A method and system for improving working efficiency of computer radiator

Abstract

The present invention discloses a method and system for improving the working efficiency of a computer radiator, comprising a computer system, a data storage module, a manual operation module, a hard disk data acquisition module, a software data acquisition module, a fan speed control module, a comprehensive module, an AI learning module and a high temperature data recording module. In the present invention, a software data acquisition module and an AI learning module are set up, and the software running data acquired in the software data acquisition module are used to process the software running number and running time data under the current system running and the related information data recorded in the historical high temperature data recording module, so as to judge whether the data under the current software running state matches the data recorded in the high temperature data recording module, thereby judging whether the fan speed needs to be adjusted, and whether the operation of the system is monitored in real time according to the software running data to trigger a high temperature warning, so as to adjust the fan speed in advance, thereby improving the working efficiency of the radiator.

Description

Technical Field

[0001] The present invention relates to the technical field of computer hardware heat dissipation, and in particular to a method and system for improving the working efficiency of a computer radiator. Background Art

[0002] As the computing power of personal computers (PCs) increases, power consumption and heat dissipation issues are becoming increasingly unavoidable. The major heat sources in computers include the CPU, motherboard (south bridge, north bridge and VRM), graphics card and other components such as hard disks and optical drives. A considerable portion of the power they consume when working will be converted into heat. The operating temperature of electronic devices directly determines their service life and stability. In order to keep the operating temperature of various PC components within a reasonable range, in addition to ensuring that the temperature of the PC working environment is within a reasonable range, it is also necessary to perform heat dissipation treatment.

[0003] Generally speaking, the operation process of the existing computer cooling system is as follows: the temperature detection module detects the temperature data inside the chassis and the CPU, and adjusts the fan speed according to the changes in the temperature data;

[0004] The operating mode of the above radiator has the following defects: First, the change of fan speed is based on the change of CPU temperature. In the process of adjusting the fan speed according to the change of CPU temperature, the CPU temperature continues to rise. Therefore, the adjusted fan speed may not meet the demand; secondly, in the process of adjustment, the CPU is still running under high temperature load, so the cooling efficiency of the fan cannot meet the demand; finally, there is also an operating mode in which artificial intelligence adjusts the fan speed. For example, before the user is ready to open the software with high core load, the fan maximum speed will be turned on in advance. This operation undoubtedly requires manual adjustment by the user, which is not convenient enough.

[0005] In summary, it is necessary to propose a method and system for improving the working efficiency of a computer radiator to solve the above problems. Summary of the invention

[0006] The object of the present invention is to provide a method and system for improving the working efficiency of a computer radiator, so as to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A system for improving the working efficiency of a computer radiator, comprising:

[0009] Computer system, data storage module, manual operation module, hard disk data acquisition module, software data acquisition module, fan speed control module, comprehensive module, AI learning module and high temperature data recording module;

[0010] The software data acquisition module includes a software running time detection module for recording the software running time, a software running log module for recording software running data, a software running data recording module for assisting in recording the number of software running, and a software data real-time uploading module for uploading software data in real time;

[0011] The hard disk data acquisition module includes a hard disk time data detection module for recording hard disk usage time, a hard disk usage log module for recording hard disk usage data, a hard disk temperature data detection module for recording hard disk temperature, a hard disk operation data detection module for recording hard disk operation status, and a real-time upload module for uploading hard disk real-time data;

[0012] The fan speed control module includes a fan operation data detection module for recording the fan operation status, a fan speed data detection module for recording the fan operation speed, a fan data recording module for recording the fan power data change, a fan operation log module for recording the fan operation data, and a fan data real-time upload module for uploading the fan real-time operation data;

[0013] The comprehensive module includes a hard disk usage time data acquisition module for acquiring hard disk usage time data, a CPU silicone grease replacement time recording module, a CPU silicone grease sheet replacement time recording module, a memory bar temperature data acquisition module, and a motherboard temperature data acquisition module;

[0014] The AI ​​learning module includes a time axis calibration module, a data alignment module, a data processing module, a prediction module, a PWM control module and a result output module. The data processing module is used to process the data uploaded by other modules. The prediction module is used to predict the fan speed adjustment scheme according to the data processed by the data processing module. The result output module is used to convert the prediction result of the prediction module into signal data and upload it to the PWM control block. The PWM control module is used to control the change of the fan speed. The time axis calibration module and the data alignment module are used to associate the data on the time axis.

[0015] The high temperature data recording module is used to record the number of CPU high temperatures and related data during the operation of the computer system.

[0016] Preferably, in the software data acquisition module, the software operation data recording module is used to record the software being run, so as to determine whether the number of currently running software will cause a load on the CPU; the software operation duration detection module is used to detect the duration for which the currently running software has been turned on, and further determine whether the number of software under the current operation duration will cause a load on the CPU; the number of software running and the operation duration data are uploaded to the AI ​​learning module in real time; the data processing module in the AI ​​learning module calculates and processes the data to determine whether the fan speed needs to be adjusted in the current operating state.

[0017] Preferably, in the hard disk data acquisition module, a hard disk time data detection module is used to detect the usage time of the hard disk, and the usage time of the hard disk is used as the time axis. The CPU and GPU temperature change records, as well as the memory bar temperature data and the motherboard temperature data are associated on the time axis. Based on the time axis, the fan speed change record is recorded, and the fan adjustment plan is simulated and predicted according to the normal usage time of the silicone grease and the silicone grease sheet, and the change in the heat dissipation efficiency of the corresponding silicone grease is calculated through the actual CPU or GPU temperature change record.

[0018] Preferably, the AI ​​learning module receives data detected by other modules, and the data processing module performs central processing on the data, including data de-noising, classification and format conversion. The data is associated on the timeline using the timeline calibration module and the data alignment module. The prediction module provides a fan adjustment prediction plan, and the result output module converts the plan output into signal data. The signal data is uploaded to the PWM control module to adjust the fan speed.

[0019] Preferably, in the high temperature data recording module, the high temperature data recording module is used to record the data of the CPU under high temperature, that is, abnormal temperature. The frequency of the high temperature data is counted under this data, and the AI ​​learning module calculates the rules. The software start and stop associated with high temperature occurs are counted, and the fan power is automatically pre-adjusted according to the started software.

[0020] A method for improving the working efficiency of a computer radiator. The specific operating steps of the system for improving the working efficiency of a computer radiator are as follows:

[0021] S1. Acquisition of system software process information: The software operation data module detects the number of software running in the system; the software operation time detection module detects the long data of each software running in the system, and the software data real-time upload module uploads the data to the AI ​​learning module;

[0022] S2. Primary judgment: The data processing module in the AI ​​learning module retrieves the information of the relevant high temperature data recording module to determine whether the system software operation data uploaded by the software data acquisition module matches the relevant information in the high temperature data recording module. If the match is successful, the next step of data acquisition is performed and the fan speed adjustment plan is predicted. If the match is unsuccessful, the data is recorded and the system continues to run;

[0023] S3. Secondary determination: In step S2, it is determined that the CPU is in or about to be in a high temperature state, and the hard disk usage time data, the replacement information data of the silicone grease and silicone grease slice in the CPU, the memory bar temperature data and the motherboard temperature data are obtained through the comprehensive module, and the replacement time and type of the silicone grease and silicone slice are actively input, and the quality and normal use time of the corresponding product are retrieved through big data, and the heat dissipation efficiency change of the corresponding silicone grease is calculated through the actual CPU or GPU temperature change record to determine whether the fan speed needs to be adjusted. If necessary, the data processing module and the prediction module are used to simulate and predict the fan speed adjustment plan. If not, the data is recorded and uploaded to the data storage module;

[0024] S4. Fan speed adjustment: According to step S3, the system determines that the fan speed needs to be adjusted, and then uses the data processing module and the prediction module to simulate and predict the fan speed adjustment plan. The result output module converts the data of the plan into a digital signal, and sends the digital signal to the PWM control module, which completes the fan speed adjustment.

[0025] Preferably, in step S1, the software operation data acquired in the software operation data acquisition module is the data of the software operation in the time period. Specifically, when the acquisition of software operation data is started at moment A, the uploaded software operation data is the operation data at moment A+B, and the value of B is 10min.

[0026] Preferably, in step S2, the high temperature data recording module records the software running data, memory bar temperature data, mainboard temperature data and hard disk temperature data when the CPU is in a high temperature state. When the data processing module in the AI ​​learning module is used to match relevant data, the above data are matched synchronously. When the matching degree is 95%, the match is successful, and if it is lower than 95%, it means the match is unsuccessful.

[0027] Preferably, in step S3, the heat dissipation efficiency of the silicone grease corresponds to the temperature change of the CPU. The greater the temperature change of the CPU, the higher the heat dissipation efficiency of the silicone grease. When using the heat dissipation efficiency of the silicone grease to determine the temperature change of the CPU, the replacement time and usage time data of the silicone grease should be uploaded to the AI ​​learning module as a basis for auxiliary judgment.

[0028] Preferably, in step S4, when performing data conversion, the scheme data is first subjected to noise reduction processing, and then each text data is converted into a corresponding digital code, and each character corresponds to a certain binary code. After the text is digitized, it is modulated onto a carrier for transmission using phase shift keying technology, and the data is transmitted using a wireless medium. It should be noted that error detection and correction codes are added during data encoding.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention sets a software data acquisition module and an AI learning module, and uses the software running data acquired in the software data acquisition module, that is, according to the number of software running and the running time data under the current system running, and the related information data recorded in the historical high temperature data recording module for data processing, that is, using the data processing module to quickly match these data, and judge whether the data in the current software running state matches the data recorded in the high temperature data recording module, so as to judge whether the fan speed needs to be adjusted. This design can monitor the operation of the system in real time according to the software running data to determine whether a high temperature warning is triggered, so as to achieve early prediction before the computer reaches a high temperature state, and then make adjustments to the fan speed in advance, thereby improving the working efficiency of the radiator;

[0031] In the present invention, the usage time of the hard disk is used as the time axis, and the temperature change records of the CPU and GPU are recorded on the time axis. The replacement time and type of silicone grease and silicon wafer are actively input, and the quality and normal usage time of the corresponding products are retrieved through big data. The heat dissipation efficiency change of the corresponding silicone grease is calculated through the actual CPU or GPU temperature change record, and the power of the radiator is adjusted according to the heat dissipation efficiency change of the silicone grease. This design further realizes the solution of adjusting the power of the radiator through high temperature early warning, thereby further ensuring that the fan speed is adjusted before the CPU reaches high temperature. At the same time, this solution can be installed with an additional hard disk and use the additional hard disk as the time axis, which will not affect the actual use of the computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 The system topology diagram for improving the working efficiency of the computer radiator of the present invention is shown;

[0033] Figure 2 The system operation flow chart for improving the working efficiency of the computer radiator of the present invention is shown. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Example

[0036] like Figure 1 As shown, a system for improving the working efficiency of a computer radiator comprises:

[0037] Computer system, data storage module, manual operation module, hard disk data acquisition module, software data acquisition module, fan speed control module, comprehensive module, AI learning module and high temperature data recording module. The manual operation module is similar to the motherboard control software in the prior art, and can adjust the power of the graphics card, CPU and cooling fan, i.e., the radiator, in real time, i.e., the radiator power can be adjusted automatically according to the software opened in the background technology, so as to avoid the high temperature of the CPU;

[0038] The data storage module can be a hard disk that comes with the computer, which is used to record and store various data during the operation of the computer;

[0039] The software data acquisition module includes a software operation time detection module for recording the software operation time, a software operation log module for recording software operation data, a software operation data recording module for assisting in recording the number of software operations, and a software data real-time upload module for real-time uploading of software data. The software operation time detection module is used to detect the operation time of a single software. This design makes the time acquired by the present invention not a single time point data, but a time period data. Compared with the traditional data acquisition method, the single time data is prone to errors and inaccurate data caused by time changes. The time period data can express not only the data of the time point, but also the data of a time period, which is convenient for data processing according to the data of this time period, and simple data prediction can also be performed according to the data of the time period during the processing process to improve the accuracy of the data;

[0040] The hard disk data acquisition module includes a hard disk time data detection module for recording hard disk usage time, a hard disk usage log module for recording hard disk usage data, a hard disk temperature data detection module for recording hard disk temperature, a hard disk operation data detection module for recording hard disk operation status, and a real-time upload module for uploading hard disk real-time data. The data acquired by the hard disk data module can be the hard disk that comes with the computer, or can be an additional hard disk used to establish a timeline. In this embodiment, the hard disk that establishes the timeline is the hard disk that comes with the computer, and the hard disk is also used to store various data generated during the operation of the system;

[0041] The fan speed control module includes a fan operation data detection module for recording the fan operation status, a fan speed data detection module for recording the fan operation speed, a fan data recording module for recording the fan power data change, a fan operation log module for recording the fan operation data, and a fan data real-time upload module for uploading the fan real-time operation data. Based on the time axis, the fan speed adjustment is recorded and uploaded to supplement the data in the high temperature data recording module, so that the entire system can be automatically updated in real time, further improving the accuracy of high temperature prediction and further improving the working efficiency of the radiator;

[0042] The comprehensive module includes a hard disk usage time data acquisition module for acquiring hard disk usage time data, a CPU silicone grease replacement time recording module, a CPU silicone grease sheet replacement time recording module, a memory bar temperature data acquisition module, and a motherboard temperature data acquisition module;

[0043] The AI ​​learning module includes a timeline calibration module, a data alignment module, a data processing module, a prediction module, a PWM control module and a result output module. The data processing module is used to process data uploaded by other modules. The prediction module is used to predict the fan speed adjustment plan according to the data processed by the data processing module. The result output module is used to convert the prediction result of the prediction module into signal data and upload it to the PWM control block. The PWM control module is used to control the change of the fan speed. The timeline calibration module and the data alignment module are used to associate the data on the timeline. The data processing module is used to process and calculate the data. The data processing includes preprocessing, classification, format conversion, etc. for the acquired data. The data calculation is to associate and match the acquired and processed data with the data in the high temperature data recording module and the large database, so as to determine whether the fan speed needs to be adjusted under the operating state;

[0044] The high temperature data recording module is used to record the number of CPU high temperatures and related data during the operation of the computer system.

[0045] Among them, in the software data acquisition module, the software operation data recording module is used to record the running software to determine whether the number of currently running software will cause a load on the CPU. The software running time detection module is used to detect the length of time that the currently running software has been turned on, and further determine whether the number of software under the current running time will cause a load on the CPU. The number of software running and the running time data are uploaded to the AI ​​learning module in real time. The data processing module in the AI ​​learning module calculates and processes the data to determine whether the current running status requires adjustment of the fan speed.

[0046] Among them, in the hard disk data acquisition module, the hard disk time data detection module is used to detect the usage time of the hard disk, and the usage time of the hard disk is used as the time axis. The CPU and GPU temperature change records, as well as the memory bar temperature data and the motherboard temperature data are recorded on the time axis. Based on the time axis, the fan speed change record is recorded. According to the normal usage time of the silicone grease and the silicone grease sheet, and the change in the heat dissipation efficiency of the corresponding silicone grease is calculated through the actual CPU or GPU temperature change record, to simulate and predict the fan adjustment plan.

[0047] Among them, the AI ​​learning module receives data detected by other modules, and the data processing module centrally processes the data, including data de-noising, classification and format conversion. The timeline calibration module and the data alignment module associate the data on the timeline. The prediction module gives a fan adjustment prediction plan, and the result output module converts the plan output into signal data. The signal data is uploaded to the PWM control module to adjust the fan speed.

[0048] Among them, in the high temperature data recording module, the high temperature data recording module is used to record the data of the CPU under high temperature, that is, abnormal temperature. The frequency of high temperature data is counted under this data, and the AI ​​learning module calculates the rules. The software start and stop associated with high temperature occurs are counted, and the fan power is automatically pre-adjusted according to the started software.

[0049] In this embodiment, the software running data obtained in the software data acquisition module, that is, the number of software running and the running time data under the current system operation, are used to perform data processing with the relevant information data recorded in the historical high temperature data recording module, that is, the data processing module is used to quickly match these data to determine whether the data under the current software running state matches the data recorded in the high temperature data recording module, so as to determine whether the fan speed needs to be adjusted. After that, the hard disk usage time is used as the time axis, and the CPU and GPU temperature change records are associated on the time axis. The replacement time and type of the silicone grease and silicon wafer are actively input, and the quality and normal use time of the corresponding product are retrieved through big data, and the heat dissipation efficiency change of the corresponding silicone grease is calculated through the actual CPU or GPU temperature change record, and the power of the radiator is adjusted according to the change in the heat dissipation efficiency of the silicone grease. This design further realizes the solution of adjusting the radiator power through high temperature warning, thereby further ensuring that the fan speed is adjusted before the CPU reaches high temperature.

[0050] Working principle:

[0051] like Figure 1-2 As shown, a method for improving the working efficiency of a computer radiator, the specific operating steps of the system for improving the working efficiency of a computer radiator are as follows:

[0052] S1. Acquisition of system software process information: The software operation data module detects the number of software running in the system; the software operation time detection module detects the long data of each software running in the system, and the software data real-time upload module uploads the data to the AI ​​learning module;

[0053] S2. Primary judgment: The data processing module in the AI ​​learning module retrieves the information of the relevant high temperature data recording module to determine whether the system software operation data uploaded by the software data acquisition module matches the relevant information in the high temperature data recording module. If the match is successful, the next step of data acquisition is performed and the fan speed adjustment plan is predicted. If the match is unsuccessful, the data is recorded and the system continues to run;

[0054] S3. Secondary determination: In step S2, it is determined that the CPU is in or about to be in a high temperature state, and the hard disk usage time data, the replacement information data of the silicone grease and silicone grease slice in the CPU, the memory bar temperature data and the motherboard temperature data are obtained through the comprehensive module, and the replacement time and type of the silicone grease and silicone slice are actively input, and the quality and normal use time of the corresponding product are retrieved through big data, and the heat dissipation efficiency change of the corresponding silicone grease is calculated through the actual CPU or GPU temperature change record to determine whether the fan speed needs to be adjusted. If necessary, the data processing module and the prediction module are used to simulate and predict the fan speed adjustment plan. If not, the data is recorded and uploaded to the data storage module;

[0055] S4. Fan speed adjustment: According to step S3, the system determines that the fan speed needs to be adjusted, and then uses the data processing module and the prediction module to simulate and predict the fan speed adjustment plan. The result output module converts the data of the plan into a digital signal, and sends the digital signal to the PWM control module, which completes the fan speed adjustment.

[0056] Among them, in step S1, the software operation data obtained in the software operation data acquisition module is the software operation data in this time period. Specifically, when the acquisition of software operation data is started at time A, the uploaded software operation data is the operation data at time A+B, and the value of B is 10min.

[0057] Among them, in step S2, the high-temperature data recording module records the software running data, memory bar temperature data, mainboard temperature data and hard disk temperature data when the CPU is in a high-temperature state. When the data processing module in the AI ​​learning module is used to match relevant data, the above data are matched synchronously. When the matching degree is 95%, the match is successful, and if it is lower than 95%, it means the match is unsuccessful.

[0058] Among them, in step S3, the heat dissipation efficiency of the silicone grease corresponds to the temperature change of the CPU. The greater the temperature change of the CPU, the higher the heat dissipation efficiency of the silicone grease. When using the heat dissipation efficiency of the silicone grease to determine the temperature change of the CPU, the replacement time and usage time data of the silicone grease should be uploaded to the AI ​​learning module as a basis for auxiliary judgment.

[0059] Among them, in step S4, when converting data, the scheme data is first subjected to noise reduction processing, and then each text data is converted into a corresponding digital code. Each character corresponds to a certain binary code. After the text is digitized, it is modulated onto a carrier for transmission using phase shift keying technology, and the data is transmitted using a wireless medium. It should be noted that error detection and correction codes are added during data encoding.

[0060] Example 2

[0061] The contents of this embodiment are substantially the same as those of Embodiment 1. In this embodiment, the hard disk used to establish the time axis is an additionally installed hard disk, which is also used to store various data during the operation of the computer.

[0062] In this embodiment, the installation of an additional hard disk allows the hard disk to be selected as needed, and the establishment of the hard disk timeline enabled thereby is more accurate. Compared with the hard disk that comes with the computer, since the hard disk is not initially used, data needs to be processed during the timeline establishment process. Secondly, the additional hard disk has a larger storage space that can be selected, which is more effective in utilizing the operation of the system.

[0063] Example 3

[0064] The contents of this embodiment are substantially the same as those of Embodiment 1, except that, in this embodiment, in step S1, the software operation data acquired in the software operation data acquisition module is the data of the software operation in the time period. Specifically, when the acquisition of the software operation data is started at moment A, the uploaded software operation data is the operation data at moment A+B, and the value of B is 30min.

[0065] By adjusting the range of the software running time period, the range of high temperature prediction can be improved, that is, the high temperature of the CPU can be predicted earlier. For some computers that require special protection, although the working efficiency of the radiator is reduced, the protection of the computer is more comprehensive. At the same time, the solution still has the function of high temperature warning, and its working efficiency is still higher than that of the traditional radiator working system.

[0066] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A system for improving the working efficiency of a computer radiator, characterized in that: It includes a computer system, a data storage module, a manual operation module, a hard disk data acquisition module, a software data acquisition module, a fan speed control module, a comprehensive module, an AI learning module and a high temperature data recording module; The software data acquisition module includes a software running time detection module for recording the software running time, a software running log module for recording software running data, a software running data recording module for assisting in recording the number of software running, and a software data real-time uploading module for uploading software data in real time; The hard disk data acquisition module includes a hard disk time data detection module for recording hard disk usage time, a hard disk usage log module for recording hard disk usage data, a hard disk temperature data detection module for recording hard disk temperature, a hard disk operation data detection module for recording hard disk operation status, and a real-time upload module for uploading hard disk real-time data; The fan speed control module includes a fan operation data detection module for recording the fan operation status, a fan speed data detection module for recording the fan operation speed, a fan data recording module for recording the fan power data change, a fan operation log module for recording the fan operation data, and a fan data real-time uploading module for uploading the fan real-time operation data; The comprehensive module includes a hard disk usage time data acquisition module for acquiring hard disk usage time data, a CPU silicone grease replacement time recording module, a CPU silicone grease sheet replacement time recording module, a memory bar temperature data acquisition module, and a motherboard temperature data acquisition module; The AI ​​learning module includes a timeline calibration module, a data alignment module, a data processing module, a prediction module, a PMW control module and a result output module. The data processing module is used to process data uploaded by other modules. The prediction module is used to predict the fan speed adjustment scheme according to the data processed by the data processing module. The result output module is used to convert the prediction result of the prediction module into signal data and upload it to the PMW control block. The PMW control module is used to control the change of the fan speed. The timeline calibration module and the data alignment module are used to associate the data on the timeline. The high temperature data recording module is used to record the number of CPU high temperatures and related data during the operation of the computer system; In the software data acquisition module, the software running data recording module is used to record the running software to determine whether the number of currently running software will cause a load on the CPU. The software running time detection module is used to detect the duration of the currently running software being turned on, and further determine whether the number of software under the current running time will cause a load on the CPU. The number of running software and the running time data are uploaded to the AI ​​learning module in real time, and the data processing module in the AI ​​learning module calculates and processes the data to determine whether the current running state requires adjustment of the fan speed; In the hard disk data acquisition module, the hard disk time data detection module is used to detect the usage time of the hard disk, and the usage time of the hard disk is used as the time axis. The CPU and GPU temperature change records, as well as the memory bar temperature data and the motherboard temperature data are associated on the time axis. Based on the time axis, the fan speed change record is recorded, and the heat dissipation efficiency change of the corresponding silicone grease is calculated according to the normal usage time of the silicone grease and the silicone grease sheet, and the actual CPU or GPU temperature change record is used to simulate and predict the fan adjustment plan; The AI ​​learning module receives data detected by other modules, and the data processing module performs centralized processing on the data, including data noise removal, classification and format conversion. The time axis calibration module and the data alignment module associate the data on the time axis. The prediction module gives a fan adjustment prediction plan, and the result output module converts the plan output into signal data. The signal data is uploaded to the PMW control module to adjust the fan speed. In the high temperature data recording module, the high temperature data recording module is used to record the data of the CPU under high temperature, that is, abnormal temperature. The frequency of high temperature data is counted under this data, and the AI ​​learning module calculates the rules. The software start and stop associated with high temperature occurs are counted, and the fan power is automatically pre-adjusted according to the started software.

2. A method for improving the working efficiency of a computer radiator, according to the system for improving the working efficiency of a computer radiator of claim 1, characterized in that: The specific operating steps of the system to improve the working efficiency of computer radiators are as follows: S1. Acquisition of system software process information: The software operation data module detects the number of software running in the system; the software operation time detection module detects the long data of each software running in the system, and the software data real-time upload module uploads the data to the AI ​​learning module; S2. Primary judgment: The data processing module in the AI ​​learning module retrieves the information of the relevant high temperature data recording module to determine whether the software operation data in the system uploaded by the software data acquisition module matches the relevant information in the high temperature data recording module. If the match is successful, the next step of data acquisition is carried out and the fan speed adjustment plan is predicted. If the match is unsuccessful, the data is recorded and the system continues to run; S3. Secondary determination: In step S2, it is determined that the CPU is in or about to be in a high temperature state, and the hard disk usage time data, the replacement information data of the silicone grease and silicone grease slice in the CPU, the memory bar temperature data and the motherboard temperature data are obtained through the comprehensive module, and the replacement time and type of the silicone grease and silicone slice are actively input, and the quality and normal use time of the corresponding product are retrieved through big data, and the heat dissipation efficiency change of the corresponding silicone grease is calculated through the actual CPU or GPU temperature change record to determine whether the fan speed needs to be adjusted. If necessary, the data processing module and the prediction module are used to simulate and predict the fan speed adjustment plan. If not, the data is recorded and uploaded to the data storage module; S4. Fan speed adjustment: According to step S3, the system determines that the fan speed needs to be adjusted, and then uses the data processing module and the prediction module to simulate and predict the fan speed adjustment plan. The result output module converts the data of the plan into a digital signal, and sends the digital signal to the PMW control module, which completes the fan speed adjustment.

3. A method for improving the working efficiency of a computer radiator according to claim 2, characterized in that: In step S1, the software operation data acquired in the software operation data acquisition module is the software operation data in the time period. Specifically, when the acquisition of software operation data is started at time A, the uploaded software operation data is the operation data at time A+B, and the value of B is 10 minutes.

4. A method for improving the working efficiency of a computer radiator according to claim 3, characterized in that: In step S2, the high temperature data recording module records the software running data, memory bar temperature data, mainboard temperature data and hard disk temperature data when the CPU is in a high temperature state. When the data processing module in the AI ​​learning module is used to match relevant data, the above data are matched synchronously. When the matching degree is 95%, the match is successful, and if it is lower than 95%, it means the match is unsuccessful.

5. A method for improving the working efficiency of a computer radiator according to claim 4, characterized in that: In step S3, the heat dissipation efficiency of the silicone grease corresponds to the temperature change of the CPU. The greater the temperature change of the CPU, the higher the heat dissipation efficiency of the silicone grease. When using the heat dissipation efficiency of the silicone grease to determine the temperature change of the CPU, the replacement time and usage time data of the silicone grease should be uploaded to the AI ​​learning module as a basis for auxiliary judgment.

6. A method for improving the working efficiency of a computer radiator according to claim 5, characterized in that: In step S4, when converting data, the scheme data is first subjected to noise reduction processing, and then each text data is converted into a corresponding digital code. Each character corresponds to a certain binary code. After the text is digitized, it is modulated onto a carrier for transmission using phase shift keying technology, and the data is transmitted using a wireless medium. It should be noted that error detection and correction codes are added during data encoding.

Images