Computer equipment temperature identification method and device based on big data, and storage medium

Abstract

The invention discloses a computer equipment temperature identification method and device based on big data, a storage medium and computer equipment, and the method comprises the steps: detecting a temperature sensor on test equipment corresponding to a to-be-tested combination, determining a target temperature sensor corresponding to a mainboard, and obtaining all temperature addresses; pressurizing the central processing unit according to a preset pressurizing rule, and recording first temperature data of the central processing unit and second temperature data of each temperature address according to a preset frequency; respectively calculating a temperature correlation coefficient between the first temperature data and the second temperature data under each temperature address, and taking the temperature address corresponding to the maximum temperature correlation coefficient as the temperature address of the target temperature sensor relative to the mainboard; packaging the mainboard model, the target temperature sensor model and the temperature address of the target temperature sensor relative to the mainboard in the to-be-tested combination to obtain a test result; and sending each test result to the target server.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a temperature identification method and device for computer equipment based on big data, a storage medium, and a computer equipment. Background Art

[0002] With the rapid development of personal computer hardware, the continuous increase in power consumption has made heat dissipation a key factor affecting computer performance and stability. In order to effectively monitor and manage the temperature of computer equipment, the motherboard is usually equipped with a temperature sensor to monitor the temperature status of the main hardware in real time. However, due to the many-to-many relationship between sensors and motherboard manufacturers, that is, different motherboard manufacturers may use the same sensor, but connect the temperature signals detected by these sensors to different pins on the motherboard, which brings challenges to the accurate identification of temperature.

[0003] Traditional temperature identification methods usually rely on a one-to-one motherboard and sensor binding configuration. This method not only requires a separate configuration for each motherboard and sensor combination, but also becomes very cumbersome and error-prone to maintain as hardware is constantly updated and iterated. Once the configuration is improper, it may lead to incorrect temperature identification, which in turn affects the computer's cooling effect and overall performance. Summary of the invention

[0004] In view of this, the present application provides a computer equipment temperature identification method and device based on big data, a storage medium, and a computer equipment. By detecting the temperature sensor on the test equipment, the target temperature sensor and its temperature address are determined, and the temperature address of the target temperature sensor relative to the mainboard is calculated through pressurization processing and temperature data recording. This method can automatically determine the target temperature address corresponding to different combinations of mainboards and target temperature sensors without the need for cumbersome one-to-one configuration. The temperature of the computer equipment can be obtained by directly reading the temperature value through the target temperature address matching the mainboard and the target temperature sensor, thereby greatly improving the accuracy and efficiency of subsequent computer equipment temperature identification.

[0005] According to one aspect of the present application, a computer device temperature identification method based on big data is provided, which is applied to a test device, and includes:

[0006] For each combination to be tested, detect the temperature sensor on the test device corresponding to the combination to be tested, determine the target temperature sensor corresponding to the mainboard of the test device, and obtain all temperature addresses of the target temperature sensor, wherein the combination to be tested includes a mainboard model and a target temperature sensor model;

[0007] Performing pressurization on the central processing unit on the test device according to a preset pressurization rule, and recording the first temperature data of the central processing unit and the second temperature data under each temperature address according to a preset frequency during the pressurization process;

[0008] respectively calculating the temperature correlation coefficients between the first temperature data and the second temperature data under each temperature address, and taking the temperature address corresponding to the maximum temperature correlation coefficient as the temperature address of the target temperature sensor relative to the mainboard;

[0009] Packing the motherboard model, the target temperature sensor model, and the temperature address of the target temperature sensor relative to the motherboard in the combination to be tested to obtain a test result corresponding to the combination to be tested;

[0010] The test results corresponding to each combination to be tested are sent to the target server, so that the target server determines the target temperature address corresponding to each combination to be tested based on the test results sent by different test devices, so as to guide the computer device to perform temperature identification based on the target temperature address.

[0011] According to another aspect of the present application, a computer equipment temperature identification device based on big data is provided, which is applied to a test device, comprising:

[0012] A temperature sensor detection module is used to detect the temperature sensor on the test device corresponding to each combination to be tested, determine the target temperature sensor corresponding to the mainboard of the test device, and obtain all temperature addresses of the target temperature sensor, wherein the combination to be tested includes a mainboard model and a target temperature sensor model;

[0013] A pressurization module, used for pressurizing the central processing unit on the test device according to a preset pressurization rule, and recording the first temperature data of the central processing unit and the second temperature data under each temperature address according to a preset frequency during the pressurization process;

[0014] a correlation coefficient calculation module, used to respectively calculate the temperature correlation coefficient between the first temperature data and the second temperature data under each temperature address, and use the temperature address corresponding to the maximum temperature correlation coefficient as the temperature address of the target temperature sensor relative to the mainboard;

[0015] A packing module, used for packing the mainboard model, the target temperature sensor model, and the temperature address of the target temperature sensor relative to the mainboard in the combination to be tested, to obtain the test result corresponding to the combination to be tested;

[0016] The sending module is used to send the test results corresponding to each combination to be tested to the target server, so that the target server can determine the target temperature address corresponding to each combination to be tested based on the test results sent by different test devices, so as to guide the computer device to perform temperature identification based on the target temperature address.

[0017] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned computer device temperature identification method based on big data is implemented.

[0018] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned computer device temperature identification method based on big data when executing the program.

[0019] By means of the above technical scheme, the present application provides a computer equipment temperature identification method and device based on big data, a storage medium, and a computer equipment. For each combination to be tested, first, all temperature sensors on the test equipment corresponding to the combination to be tested need to be detected to determine the target temperature sensor on the mainboard of the test equipment, and obtain all temperature addresses of the target temperature sensor. In order to simulate the actual workload of the computer equipment, the central processing unit (CPU) on the test equipment can be pressurized according to the preset pressure rule. During the pressurization process, the first temperature data of the CPU and the second temperature data under each temperature address can be recorded according to the preset frequency. Then, the temperature correlation coefficient between the first temperature data of the CPU and the second temperature data under each temperature address is calculated respectively. After that, the temperature address corresponding to the maximum temperature correlation coefficient is used as the temperature address of the target temperature sensor relative to the mainboard. After determining the temperature address of the target temperature sensor relative to the mainboard, further, the mainboard model, the target temperature sensor model, and the determined temperature address of the target temperature sensor relative to the mainboard in the combination to be tested can be packaged and processed to obtain the test result corresponding to the combination to be tested. After all the combinations to be tested are tested, the test results corresponding to each combination to be tested can be sent to the target server. In this way, the target server can determine the final target temperature address corresponding to each combination to be tested through data analysis and processing based on the test results sent by different test devices. The embodiment of the present application detects the temperature sensor on the test device, determines the target temperature sensor and its temperature address, and calculates the temperature address of the target temperature sensor relative to the mainboard through pressurization processing and temperature data recording. This method can automatically determine the target temperature address corresponding to different mainboard and target temperature sensor combinations without cumbersome one-to-one configuration. The temperature of the computer device can be obtained by directly reading the temperature value through the target temperature address matching the mainboard and the target temperature sensor, thereby greatly improving the accuracy and efficiency of subsequent computer device temperature identification.

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1A schematic diagram of a process flow of a computer device temperature identification method based on big data provided in an embodiment of the present application is shown;

[0023] Figure 2 A schematic diagram of the structure of a computer equipment temperature identification device based on big data provided in an embodiment of the present application is shown;

[0024] Figure 3 A schematic diagram of the device structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0026] In this embodiment, a computer device temperature recognition method based on big data is provided, which is applied to test equipment, such as Figure 1 As shown, the method includes:

[0027] Step 101, for each combination to be tested, detect the temperature sensor on the test device corresponding to the combination to be tested, determine the target temperature sensor corresponding to the mainboard of the test device, and obtain all temperature addresses of the target temperature sensor, wherein the combination to be tested includes a mainboard model and a target temperature sensor model.

[0028] A computer device temperature identification method based on big data provided in an embodiment of the present application is mainly used in test equipment, and is intended to determine the target temperature address of the target temperature sensor relative to the motherboard under different combinations of motherboard models and target temperature sensor models in an automated manner, so that the remaining computer devices can be guided to accurately identify the device temperature based on the obtained target temperature address. Here, the test equipment can be a computer device used for testing. Before the test equipment works, a plurality of combinations to be tested can be determined first, each combination to be tested consists of a specific motherboard model and a specific target temperature sensor model, wherein the target temperature sensor refers to a temperature sensor installed on the motherboard that can be used to test the temperature of the motherboard, and these combinations to be tested represent the pairing of various motherboards and target temperature sensors existing on the market.

[0029] After determining multiple combinations to be tested, further, for each combination to be tested, firstly, all temperature sensors on the test device corresponding to the combination to be tested need to be detected to determine the target temperature sensor on the mainboard of the test device, and obtain all temperature addresses of the target temperature sensor. Among them, the test device corresponding to the combination to be tested refers to a device equipped with a mainboard consistent with the mainboard model in the combination to be tested, and a temperature sensor consistent with the target temperature sensor model; the temperature address refers to the address of the target temperature sensor for storing temperature, and the target temperature sensor can correspond to multiple temperature addresses.

[0030] Step 102, pressurizing the central processing unit on the test device according to a preset pressurizing rule, and recording the first temperature data of the central processing unit and the second temperature data of each temperature address at a preset frequency during the pressurizing process.

[0031] In this embodiment, in order to simulate the actual workload of the computer device, the central processing unit (CPU) on the test device can be pressurized according to the preset pressurization rules. The preset pressurization rules may include specific computing tasks, running time, power consumption level and other parameters to ensure that the test environment can truly reflect the operating status of the computer device. During the pressurization process, the first temperature data of the CPU and the second temperature data under each temperature address can be recorded at a preset frequency. Here, the first temperature data refers to the core temperature of the CPU, which can be read by system tools or third-party software, and is not limited here. The preset frequency can be determined according to actual needs, for example, reading once per second. It should be noted that the CPU is installed on the motherboard, so by analyzing the changes in the CPU core temperature, the temperature changes collected by the target temperature sensor on the motherboard can be indirectly reflected.

[0032] Step 103, respectively calculating the temperature correlation coefficient between the first temperature data and the second temperature data under each temperature address, and taking the temperature address corresponding to the maximum temperature correlation coefficient as the temperature address of the target temperature sensor relative to the mainboard.

[0033] In this embodiment, the temperature correlation coefficient between the first temperature data of the CPU and the second temperature data under each temperature address is calculated respectively. The temperature correlation coefficient is an indicator to measure the degree of correlation between two temperature data. The larger the value, the stronger the correlation between the two sets of data. After that, the temperature address corresponding to the maximum temperature correlation coefficient is used as the temperature address of the target temperature sensor relative to the motherboard, so that the temperature address most related to the CPU core temperature is found, that is, when the target temperature sensor is installed on the motherboard, which temperature address is the temperature address corresponding to the motherboard temperature.

[0034] Step 104 , packaging the mainboard model, target temperature sensor model, and the temperature address of the target temperature sensor relative to the mainboard in the combination to be tested to obtain a test result corresponding to the combination to be tested.

[0035] In this embodiment, after determining the temperature address of the target temperature sensor relative to the mainboard, the mainboard model, the target temperature sensor model and the determined temperature address of the target temperature sensor relative to the mainboard in the combination to be tested can be packaged and processed to obtain the test results corresponding to the combination to be tested. These test results contain complete information about the mainboard, the temperature sensor on the mainboard and the temperature address, providing a basis for subsequent data analysis and processing.

[0036] Step 105, sending the test results corresponding to each combination to be tested to the target server, so that the target server determines the target temperature address corresponding to each combination to be tested based on the test results sent by different test devices, so as to guide the computer device to perform temperature identification based on the target temperature address.

[0037] In this embodiment, the test device can be used to repeatedly obtain the temperature address of the target temperature sensor relative to the mainboard in each combination to be tested. It should be noted that when the combination to be tested changes, the mainboard and the target temperature sensor on the test device must also change accordingly. After all combinations to be tested are tested, the test results corresponding to each combination to be tested can be sent to the target server. In this way, the target server can determine the final target temperature address corresponding to each combination to be tested through data analysis and processing based on the test results sent by different test devices. These target temperature addresses will serve as the basis for subsequent temperature identification by computer equipment.

[0038] By applying the technical solution of this embodiment, for each combination to be tested, it is first necessary to detect all temperature sensors on the test device corresponding to the combination to be tested to determine the target temperature sensor on the mainboard of the test device and obtain all temperature addresses of the target temperature sensor. In order to simulate the actual workload of the computer device, the central processing unit (CPU) on the test device can be pressurized according to the preset pressure rule. During the pressurization process, the first temperature data of the CPU and the second temperature data under each temperature address can be recorded according to the preset frequency. Then, the temperature correlation coefficient between the first temperature data of the CPU and the second temperature data under each temperature address is calculated respectively. After that, the temperature address corresponding to the maximum temperature correlation coefficient is used as the temperature address of the target temperature sensor relative to the mainboard. After determining the temperature address of the target temperature sensor relative to the mainboard, further, the mainboard model, the target temperature sensor model and the determined temperature address of the target temperature sensor relative to the mainboard in the combination to be tested can be packaged and processed to obtain the test results corresponding to the combination to be tested. After all the combinations to be tested are tested, the test results corresponding to each combination to be tested can be sent to the target server. In this way, the target server can determine the final target temperature address corresponding to each combination to be tested through data analysis and processing based on the test results sent by different test devices. The embodiment of the present application determines the target temperature sensor and its temperature address by detecting the temperature sensor on the test device, and calculates the temperature address of the target temperature sensor relative to the mainboard through pressurization processing and temperature data recording. This method can automatically determine the target temperature address corresponding to different combinations of mainboards and target temperature sensors without the need for cumbersome one-to-one configuration. The temperature of the computer device can be obtained by subsequently reading the temperature value directly from the target temperature address that matches the mainboard and the target temperature sensor, thereby greatly improving the accuracy and efficiency of subsequent temperature identification of the computer device.

[0039] In an embodiment of the present application, optionally, when the combination to be tested corresponds to multiple pressurization cycles, the "respectively calculating the temperature correlation coefficient between the first temperature data and the second temperature data under each temperature address" in step 103 includes: dividing the first temperature data and the second temperature data under each temperature address according to each pressurization cycle, to obtain multiple first temperature subsets corresponding to the first temperature data, and multiple second temperature subsets corresponding to the second temperature data under each temperature address; for each pressurization cycle, respectively calculating the sub-temperature correlation coefficient between the first temperature subset under the pressurization cycle and each second temperature subset under the pressurization cycle; respectively calculating the temperature correlation coefficient corresponding to the temperature address according to the sub-temperature correlation coefficients corresponding to each pressurization cycle under each temperature address.

[0040] In this embodiment, a combination to be tested can undergo multiple pressurization cycles to more comprehensively simulate the actual workload and temperature changes of the computer device. Therefore, when the combination to be tested corresponds to multiple pressurization cycles, the first temperature data (CPU core temperature data) and the second temperature data under each temperature address can be first divided according to each pressurization cycle, so that the continuous temperature data can be divided into multiple data subsets corresponding to the pressurization cycle, so as to calculate the sub-temperature correlation coefficient later. After division, multiple first temperature subsets corresponding to the first temperature data and multiple second temperature subsets corresponding to the second temperature data under each temperature address can be obtained. These subsets correspond to different pressurization cycles, respectively.

[0041] For each pressurization cycle, the sub-temperature correlation coefficient between the first temperature subset under the pressurization cycle and each second temperature subset under the pressurization cycle is calculated respectively, so that the degree of correlation between the CPU core temperature and the temperature under each temperature address in each pressurization cycle can be evaluated. Among them, the calculation of the sub-temperature correlation coefficient can adopt a variety of statistical methods, such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc. In the calculation process, the first temperature subset and the second temperature subset can be used as input, and the corresponding sub-temperature correlation coefficient value is obtained by calculation. After obtaining the sub-temperature correlation coefficient corresponding to each pressurization cycle under each temperature address, further, the temperature correlation coefficient corresponding to each temperature address is calculated. The calculation of the temperature correlation coefficient can be based on the statistical quantities such as the average value, median, weighted average value of the sub-temperature correlation coefficient, which is not limited here. The embodiment of the present application can more comprehensively evaluate the degree of correlation between the CPU core temperature and the temperature under each temperature address by considering the temperature data of multiple pressurization cycles; by calculating the sub-temperature correlation coefficient and the temperature correlation coefficient, the temperature address most related to the CPU core temperature can be more accurately identified.

[0042] In an embodiment of the present application, optionally, the "for each pressurization cycle, respectively calculating the sub-temperature correlation coefficient between the first temperature subset under the pressurization cycle and each second temperature subset under the pressurization cycle" includes: for each pressurization cycle, calculating the sub-temperature correlation coefficient between the first temperature subset under the pressurization cycle and each second temperature subset under the pressurization cycle according to the Pearson correlation coefficient method; or, for each pressurization cycle, each time inputting the first temperature subset under the pressurization cycle and a second temperature subset under the pressurization cycle into a preset correlation recognition model, respectively extracting the first temperature feature corresponding to the first temperature subset and the second temperature feature corresponding to the second temperature subset through the preset correlation recognition model, and based on the first temperature feature and the second temperature feature, outputting the sub-temperature correlation coefficient between the first temperature subset and the second temperature subset, wherein the temperature feature includes a temperature change trend feature, a temperature average feature, a temperature peak and valley feature, and a temperature standard deviation feature.

[0043] In this embodiment, the correlation between different temperature subsets is calculated under each pressurization cycle, which can be achieved by different methods. One method can be calculated by the Pearson correlation coefficient method. The Pearson correlation coefficient is an indicator to measure the degree of linear correlation between two variables, and its value is between -1 and 1. When the correlation coefficient is 1, it indicates a complete positive correlation; when it is -1, it indicates a complete negative correlation; when it is 0, it indicates no correlation. Specifically, for each pressurization cycle, first determine the first temperature subset under the cycle and the second temperature subset under each temperature address. Afterwards, use the Pearson correlation coefficient formula to calculate the correlation coefficient between the first temperature subset and each second temperature subset, respectively.

[0044] In addition, the sub-temperature correlation coefficient can also be determined based on a preset correlation recognition model. The method can pre-train a correlation recognition model that can extract key features from the input temperature data and calculate the correlation between temperature subsets based on these features. Specifically, for each pressurization cycle, the first temperature subset and the second temperature subset are input into the preset correlation recognition model each time, and the preset correlation recognition model can extract the first temperature feature and the second temperature feature of the two temperature subsets, respectively. These features may include temperature change trend features (such as rising, falling, stable, etc.), temperature average features, temperature peak and valley features, and temperature standard deviation features. Furthermore, based on the extracted temperature features, the preset correlation recognition model can calculate the sub-temperature correlation coefficient between the first temperature subset and the second temperature subset. Here, the preset correlation recognition model can be a machine learning model.

[0045] The embodiment of the present application can simply and directly determine the sub-temperature correlation coefficient through the Pearson correlation coefficient method, which is suitable for scenarios where fast calculations are required. The sub-temperature correlation coefficient can also be calculated based on a preset correlation identification model, which can capture more complex nonlinear relationships, so that the calculation results can be more accurate.

[0046] In an embodiment of the present application, optionally, for multiple test results corresponding to any combination to be tested, the target server counts the temperature addresses contained in the multiple test results, and uses the temperature address with the largest number as the target temperature address corresponding to any combination to be tested; or, for multiple test results corresponding to any combination to be tested, the target server respectively determines the test device corresponding to each test result, and obtains the device reliability characteristics, historical test performance characteristics and test environment characteristics of the test device within a preset time interval, determines the weight corresponding to each test result according to the device reliability characteristics, the historical test performance characteristics and the test environment characteristics, and obtains the target temperature address corresponding to any combination to be tested based on each test result and the weight corresponding to each test result.

[0047] In this embodiment, the target server may determine the target temperature address corresponding to each combination to be tested based on the following two methods.

[0048] Method 1: Method based on temperature address statistics. In this method, the target server mainly relies on statistics on the temperature addresses contained in multiple test results to determine the temperature address with the largest number as the target temperature address. Specifically, for any combination to be tested, the target server first collects multiple test results corresponding to it. These test results can come from different test devices, that is, different test devices can test the same combination to be tested, so the same combination to be tested can correspond to multiple temperature addresses. Next, the target server counts the collected test results and calculates the number of times each temperature address appears. Finally, the target server determines the temperature address with the largest number as the target temperature address corresponding to the combination to be tested, that is, the target temperature address appears most significantly or frequently in multiple test results.

[0049] Method 2: Method based on test result weight. In this method, the target server not only considers the temperature address in the test result, but also considers the reliability characteristics, historical test performance characteristics and test environment characteristics of the test equipment related to each test result. These factors jointly determine the weight of each test result. Specifically, for any combination to be tested, the target server first collects multiple test results corresponding to it and determines the test equipment corresponding to each test result. Then, the device reliability characteristics (such as failure rate, maintenance record, etc.), historical test performance characteristics (such as accuracy and stability of past test results, etc.) and test environment characteristics (such as ambient temperature, humidity, etc.) of these test equipment within a preset time interval are obtained. Based on the collected device reliability characteristics, historical test performance characteristics and test environment characteristics, the target server uses a preset algorithm or model to determine the weight corresponding to each test result, which reflects the reliability and importance of each test result. Next, the target server calculates the final weight corresponding to each temperature address based on the temperature address and the corresponding weight in each test result. Finally, the target server determines the temperature address with the highest weight as the target temperature address corresponding to the combination to be tested. For example, for the combination to be tested 1, test devices a, test devices b, test devices c, and test devices d all tested the combination to be tested and obtained 4 test results, namely test result a', test result b', test result c', and test result d'. Among them, the temperature address corresponding to test result a' is A1, the temperature address corresponding to test result b' is A1, the temperature address corresponding to test result c' is A2, and the temperature address corresponding to test result d' is A2. The weight of test device a is 0.2, the weight of test device b is 0.15, the weight of test device c is 0.35, and the weight of test device d is 0.3. Then the final weight corresponding to temperature address A1 is 0.35, and the final weight corresponding to temperature address A2 is 0.65. Therefore, the target server can finally use temperature address A2 as the target temperature address for the combination to be tested 1.

[0050] In an embodiment of the present application, optionally, the target server receives a query instruction for a target temperature address sent by a computer device, obtains a motherboard model and a target temperature sensor model corresponding to the query instruction, determines a target temperature address that matches the query instruction from multiple stored target temperature addresses based on the motherboard model and the target temperature sensor model corresponding to the query instruction, and returns the matched target temperature address to the computer device, so that the computer device reads a temperature value based on the target temperature address as the temperature corresponding to the computer device.

[0051] In this embodiment, when the computer device wants to query the target temperature address from the target server, a query instruction can be sent to the target server. This instruction contains information about the query motherboard model and the target temperature sensor model. Among them, the query instruction can be automatically generated. For example, in a scenario where the computer device temperature needs to be monitored in real time to ensure the safe operation of the computer device, the monitoring system can automatically generate a query instruction on demand after startup to obtain the latest temperature information. Alternatively, the user can generate a query instruction by inputting the motherboard model and the target temperature sensor model through a certain user interface (such as a command line interface, a graphical user interface, etc.).

[0052] After receiving the query instruction sent by the computer device, the target server first parses it to extract the information of the motherboard model and the target temperature sensor model. Then, according to the parsed motherboard model and temperature sensor model information, it matches with the existing stored data to find a consistent combination to be tested, and uses the target temperature address corresponding to the consistent combination to be tested as the target temperature address corresponding to the query instruction, and returns the target temperature address to the computer device. After receiving the target temperature address returned by the target server, the computer device uses the target temperature address to read the temperature value, and the read temperature value can be used as the temperature corresponding to the computer device.

[0053] The embodiments of the present application can adapt to different models of mainboards and target temperature sensors, and it is only necessary to specify the corresponding model in the query instruction; by matching the mainboard model and the target temperature sensor model, it can be ensured that the returned target temperature address is accurate, thereby avoiding reading the wrong temperature value, and there is no need for cumbersome one-to-one configuration; with the introduction of new models of mainboards and target temperature sensors, it is only necessary to update the corresponding storage information in the target server to support new query requirements.

[0054] In an embodiment of the present application, optionally, the "sending the test results corresponding to each combination to be tested to the target server" in step 105 includes: encrypting the test results corresponding to each combination to be tested according to a preset encryption algorithm, and sending the encrypted data to the target server.

[0055] In this embodiment, before the test results are sent to the target server, the test results can also be encrypted and then sent to the target server. Specifically, the preset encryption algorithm can select a symmetric encryption algorithm such as AES. The AES algorithm has the advantages of high efficiency, security, and flexibility, supports a variety of key lengths (such as 128 bits, 192 bits, and 256 bits), and can select a suitable key length according to demand. Before the encryption process, a key for encryption can be generated. For a symmetric encryption algorithm (such as AES), a symmetric key can be generated. Then, the test results are encrypted using the selected encryption algorithm and key. After the encryption process is completed, an encrypted data block can be obtained. This data block contains the encrypted test result information and cannot be directly read or tampered by unauthorized users. Finally, the encrypted data block is sent to the target server. After the target server receives the data block, it performs parsing and verification operations to ensure the correctness and integrity of the data. At the same time, a reception confirmation message can be sent to the sender to confirm that the data has been successfully received. The embodiment of the present application ensures the security and confidentiality of the test results during transmission through encryption processing, effectively preventing the risk of data leakage and tampering.

[0056] In an embodiment of the present application, optionally, the preset pressurization rule is determined based on the temperature change characteristics of the CPU of the sample user.

[0057] In this embodiment, a set of preset pressure rules can be determined by analyzing and learning the temperature change characteristics of the central processing unit (CPU) of sample users. First, representative sample users can be screened out from the target user group. These users should be widely representative and cover factors such as different usage habits, hardware configurations and working environments. For each sample user, the CPU temperature change data during use is collected. Afterwards, the collected CPU temperature change data is preprocessed, including data cleaning (removing outliers, duplicate values, etc.), data normalization (converting data of different dimensions to the same dimension), and other steps. Indicators that can reflect the characteristics of CPU temperature changes are extracted from the preprocessed data. These characteristics may include the rate of temperature change, the amplitude of temperature fluctuation, the difference between the temperature peak and the valley value, etc. Subsequently, based on the results of the feature analysis, a set of preset pressure rules is formulated. For example, the preset pressure rules may be: when the CPU temperature reaches a certain threshold, start to increase the load to test its stability; adjust the speed and amplitude of the load increase according to the rate and amplitude of the temperature change; maintain a certain load level within a specific time period to observe the long-term performance of the CPU; when the temperature exceeds the safety limit, automatically reduce the load to avoid equipment damage. The embodiment of the present application learns the CPU temperature change characteristics of sample users so that the formulated pressure increase rules are closer to actual usage, thereby improving the accuracy and practicality of the test.

[0058] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a computer equipment temperature recognition device based on big data, which is applied to test equipment, such as Figure 2 As shown, the device comprises:

[0059] A temperature sensor detection module is used to detect the temperature sensor on the test device corresponding to each combination to be tested, determine the target temperature sensor corresponding to the mainboard of the test device, and obtain all temperature addresses of the target temperature sensor, wherein the combination to be tested includes a mainboard model and a target temperature sensor model;

[0060] A pressurization module, used for pressurizing the central processing unit on the test device according to a preset pressurization rule, and recording the first temperature data of the central processing unit and the second temperature data under each temperature address according to a preset frequency during the pressurization process;

[0061] a correlation coefficient calculation module, used to respectively calculate the temperature correlation coefficient between the first temperature data and the second temperature data under each temperature address, and use the temperature address corresponding to the maximum temperature correlation coefficient as the temperature address of the target temperature sensor relative to the mainboard;

[0062] A packing module, used for packing the mainboard model, the target temperature sensor model, and the temperature address of the target temperature sensor relative to the mainboard in the combination to be tested, to obtain the test result corresponding to the combination to be tested;

[0063] The sending module is used to send the test results corresponding to each combination to be tested to the target server, so that the target server can determine the target temperature address corresponding to each combination to be tested based on the test results sent by different test devices, so as to guide the computer device to perform temperature identification based on the target temperature address.

[0064] Optionally, when the combination to be tested corresponds to multiple pressurization cycles, the correlation coefficient calculation module is used to:

[0065] Divide the first temperature data and the second temperature data under each temperature address according to each pressurization cycle to obtain a plurality of first temperature subsets corresponding to the first temperature data and a plurality of second temperature subsets corresponding to the second temperature data under each temperature address;

[0066] For each pressurization cycle, respectively calculating the sub-temperature correlation coefficient between the first temperature subset in the pressurization cycle and each second temperature subset in the pressurization cycle;

[0067] The temperature correlation coefficient corresponding to the temperature address is calculated based on the sub-temperature correlation coefficient corresponding to each pressurization cycle under each temperature address.

[0068] Optionally, the correlation coefficient calculation module is further used to:

[0069] For each pressurization cycle, calculating the sub-temperature correlation coefficient between the first temperature subset in the pressurization cycle and each second temperature subset in the pressurization cycle according to the Pearson correlation coefficient method; or,

[0070] For each pressurization cycle, a first temperature subset under the pressurization cycle and a second temperature subset under the pressurization cycle are input into a preset correlation recognition model each time, and a first temperature feature corresponding to the first temperature subset and a second temperature feature corresponding to the second temperature subset are respectively extracted through the preset correlation recognition model, and based on the first temperature feature and the second temperature feature, a sub-temperature correlation coefficient between the first temperature subset and the second temperature subset is output, wherein the temperature features include temperature change trend features, temperature average features, temperature peak and valley features, and temperature standard deviation features.

[0071] Optionally, the target server is used to:

[0072] For a plurality of test results corresponding to any combination to be tested, the temperature addresses contained in the plurality of test results are counted, and the temperature address with the largest number is used as the target temperature address corresponding to any combination to be tested; or

[0073] For multiple test results corresponding to any combination to be tested, determine the test equipment corresponding to each test result respectively, and obtain the equipment reliability characteristics, historical test performance characteristics and test environment characteristics of the test equipment within a preset time interval. According to the equipment reliability characteristics, the historical test performance characteristics and the test environment characteristics, determine the weight corresponding to each test result. Based on each test result and the weight corresponding to each test result, obtain the target temperature address corresponding to any combination to be tested.

[0074] Optionally, the target server is further used to:

[0075] Receive a query instruction of a target temperature address sent by a computer device, obtain a motherboard model and a target temperature sensor model corresponding to the query instruction, determine a target temperature address that matches the query instruction from multiple stored target temperature addresses based on the motherboard model and the target temperature sensor model corresponding to the query instruction, and return the matched target temperature address to the computer device, so that the computer device reads a temperature value based on the target temperature address as the temperature corresponding to the computer device.

[0076] Optionally, the sending module is used to:

[0077] According to the preset encryption algorithm, the test results corresponding to each combination to be tested are encrypted, and the encrypted data is sent to the target server.

[0078] Optionally, the preset pressurization rule is determined based on the temperature change characteristics of the CPU of the sample user.

[0079] It should be noted that for other corresponding descriptions of the functional units involved in the computer equipment temperature identification device based on big data provided in the embodiment of the present application, reference can be made to Figure 1 The corresponding description in the method will not be repeated here.

[0080] The present application also provides a computer device, which may be a personal computer, a server, a network device, etc. Figure 3 As shown, the computer device includes a bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device. 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 database of the computer device is used to store location information. 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, the steps in each method embodiment are implemented.

[0081] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0082] In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium may be non-volatile or volatile, and stores a computer program thereon. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0083] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0084] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0085] 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 the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0086] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A computer equipment temperature identification method based on big data, applied to test equipment, characterized in that: include: For each combination to be tested, detect the temperature sensor on the test device corresponding to the combination to be tested, determine the target temperature sensor corresponding to the mainboard of the test device, and obtain all temperature addresses of the target temperature sensor, wherein the combination to be tested includes a mainboard model and a target temperature sensor model; Performing pressurization on the central processing unit on the test device according to a preset pressurization rule, and recording the first temperature data of the central processing unit and the second temperature data under each temperature address according to a preset frequency during the pressurization process; respectively calculating the temperature correlation coefficients between the first temperature data and the second temperature data under each temperature address, and taking the temperature address corresponding to the maximum temperature correlation coefficient as the temperature address of the target temperature sensor relative to the mainboard; Packing the motherboard model, the target temperature sensor model, and the temperature address of the target temperature sensor relative to the motherboard in the combination to be tested to obtain a test result corresponding to the combination to be tested; The test results corresponding to each combination to be tested are sent to the target server, so that the target server determines the target temperature address corresponding to each combination to be tested based on the test results sent by different test devices, so as to guide the computer device to perform temperature identification based on the target temperature address.

2. The method according to claim 1, characterized in that When the combination to be tested corresponds to multiple pressurization cycles, respectively calculating the temperature correlation coefficient between the first temperature data and the second temperature data under each temperature address includes: Divide the first temperature data and the second temperature data under each temperature address according to each pressurization cycle to obtain a plurality of first temperature subsets corresponding to the first temperature data and a plurality of second temperature subsets corresponding to the second temperature data under each temperature address; For each pressurization cycle, respectively calculating the sub-temperature correlation coefficient between the first temperature subset in the pressurization cycle and each second temperature subset in the pressurization cycle; The temperature correlation coefficient corresponding to the temperature address is calculated based on the sub-temperature correlation coefficient corresponding to each pressurization cycle under each temperature address.

3. The method according to claim 2, characterized in that For each pressurization cycle, respectively calculating the sub-temperature correlation coefficient between the first temperature subset in the pressurization cycle and each second temperature subset in the pressurization cycle, comprises: For each pressurization cycle, calculating the sub-temperature correlation coefficient between the first temperature subset in the pressurization cycle and each second temperature subset in the pressurization cycle according to the Pearson correlation coefficient method; or, For each pressurization cycle, a first temperature subset under the pressurization cycle and a second temperature subset under the pressurization cycle are input into a preset correlation recognition model each time, and a first temperature feature corresponding to the first temperature subset and a second temperature feature corresponding to the second temperature subset are respectively extracted through the preset correlation recognition model, and based on the first temperature feature and the second temperature feature, a sub-temperature correlation coefficient between the first temperature subset and the second temperature subset is output, wherein the temperature features include temperature change trend features, temperature average features, temperature peak and valley features, and temperature standard deviation features.

4. The method according to claim 1, characterized in that: For a plurality of test results corresponding to any combination to be tested, the target server counts the temperature addresses included in the plurality of test results, and uses the temperature address with the largest number as the target temperature address corresponding to any combination to be tested; or, For multiple test results corresponding to any combination to be tested, the target server respectively determines the test equipment corresponding to each test result, and obtains the equipment reliability characteristics, historical test performance characteristics and test environment characteristics of the test equipment within a preset time interval, and determines the weight corresponding to each test result based on the equipment reliability characteristics, the historical test performance characteristics and the test environment characteristics, and obtains the target temperature address corresponding to any combination to be tested based on each test result and the weight corresponding to each test result.

5. The method according to any one of claims 1 to 4, characterized in that The target server receives a query instruction for a target temperature address sent by a computer device, obtains a motherboard model and a target temperature sensor model corresponding to the query instruction, determines a target temperature address that matches the query instruction from multiple stored target temperature addresses based on the motherboard model and the target temperature sensor model corresponding to the query instruction, and returns the matched target temperature address to the computer device, so that the computer device reads a temperature value based on the target temperature address as the temperature corresponding to the computer device.

6. The method according to claim 1, characterized in that The step of sending the test results corresponding to each combination to be tested to the target server includes: According to the preset encryption algorithm, the test results corresponding to each combination to be tested are encrypted, and the encrypted data is sent to the target server.

7. The method according to claim 1, characterized in that The preset pressure application rule is determined based on the CPU temperature variation characteristics of the sample users.

8. A computer equipment temperature recognition device based on big data, applied to test equipment, characterized in that: include: A temperature sensor detection module is used to detect the temperature sensor on the test device corresponding to each combination to be tested, determine the target temperature sensor corresponding to the mainboard of the test device, and obtain all temperature addresses of the target temperature sensor, wherein the combination to be tested includes a mainboard model and a target temperature sensor model; A pressurization module, used for pressurizing the central processing unit on the test device according to a preset pressurization rule, and recording the first temperature data of the central processing unit and the second temperature data under each temperature address according to a preset frequency during the pressurization process; a correlation coefficient calculation module, used to respectively calculate the temperature correlation coefficient between the first temperature data and the second temperature data under each temperature address, and use the temperature address corresponding to the maximum temperature correlation coefficient as the temperature address of the target temperature sensor relative to the mainboard; A packing module, used for packing the mainboard model, the target temperature sensor model, and the temperature address of the target temperature sensor relative to the mainboard in the combination to be tested, to obtain the test result corresponding to the combination to be tested; The sending module is used to send the test results corresponding to each combination to be tested to the target server, so that the target server can determine the target temperature address corresponding to each combination to be tested based on the test results sent by different test devices, so as to guide the computer device to perform temperature identification based on the target temperature address.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images