. If the operating status reaches a preset operating threshold, an alarm signal is generated and automatically sent to the user end.

[0095] Specifically, during the test, various sensors and monitoring tools are used to track the operating status of the SSD in real time, and a series of thresholds are set for the operating status of the SSD. These thresholds are set based on the technical specifications and performance standards of the SSD. For example, the temperature threshold can prevent overheating, and the error rate threshold can ensure the reliability of the data. When the monitored operating status of the SSD reaches or exceeds the preset threshold, the system will automatically generate an alarm signal, which will be automatically sent to the user or administrator of the SSD via email, SMS, application push or other communication methods, and necessary response measures will be taken, such as stopping the test, checking the hardware, updating the firmware or replacing the SSD.

[0096] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0097] In one embodiment, an intelligent solid-state hard disk quality detection system is provided, and the intelligent solid-state hard disk quality detection system corresponds one-to-one to the intelligent solid-state hard disk quality detection method in the above embodiment. Figure 7 As shown, the intelligent solid state hard disk quality inspection system includes a demand acquisition module, a model analysis module, a virtual test module and a solution adjustment module. The detailed description of each functional module is as follows:

[0098] The requirement acquisition module is used to acquire the test requirement data of the solid state drive to be tested, and extract the feature point data in the test requirement data from the test requirement data by using the feature extraction algorithm to obtain the requirement feature point data;

[0099] The model analysis module is used to obtain environmental data, transmit the demand feature point data and environmental data to the pre-trained detection model for comparison and analysis, and obtain the test adjustment plan;

[0100] A virtual test module is used to perform a virtual environment test according to a test adjustment plan and obtain a virtual environment test result;

[0101] The scheme adjustment module is used to obtain difference information from the virtual environment test results when the virtual environment test results do not meet expectations, modify the test adjustment scheme accordingly according to the difference information, obtain an optimized adjustment scheme, and adjust the test process and parameter configuration of the solid-state hard disk to be tested according to the optimized adjustment scheme.

[0102] Optionally, the intelligent solid state hard disk quality detection system further includes:

[0103] The historical data collection module is used to collect historical test data and actual failure cases of SSDs to be tested in different environments, pre-process and annotate the historical test data and actual failure cases to obtain a training set;

[0104] A model training module is used to perform forward propagation and back propagation training on the detection model built based on the convolutional neural network and the recurrent neural network using the training set to obtain the detection model after propagation training;

[0105] The model parameter optimization module is used to optimize the parameters of the detection model after propagation training using a genetic algorithm to obtain a pre-trained detection model.

[0106] A model updating module is used to feed back the virtual environment test results and the optimized adjustment plan to the pre-trained detection model, and continuously learn and update the pre-trained detection model according to the virtual environment test results and the optimized adjustment plan;

[0107] A parallel testing module is used to coordinate the test nodes of the SSD to be tested based on a distributed testing architecture;

[0108] The abnormal alarm module is used to monitor the operating status of the solid-state hard disk to be tested in real time during the test process. If the operating status reaches a preset operating threshold, an alarm signal is generated and automatically sent to the user end.

[0109] Optionally, the requirements module includes:

[0110] The project acquisition submodule is used to acquire the test items that the user needs to test for the solid-state hard disk to be tested through the user interface, and to statistically integrate the data of the test items to obtain the test requirement data of the solid-state hard disk to be tested;

[0111] The cluster analysis submodule is used to perform cluster analysis on the test demand data using the k-means algorithm to obtain demand feature point data.

[0112] Optionally, the model analysis module includes:

[0113] A real-time detection submodule is used to detect the data of the external environment of the solid-state hard disk to be detected in real time through an environmental sensor to obtain environmental data;

[0114] The normalization submodule is used to normalize the demand feature point data and the environmental data to obtain the normalized data, and compare and analyze the normalized data with the data in the pre-trained detection model to obtain a test adjustment plan.

[0115] Optional virtual test modules include:

[0116] The simulation submodule is used to input the test adjustment plan into the virtualization platform, perform multi-dimensional simulation tests according to the test adjustment plan, and obtain simulation test logs and error information;

[0117] The log analysis submodule is used to analyze the simulation test log and error information through the log analysis tool to obtain the virtual environment test results.

[0118] The specific definition of an intelligent solid-state hard disk quality detection system can be found in the definition of an intelligent solid-state hard disk quality detection method mentioned above, which will not be repeated here. Each module in the above-mentioned intelligent solid-state hard disk quality detection system can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0119] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent solid-state hard disk quality detection method is implemented.

[0120] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0121] Acquire test requirement data of the solid state drive to be tested, extract feature point data in the test requirement data from the test requirement data using a feature extraction algorithm, and obtain requirement feature point data;

[0122] Obtain environmental data, transfer the demand feature point data and environmental data to the pre-trained detection model for comparison and analysis, and obtain the test adjustment plan;

[0123] Perform virtual environment testing according to the test adjustment plan to obtain virtual environment testing results;

[0124] When the virtual environment test results do not meet expectations, difference information is obtained from the virtual environment test results, the test adjustment plan is modified accordingly according to the difference information to obtain an optimized adjustment plan, and the test process and parameter configuration of the solid state drive to be tested are adjusted according to the optimized adjustment plan.

[0125] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0126] Acquire test requirement data of the solid state drive to be tested, extract feature point data in the test requirement data from the test requirement data using a feature extraction algorithm, and obtain requirement feature point data;

[0127] Obtain environmental data, transfer the demand feature point data and environmental data to the pre-trained detection model for comparison and analysis, and obtain the test adjustment plan;

[0128] Perform virtual environment testing according to the test adjustment plan to obtain virtual environment testing results;

[0129] When the virtual environment test results do not meet expectations, difference information is obtained from the virtual environment test results, the test adjustment plan is modified accordingly according to the difference information to obtain an optimized adjustment plan, and the test process and parameter configuration of the solid state drive to be tested are adjusted according to the optimized adjustment plan.

[0130] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0131] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0132] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent solid state hard disk quality detection method, characterized in that: The intelligent solid state hard disk quality detection method comprises: Acquire test requirement data of a solid-state hard disk to be detected, and extract feature point data in the test requirement data from the test requirement data using a feature extraction algorithm to obtain requirement feature point data; the acquiring test requirement data of a solid-state hard disk to be detected, and extracting feature point data in the test requirement data from the test requirement data using a feature extraction algorithm to obtain requirement feature point data includes: acquiring test items that a user needs to test on the solid-state hard disk to be detected through a user interface, and statistically integrating the data of the test items to obtain the test requirement data of the solid-state hard disk to be detected; and performing cluster analysis on the test requirement data using a k-means algorithm to obtain the requirement feature point data; Collect historical test data and actual failure cases of solid state hard disks under different environments, pre-process and annotate the historical test data and actual failure cases of solid state hard disks under different environments to obtain a training set; Using the training set to perform forward propagation and back propagation training on a detection model built based on a convolutional neural network and a recurrent neural network, to obtain a detection model after propagation training; Optimizing the parameters of the detection model after propagation training by using a genetic algorithm to obtain a pre-trained detection model; Acquire environmental data, transmit the demand feature point data and the environmental data to a pre-trained detection model for comparison and analysis, and obtain a test adjustment plan; the acquisition of environmental data, transmit the demand feature point data and the environmental data to a pre-trained detection model for comparison and analysis, and obtain a test adjustment plan includes: performing real-time detection of the data of the external environment of the solid-state hard disk to be detected by an environmental sensor to obtain the environmental data; normalize the demand feature point data and the environmental data to obtain normalized data, and compare and analyze the normalized data with the data in the pre-trained detection model to obtain the test adjustment plan; Perform a virtual environment test according to the test adjustment plan to obtain a virtual environment test result; When the virtual environment test results do not meet expectations, difference information is obtained from the virtual environment test results, the test adjustment plan is modified accordingly according to the difference information to obtain an optimized adjustment plan, and the test process and parameter configuration of the solid-state hard drive to be tested are adjusted according to the optimized adjustment plan.

2. The intelligent solid state hard disk quality detection method according to claim 1, characterized in that: The performing of the virtual environment test according to the test adjustment scheme to obtain the virtual environment test result comprises: Input the test adjustment plan into the virtualization platform, perform multi-dimensional simulation tests according to the test adjustment plan, and obtain simulation test logs and error information; The simulation test log and error information are analyzed by a log analysis tool to obtain the virtual environment test result.

3. The intelligent solid state hard disk quality detection method according to claim 1, characterized in that: The intelligent solid state hard disk quality detection method further includes: Feeding back the virtual environment test results and the optimized adjustment scheme to the pre-trained detection model, and continuously learning and updating the pre-trained detection model according to the virtual environment test results and the optimized adjustment scheme; Based on the distributed testing architecture, multiple test nodes are coordinated to perform quality inspection of SSDs in parallel, improving testing efficiency and flexibility. During the test, the operating status of the solid-state hard disk to be tested is monitored in real time. If the operating status reaches a preset operating threshold, an alarm signal is generated and automatically sent to the user end.

4. An intelligent solid state hard disk quality detection system, characterized in that: The intelligent solid state hard disk quality detection system comprises: The requirement acquisition module is used to acquire the test requirement data of the solid state drive to be detected, and extract the feature point data in the test requirement data from the test requirement data by using a feature extraction algorithm to obtain the requirement feature point data; A historical data collection module is used to collect historical test data and actual failure cases of solid state hard disks under different environments, and pre-process and annotate the historical test data and actual failure cases of solid state hard disks under different environments to obtain a training set; A model training module, used to use the training set to perform forward propagation and back propagation training on the detection model constructed based on the convolutional neural network and the recurrent neural network to obtain the detection model after propagation training; A model parameter optimization module, used to optimize the parameters of the detection model after propagation training by using a genetic algorithm to obtain a pre-trained detection model; A model analysis module is used to obtain environmental data, transmit the demand feature point data and the environmental data to a pre-trained detection model for comparison and analysis, and obtain a test adjustment plan; A virtual testing module, used to perform a virtual environment test according to the test adjustment scheme to obtain a virtual environment test result; A scheme adjustment module, used for obtaining difference information from the virtual environment test result when the virtual environment test result does not meet expectations, modifying the test adjustment scheme accordingly according to the difference information to obtain an optimized adjustment scheme, and adjusting the test process and parameter configuration of the solid state drive to be tested according to the optimized adjustment scheme; The acquisition requirement module includes: an acquisition item submodule, which is used to acquire the test items that the user needs to test the solid-state hard disk to be tested through the user interface, and statistically integrate the data of the test items to obtain the test requirement data of the solid-state hard disk to be tested; a cluster analysis submodule, which is used to perform cluster analysis on the test requirement data using the k-means algorithm to obtain the requirement feature point data; The model analysis module includes: a real-time detection submodule, which is used to perform real-time detection of the data of the external environment of the solid-state hard disk to be detected through an environmental sensor to obtain the environmental data; a normalization submodule, which is used to normalize the demand feature point data and the environmental data to obtain the normalized data, and compare and analyze the normalized data with the data in the pre-trained detection model to obtain the test adjustment plan.

5. The intelligent solid state hard disk quality detection system according to claim 4, characterized in that: The intelligent solid state hard disk quality detection system further includes: A model updating module, used for feeding back the virtual environment test results and the optimized adjustment scheme to the pre-trained detection model, and continuously learning and updating the pre-trained detection model according to the virtual environment test results and the optimized adjustment scheme; The parallel testing module is used to coordinate multiple test nodes to perform quality inspection on SSDs in parallel based on a distributed testing architecture; The abnormal alarm module is used to monitor the operating status of the solid-state hard disk to be tested in real time during the test process. If the operating status reaches a preset operating threshold, an alarm signal is generated and automatically sent to the user end.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of an intelligent solid state hard disk quality detection method as described in any one of claims 1 to 3 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of an intelligent solid state hard disk quality detection method as described in any one of claims 1 to 3 are implemented.

Images