Domestic mainboard operation supervision system based on artificial intelligence

Abstract

The invention discloses a localized mainboard operation supervision system based on artificial intelligence, and belongs to the technical field of localized mainboard operation supervision. The localized mainboard operation supervision system comprises a time sequence module and a peripheral management module; the time sequence module is used for performing time sequence analysis control on each peripheral device connected with the mainboard of the domestic all-in-one machine, identifying peripheral information of each connected peripheral device in real time, analyzing each peripheral information and adjusting time sequence parameters according to an analysis result; the peripheral management module is used for managing each peripheral device and establishing a prediction model and an early warning monitoring model of the peripheral device; analyzing the operation monitoring data through a prediction model and an early warning monitoring model to obtain a prediction result and an early warning result; according to the method and the system, the unicity of EC control or CPLD control is effectively avoided, relatively complex time sequence control is realized through an effectively combined design method, the flexibility of peripheral control is improved, meanwhile, production resources are effectively utilized, extra cost can be saved, and improvement of production efficiency can be promoted.

Description

Technical Field

[0001] The present invention belongs to the technical field of domestic motherboard operation supervision, and specifically is a domestic motherboard operation supervision system based on artificial intelligence. Background Art

[0002] In the design of computer motherboards, EC (Embedded Controller) and CPLD (Complex Programmable Logic Device) play a vital role. EC is mainly responsible for power management, peripheral control (such as keyboard, mouse, fan, indicator light, etc.) and sensor monitoring to ensure efficient and stable operation of the equipment. CPLD focuses on signal processing and control, such as conversion, combination or routing of bus signals, and can work with other chips or circuits to realize complex control logic.

[0003] In the design of domestic all-in-one motherboards, due to the complexity of timing control and the wide variety of peripherals, relying solely on EC or CPLD is difficult to meet the flexibility and accuracy requirements of the motherboard's peripheral control.

[0004] Based on this, the present invention provides a domestically produced motherboard operation monitoring system based on artificial intelligence. Summary of the invention

[0005] In order to solve the problems existing in the above-mentioned solutions, the present invention provides a domestic motherboard operation monitoring system based on artificial intelligence.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A domestic motherboard operation supervision system based on artificial intelligence, including a timing module and a peripheral management module;

[0008] The timing module is used to perform timing analysis and control on each peripheral device connected to the domestic all-in-one machine mainboard, identify the peripheral information of each connected peripheral device in real time, analyze each peripheral information, and adjust the timing parameters according to the analysis results.

[0009] Furthermore, the method for analyzing each peripheral device information includes:

[0010] Establishing a peripheral library, the peripheral library is used to store various peripheral storage data; identifying peripheral information, and inputting the peripheral information into the peripheral library for matching;

[0011] When the peripheral storage data is matched, verification and analysis are performed based on the peripheral storage data and peripheral information to determine whether the corresponding timing parameters meet the timing control requirements. If the timing control requirements are met, the corresponding timing parameters are output; if the timing control requirements are not met, the corresponding timing parameters are adjusted until the timing control requirements are met, and the corresponding timing parameters are output;

[0012] When no peripheral storage data is matched, a peripheral model is established according to the peripheral information, timing parameters are determined according to the peripheral model, and the timing parameters are output.

[0013] Furthermore, the domestically produced all-in-one mainboard includes an EC chip, a reference chip, a mainboard, and a C PLD chip; the EC chip is connected through a bus interface on the mainboard to communicate with each reference chip on the mainboard; the C PLD chip is used to process and automatically control various signals on the mainboard, process input signals according to preset logic rules, generate corresponding output signals, and perform timing control according to a clock circuit.

[0014] Furthermore, the domestically produced all-in-one motherboard has two configurations: low-end and high-end.

[0015] It also includes a timing monitoring and optimization module, which is used to perform timing control analysis, identify peripheral devices with abnormal timing control, mark them as abnormal peripheral devices, and adjust the timing control of the abnormal peripheral devices.

[0016] Furthermore, the method for determining an abnormal peripheral device includes:

[0017] Set each timing monitoring item and the corresponding timing abnormality standard; perform real-time data collection according to each timing monitoring item to obtain the timing monitoring data of each peripheral device;

[0018] A timing anomaly model is established according to the timing anomaly standard. The expression of the timing anomaly model is:

[0019]

[0020] Where: s is the input data, the input data is the time series monitoring data, and the output data is the time series monitoring value YA(s);

[0021] The timing monitoring data is analyzed in real time through the timing anomaly model to obtain the timing monitoring value corresponding to the corresponding peripheral device, and a timing monitoring curve is generated according to the time corresponding to each timing monitoring value. The horizontal axis of the timing monitoring curve is time, and the vertical axis is the timing monitoring value;

[0022] Fit the time series monitoring curve to obtain the time series monitoring function, which is marked as H(t), where t is time;

[0023] According to the formula Calculate the corresponding time series anomaly value;

[0024] Where: PC is the time series anomaly; X1 is the threshold, [t1, t2] is the evaluation interval, t2 is the current time, and t1 is the evaluation starting time;

[0025] When the timing anomaly value is greater than 0, the corresponding peripheral device is marked as a peripheral abnormal device;

[0026] When the time series outlier value is not greater than 0, the corresponding operation will be performed.

[0027] Furthermore, the method for adjusting the timing control of the abnormal peripheral device includes:

[0028] Establishing a timing control strategy library, the timing control strategy library is used to store various optimization control strategies; establishing a simulation model according to each optimization control strategy stored in the timing control strategy library; the simulation model is used to simulate the optimization result of the corresponding optimization control strategy on the corresponding timing abnormal data to obtain a simulation result;

[0029] Obtaining a timing monitoring curve corresponding to the abnormal peripheral device, identifying a time period corresponding to when the timing monitoring value in the timing monitoring curve is 1, and marking it as an abnormal time period; collecting abnormal features according to the abnormal time period to obtain timing abnormality data;

[0030] Input the abnormal timing data into the timing control strategy library for matching, and obtain each candidate control strategy; simulate and analyze the abnormal timing data and each candidate control strategy through the simulation model, and obtain the simulation results corresponding to each candidate control strategy;

[0031] The candidate control strategies are screened according to the simulation results to obtain the target control strategy, and the timing control is adjusted according to the target control strategy.

[0032] The peripheral management module is used to manage each peripheral device, preset the operation monitoring items of each peripheral device, monitor the peripheral device in real time according to each operation monitoring item, and obtain the operation monitoring data of each peripheral device;

[0033] Setting device material data of each of the peripheral devices according to each of the operation monitoring data, wherein the device material data is the historical operation monitoring data of the corresponding peripheral device;

[0034] A prediction model and an early warning monitoring model for the peripheral device are established according to the device material data; the prediction model predicts the usage mode and demand of the peripheral device; the early warning monitoring model is used to perform early warning analysis on the operating status of the peripheral device to determine whether the peripheral device is operating abnormally;

[0035] The operation monitoring data of the peripheral equipment are analyzed separately through the prediction model and the early warning monitoring model to obtain the prediction results and early warning results corresponding to the peripheral equipment; the corresponding early warning processing is performed on the peripheral equipment according to the early warning results; and the corresponding control adjustment is performed according to the prediction results.

[0036] Furthermore, the working method of the early warning model includes:

[0037] The expression of the early warning monitoring model is:

[0038]

[0039] In the formula: qi is the input data, which is the early warning analysis data corresponding to each early warning item; i = 1, 2, ..., n, n is a positive integer; the output data is the early warning monitoring value YB (qi), which is 1 or 0;

[0040] Classify the operation monitoring data according to the preset warning items, obtain the operation monitoring data corresponding to each warning item, and mark it as warning analysis data;

[0041] The early warning analysis data is analyzed through the predicted monitoring model to obtain the early warning monitoring value of each monitoring item; and the early warning result is determined according to each early warning monitoring value.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] Through the mutual cooperation between the timing module, the timing monitoring and optimization module and the peripheral management module, the singleness of EC control or CPLD control is effectively avoided. Through the effective combination of design methods, more complex timing control is achieved, the flexibility of peripheral control is improved, and at the same time, production resources are effectively utilized, which helps to save additional costs, promote the improvement of production efficiency, and has good applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. 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.

[0047] like Figure 1 As shown, the domestic motherboard operation supervision system based on artificial intelligence includes a timing module, a timing monitoring optimization module, and a peripheral management module;

[0048] The timing module is used to perform timing analysis and control on each connected peripheral device, and to identify the peripheral information of each connected peripheral device in real time, such as the type, model, startup time, response time, data transmission rate and other related information of the peripheral device, and can be combined with the corresponding existing driver, hardware interface, identification algorithm, etc. to identify the peripheral information; it mainly analyzes the peripherals on the domestic all-in-one motherboard;

[0049] Analyze the information of each peripheral and automatically adjust the timing parameters to ensure that the peripheral devices can work in the predetermined order and rhythm.

[0050] In one embodiment, the method for analyzing each peripheral device information includes:

[0051] Establish a peripheral library, which is used to store various peripheral storage data that have been analyzed and verified. The peripheral storage data may include peripheral information, suitable timing parameters, peripheral models and other related data. The peripheral model is based on machine learning or deep learning algorithms to process and model peripheral information. Common timing modeling methods include autoregressive model (AR), moving average model (MA), autoregressive moving average model (ARMA) and more complex deep learning models, such as recurrent neural network (RNN), long short-term memory network (LSTM), etc.;

[0052] Identify peripheral information and input the peripheral information into the peripheral library for matching;

[0053] When the peripheral storage data is matched, verification and analysis are performed based on the peripheral storage data and peripheral information to determine whether the corresponding timing parameters meet the timing control requirements. If the timing control requirements are met, the corresponding timing parameters are output; if the timing control requirements are not met, the corresponding timing parameters are adjusted until the timing control requirements are met, and the corresponding timing parameters are output;

[0054] When the peripheral storage data is not matched, a peripheral model is established according to the peripheral information, and the peripheral model is analyzed to identify potential problems and optimization space in the peripheral timing. According to the analysis results, the timing parameters are automatically adjusted, such as adjusting the startup sequence of the peripherals, optimizing the data transmission rate, etc., to improve the performance and stability of the mainboard and peripherals, and output the corresponding timing parameters; the corresponding peripheral storage data is integrated and stored in the peripheral library.

[0055] In other embodiments, the peripheral information may be analyzed based on the existing technology to implement corresponding timing parameter adjustments.

[0056] In one embodiment, the domestically produced all-in-one mainboard is as follows: the EC chip is connected through the bus interface on the mainboard, communicates with other chips on the mainboard, and marks other chips as basic chips; and monitors the temperature sensor, automatically controls the fan speed, and monitors the hardware device status or errors. When a hardware failure occurs, a warning is given in time and related repair operations are performed; the CPLD chip realizes the processing and automatic control of various signals on the mainboard, processes the input signal according to the set logic rules, and generates corresponding output signals, thereby controlling the device's selection, state switching, etc., and cooperates with the clock circuit to realize precise timing control.

[0057] In actual applications, there are two configurations, low-end and high-end. Without changing the hardware status of the motherboard, the operating system automatically detects and automatically reads the configuration parameters pre-stored in the EC chip, such as low-end: processor main frequency 2.0GHz, processor core number 4 cores, fan speed 3000rpm, etc. High-end: processor main frequency 2.4GHz, processor core number 8 cores, fan speed 5000rpm, etc. According to the EC configuration parameters, relevant control processing is performed through the CPLD chip.

[0058] The timing monitoring and optimization module is used to perform timing control analysis, identify peripheral devices with abnormal timing control, mark them as abnormal peripheral devices, and adjust the timing control of the abnormal peripheral devices.

[0059] In one embodiment, the determination of abnormal peripheral devices can be marked according to the user's usage experience, and specific peripheral information can be uploaded. For example, some complex peripheral devices may cause incorrect identification of peripheral information, which will lead to abnormal timing control. Therefore, the user can obtain the real information of the corresponding peripheral device based on QR code, barcode, etc., and then upload the corresponding peripheral information; therefore, it is necessary to set up corresponding manual functions to facilitate users to mark abnormal peripheral devices and upload peripheral information.

[0060] In one embodiment, the determination of abnormal peripheral devices can be evaluated by establishing a timing anomaly model, that is, setting each timing monitoring item and the corresponding timing anomaly standard according to the performance characteristics of the timing anomaly; performing real-time data collection according to each timing monitoring item to obtain the timing monitoring data of each peripheral device; establishing a timing anomaly model according to the timing anomaly standard, and the expression of the timing anomaly model is: In the formula: s is the input data, the input data is the time series monitoring data, and the output data is the time series monitoring value YA(s); meeting the time series anomaly standard indicates that it is a time series anomaly;

[0061] The timing monitoring data is analyzed in real time through the timing anomaly model to obtain the timing monitoring value corresponding to the corresponding peripheral device, and a timing monitoring curve is generated according to the time corresponding to each timing monitoring value, with the horizontal axis being time and the vertical axis being the timing monitoring value;

[0062] Fit the time series monitoring curve to obtain the time series monitoring function, which is marked as H(t), where t is time;

[0063] According to the formula Calculate the corresponding time series anomaly value;

[0064] Where: PC is the time series anomaly value; X1 is the threshold value, which is set according to the cumulative duration that cannot exceed the anomaly within a period of time; [t1, t2] is the evaluation interval, t2 is the current time, and t1 is the evaluation starting time determined according to the preset evaluation duration and the current time. If the evaluation is performed in one hour, the preset evaluation duration is one hour, which is specifically set by professionals;

[0065] When the timing anomaly value is greater than 0, the corresponding peripheral device is marked as a peripheral abnormal device;

[0066] When the time series outlier value is not greater than 0, the corresponding operation will be performed.

[0067] In one embodiment, the method for adjusting the timing control of the abnormal peripheral device is to perform control adjustment based on the existing technology, such as analyzing according to the above-mentioned method of obtaining the timing parameters, adjusting the timing control strategy, etc.

[0068] In one embodiment, a method for adjusting the timing control of an abnormal peripheral device includes:

[0069] Establish a timing control strategy library, which is used to store various optimization control strategies for different peripherals and different states, and establish a simulation model based on the optimization control strategies stored in the timing control strategy library. The simulation model is used to simulate various timing abnormalities, specifically, to apply the corresponding optimization control strategy to optimize the corresponding timing abnormality to adjust the model, determine whether the abnormality can be solved, and the corresponding optimization degree, that is, compare the simulation effect with the original situation, determine the degree of optimization, and mark it as the optimization value;

[0070] It can be specifically established based on existing simulation technology, and can also be established based on existing neural network and other technologies, as long as the corresponding optimization situation judgment can be achieved, and then the optimization value can be judged and calculated according to the corresponding effect.

[0071] Obtain the timing monitoring curve corresponding to the abnormal peripheral device, identify the time period corresponding to the timing monitoring value of 1 in the timing monitoring curve, mark it as the abnormal time period, collect abnormal features according to the abnormal time period, and obtain timing abnormal data, that is, various feature data related to abnormal timing conditions, such as peripheral device information, abnormal performance characteristics and other related data;

[0072] Input the abnormal timing data into the timing control strategy library for matching, obtain various optimized control strategies that meet the application requirements of the abnormal peripheral device, and mark them as candidate control strategies; evaluate the abnormal timing data and each candidate control strategy through a simulation model, and obtain the simulation results corresponding to each candidate control strategy, including whether the abnormal situation can be solved and the corresponding optimization value;

[0073] Screening each candidate control strategy according to the simulation results to obtain the target control strategy, that is, the candidate control strategy with the highest optimization value that can solve the abnormal situation;

[0074] Adjust timing control according to the target control strategy.

[0075] The peripheral management module is used to manage various peripheral devices, preset operation monitoring items of various peripheral devices, such as connection status, resolution, working status, performance parameters, usage frequency, working time, energy consumption and other related data; according to the preset operation monitoring items, the corresponding peripheral devices are monitored in real time to obtain the operation monitoring data of each peripheral device;

[0076] According to the operation monitoring data of each peripheral device, the historical operation monitoring data of each peripheral device is obtained and marked as device material data;

[0077] Establish prediction models and early warning monitoring models based on equipment material data;

[0078] The prediction model is used to predict the usage pattern and demand of peripheral devices. Subsequently, corresponding decisions can be made based on the prediction results, such as adjusting the working status of the peripherals, optimizing resource allocation, etc., to meet the usage needs of the peripherals and improve system performance; for example, the power supply and distribution can be intelligently adjusted according to the usage pattern and demand prediction results of the peripherals to save energy and reduce operating costs; when it is predicted that a certain peripheral will soon require a large amount of computing resources, sufficient processor and memory resources can be reserved for it in advance; specifically, it is established based on neural networks and uses existing prediction technologies for prediction; illustratively, the device material data is preprocessed, cleaned and feature extracted to form a data set that can be used for training and prediction; machine learning or deep learning algorithms, such as time series analysis, neural networks, etc., are used to model and train the preprocessed data; through continuous iteration and optimization, the model can learn the usage pattern and demand rules of the peripherals, and have the ability to predict new data; new operating data is received in real time and predictive analysis is performed.

[0079] The early warning monitoring model is used to perform early warning analysis on the operating status of peripheral equipment to determine whether there are any abnormal operating conditions. It can also be established based on a neural network.

[0080] The operation monitoring data are analyzed through the prediction model and the early warning monitoring model respectively to obtain the prediction results and early warning results corresponding to each peripheral device; the corresponding early warning processing is carried out on the corresponding peripheral device according to the obtained early warning results; and the corresponding control adjustments are made according to the prediction results.

[0081] In one embodiment, the expression of the early warning monitoring model is:

[0082]

[0083] In the formula: qi is the input data, which is the warning analysis data corresponding to each warning item; i = 1, 2, ..., n, where n is a positive integer; the output data is the warning monitoring value YB(qi), which is 1 or 0; if it meets the corresponding warning standard, it means that the corresponding warning item has reached the warning standard and needs to be warned;

[0084] Specifically, the warning standards are set manually and trained based on historical warning analysis data. After implementation, evaluation and judgment are made based on the warning analysis data and warning standards.

[0085] Determine the warning items that need to be monitored based on the peripheral equipment, classify the operation monitoring data according to the warning items, obtain the operation monitoring data corresponding to each warning item, and mark it as warning analysis data;

[0086] Through the analysis of the predicted monitoring model, the early warning monitoring value of each monitoring item is obtained; the early warning result is determined based on the obtained early warning monitoring value.

[0087] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0088] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The domestic motherboard operation supervision system based on artificial intelligence is characterized by: Including timing module and peripheral management module; The timing module is used to perform timing analysis and control on each peripheral device connected to the domestic integrated machine mainboard, identify the peripheral information of each connected peripheral device in real time, analyze each peripheral information, and adjust the timing parameters according to the analysis results; The peripheral management module is used to manage each peripheral device, preset the operation monitoring items of each peripheral device, monitor the peripheral device in real time according to each operation monitoring item, and obtain the operation monitoring data of each peripheral device; Setting device material data of each of the peripheral devices according to each of the operation monitoring data, wherein the device material data is the historical operation monitoring data of the corresponding peripheral device; Establishing a prediction model and an early warning monitoring model for the peripheral device according to the device material data; the prediction model predicts the usage pattern and demand of the peripheral device; The early warning monitoring model is used to perform early warning analysis on the operating status of the peripheral device to determine whether the peripheral device is operating abnormally; Analyze the operation monitoring data of the peripheral device respectively through the prediction model and the early warning monitoring model to obtain the prediction result and early warning result corresponding to the peripheral device; perform corresponding early warning processing on the peripheral device according to the early warning result; Corresponding control adjustments are made according to the prediction results.

2. According to claim 1, the localized motherboard operation monitoring system based on artificial intelligence is characterized in that: The method for analyzing each peripheral information includes: Establishing a peripheral library, the peripheral library is used to store various peripheral storage data; identifying peripheral information, and inputting the peripheral information into the peripheral library for matching; When the peripheral storage data is matched, verification and analysis are performed based on the peripheral storage data and peripheral information to determine whether the corresponding timing parameters meet the timing control requirements. If the timing control requirements are met, the corresponding timing parameters are output; if the timing control requirements are not met, the corresponding timing parameters are adjusted until the timing control requirements are met, and the corresponding timing parameters are output; When no peripheral storage data is matched, a peripheral model is established according to the peripheral information, timing parameters are determined according to the peripheral model, and the timing parameters are output.

3. According to claim 1, the localized motherboard operation supervision system based on artificial intelligence is characterized in that: The domestic integrated machine motherboard includes EC chip, reference chip, motherboard and CPLD chip; The EC chip is connected through the bus interface on the mainboard and communicates with each reference chip on the mainboard; The CPLD chip is used to process and automatically control various signals on the motherboard, process input signals according to preset logic rules, generate corresponding output signals, and perform timing control according to the clock circuit.

4. The artificial intelligence-based domestic motherboard operation monitoring system according to claim 3 is characterized in that: The domestically produced all-in-one motherboard has two configurations: low-end and high-end.

5. The artificial intelligence-based domestic motherboard operation monitoring system according to claim 1 is characterized in that: It also includes a timing monitoring and optimization module, which is used to perform timing control analysis, identify peripheral devices with abnormal timing control, mark them as abnormal peripheral devices, and adjust the timing control of the abnormal peripheral devices.

6. The artificial intelligence-based domestic motherboard operation monitoring system according to claim 5 is characterized in that: Methods for determining abnormal peripheral devices include: Set each timing monitoring item and the corresponding timing abnormality standard; perform real-time data collection according to each timing monitoring item to obtain the timing monitoring data of each peripheral device; A timing anomaly model is established according to the timing anomaly standard. The expression of the timing anomaly model is: Where: s is the input data, the input data is the time series monitoring data, and the output data is the time series monitoring value YA(s); The timing monitoring data is analyzed in real time through the timing anomaly model to obtain the timing monitoring value corresponding to the corresponding peripheral device, and a timing monitoring curve is generated according to the time corresponding to each timing monitoring value. The horizontal axis of the timing monitoring curve is time, and the vertical axis is the timing monitoring value; Fit the time series monitoring curve to obtain the time series monitoring function, which is marked as H(t), where t is time; According to the formula Calculate the corresponding time series anomaly value; Where: PC is the time series anomaly; X1 is the threshold, [t1, t2] is the evaluation interval, t2 is the current time, and t1 is the evaluation starting time; When the timing anomaly value is greater than 0, the corresponding peripheral device is marked as a peripheral abnormal device; When the time series outlier value is not greater than 0, the corresponding operation will be performed.

7. The artificial intelligence-based domestic motherboard operation monitoring system according to claim 5 is characterized in that: Methods for adjusting the timing control of abnormal peripheral devices include: Establishing a timing control strategy library, the timing control strategy library is used to store various optimization control strategies; establishing a simulation model according to each optimization control strategy stored in the timing control strategy library; the simulation model is used to simulate the optimization result of the corresponding optimization control strategy on the corresponding timing abnormal data to obtain a simulation result; Obtaining a timing monitoring curve corresponding to the abnormal peripheral device, identifying a time period corresponding to when the timing monitoring value in the timing monitoring curve is 1, and marking it as an abnormal time period; collecting abnormal features according to the abnormal time period to obtain timing abnormality data; Input the abnormal timing data into the timing control strategy library for matching, and obtain each candidate control strategy; simulate and analyze the abnormal timing data and each candidate control strategy through the simulation model, and obtain the simulation results corresponding to each candidate control strategy; The candidate control strategies are screened according to the simulation results to obtain the target control strategy, and the timing control is adjusted according to the target control strategy.

8. The artificial intelligence-based domestic motherboard operation monitoring system according to claim 1 is characterized in that: The working methods of the early warning model include: The expression of the early warning monitoring model is: In the formula: qi is the input data, which is the early warning analysis data corresponding to each early warning item; i = 1, 2, ..., n, n is a positive integer; the output data is the early warning monitoring value YB (qi), which is 1 or 0; Classify the operation monitoring data according to the preset warning items, obtain the operation monitoring data corresponding to each warning item, and mark it as warning analysis data; The early warning analysis data is analyzed through the predicted monitoring model to obtain the early warning monitoring value of each monitoring item; and the early warning result is determined according to each early warning monitoring value.

Images