CPU stable operation verification method, system, computer motherboard and storage medium

Through interface testing, program testing and verification of models, the stability of laptop CPU on desktop computer motherboard is verified, which solves the problem of insufficient accuracy in the existing technology, and improves the accuracy and system stability of CPU stability verification.

CN117909156BActive Publication Date: 2024-11-08SHENZHEN GUOSHUOHONG ELECTRONICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410084582.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-19
Publication Date
2024-11-08
Estimated Expiration
2044-01-19

AI Technical Summary

Technical Problem

When verifying whether the laptop CPU is running stably on the desktop computer motherboard, the existing technology only relies on CPU test parameters and real-time status data, which is insufficient accuracy and it is difficult to accurately judge the stability of the CPU.

Method used

Through interface testing tasks, program testing processes and target verification models, verify whether the physical connection between the laptop CPU and the desktop computer motherboard is normal, drive the CPU into the program testing process, verify whether the main frequency meets the preset threshold, and use the pre-trained verification model The stability of the CPU is judged based on the running data.

Benefits of technology

Improve the accuracy and comprehensiveness of CPU stability verification, reduce misjudgments caused by physical connection abnormalities or unstable factors, and ensure system stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117909156B_ABST
    Figure CN117909156B_ABST
Patent Text Reader

Abstract

The present application relates to the field of communication technology, and in particular to a method, system, computer motherboard and storage medium for verifying the stable operation of a CPU. The present application verifies whether the physical connection port between the CPU of a laptop computer and the computer motherboard of a desktop computer is normally connected according to a pre-established interface test task. When it is determined that the physical connection port is normally connected, the CPU is driven to enter a program test process, and it is verified whether there is a target test subprocess in the program test process that causes the CPU to be unstable. When it is determined that there is no target test subprocess in the program test process, the CPU main frequency of the CPU is controlled to meet a preset main frequency threshold, and the first operating data corresponding to the CPU under the preset main frequency threshold is obtained. The CPU stability of the CPU is further verified based on the first operating data using a pre-trained target verification model, thereby improving the comprehensiveness and accuracy of the CPU stability verification.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method, system, computer motherboard and storage medium for verifying stable operation of a CPU. Background Art

[0002] At present, with the continuous advancement of computer hardware technology, users often need to combine or replace hardware components of different brands and models. Among them, the use of laptop CPUs for desktop computer motherboards is gradually increasing. Since there are differences between laptop CPUs and desktop CPUs, when applying laptop CPUs to desktop computer motherboards, it is necessary to verify whether the laptop CPU can run stably on the desktop computer motherboard.

[0003] In the prior art, by obtaining CPU test parameters and CPU real-time status data, it is determined whether they are within the effective floating range based on the difference between the CPU test parameters and the CPU real-time status data. If so, it is determined that the CPU is operating normally; if not, it is determined that the CPU is operating abnormally. It is not accurate to verify whether the CPU is operating stably by relying on only two sets of data. Summary of the invention

[0004] In view of the above, the present application provides a method, system, computer motherboard and storage medium for verifying the stable operation of the CPU, which verifies whether the CPU is running stably through interface test tasks, program test processes and target verification models, thereby improving the accuracy of verification of the stable operation of the CPU.

[0005] A first aspect of the present application provides a method for verifying stable operation of a CPU, the method comprising:

[0006] Verify that the physical connection between the laptop's CPU and the desktop's motherboard is working properly according to the pre-defined interface test tasks;

[0007] When it is determined that the physical connection port is normally connected, the CPU is driven to enter a program test process, and it is verified whether the program test process has a target test subprocess, wherein the target test subprocess is a test subprocess in the program test process that causes the CPU to become unstable;

[0008] When it is determined that the target test subprocess does not exist in the program test process, controlling the CPU main frequency of the CPU to meet a preset main frequency threshold;

[0009] Acquire first operating data corresponding to the CPU under the preset main frequency threshold;

[0010] The CPU stability of the CPU is verified based on the first operating data using a pre-trained target verification model.

[0011] In an optional implementation, the program test process includes program installation, program update, and program uninstallation, and driving the CPU to enter the program test process and verifying whether the program test process has a target test subprocess includes:

[0012] Acquire from the driver library a first driver corresponding to the program installation, a second driver corresponding to the program update, and a third driver corresponding to the program uninstallation;

[0013] Using the first driver to drive the CPU to execute the program installation;

[0014] When it is determined that the first test result corresponding to the program installation is a test success, using the second driver to drive the CPU to execute the program update;

[0015] When it is determined that the second test result corresponding to the program update is a test success, using the third driver to drive the CPU to execute the program uninstallation;

[0016] When it is determined that the third test result corresponding to the program update is a test success, determining that the target test subprocess does not exist in the program test process;

[0017] When it is determined that the first test result is a test failure, and / or the second test result is a test failure, and / or the third test result is a test failure, it is determined that the target test subprocess exists in the program test process.

[0018] In an optional implementation, the first operation data includes CPU load, and the method further includes:

[0019] Verify whether the second operation data of the CPU has abnormal data according to the CPU load and the preset load threshold segment interval;

[0020] Compare the second operating data with the standard operating data corresponding to the CPU in the preset load threshold segmentation interval;

[0021] When it is determined that the second operating data is less than the standard operating data, determining that the second operating data does not contain the abnormal data;

[0022] When it is determined that the second operating data is greater than the standard operating data, determining that the second operating data contains the abnormal data, and determining a target alarm mode corresponding to the abnormal data;

[0023] An alarm is issued according to the target alarm mode, and a record log is generated.

[0024] In an optional implementation, the second operating data includes CPU temperature, the standard operating data includes a temperature threshold, and the method further includes:

[0025] Determine whether the CPU temperature is greater than the temperature threshold;

[0026] When it is determined that the CPU temperature is greater than the temperature threshold, the heat dissipation frequency of the computer motherboard is adjusted so that the CPU temperature is less than the temperature threshold.

[0027] In an optional embodiment, the second operating data includes a data transmission speed, the standard operating data includes a speed threshold, and the method further includes:

[0028] Verifying whether the data transmission speed satisfies the speed threshold;

[0029] When it is determined that the data transmission speed meets the speed threshold, the target data transmission amount and the actual data transmission amount corresponding to the CPU at the data transmission speed within a preset time period are obtained,

[0030] A verification report is generated according to the preset load threshold segment interval, the data transmission speed, the target data transmission volume and the actual data transmission volume.

[0031] In an optional embodiment, the method further comprises:

[0032] Step 1, obtaining historical operation data corresponding to each CPU in the plurality of CPUs being under the preset main frequency threshold, so as to obtain a historical operation data set, wherein each historical operation data in the historical operation data set includes historical CPU stability;

[0033] Step 2: preprocess each of the historical operation data to obtain a target training sample set;

[0034] Step 3: construct an initial verification model based on the feedforward neural network model;

[0035] Step 4: input the target training sample into the initial verification model to obtain a verification result corresponding to the target training sample, wherein the target training sample is any one of the target training sample sets;

[0036] Step 5: adjusting the loss function in the initial verification model based on the difference between the verification result and the historical CPU stability in the target training sample;

[0037] Step 6, iteratively executing steps 4 to 5 based on the adjusted loss function until a preset iteration termination condition is met;

[0038] Step 7: Determine the initial verification model that meets the preset iteration termination condition as the target verification model.

[0039] In an optional implementation, the preprocessing of each historical operation data to obtain a target training sample set includes:

[0040] Calculate the correlation coefficient between each sub-operation data in each historical operation data and the historical CPU stability;

[0041] comparing the correlation coefficient with a preset coefficient threshold;

[0042] Determine the sub-operation data in the historical operation data set whose correlation coefficient is greater than the preset coefficient threshold as the operation data training set;

[0043] Determine a CPU stability training set corresponding to the operation data training set from the historical CPU stability in the historical operation data set;

[0044] The operation data training set and the CPU stability training set are normalized, and the normalized operation data training set and the CPU stability training set are determined as the target training sample set.

[0045] A second aspect of the present application provides a CPU stable operation verification system, the system comprising:

[0046] The first verification module is used to verify whether the physical connection interface between the CPU of the notebook computer and the computer motherboard of the desktop computer is normally connected according to a pre-defined interface test task;

[0047] A second verification module is used to drive the CPU to enter a program test process when it is determined that the physical connection port is normally connected, and verify whether there is a target test subprocess in the program test process, wherein the target test subprocess is a test subprocess in the program test process that causes the CPU to become unstable;

[0048] A control module, configured to control the CPU main frequency of the CPU to meet a preset main frequency threshold when it is determined that the target test subprocess does not exist in the program test process;

[0049] An acquisition module, used for acquiring first operation data corresponding to the CPU under the preset main frequency threshold;

[0050] The third verification module is used to verify the CPU stability of the CPU based on the first operating data by using a pre-trained target verification model.

[0051] A third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, steps of a method for verifying stable operation of the CPU are implemented.

[0052] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for verifying stable operation of the CPU.

[0053] In summary, the verification method, system, computer motherboard and storage medium for stable operation of the CPU provided in the present application can reduce the misjudgment of CPU stability caused by abnormal connection of the physical connection port in the subsequent CPU stability verification process by verifying whether the physical connection port between the CPU of the laptop computer and the computer motherboard of the desktop computer is connected normally according to the interface test task, thereby improving the stability of the system. Then, the CPU is driven to enter the program test process, and it is verified whether there is a test sub-process in the program test process that causes the CPU to be unstable, thereby reducing the instability factors in the subsequent stability verification. The CPU main frequency of the CPU is further controlled to meet the preset main frequency threshold, and the first operating data corresponding to the CPU under the preset main frequency threshold is obtained, and the CPU stability of the CPU is verified based on the first operating data using the pre-trained target verification model, thereby improving the comprehensiveness and accuracy of the CPU stability verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of a method for verifying stable operation of a CPU shown in an embodiment of the present application;

[0055] Figure 2 It is a functional module diagram of a CPU stable operation verification system shown in an embodiment of the present application;

[0056] Figure 3 It is a schematic diagram of the structure of a computer motherboard shown in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0058] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0059] Reference Figure 1 , which is a flow chart of a method for verifying stable operation of a CPU according to an embodiment of the present application, and the method for verifying stable operation of a CPU includes the following steps.

[0060] S11, verifying whether the physical connection interface between the CPU of the notebook computer and the computer motherboard of the desktop computer is normally connected according to a pre-defined interface test task.

[0061] When the CPU of a laptop is installed on the computer motherboard of a desktop computer, it is necessary to verify whether the CPU is in communication connection with the computer motherboard. The interface test task may include an I / O interface test, a memory interface test, a storage interface test, a power interface test, etc. When the physical connection port between the CPU of the laptop and the computer motherboard of the desktop computer is normally connected, the modules corresponding to the I / O interface, the memory interface, the storage interface and the power interface can operate normally. The interface test task may also include a test sequence, and each sub-test task in the interface test task is executed according to the test sequence. For example, the test sequence corresponding to the I / O interface test is 1, the test sequence corresponding to the power interface test is 2, the test sequence corresponding to the memory interface test is 3, and the test sequence corresponding to the storage interface test is 4. That is, the test of the I / O interface test is executed first, and when the test result of the I / O interface test is a successful test, the power interface test is executed, and when the test result of the power interface test is a successful test, the memory interface test is executed, and when the test result of the memory interface test is a successful test, the storage interface test is executed. When the test results of the I / O interface test, the memory interface test, the storage interface test, and the power interface test are all qualified, it can be determined that the physical connection port between the CPU of the laptop computer and the computer motherboard of the desktop computer is normally connected.

[0062] In some embodiments, a verification interaction interface may be pre-set, and when an interface test task is executed, the test results may be visually displayed through the verification interaction interface.

[0063] Through the above-mentioned optional implementation mode, the interface test task is executed according to the test sequence to verify whether the physical interface between the CPU and the computer motherboard is correctly connected. This can quickly locate which of the physical interfaces has a connection abnormality, reduce the fluctuation of the CPU stability corresponding to the CPU of the laptop computer caused by the physical interface connection abnormality, and improve the system stability.

[0064] After confirming that the physical interface is connected normally, the communication connection between the CPU and the computer motherboard can be confirmed so that the CPU can operate normally.

[0065] S12, when it is determined that the physical connection port is normally connected, driving the CPU to enter a program test process, and verifying whether the program test process has a target test subprocess.

[0066] The target test subprocess is a test subprocess in the program test process that causes the CPU to become unstable.

[0067] After verifying that the physical connection between the CPU of the laptop and the computer motherboard of the desktop computer is normally connected, the CPU can be driven to enter the program test process. The program test process may include program installation, program update, and program uninstallation.

[0068] In some embodiments, the driver corresponding to the program test process can be stored in the driver library in advance, and the corresponding test sequence for the program installation, program update, and program uninstallation of the program test process can be set in advance. When it is determined that the physical connection port between the CPU of the laptop computer and the computer motherboard of the desktop computer is normally connected, the first driver corresponding to the program installation is immediately obtained from the driver library, and the first driver is used to drive the CPU of the laptop computer to execute the program installation, and verify whether the first test result corresponding to the program installation is a test success. When it is determined that the first test result is a test success, the second driver corresponding to the program update is obtained from the driver library, and the second driver is used to drive the CPU of the laptop computer to execute the program update, and verify whether the second test result corresponding to the program update is a test success. When it is determined that the second test result is a test success, the third driver corresponding to the program uninstallation is obtained from the driver library, and the third driver is used to drive the CPU of the laptop computer to execute the program uninstallation, and verify whether the third test result corresponding to the program uninstallation is a test success. When it is determined that the third test result is a test success, it is determined that the program test process does not have a test subprocess that causes the CPU of the laptop computer to produce an unstable phenomenon. When it is confirmed that the first test result is a test failure, and / or when it is determined that the second test result is a test failure, and / or when it is determined that the third test result is a test failure, it is determined that there is a test sub-process in the program test process that causes the CPU to become unstable.

[0069] In some embodiments, when the first test result is indeed a test failure, a first error log file is generated according to the first test result, and the specific error information causing the first test result to be a test failure is determined according to the first error log file, such as whether the first driver is complete and not damaged, whether the first driver is compatible with the CPU of the notebook computer, etc. When it is determined that the first driver is incomplete or the first driver is complete but damaged, the first driver in the driver library is updated, and the CPU of the notebook computer is re-driven to execute the program installation using the updated first driver. When it is determined that the first driver is incompatible with the CPU of the notebook computer, the CPU architecture corresponding to the CPU of the notebook computer is determined, and the first driver in the driver library is updated to support the CPU architecture, and the CPU of the notebook computer is re-driven to execute the program installation using the updated first driver.

[0070] When it is determined that the second test result is a test failure and / or the third test result is a test failure, the second driver and / or the third driver are updated according to the same embodiment as above, and the updated second driver is used to redrive the CPU of the laptop computer to execute the program update, and / or the updated third driver is used to redrive the CPU of the laptop computer to execute the program uninstall.

[0071] Through the above-mentioned optional implementation method, the driver drives the CPU of the laptop computer to execute program installation, program update, and program uninstallation in accordance with the test sequence, so as to fully verify the compatibility of the CPU with different types of application installation, update and uninstallation processes, and verify the stability of the CPU in different usage scenarios, thereby ensuring that the CPU of the laptop computer can run stably in different usage scenarios of the desktop computer.

[0072] S13, when it is determined that the target test sub-process does not exist in the program test process, controlling the CPU main frequency of the CPU to meet a preset main frequency threshold.

[0073] In some embodiments, a main frequency threshold can be preset to determine whether the main frequency of the CPU corresponding to the laptop computer's CPU is in a CPU overclocking state. When it is determined that the test results corresponding to the program installation, program update, and program uninstallation are all successful, the main frequency of the CPU corresponding to the laptop computer's CPU is controlled to meet the preset main frequency threshold, that is, the main frequency of the CPU is controlled to be in a CPU overclocking state.

[0074] S14, obtaining first operating data corresponding to the CPU under the preset main frequency threshold.

[0075] When the CPU main frequency is in the CPU overclocking state, the operation data corresponding to the CPU of the laptop computer in the CPU overclocking state is obtained, and the operation data generated when the CPU is running in the CPU overclocking state is called the first operation data. The first operation data may include CPU voltage, CPU current, CPU load, CPU power, etc.

[0076] S15, using a pre-trained target verification model to verify the CPU stability of the CPU based on the first operating data.

[0077] In some embodiments, the historical operation data corresponding to each CPU of multiple laptop computers in a CPU overclocking state can be obtained in advance, and a target verification model can be trained based on a feedforward neural network model using the historical operation data. When the training is completed, the first operation data obtained is input into the target verification model, and the CPU stability corresponding to the first operation data can be output. According to the CPU stability output by the target verification model, it is determined whether the CPU of the laptop computer is running stably on the computer motherboard of the desktop computer.

[0078] In some embodiments, when training the target verification model, historical operating data can be used to annotate CPU stability. During the training process, the CPU stability can be converted into data so that the CPU stability output by the target verification model is a continuous value. A numerical threshold can also be pre-set to divide the output CPU stability into two categories: "stable" and "unstable". Exemplarily, assuming that the numerical threshold is 0.75, when the CPU stability output by the target verification model is greater than or equal to 0.75, the CPU stability corresponding to the first operating data is determined to be "stable", and when the CPU stability output by the target verification model is less than 0.75, the CPU stability corresponding to the first operating data is determined to be "unstable".

[0079] Through the above optional implementation, by verifying the model, the stability of the CPU in the overclocked state can be known in advance. When the model output indicates that the CPU is unstable at the CPU main frequency, the overclocking setting can be reduced in time to balance the performance and stability of the CPU.

[0080] In an optional embodiment, the method further comprises:

[0081] Step 1, obtaining historical operation data corresponding to each CPU in the plurality of CPUs being under the preset main frequency threshold, so as to obtain a historical operation data set, wherein each historical operation data in the historical operation data set includes historical CPU stability;

[0082] Step 2: preprocess each of the historical operation data to obtain a target training sample set;

[0083] Step 3: construct an initial verification model based on the feedforward neural network model;

[0084] Step 4: input the target training sample into the initial verification model to obtain a verification result corresponding to the target training sample, wherein the target training sample is any one of the target training sample sets;

[0085] Step 5: adjusting the loss function in the initial verification model based on the difference between the verification result and the historical CPU stability in the target training sample;

[0086] Step 6, iteratively executing steps 4 to 5 based on the adjusted loss function until a preset iteration termination condition is met;

[0087] Step 7: Determine the initial verification model that meets the preset iteration termination condition as the target verification model.

[0088] In some embodiments, when historical operation data of the CPU main frequency of multiple CPUs is obtained under a preset main frequency threshold, a historical operation data set sufficient for training is obtained. Wherein, each historical operation data in the historical operation data set includes historical CPU stability. After the historical operation data set is obtained, each historical operation data in the historical operation data set can be preprocessed to obtain a target training sample set. Specifically, each historical operation data can be traversed, and the correlation coefficient between each sub-operation data and the historical CPU stability in each historical operation data can be calculated, for example, the Spearman correlation coefficient or the Pearson correlation coefficient. By comparing the calculated correlation coefficient with a preset coefficient threshold, when it is determined that the correlation coefficient is greater than the preset coefficient threshold, it can be determined that the sub-operation data in the historical operation data set corresponding to the correlation coefficient greater than the preset coefficient threshold is data with a strong correlation with the historical CPU stability, and the sub-operation data is determined as the operation data training set, and the historical CPU stability corresponding to the sub-operation data in the historical operation data set is determined as the CPU stability training set corresponding to the operation data training set. Furthermore, each sub-operation data and each historical CPU stability in the operation data training set and the CPU stability training set are normalized to obtain a target training sample set for training.

[0089] In some embodiments, an initial verification model can be constructed based on a feedforward neural network model (e.g., a generalized regression neural network (GRNN)). GRNN is a feedforward neural network model based on nonlinear regression theory, which uses sample data as a posteriori condition, performs Parzen nonparametric estimation, and calculates network output based on the maximum probability principle; the GRNN model is based on a radial basis function neural network, has strong nonlinear mapping capabilities and learning speed, and has a good processing effect on small samples and unstable data. The GRNN model consists of an input layer, a pattern layer, a summation layer, and an output layer.

[0090] After the initial verification model is constructed, a training sample can be randomly selected from the target training sample set as the target training sample, and the target training sample can be input into the initial verification model to obtain the verification result corresponding to the target training sample. Since each training sample in the target training sample set includes historical CPU stability, the target training sample can be verified by the initial verification model. After obtaining the verification result, the loss function of the initial verification model can be adjusted based on the difference between the verification result and the historical CPU stability corresponding to the target training sample. That is, the difference between the actual value of the training sample and the output value of the last layer of the neural network structure when the initial verification model is used to train the training sample can be determined, and the loss function of the initial verification model can be adjusted by the difference until the preset iteration termination condition is met. In the process of each iterative training, it will be verified whether the current iterative training has met the preset iteration termination condition. If the preset iteration termination condition is met, the iterative training is stopped, and the initial verification model when the preset iteration termination condition is met is determined as the target verification model.

[0091] In some embodiments, a threshold of the number of iterations is preset (for example, 100 times). When the number of iterations meets the threshold of the number of iterations, it can be determined that the current training meets the preset iteration termination condition. In other embodiments, it can also be determined whether the loss function of the initial verification model has converged, that is, when it is determined that the loss function of the initial verification model no longer changes significantly after multiple iterations, it can be determined that the loss function of the initial verification model has converged, and it is determined that the current training meets the preset iteration termination condition.

[0092] In an optional implementation, the first operation data includes CPU load, and the method further includes:

[0093] Verify whether the second operation data of the CPU has abnormal data according to the CPU load and the preset load threshold segment interval;

[0094] Compare the second operating data with the standard operating data corresponding to the CPU in the preset load threshold segmentation interval;

[0095] When it is determined that the second operating data is less than the standard operating data, determining that the second operating data does not contain the abnormal data;

[0096] When it is determined that the second operating data is greater than the standard operating data, determining that the second operating data contains the abnormal data, and determining a target alarm mode corresponding to the abnormal data;

[0097] An alarm is issued according to the target alarm mode, and a record log is generated.

[0098] The preset load threshold segment interval includes multiple load threshold intervals, for example, a low load interval, a medium load interval, and a high load interval. Each load threshold interval corresponds to a standard operating data. The second operating data corresponds to the standard operating data one by one, and the second operating data may include CPU occupancy, CPU current, CPU temperature, CPU power consumption, etc. When the second operating data is CPU temperature, the corresponding standard operating data may be a temperature threshold.

[0099] In some embodiments, multiple load threshold intervals can be pre-set. When the first operation data is the CPU load, the CPU load is controlled to be in each load threshold interval, and the second operation data corresponding to the CPU in the load threshold interval is obtained, and the second operation data is verified according to the standard operation data corresponding to the CPU in the load threshold interval. Wherein, the standard operation data refers to the operation data corresponding to the stable operation of the CPU in the load threshold interval. When it is determined that the second operation data is less than or equal to the standard operation data, it can be determined that there is no abnormal data in the second operation data. When it is determined that the second operation data is greater than the standard operation data, it can be determined that there is abnormal data in the second operation data, and the target alarm mode corresponding to the abnormal data can be further determined. Wherein, the second operation data may include multiple operation data, each operation data corresponds to an alarm mode. When it is determined that there is abnormal data in the second operation data, it is determined to which type of operation data the abnormal data belongs, and an alarm is issued according to the target alarm mode corresponding to the operation data. In addition to the alarm, the computer motherboard can also generate a record log to record which operation data has an abnormality and causes the unstable operation of the CPU.

[0100] In some embodiments, a relationship mapping table may be pre-set according to each load threshold interval and standard operation data. After determining which load threshold interval the CPU load is in, the standard operation data corresponding to the CPU in the load threshold segment interval is obtained from the relationship mapping table.

[0101] In an optional implementation, the second operating data includes CPU temperature, the standard operating data includes a temperature threshold, and the method further includes:

[0102] Determine whether the CPU temperature is greater than the temperature threshold;

[0103] When it is determined that the CPU temperature is greater than the temperature threshold, the heat dissipation frequency of the computer motherboard is adjusted so that the CPU temperature is less than the temperature threshold.

[0104] When the second operating data is the CPU temperature, the corresponding standard operating data is the temperature threshold.

[0105] In some embodiments, when the CPU load is in different load threshold intervals, different temperature thresholds correspond. When the CPU temperature is obtained, the CPU temperature is compared with the temperature threshold corresponding to the load threshold interval. When it is determined that the CPU temperature is greater than the temperature threshold, it means that the CPU is in an unstable operating state, and the heat dissipation frequency of the computer motherboard can be increased. For example, a heat dissipation device (e.g., fan) speed control curve is set in the basic input output system (BIOS) of the computer motherboard, and the heat dissipation frequency is adjusted by adjusting the speed control curve so that the CPU temperature is reduced to below the temperature threshold corresponding to the load threshold interval, ensuring that the CPU can maintain an appropriate CPU temperature under different CPU loads, so that the CPU's operating state can be further adjusted to achieve stability.

[0106] Exemplarily, when the CPU load is in the first load threshold interval, i.e., the low load interval, it corresponds to the first temperature threshold, for example, 25° C. When the CPU load is in the second load threshold interval, i.e., the medium load interval, it corresponds to the second temperature threshold, for example, 40° C. When the CPU load is in the third load threshold interval, i.e., the high load interval, it corresponds to the third temperature threshold, for example, 50° C.

[0107] In an optional embodiment, the second operating data includes a data transmission speed, the standard operating data includes a speed threshold, and the method further includes:

[0108] Verifying whether the data transmission speed satisfies the speed threshold;

[0109] When it is determined that the data transmission speed meets the speed threshold, the target data transmission amount and the actual data transmission amount corresponding to the CPU at the data transmission speed within a preset time period are obtained,

[0110] A verification report is generated according to the preset load threshold segment interval, the data transmission speed, the target data transmission volume and the actual data transmission volume.

[0111] In some embodiments, when the second operating data is the data transmission speed, the corresponding standard operating data is the speed threshold. The data transmission speed corresponding to the CPU in each load threshold interval in the preset load threshold segmentation interval is obtained, and the data transmission speed and the speed threshold are compared to verify whether the operating state of the CPU in the corresponding load threshold interval is stable. When it is determined that the data transmission speed does not meet the speed threshold, the reasons causing the data transmission speed not to meet the speed threshold can be determined, such as network bandwidth, load balancing, etc. It is preferentially determined whether there is a problem with the network bandwidth. When it is determined that the data transmission speed does not meet the speed threshold due to the network bandwidth, the network bandwidth can be increased. When it is determined that there is no problem with the network bandwidth, that is, the data transmission speed does not meet the speed threshold due to the network bandwidth, it can be determined that the unstable CPU operating state is due to CPU load imbalance.

[0112] When it is determined that the data transmission speed meets the speed threshold, the data transmission volume corresponding to the CPU at the data transmission speed within a preset time period (for example, 10 minutes) can be obtained. The target data transmission volume refers to the actual data transmission volume of the CPU at the data transmission speed within the preset time period, and the actual data transmission volume is the data transmission volume that needs to be transmitted within the preset time period. Further, a verification report including the target data transmission volume and the actual data transmission volume corresponding to the CPU under the preset load threshold segmentation interval and the data transmission speed can be generated.

[0113] In some embodiments, the target data transmission volume may be compared with the actual data transmission volume to verify whether there is data packet loss at the data transmission speed.

[0114] Reference Figure 2 , which is a functional module diagram of a CPU stable operation verification system shown in an embodiment of the present application.

[0115] In some embodiments, the CPU stable operation verification system 20 may include multiple functional modules composed of computer program segments. The computer programs of the various program segments of the CPU stable operation verification system 20 may be stored in the memory of the electronic device and executed by at least one processor to perform (see Figure 1 Description) This function verifies the stable operation of the CPU.

[0116] In this embodiment, the verification system 20 for stable operation of the CPU can be divided into multiple functional modules according to the functions performed. The functional modules may include: a first verification module 201, a second verification module 202, a control module 203, an acquisition module 204, a third verification module 205 and a fourth verification module 206. The module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0117] The first verification module 201 is used to verify whether the physical connection interface between the CPU of the notebook computer and the computer motherboard of the desktop computer is normally connected according to a pre-defined interface test task.

[0118] The second verification module 202 is used to drive the CPU to enter the program test process when it is determined that the physical connection port is normally connected, and to verify whether there is a target test sub-process in the program test process, wherein the target test sub-process is the test sub-process in the program test process that causes the CPU to become unstable.

[0119] The second verification module 202 is further specifically configured to:

[0120] Acquire from the driver library a first driver corresponding to the program installation, a second driver corresponding to the program update, and a third driver corresponding to the program uninstallation;

[0121] Using the first driver to drive the CPU to execute the program installation;

[0122] When it is determined that the first test result corresponding to the program installation is a test success, using the second driver to drive the CPU to execute the program update;

[0123] When it is determined that the second test result corresponding to the program update is a test success, using the third driver to drive the CPU to execute the program uninstallation;

[0124] When it is determined that the third test result corresponding to the program update is a test success, determining that the target test subprocess does not exist in the program test process;

[0125] When it is determined that the first test result is a test failure, and / or the second test result is a test failure, and / or the third test result is a test failure, it is determined that the target test subprocess exists in the program test process.

[0126] The control module 203 is used to control the CPU main frequency of the CPU to meet a preset main frequency threshold when it is determined that the target test sub-process does not exist in the program test process.

[0127] The acquisition module 204 is used to acquire first operating data corresponding to the CPU under the preset main frequency threshold.

[0128] The third verification module 205 is used to verify the CPU stability of the CPU based on the first operating data using a pre-trained target verification model.

[0129] The fourth verification module 206 is used to:

[0130] Verify whether the second operation data of the CPU has abnormal data according to the CPU load and the preset load threshold segment interval;

[0131] Compare the second operating data with the standard operating data corresponding to the CPU in the preset load threshold segmentation interval;

[0132] When it is determined that the second operating data is less than the standard operating data, determining that the second operating data does not contain the abnormal data;

[0133] When it is determined that the second operating data is greater than the standard operating data, determining that the second operating data contains the abnormal data, and determining a target alarm mode corresponding to the abnormal data;

[0134] An alarm is issued according to the target alarm mode, and a record log is generated.

[0135] The fourth verification module 206 is further used for:

[0136] Determine whether the CPU temperature is greater than the temperature threshold;

[0137] When it is determined that the CPU temperature is greater than the temperature threshold, the heat dissipation frequency of the computer motherboard is adjusted so that the CPU temperature is less than the temperature threshold.

[0138] The fourth verification module 206 is further used for:

[0139] Verifying whether the data transmission speed satisfies the speed threshold;

[0140] When it is determined that the data transmission speed meets the speed threshold, the target data transmission amount and the actual data transmission amount corresponding to the CPU at the data transmission speed within a preset time period are obtained,

[0141] A verification report is generated according to the preset load threshold segment interval, the data transmission speed, the target data transmission volume and the actual data transmission volume.

[0142] The third verification module 205 is further used for:

[0143] Step 1, obtaining historical operation data corresponding to each CPU in the plurality of CPUs being under the preset main frequency threshold, so as to obtain a historical operation data set, wherein each historical operation data in the historical operation data set includes historical CPU stability;

[0144] Step 2: preprocess each of the historical operation data to obtain a target training sample set;

[0145] Step 3: construct an initial verification model based on the feedforward neural network model;

[0146] Step 4: input the target training sample into the initial verification model to obtain a verification result corresponding to the target training sample, wherein the target training sample is any one of the target training sample sets;

[0147] Step 5: adjusting the loss function in the initial verification model based on the difference between the verification result and the historical CPU stability in the target training sample;

[0148] Step 6, iteratively executing steps 4 to 5 based on the adjusted loss function until a preset iteration termination condition is met;

[0149] Step 7: Determine the initial verification model that meets the preset iteration termination condition as the target verification model.

[0150] The third verification module 205 is further specifically used for:

[0151] Calculate the correlation coefficient between each sub-operation data in each historical operation data and the historical CPU stability;

[0152] comparing the correlation coefficient with a preset coefficient threshold;

[0153] Determine the sub-operation data in the historical operation data set whose correlation coefficient is greater than the preset coefficient threshold as the operation data training set;

[0154] Determine a CPU stability training set corresponding to the operation data training set from the historical CPU stability in the historical operation data set;

[0155] The operation data training set and the CPU stability training set are normalized, and the normalized operation data training set and the CPU stability training set are determined as the target training sample set.

[0156] It should be understood that the various variations and specific embodiments of the CPU stable operation verification method provided in the above-mentioned embodiments are also applicable to the CPU stable operation verification system of the present embodiment. Through the above-mentioned detailed description of the CPU stable operation verification method, those skilled in the art can clearly know the implementation method of the CPU stable operation verification system in the present embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0157] See also Figure 3 , which is a schematic diagram of the structure of a computer motherboard according to an embodiment of the present application. In a preferred embodiment of the present application, the computer motherboard 3 includes a memory 31 , at least one processor 32 and at least one communication bus 33 .

[0158] Those skilled in the art should understand that Figure 3 The structure of the electronic device shown does not constitute a limitation of the embodiments of the present application, and the computer motherboard 3 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components. In some embodiments, a computer program is stored in the memory 31, and when the computer program is executed by the at least one processor 32, all or part of the steps in the verification method for stable operation of the CPU as described above are implemented. The at least one processor 32 is the control core (Control Unit) of the computer motherboard 3, and uses various interfaces and lines to connect the various components of the entire computer motherboard 3, and executes or executes the programs or modules stored in the memory 31, and calls the data stored in the memory 31 to execute various functions of the computer motherboard 3 and process data.

[0159] The above integrated unit implemented in the form of software function modules can be stored in a computer-readable storage medium.

[0160] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for verifying stable operation of a CPU, characterized in that: The method comprises: Verify whether the physical connection interface between the CPU of the laptop and the computer motherboard of the desktop computer is normally connected according to the pre-defined interface test tasks, wherein the interface test tasks include I / O interface test, memory interface test, storage interface test and power interface test; When it is determined that the physical connection port is normally connected, the CPU is driven to enter a program test process, and it is verified whether the program test process has a target test subprocess, wherein the target test subprocess is a test subprocess in the program test process that causes the CPU to be unstable, and the program test process includes program installation, program update, and program uninstallation; When it is determined that the target test subprocess does not exist in the program test process, controlling the CPU main frequency of the CPU to meet a preset main frequency threshold; Acquire first operating data corresponding to the CPU under the preset main frequency threshold; Verifying the CPU stability of the CPU based on the first operating data using a pre-trained target verification model; The driving the CPU to enter the program test process and verifying whether the program test process has a target test subprocess includes: Acquire from a driver library a first driver corresponding to the program installation, a second driver corresponding to the program update, and a third driver corresponding to the program uninstallation; Using the first driver to drive the CPU to execute the program installation; When it is determined that the first test result corresponding to the program installation is a test success, using the second driver to drive the CPU to execute the program update; When it is determined that the second test result corresponding to the program update is a test success, using the third driver to drive the CPU to execute the program uninstallation; When it is determined that the third test result corresponding to the program update is a test success, determining that the target test subprocess does not exist in the program test process; When it is determined that the first test result is a test failure, and / or the second test result is a test failure, and / or the third test result is a test failure, it is determined that the target test subprocess exists in the program test process.

2. The method for verifying stable operation of a CPU according to claim 1, characterized in that: The first operation data includes CPU load, and the method further includes: Verify whether the second operation data of the CPU has abnormal data according to the CPU load and the preset load threshold segment interval; Compare the second operating data with the standard operating data corresponding to the CPU in the preset load threshold segmentation interval; When it is determined that the second operating data is less than the standard operating data, determining that the second operating data does not contain the abnormal data; When it is determined that the second operating data is greater than the standard operating data, determining that the second operating data contains the abnormal data, and determining a target alarm mode corresponding to the abnormal data; An alarm is issued according to the target alarm mode, and a record log is generated.

3. The method for verifying stable operation of a CPU according to claim 2, characterized in that: The second operating data includes CPU temperature, the standard operating data includes a temperature threshold, and the method further includes: Determine whether the CPU temperature is greater than the temperature threshold; When it is determined that the CPU temperature is greater than the temperature threshold, the heat dissipation frequency of the computer motherboard is adjusted so that the CPU temperature is less than the temperature threshold.

4. The method for verifying stable operation of a CPU according to claim 2, characterized in that: The second operating data includes a data transmission speed, the standard operating data includes a speed threshold, and the method further includes: Verifying whether the data transmission speed satisfies the speed threshold; When it is determined that the data transmission speed meets the speed threshold, the target data transmission amount and the actual data transmission amount corresponding to the CPU at the data transmission speed within a preset time period are obtained, A verification report is generated according to the preset load threshold segment interval, the data transmission speed, the target data transmission volume and the actual data transmission volume.

5. The method for verifying stable operation of a CPU according to claim 1, characterized in that: The method further comprises: Step 1, obtaining historical operation data corresponding to each CPU in the plurality of CPUs being under the preset main frequency threshold, so as to obtain a historical operation data set, wherein each historical operation data in the historical operation data set includes historical CPU stability; Step 2: preprocess each of the historical operation data to obtain a target training sample set; Step 3: construct an initial verification model based on the feedforward neural network model; Step 4: input the target training sample into the initial verification model to obtain a verification result corresponding to the target training sample, wherein the target training sample is any one of the target training sample sets; Step 5: adjusting the loss function in the initial verification model based on the difference between the verification result and the historical CPU stability in the target training sample; Step 6, iteratively executing steps 4 to 5 based on the adjusted loss function until a preset iteration termination condition is met; Step 7: Determine the initial verification model that meets the preset iteration termination condition as the target verification model.

6. The method for verifying stable operation of a CPU according to claim 5, characterized in that: The preprocessing of each historical operation data to obtain a target training sample set includes: Calculate the correlation coefficient between each sub-operation data in each historical operation data and the historical CPU stability; comparing the correlation coefficient with a preset coefficient threshold; Determine the sub-operation data in the historical operation data set whose correlation coefficient is greater than the preset coefficient threshold as the operation data training set; Determine a CPU stability training set corresponding to the operation data training set from the historical CPU stability in the historical operation data set; The operation data training set and the CPU stability training set are normalized, and the normalized operation data training set and the CPU stability training set are determined as the target training sample set.

7. A CPU stable operation verification system, characterized in that: The system comprises: A first verification module is used to verify whether the physical connection interface between the CPU of the laptop computer and the computer motherboard of the desktop computer is normally connected according to a pre-defined interface test task, wherein the interface test task includes an I / O interface test, a memory interface test, a storage interface test, and a power interface test; A second verification module is used to drive the CPU to enter a program test process when it is determined that the physical connection port is normally connected, and verify whether the program test process has a target test subprocess, wherein the target test subprocess is a test subprocess in the program test process that causes the CPU to be unstable, and the program test process includes program installation, program update, and program uninstallation; A control module, configured to control the CPU main frequency of the CPU to meet a preset main frequency threshold when it is determined that the target test subprocess does not exist in the program test process; An acquisition module, used for acquiring first operation data corresponding to the CPU under the preset main frequency threshold; A third verification module, configured to verify the CPU stability of the CPU based on the first operating data using a pre-trained target verification model; The second verification module is specifically used for: Acquire from a driver library a first driver corresponding to the program installation, a second driver corresponding to the program update, and a third driver corresponding to the program uninstallation; Using the first driver to drive the CPU to execute the program installation; When it is determined that the first test result corresponding to the program installation is a test success, using the second driver to drive the CPU to execute the program update; When it is determined that the second test result corresponding to the program update is a test success, using the third driver to drive the CPU to execute the program uninstallation; When it is determined that the third test result corresponding to the program update is a test success, determining that the target test subprocess does not exist in the program test process; When it is determined that the first test result is a test failure, and / or the second test result is a test failure, and / or the third test result is a test failure, it is determined that the target test subprocess exists in the program test process.

8. A computer motherboard, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for verifying stable operation of a CPU according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for verifying stable operation of a CPU according to any one of claims 1 to 6 are implemented.