Intelligent flat panel heat dissipation control method, system, device and medium

Abstract

The present invention relates to a method, system, device and medium for controlling heat dissipation of a smart tablet, and relates to the field of heat dissipation control, including: when the smart tablet is running, receiving the current operating status of each tablet heat source and the predicted temperature at the last moment; collecting the ambient temperature, and based on the ambient temperature and heat source temperature prediction model, predicting the temperature of each heat source to obtain the temperature value of each heat source; analyzing and obtaining the target heat dissipation rate and the heat dissipation rate threshold; when the target heat dissipation rate is greater than or equal to the threshold and the deviation between the two is greater than or equal to the preset value, sending an overheating risk signal to the visualization interface for early warning. The present application solves the technical problem in the prior art that the heat dissipation monitoring range of the smart tablet is not comprehensive and it is difficult to accurately warn of overheating risks due to the limited arrangement position of the temperature sensor. By constructing a heat source temperature prediction model and heat dissipation rate analysis, the comprehensive temperature monitoring of each heat source inside the smart tablet is achieved, and the technical effect of improving the accuracy of the overheating risk early warning is achieved.

Description

Technical Field

[0001] The present invention relates to the field of heat dissipation control, and in particular to a method, system, device and medium for heat dissipation control of an intelligent flat panel. Background Art

[0002] With the rapid development of electronic technology, smart tablets have become an important tool for people to work, study and entertain. However, smart tablets generate a lot of heat during operation. If the heat dissipation is not timely or sufficient, it is easy to cause the device to overheat, which not only affects the user experience, but also may damage the hardware and shorten the service life of the device. In the prior art, the device temperature is usually monitored by setting temperature sensors at some key heat source locations inside the smart tablet. When the sensor detects that the temperature inside the tablet exceeds the preset threshold, it will issue an overheating warning to the user, reminding the user to take necessary measures to prevent the device from overheating and damage. However, the existing smart tablet heat dissipation control scheme has the following shortcomings: First, due to the internal structure layout of the smart tablet, the arrangement position of the temperature sensor is relatively limited, and it is difficult to cover all heat sources, resulting in an incomplete heat dissipation monitoring range; second, due to limited monitoring data, it is difficult to achieve accurate overheating warning by relying only on the data collected by a limited number of temperature sensors to determine whether it is overheating. Summary of the invention

[0003] The present invention aims to solve the technical problem in the prior art that the heat dissipation monitoring range of smart flat panels is incomplete and it is difficult to accurately warn of overheating risks due to the limited arrangement position of temperature sensors. A smart flat panel heat dissipation control method, system, device and medium are provided to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a method for controlling heat dissipation of an intelligent flat panel, comprising: when the intelligent flat panel is running, receiving a first flat panel heat source state and a first flat panel heat source initial temperature, a second flat panel heat source state and a second flat panel heat source initial temperature, until an Nth flat panel heat source state and an Nth flat panel heat source initial temperature, wherein the first flat panel heat source state, the second flat panel heat source state, until the Nth flat panel heat source initial temperature are the flat panel heat source operating states at the current moment, and the first flat panel heat source initial temperature, the second flat panel heat source initial temperature, until the Nth flat panel heat source initial temperature are the predicted temperatures of the flat panel heat source at the previous moment; collecting an ambient temperature signal through an ambient temperature sensor; and predicting the first flat panel heat source state and the first flat panel heat source initial temperature, the second flat panel heat source state, and the Nth flat panel heat source initial temperature based on the ambient temperature signal through a heat source temperature prediction model of the intelligent flat panel heat dissipation control system. The initial temperature of the second flat plate heat source is used to predict the temperature until the Nth flat plate heat source state and the initial temperature of the Nth flat plate heat source, and the first flat plate heat source temperature, the second flat plate heat source temperature and the Nth flat plate heat source temperature are obtained; a target heat dissipation rate analysis is performed according to the first flat plate heat source temperature, the second flat plate heat source temperature and the Nth flat plate heat source temperature and the ambient temperature signal to obtain a target heat dissipation rate; a threshold heat dissipation rate analysis is performed according to the first flat plate heat source temperature, the second flat plate heat source temperature and the Nth flat plate heat source temperature and the ambient temperature signal to obtain a heat dissipation rate threshold; when the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to the preset heat dissipation rate deviation, an overheating risk signal is generated and sent to the smart tablet visualization interface for an overheating early warning reminder.

[0006] In a second aspect, the present invention provides an intelligent flat-panel heat dissipation control system, including: a heat source data receiving module, which is used to receive a first flat-panel heat source state and a first flat-panel heat source initial temperature, a second flat-panel heat source state and a second flat-panel heat source initial temperature, until an Nth flat-panel heat source state and an Nth flat-panel heat source initial temperature when the intelligent flat-panel is running, wherein the first flat-panel heat source state, the second flat-panel heat source state, until the Nth flat-panel heat source initial temperature are the flat-panel heat source operation states at the current moment, and the first flat-panel heat source initial temperature, the second flat-panel heat source initial temperature, until the Nth flat-panel heat source initial temperature are the predicted temperatures of the flat-panel heat source at the previous moment; an ambient temperature acquisition module, which is used to acquire an ambient temperature signal through an ambient temperature sensor; a temperature prediction and analysis module, which is used to predict the first flat-panel heat source state and the first flat-panel heat source initial temperature, the second flat-panel heat source state, and the Nth flat-panel heat source initial temperature based on the ambient temperature signal through a heat source temperature prediction model of the intelligent flat-panel heat dissipation control system. the initial temperature of the second flat plate heat source, the temperature prediction is performed on the state of the Nth flat plate heat source and the initial temperature of the Nth flat plate heat source, and the first flat plate heat source temperature, the second flat plate heat source temperature and the Nth flat plate heat source temperature are obtained; a target heat dissipation analysis module is used to perform a target heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature and the Nth flat plate heat source temperature and the ambient temperature signal to obtain a target heat dissipation rate; a threshold heat dissipation analysis module is used to perform a threshold heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature and the Nth flat plate heat source temperature and the ambient temperature signal to obtain a heat dissipation rate threshold; an overheating warning reminder module is used to generate an overheating risk signal and send it to the smart tablet visualization interface for an overheating warning reminder when the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to the preset heat dissipation rate deviation.

[0007] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute a smart tablet heat dissipation control method provided in the present application.

[0008] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute a smart flat panel heat dissipation control method provided by the present application.

[0009] The beneficial effects of the present invention are:

[0010] When the smart flat panel is running, the status and initial temperature of the first to Nth flat panel heat sources are received, where the heat source status indicates the current operating status of the heat source, and the initial temperature of the heat source is the predicted temperature of the heat source at the previous moment. By obtaining the real-time status and initial temperature value of each heat source inside the flat panel, the necessary input parameters are provided for subsequent temperature prediction; the ambient temperature signal is collected through the ambient temperature sensor, which provides a basis for subsequent heat dissipation demand analysis; the heat source temperature prediction model of the smart flat panel heat dissipation control system is used to predict the temperature of the first to Nth flat panel heat sources based on the ambient temperature signal and the status and initial temperature of each heat source, and the predicted temperature is obtained, thereby realizing the prediction of the temperature of each heat source inside the flat panel; the target heat dissipation rate is analyzed according to the predicted temperature of each heat source and the ambient temperature signal, and the target The heat dissipation rate lays the foundation for precise heat dissipation control; the threshold heat dissipation rate analysis is performed according to the predicted temperature of each heat source and the ambient temperature signal to obtain the heat dissipation rate threshold, and the warning line of the tablet heat dissipation rate is obtained as a standard for judging whether it is overheating; when the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the deviation between the two is greater than or equal to the preset value, an overheating risk signal is generated and sent to the tablet interface for early warning. By comparing the relationship between the target heat dissipation rate and the threshold, it is determined whether the tablet is at risk of overheating. Once the conditions are met, an early warning is issued in time to remind the user, which solves the problems of incomplete heat dissipation monitoring and inaccurate overheating warning in the existing technology, thereby effectively avoiding the possible harm caused by overheating and achieving the purpose of preventing tablet overheating damage, extending equipment life, and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a flow chart of a heat dissipation control method for an intelligent flat panel provided by the present invention;

[0012] Figure 2 A schematic diagram of the structure of an intelligent flat-panel heat dissipation control system provided by the present invention;

[0013] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention;

[0014] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0015] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0016] Heat source data receiving module 110, ambient temperature acquisition module 120, temperature prediction and analysis module 130, target heat dissipation analysis module 140, threshold heat dissipation analysis module 150, overheating warning module 160, electronic device 200, memory 210, processor 220, first computer program 211, computer readable storage medium 300, second computer program 311. DETAILED DESCRIPTION

[0017] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0018] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0019] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0020] Embodiment 1:

[0021] like Figure 1 As shown, an embodiment of the present invention provides a smart tablet heat dissipation control method, which is applied to a smart tablet heat dissipation control system. The system is embedded in a smart tablet, and the smart tablet has an ambient temperature sensor.

[0022] Specifically, a smart tablet heat dissipation control method is applied to a smart tablet heat dissipation control system, which is not independent but embedded in the smart tablet device. Through the embedded design, the heat dissipation control system can be closely integrated with other hardware and software of the smart tablet to achieve efficient and real-time heat dissipation management. At the same time, the smart tablet device is also equipped with an ambient temperature sensor to collect temperature information of the environment in which the smart tablet is located, providing an important reference for heat dissipation control.

[0023] The intelligent flat panel heat dissipation control method includes:

[0024] S100: When the smart tablet is running, a first flat plate heat source state and a first flat plate heat source initial temperature, a second flat plate heat source state and a second flat plate heat source initial temperature are received, until an Nth flat plate heat source state and an Nth flat plate heat source initial temperature, wherein the first flat plate heat source state, the second flat plate heat source state, until the Nth flat plate heat source initial temperature are the flat plate heat source operating states at the current moment, and the first flat plate heat source initial temperature, the second flat plate heat source initial temperature, until the Nth flat plate heat source initial temperature are the predicted temperatures of the flat plate heat sources at the previous moment.

[0025] Specifically, when the smart tablet is running, the smart tablet heat dissipation control system continuously receives the status information and initial temperature information of each flat heat source. Specifically, at each monitoring moment, the heat dissipation control system receives the status of the first flat heat source and the initial temperature of the first flat heat source, the status of the second flat heat source and the initial temperature of the second flat heat source, and so on, until the status of the Nth flat heat source and the initial temperature of the Nth flat heat source. Among them, N is the total number of flat heat sources inside the smart tablet. Among them, the status of the first flat heat source, the status of the second flat heat source until the status of the Nth flat heat source reflect the operating status of each flat heat source at the current moment. These status information vary according to the type of flat heat source. For example, for the CPU as a flat heat source, its status is the CPU occupancy rate; for the screen as a flat heat source, its status is the screen brightness, etc. The initial temperature of the first flat heat source, the initial temperature of the second flat heat source until the initial temperature of the Nth flat heat source refer to the temperatures of each flat heat source predicted at the previous monitoring moment, which provides an important reference for the temperature prediction at the current moment.

[0026] By continuously acquiring the status of the flat panel heat source and the initial temperature of the flat panel heat source, the thermal conditions inside the smart panel can be understood in real time, providing necessary data for subsequent heat dissipation rate analysis, overheating risk warning, etc., and providing a basis for realizing intelligent heat dissipation control.

[0027] S200: Collecting an ambient temperature signal through an ambient temperature sensor.

[0028] Specifically, the smart tablet device has a built-in ambient temperature sensor that can detect temperature changes around the tablet in real time, and convert the collected temperature data into an ambient temperature signal, which is provided to the heat dissipation control system.

[0029] Ambient temperature is an important external factor that affects the heat dissipation of smart tablets. When the ambient temperature is high, the heat generated inside the tablet is not easy to dissipate to the external environment, which easily causes heat to accumulate inside the tablet, thereby increasing the risk of overheating of the tablet. On the contrary, when the ambient temperature is low, the heat inside the tablet is more easily conducted and convected to the external environment, which is conducive to the heat dissipation of the tablet.

[0030] Therefore, by collecting ambient temperature signals, the heat dissipation control system can fully perceive the internal and external factors that affect the heat dissipation of the smart tablet, not just the temperature changes of the heat source inside the tablet, providing more comprehensive and accurate data support for subsequent heat dissipation rate analysis and overheating warning.

[0031] S300: Based on the ambient temperature signal, a heat source temperature prediction model of the intelligent flat-panel heat dissipation control system is used to predict the state of the first flat-panel heat source and the initial temperature of the first flat-panel heat source, the state of the second flat-panel heat source and the initial temperature of the second flat-panel heat source, up to the state of the Nth flat-panel heat source and the initial temperature of the Nth flat-panel heat source, to obtain the first flat-panel heat source temperature, the second flat-panel heat source temperature, up to the Nth flat-panel heat source temperature.

[0032] Specifically, the heat source temperature prediction model is the core component of the heat dissipation control system. The model uses a machine learning algorithm to establish a nonlinear mapping relationship between the flat plate heat source state, the initial temperature of the flat plate heat source, and the temperature of the flat plate heat source. First, the acquired states of each flat plate heat source and the initial temperature of the flat plate heat source, as well as the collected ambient temperature signal, are input into the heat source temperature prediction model. Then, based on these input data, the heat source temperature prediction model comprehensively considers the heating state of the internal heat source of the flat plate, the temperature level at the previous moment, and the temperature conditions of the environment in which the flat plate is located, and predicts the first flat plate heat source temperature, the second flat plate heat source temperature, and the Nth flat plate heat source temperature at the current moment through nonlinear calculation. Among them, the predicted flat plate heat source temperature reflects the temperature change trend of each heat source in the current state, providing a predictive decision-making basis for the heat dissipation control of the smart flat plate. By accurately predicting the flat plate heat source temperature, the heat dissipation control system can judge the possible overheating risk in advance and take corresponding measures to prevent the occurrence of overheating.

[0033] By introducing the heat source temperature prediction model, the temperature of the flat panel heat source can be accurately estimated, providing forward-looking decision-making information for the heat dissipation control system. This predictive temperature analysis method improves the initiative and timeliness of intelligent flat panel heat dissipation.

[0034] S400: Analyze a target heat dissipation rate according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature, and the ambient temperature signal to obtain a target heat dissipation rate.

[0035] Specifically, the target heat dissipation rate refers to the heat dissipation rate that needs to be achieved in order to maintain the temperature of each heat source of the smart tablet within a safe range. Therefore, the target heat dissipation rate is a key indicator for evaluating the heat dissipation performance of the smart tablet, and directly determines whether the smart tablet can effectively avoid overheating risks.

[0036] First, the predicted temperature of each tablet heat source and the ambient temperature conditions are comprehensively considered. According to the principle of thermal balance, the heat generation inside the tablet and the heat exchange outside the tablet are taken into account to estimate the heat dissipation required by the current smart tablet. Then, the estimated heat dissipation is divided by the heat dissipation area of ​​the smart tablet to obtain the heat dissipation rate per unit area and unit time, which is the target heat dissipation rate.

[0037] Through target heat dissipation rate analysis, the heat dissipation requirements of smart tablets can be quantitatively evaluated, making the heat dissipation control of smart tablets more scientific and accurate, and effectively improving the heat dissipation efficiency and reliability.

[0038] S500: Performing a threshold heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature, and the ambient temperature signal to obtain a heat dissipation rate threshold.

[0039] Specifically, the heat dissipation rate threshold indicates the minimum heat dissipation rate that the smart tablet must reach in the current working state and ambient temperature to prevent overheating risks. When the actual heat dissipation rate of the smart tablet is lower than the threshold, it means that the heat accumulation rate inside the tablet exceeds the heat dissipation rate. If this continues for a long time, the tablet temperature may exceed the safe range and cause overheating problems.

[0040] During the threshold heat dissipation rate analysis process, the heat dissipation control system comprehensively considers the safe temperature limits of each heat source of the smart tablet and the maximum heat dissipation capacity of the whole machine heat dissipation design, and obtains the heat dissipation rate threshold through thermal engineering calculation. In addition, when the ambient temperature is high, the temperature difference between the tablet surface and the environment decreases, and the difficulty of heat transfer from the inside of the tablet to the outside increases, resulting in a decrease in heat dissipation efficiency. In order to compensate for this effect, the ambient temperature correction coefficient is introduced when calculating the heat dissipation rate threshold according to the ambient temperature signal to ensure the adaptability of the threshold. Among them, the determination of the heat dissipation rate threshold needs to balance the relationship between performance and safety. On the one hand, setting the threshold too high will limit the performance of the smart tablet; on the other hand, setting the threshold too low may not effectively prevent the risk of overheating. Therefore, it is necessary to dynamically adjust the heat dissipation rate threshold according to the actual use scenario and user preferences of the smart tablet to achieve the best balance between performance and heat dissipation. For example, for gaming scenarios with high performance requirements, the heat dissipation rate threshold is appropriately lowered to release more performance; in daily office scenarios, the threshold is moderately increased to reduce the noise of the cooling fan and create a more comfortable use environment.

[0041] Through threshold heat dissipation rate analysis, the heat dissipation rate threshold is obtained, and a safety baseline for heat dissipation control is established, which provides a quantitative standard for timely detection and warning of overheating risks, ensuring that the smart tablet can maintain reliable heat dissipation performance under various working conditions.

[0042] S600: When the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to the preset heat dissipation rate deviation, an overheating risk signal is generated and sent to the smart tablet visualization interface for overheating warning.

[0043] Specifically, by comparing the target heat dissipation rate and the heat dissipation rate threshold, the overheating risk of the smart tablet is dynamically evaluated, and a corresponding overheating risk signal is generated to promptly remind the user to take necessary heat dissipation measures.

[0044] First, determine whether the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold. If the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, it indicates that the heat dissipation demand of the smart tablet has reached or exceeded the lower limit of safe heat dissipation, and there is a potential risk of overheating. At the same time, the difference between the target heat dissipation rate and the heat dissipation rate threshold is calculated to obtain the heat dissipation rate deviation, which is compared with the preset heat dissipation rate deviation. If the heat dissipation rate deviation is greater than or equal to the preset heat dissipation rate deviation, it is further confirmed that the smart tablet has an overheating risk. When the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to the preset heat dissipation rate deviation, it is confirmed that there is an overheating risk. At this time, the heat dissipation control system generates an overheating risk signal and issues an overheating warning reminder to the user through the visual interface of the smart tablet. This reminder can be in the form of pop-up windows, notifications, warning lights, etc. to ensure that the user can be informed of the overheating status of the tablet in a timely manner.

[0045] Through overheating risk assessment and early warning, users can be promptly reminded of the overheating risk of smart tablets, providing decision support for taking heat dissipation measures, thereby effectively preventing performance degradation, component loss and other problems that may be caused by tablet overheating, and ensuring the safe and reliable operation of the tablet.

[0046] Furthermore, the embodiment of the present application also includes:

[0047] S110: when the flat plate heat source is a CPU, the flat plate heat source state attribute is a CPU occupancy rate;

[0048] S120: when the flat plate heat source is a GPU, the flat plate heat source state attribute is a GPU occupancy rate;

[0049] S130: When the flat plate heat source is memory, the flat plate heat source state attribute is memory occupancy rate;

[0050] S140: When the flat panel heat source is a screen, the flat panel heat source state attribute is screen brightness;

[0051] S150: When the flat plate heat source is in a non-charging state, the flat plate heat source state attribute is a battery discharge rate;

[0052] S160: When the flat plate heat source is in a charging state, the flat plate heat source state attributes are a battery discharge rate and a battery charge rate.

[0053] In a feasible implementation, in order to accurately reflect the operating status of each heat source of the smart flat panel, corresponding state attribute parameters are defined according to different types of flat panel heat sources. These state attribute parameters can directly reflect the workload of each heat source, thereby providing a reliable data basis for subsequent temperature prediction.

[0054] For the core heat source of CPU, the CPU occupancy rate is selected as its state attribute parameter. The CPU occupancy rate directly reflects the workload of the processor. The higher the occupancy rate, the more tasks the CPU needs to process and the greater the heat generated. By real-time monitoring of the CPU occupancy rate, the heating condition of the CPU can be accurately evaluated. For the GPU heat source, the GPU occupancy rate is used as the state attribute parameter. When processing tasks such as graphics rendering and 3D computing, the GPU generates a lot of heat, and its occupancy rate is directly related to the heat generated by the GPU. Especially when performing GPU-intensive tasks such as games and video processing, monitoring the GPU occupancy rate is particularly important. For the memory heat source, the memory occupancy rate is used as its state attribute parameter. When performing data read and write operations, the memory generates heat. The higher the memory occupancy rate, the more frequent the data access is and the more heat is generated. By monitoring the memory occupancy rate, the heating trend of the memory module can be estimated. For the screen heat source, the screen brightness is selected as the state attribute parameter. The higher the screen brightness, the greater the power consumed by the backlight module and the more heat generated. For the battery heat source, the corresponding state attribute parameters are defined according to the different charging states. When in the non-charging state, the battery discharge rate is used as the state attribute parameter; when in the charging state, the battery discharge rate and charging rate are monitored simultaneously. This is because the battery generates heat during the charging and discharging process, especially during fast charging, and the charging heat will significantly affect the temperature distribution of the smart tablet.

[0055] By defining corresponding state attribute parameters for different types of flat plate heat sources, a comprehensive heat source state monitoring system is established. These state attribute parameters can not only accurately reflect the working status of each heat source, but also are easy to collect and calculate, laying the foundation for the accurate prediction of the heat source temperature.

[0056] Furthermore, the embodiment of the present application also includes:

[0057] S310: The heat source temperature prediction model includes a charging mode heat source temperature prediction model and a non-charging mode heat source temperature prediction model;

[0058] S320: When in the charging mode, according to the charging mode heat source temperature prediction model, the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, until the Nth flat plate heat source state and the Nth flat plate heat source initial temperature are predicted to obtain the first flat plate heat source temperature, the second flat plate heat source temperature, until the Nth flat plate heat source temperature;

[0059] S330: When in non-charging mode, according to the non-charging mode heat source temperature prediction model, temperature prediction is performed on the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, until the Nth flat plate heat source state and the Nth flat plate heat source initial temperature, to obtain the first flat plate heat source temperature, the second flat plate heat source temperature, until the Nth flat plate heat source temperature.

[0060] Specifically, in order to improve the accuracy of heat source temperature prediction, two special heat source temperature prediction models are constructed according to the charging status of the smart tablet to distinguish between charging mode and non-charging mode, so as to better adapt to the temperature change characteristics of the tablet under different working conditions.

[0061] In the charging state, the battery charging process will generate additional heat, and the charging current will also affect the temperature distribution of other components; in the non-charging state, the heating of the tablet mainly comes from the normal operation of each functional component. Therefore, the heat source temperature prediction model is divided into two sub-models: the charging mode heat source temperature prediction model and the non-charging mode heat source temperature prediction model, so as to more accurately describe the temperature change law under different working modes. When the smart tablet is in the charging mode, the charging mode heat source temperature prediction model is automatically called. The model receives the state information and initial temperature information of each heat source as input, including the state of the first flat plate heat source and the initial temperature of the first flat plate heat source, the state of the second flat plate heat source and the initial temperature of the second flat plate heat source, and so on until the relevant information of the Nth heat source. When predicting the heat source temperature, the charging mode heat source temperature prediction model will take into account the additional heat impact brought by the charging process, so as to more accurately predict the temperature change of each heat source in the charging state, and obtain the first flat plate heat source temperature, the second flat plate heat source temperature, and the Nth flat plate heat source temperature. Correspondingly, when the smart tablet is in the non-charging mode, the non-charging mode heat source temperature prediction model is called. The model also receives the status and initial temperature information of each heat source, but in the prediction calculation, it mainly focuses on the heating characteristics of each functional component under normal working conditions, without considering the heat impact caused by charging, so as to obtain a temperature prediction result that is more in line with the non-charging state, and obtains the temperature of the first flat plate heat source, the second flat plate heat source temperature, and so on to the Nth flat plate heat source temperature.

[0062] By distinguishing between charging mode and non-charging mode, a dedicated temperature prediction model is established to improve the pertinence and accuracy of temperature prediction. This mode division method not only takes into account the significant impact of the charging process on the temperature distribution of the whole machine, but also simplifies the prediction calculation complexity under each mode, making the prediction result more reliable. At the same time, the two prediction models can be optimized and updated independently, further improving the maintainability and scalability of the system.

[0063] Furthermore, the embodiment of the present application also includes:

[0064] S311: Collecting operation logs of the non-charging mode tablet and the charging mode tablet;

[0065] Wherein, the non-charging mode flat panel operation log includes a first flat panel heat source state non-charging mode record data set and a first flat panel heat source initial temperature non-charging mode record data set, a second flat panel heat source state non-charging mode record data set and a second flat panel heat source initial temperature non-charging mode record data set, until the Nth flat panel heat source state non-charging mode record data set and the Nth flat panel heat source initial temperature non-charging mode record data set, and a first flat panel heat source temperature non-charging mode identification data set, a second flat panel heat source temperature non-charging mode identification data set, until the Nth flat panel heat source non-charging mode temperature identification data set;

[0066] Wherein, the charging mode flat panel operation log includes a first flat panel heat source state charging mode record data set and a first flat panel heat source initial temperature charging mode record data set, a second flat panel heat source state charging mode record data set and a second flat panel heat source initial temperature charging mode record data set, until the Nth flat panel heat source state charging mode record data set and the Nth flat panel heat source initial temperature charging mode record data set, and a first flat panel heat source temperature charging mode identification data set, a second flat panel heat source temperature charging mode identification data set, until the Nth flat panel heat source charging mode temperature identification data set;

[0067] S312: using the first flat plate heat source temperature non-charging mode identification data set, the second flat plate heat source temperature non-charging mode identification data set, and the Nth flat plate heat source non-charging mode temperature identification data set as supervision data, using the first flat plate heat source state non-charging mode record data set and the first flat plate heat source initial temperature non-charging mode record data set, the second flat plate heat source state non-charging mode record data set, and the second flat plate heat source initial temperature non-charging mode record data set, and the Nth flat plate heat source state non-charging mode record data set, and the Nth flat plate heat source initial temperature non-charging mode record data set as input data, training a BP neural network, and generating the non-charging mode heat source temperature prediction model;

[0068] S313: Using the first flat plate heat source temperature charging mode identification data set, the second flat plate heat source temperature charging mode identification data set, and the Nth flat plate heat source charging mode temperature identification data set as supervision data, using the first flat plate heat source state charging mode record data set and the first flat plate heat source initial temperature charging mode record data set, the second flat plate heat source state charging mode record data set, and the second flat plate heat source initial temperature charging mode record data set, and the Nth flat plate heat source state charging mode record data set and the Nth flat plate heat source initial temperature charging mode record data set as input data, training a BP neural network, and generating the charging mode heat source temperature prediction model.

[0069] In a preferred embodiment, a large amount of operating data is collected and a machine learning method is used to train a heat source temperature prediction model to ensure that the prediction model can accurately reflect the temperature change characteristics of the smart panel under different working conditions.

[0070] Specifically, the tablet operation log is collected, and the tablet operation log is divided into a non-charging mode tablet operation log and a charging mode tablet operation log. By collecting these operation logs, a data basis is provided for subsequent model training. In the non-charging mode tablet operation log, two types of key data are included. The first type is a record data set, including a state non-charging mode record data set from the first flat plate heat source to the Nth flat plate heat source and an initial temperature non-charging mode record data set. These data reflect the working conditions and initial temperature information of each heat source in the non-charging state. The second type is an identification data set, including a temperature non-charging mode identification data set from the first flat plate heat source to the Nth flat plate heat source. These data record the actual temperature changes of each heat source in the non-charging state. The structure of the charging mode tablet operation log is similar to that of the non-charging mode, and also includes a record data set and an identification data set. Among them, the record data set includes a state charging mode record data set from the first flat plate heat source to the Nth flat plate heat source and an initial temperature charging mode record data set, and the identification data set includes a temperature charging mode identification data set from the first flat plate heat source to the Nth flat plate heat source. These data comprehensively record the working status, temperature change and other information of each heat source in the charging state of the smart tablet.

[0071] After completing the data collection, the BP neural network is used to construct the non-charging mode heat source temperature prediction model and the charging mode heat source temperature prediction model respectively. For the non-charging mode, the non-charging mode identification data set of each heat source is used as the supervision data, and the corresponding state non-charging mode record data set and the initial temperature non-charging mode record data set are used as the input data. Through the training of the BP neural network, a non-charging mode heat source temperature prediction model that can accurately predict the heat source temperature in the non-charging state is generated. Similarly, for the charging mode, the charging mode identification data set of each heat source is used as the supervision data, and the corresponding state charging mode record data set and the initial temperature charging mode record data set are used as the input data to train another BP neural network to generate a charging mode heat source temperature prediction model specifically for the charging state. By training separately, it is ensured that both prediction models can accurately reflect the temperature change law under their corresponding working modes.

[0072] Through the data-driven model building method, the collection and analysis of a large amount of operating data, combined with the powerful nonlinear mapping ability of the BP neural network, the accurate prediction of the heat source temperature of the smart tablet is achieved. The prediction models for charging mode and non-charging mode are constructed separately, which not only improves the accuracy of the prediction, but also enables the model to better adapt to different working scenarios, providing reliable support for subsequent heat dissipation warnings, and effectively improving the performance and reliability of heat dissipation control of smart tablets.

[0073] Furthermore, the embodiment of the present application also includes:

[0074] S3131: Construct training loss function:

[0075] ,

[0076] ,

[0077] in, Represents the global loss function, Represents the mean loss function, Characterizes the predicted temperature of the non-charging mode of the i-th flat plate heat source, Characterize the temperature identification data of the non-charging mode of the i-th flat plate heat source, represents the temperature deviation threshold, Q represents the number of heat sources on the plate;

[0078] S3132: Based on the global loss threshold and the mean loss threshold, the training loss function is retrieved, and the first flat plate heat source temperature non-charging mode identification data set, the second flat plate heat source temperature non-charging mode identification data set, and the Nth flat plate heat source non-charging mode temperature identification data set are used as supervision data, and the first flat plate heat source state non-charging mode record data set and the first flat plate heat source initial temperature non-charging mode record data set, the second flat plate heat source state non-charging mode record data set, and the second flat plate heat source initial temperature non-charging mode record data set, and the Nth flat plate heat source state non-charging mode record data set, and the Nth flat plate heat source initial temperature non-charging mode record data set are used as input data to train the BP neural network and generate the non-charging mode heat source temperature prediction model.

[0079] In a preferred embodiment, during the training process of the non-charging mode heat source temperature prediction model, in order to ensure the prediction accuracy of the model, two loss functions are provided to evaluate the performance of the prediction model from different perspectives.

[0080] First, construct the training loss function, including the global loss function And the mean loss function Two loss functions.

[0081] Among them, the global loss function It is used to evaluate the proportion of prediction results that exceed the allowable error range. The calculation formula is: , in this formula, represents the predicted temperature of the non-charged mode of the ith flat plate heat source, Represents the non-charging mode temperature identification data of the i-th flat plate heat source, that is, the actual measured temperature. is a pre-set temperature deviation threshold, which is used to determine whether the deviation between the predicted temperature and the actual temperature is within an acceptable range. Q represents the total number of plate heat sources. This function reflects the global accuracy of the prediction model by counting the proportion of heat sources whose predicted deviation exceeds the threshold. At the same time, the mean loss function In the form of mean square error, the calculation formula is: , which calculates the mean of the sum of squares of the differences between the predicted temperature and the actual temperature of all heat sources, and can reflect the overall fit between the predicted temperature and the actual temperature. By introducing the square term, the function imposes a greater penalty on larger prediction errors, thus prompting the model to pay more attention to reducing prediction deviations during training.

[0082] In the model training stage, based on the pre-set global loss threshold and mean loss threshold, these two loss functions are used to guide the training process of the BP neural network. Specifically, the non-charging mode temperature identification data set of each flat heat source is used as the supervision data, and the corresponding state non-charging mode record data set and the initial temperature non-charging mode record data set are used as the input data. The network parameters are continuously adjusted through the back propagation algorithm so that the values ​​of the two loss functions can meet the requirements of the preset thresholds, thereby obtaining the non-charging mode heat source temperature prediction model.

[0083] Through the dual loss function, the global loss function ensures that most prediction results are within an acceptable error range, while the mean loss function ensures the stability of the overall prediction accuracy. The combined use of the two loss functions not only improves the prediction accuracy of the model, but also enhances the reliability and stability of the prediction results, thereby ensuring that the non-charging mode heat source temperature prediction model can accurately predict the temperature changes of each heat source and provide a reliable decision-making basis for the heat dissipation control of the smart tablet.

[0084] Furthermore, the embodiment of the present application also includes:

[0085] S410: Tablet model is used as a fixed constraint;

[0086] S420: constructing dynamic constraints on the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature, and the ambient temperature signal based on the temperature deviation tolerance interval;

[0087] S430: According to the fixed constraint and the dynamic constraint, a data set of heat production records per unit time is collected, and a mode analysis is performed to obtain a mode heat production per unit time;

[0088] S440: Calculate the mean of the majority of heat production per unit time to obtain the target heat dissipation rate.

[0089] In a preferred embodiment, the target heat dissipation rate is obtained by comprehensively considering fixed constraints and dynamic constraints and combining statistical analysis methods.

[0090] Since different models of smart tablets have differences in structural design, heat dissipation system and material properties, these differences will directly affect the heat dissipation performance of the tablet. First, the tablet model is set as a fixed constraint to ensure that the subsequent heat dissipation rate analysis is based on a specific hardware platform and improve the pertinence of the analysis results. Secondly, based on the temperature deviation fault tolerance interval, a dynamic constraint is constructed. Specifically, the temperature of each tablet heat source (i.e., the temperature of the first tablet heat source to the temperature of the Nth tablet heat source) and the ambient temperature signal are used as variables to establish a dynamic constraint relationship within the temperature deviation fault tolerance interval. This dynamic constraint takes into account the uncertainty in the temperature measurement process, so that the heat dissipation rate analysis has a certain fault tolerance capability and improves stability and reliability.

[0091] After determining the constraints, according to the requirements of fixed constraints and dynamic constraints, a data set of heat generation records per unit time is collected. These data reflect the heat generated by each heat source of the flat panel per unit time under specific constraints. In order to obtain representative values ​​from these data, mode analysis is performed on the collected data. Mode analysis can find the heat generation value with the highest frequency in the data set, that is, the mode heat generation per unit time, which can better reflect the heat generation characteristics of the flat panel under normal working conditions. Afterwards, the mean of the obtained mode heat generation per unit time is calculated to obtain the target heat dissipation rate, which is expressed as the heat that needs to be dissipated per unit time, and directly reflects the heat dissipation capacity required by the smart flat panel under the current working state.

[0092] By obtaining the target heat dissipation rate based on multiple constraints, an important reference indicator is provided for the heat dissipation control of the smart tablet, which effectively improves the accuracy and adaptability of the heat dissipation control.

[0093] Furthermore, the embodiment of the present application also includes:

[0094] S510: According to the fixed constraint and the dynamic constraint, a data set of heat dissipation records per unit time is collected, and a mode analysis is performed to obtain a mode heat dissipation per unit time;

[0095] S520: Calculate the mean of the majority of heat dissipation per unit time to obtain the heat dissipation rate threshold.

[0096] In a preferred embodiment, in order to obtain the heat dissipation rate threshold, first, based on the aforementioned fixed constraints (i.e., tablet computer model) and dynamic constraints (constraints constructed based on the temperature deviation tolerance interval), a data set of heat dissipation records per unit time is collected. These data reflect the heat dissipated by the tablet to the outside world through its heat dissipation system per unit time under specific constraints. Different from heat generation, heat dissipation is mainly affected by factors such as the tablet heat dissipation structure design, heat dissipation material characteristics, and ambient temperature, and has its own specific change law.

[0097] In order to obtain representative heat dissipation capacity indicators from the collected data, a mode analysis is performed on the heat dissipation record data set per unit time to obtain the mode heat dissipation per unit time. This statistical method can find the heat dissipation value with the highest frequency in the data set, effectively filter out the influence of some extreme cases or outliers, and ensure the stability and reliability of the analysis results. After that, the mean of the mode heat dissipation per unit time is calculated to obtain the heat dissipation rate threshold, which represents the maximum heat dissipation rate that the smart tablet can maintain under normal working conditions and is an important reference standard for judging whether the tablet has an overheating risk. When the target heat dissipation rate exceeds this threshold, it means that the heat generated by the tablet has exceeded the processing capacity of its cooling system, and corresponding early warning measures need to be taken.

[0098] By obtaining the heat dissipation rate threshold, together with the target heat dissipation rate, it constitutes an indicator for the overheating risk warning of the smart tablet, effectively improving the reliability and practicality of the heat dissipation control system.

[0099] The embodiment of the present invention provides a method for controlling heat dissipation of a smart tablet, which has at least the following technical effects:

[0100] When the smart tablet is running, the first tablet heat source state and the first tablet heat source initial temperature, the second tablet heat source state and the second tablet heat source initial temperature are received, until the Nth tablet heat source state and the Nth tablet heat source initial temperature, wherein the first tablet heat source state, the second tablet heat source state until the Nth tablet heat source initial temperature are the tablet heat source operation state at the current moment, and the first tablet heat source initial temperature, the second tablet heat source initial temperature until the Nth tablet heat source initial temperature are the predicted temperature of the tablet heat source at the previous moment, so as to fully grasp the real-time working state inside the tablet, provide real and reliable data support for subsequent temperature prediction, and improve the accuracy of temperature prediction. Through the ambient temperature sensor, the ambient temperature signal is collected, so that the heat dissipation demand analysis is closer to the actual application scenario, avoiding the heat dissipation control decision deviation caused by ignoring the ambient temperature. Through the heat source temperature prediction model of the intelligent flat-panel heat dissipation control system, based on the ambient temperature signal, the temperature prediction is performed on the first flat-panel heat source state and the first flat-panel heat source initial temperature, the second flat-panel heat source state and the second flat-panel heat source initial temperature, until the Nth flat-panel heat source state and the Nth flat-panel heat source initial temperature, and the first flat-panel heat source temperature, the second flat-panel heat source temperature, and the Nth flat-panel heat source temperature are obtained, so as to realize comprehensive monitoring of all heat source temperatures inside the flat panel. According to the first flat-panel heat source temperature, the second flat-panel heat source temperature, and the Nth flat-panel heat source temperature, the target heat dissipation rate is analyzed to obtain the target heat dissipation rate, which provides a basis for precise control of heat dissipation. According to the first flat-panel heat source temperature, the second flat-panel heat source temperature, and the Nth flat-panel heat source temperature, and the ambient temperature signal, the threshold heat dissipation rate analysis is performed to obtain the heat dissipation rate threshold, which defines the safe operation limit for flat-panel heat dissipation. When the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to the preset heat dissipation rate deviation, an overheating risk signal is generated and sent to the smart tablet visualization interface for overheating warning reminder, thereby realizing real-time monitoring and timely warning of tablet overheating risks, allowing users to take necessary preventive measures before the tablet overheats, thereby maximizing the safety and stability of the tablet operation.

[0101] Embodiment 2:

[0102] like Figure 2 As shown, based on the same inventive concept of a smart tablet heat dissipation control method provided in Embodiment 1, an embodiment of the present invention further provides a smart tablet heat dissipation control system, which is embedded in a smart tablet, and the smart tablet has an ambient temperature sensor, and the system includes:

[0103] The heat source data receiving module 110 is used to receive, when the smart flat panel is running, a first flat panel heat source state and a first flat panel heat source initial temperature, a second flat panel heat source state and a second flat panel heat source initial temperature, until an Nth flat panel heat source state and an Nth flat panel heat source initial temperature, wherein the first flat panel heat source state, the second flat panel heat source state, until the Nth flat panel heat source initial temperature are the flat panel heat source running states at the current moment, and the first flat panel heat source initial temperature, the second flat panel heat source initial temperature, until the Nth flat panel heat source initial temperature are the predicted temperatures of the flat panel heat source at the previous moment;

[0104] The ambient temperature acquisition module 120 is used to acquire an ambient temperature signal through an ambient temperature sensor;

[0105] The temperature prediction and analysis module 130 is used to perform temperature prediction on the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, up to the Nth flat plate heat source state and the Nth flat plate heat source initial temperature through the heat source temperature prediction model of the intelligent flat plate heat dissipation control system based on the ambient temperature signal, and obtain the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature;

[0106] A target heat dissipation analysis module 140 is used to perform a target heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature to the Nth flat plate heat source temperature and the ambient temperature signal to obtain a target heat dissipation rate;

[0107] A threshold heat dissipation analysis module 150 is used to perform a threshold heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature and the ambient temperature signal to obtain a heat dissipation rate threshold;

[0108] The overheating warning reminder module 160 is used to generate an overheating risk signal and send it to the smart tablet visualization interface for overheating warning reminder when the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to the preset heat dissipation rate deviation.

[0109] Furthermore, the heat source data receiving module 110 includes the following execution steps:

[0110] When the plate heat source is the CPU, the plate heat source status attribute is the CPU occupancy rate;

[0111] When the flat plate heat source is a GPU, the flat plate heat source state attribute is the GPU occupancy rate;

[0112] When the plate heat source is memory, the plate heat source state attribute is memory occupancy;

[0113] When the flat panel heat source is the screen, the flat panel heat source state attribute is the screen brightness;

[0114] When the flat plate heat source is in a non-charging state, the flat plate heat source state attribute is the battery discharge rate;

[0115] When the flat plate heat source is in a charging state, the flat plate heat source state attributes are a battery discharge rate and a battery charge rate.

[0116] Furthermore, the temperature prediction and analysis module 130 includes the following execution steps:

[0117] The heat source temperature prediction model includes a charging mode heat source temperature prediction model and a non-charging mode heat source temperature prediction model;

[0118] When in the charging mode, according to the charging mode heat source temperature prediction model, the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, until the Nth flat plate heat source state and the Nth flat plate heat source initial temperature are predicted to obtain the first flat plate heat source temperature, the second flat plate heat source temperature, until the Nth flat plate heat source temperature;

[0119] When in non-charging mode, according to the non-charging mode heat source temperature prediction model, temperature prediction is performed on the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, until the Nth flat plate heat source state and the Nth flat plate heat source initial temperature, to obtain the first flat plate heat source temperature, the second flat plate heat source temperature, until the Nth flat plate heat source temperature.

[0120] Furthermore, the temperature prediction and analysis module 130 further includes the following execution steps:

[0121] Collect non-charging mode tablet operation logs and charging mode tablet operation logs;

[0122] Wherein, the non-charging mode flat panel operation log includes a first flat panel heat source state non-charging mode record data set and a first flat panel heat source initial temperature non-charging mode record data set, a second flat panel heat source state non-charging mode record data set and a second flat panel heat source initial temperature non-charging mode record data set, until the Nth flat panel heat source state non-charging mode record data set and the Nth flat panel heat source initial temperature non-charging mode record data set, and a first flat panel heat source temperature non-charging mode identification data set, a second flat panel heat source temperature non-charging mode identification data set, until the Nth flat panel heat source non-charging mode temperature identification data set;

[0123] Wherein, the charging mode flat panel operation log includes a first flat panel heat source state charging mode record data set and a first flat panel heat source initial temperature charging mode record data set, a second flat panel heat source state charging mode record data set and a second flat panel heat source initial temperature charging mode record data set, until the Nth flat panel heat source state charging mode record data set and the Nth flat panel heat source initial temperature charging mode record data set, and a first flat panel heat source temperature charging mode identification data set, a second flat panel heat source temperature charging mode identification data set, until the Nth flat panel heat source charging mode temperature identification data set;

[0124] The first flat plate heat source temperature non-charging mode identification data set, the second flat plate heat source temperature non-charging mode identification data set, and the Nth flat plate heat source non-charging mode temperature identification data set are used as supervision data, and the first flat plate heat source state non-charging mode record data set and the first flat plate heat source initial temperature non-charging mode record data set, the second flat plate heat source state non-charging mode record data set, and the second flat plate heat source initial temperature non-charging mode record data set, and the Nth flat plate heat source state non-charging mode record data set and the Nth flat plate heat source initial temperature non-charging mode record data set are used as input data to train a BP neural network to generate the non-charging mode heat source temperature prediction model;

[0125] The first flat plate heat source temperature charging mode identification data set, the second flat plate heat source temperature charging mode identification data set, and the Nth flat plate heat source charging mode temperature identification data set are used as supervision data; the first flat plate heat source state charging mode record data set and the first flat plate heat source initial temperature charging mode record data set, the second flat plate heat source state charging mode record data set, and the second flat plate heat source initial temperature charging mode record data set, and the Nth flat plate heat source state charging mode record data set and the Nth flat plate heat source initial temperature charging mode record data set are used as input data to train a BP neural network and generate the charging mode heat source temperature prediction model.

[0126] Furthermore, the temperature prediction and analysis module 130 further includes the following execution steps:

[0127] Construct the training loss function:

[0128] ,

[0129] ,

[0130] in, Represents the global loss function, Represents the mean loss function, Characterizes the predicted temperature of the non-charging mode of the i-th flat plate heat source, Characterize the temperature identification data of the non-charging mode of the i-th flat plate heat source, represents the temperature deviation threshold, Q represents the number of heat sources on the plate;

[0131] Based on the global loss threshold and the mean loss threshold, the training loss function is called up, and the first flat plate heat source temperature non-charging mode identification data set, the second flat plate heat source temperature non-charging mode identification data set, and the Nth flat plate heat source non-charging mode temperature identification data set are used as supervision data; the first flat plate heat source state non-charging mode record data set and the first flat plate heat source initial temperature non-charging mode record data set, the second flat plate heat source state non-charging mode record data set, and the second flat plate heat source initial temperature non-charging mode record data set, and the Nth flat plate heat source state non-charging mode record data set, and the Nth flat plate heat source initial temperature non-charging mode record data set are used as input data to train the BP neural network and generate the non-charging mode heat source temperature prediction model.

[0132] Furthermore, the target heat dissipation analysis module 140 includes the following execution steps:

[0133] Tablet model is used as a fixed constraint;

[0134] Based on the temperature deviation tolerance interval, constructing dynamic constraints on the first flat plate heat source temperature, the second flat plate heat source temperature up to the Nth flat plate heat source temperature and the ambient temperature signal;

[0135] According to the fixed constraint and the dynamic constraint, a data set of heat production records per unit time is collected, and a mode analysis is performed to obtain a mode heat production per unit time;

[0136] The target heat dissipation rate is obtained by calculating the mean of the heat generated per unit time.

[0137] Furthermore, the threshold heat dissipation analysis module 150 includes the following execution steps:

[0138] According to the fixed constraint and the dynamic constraint, a data set of heat dissipation records per unit time is collected, and a mode analysis is performed to obtain a mode heat dissipation per unit time;

[0139] The heat dissipation rate threshold is obtained by calculating the mean of the mode heat dissipation per unit time.

[0140] Embodiment three:

[0141] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3As shown, an electronic device 200 provided by an embodiment of the present invention includes a memory 210, a processor 220, and a first computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the first computer program 211, an intelligent flat-panel heat dissipation control method is implemented.

[0142] Embodiment 4:

[0143] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 300 on which a second computer program 311 is stored. When the second computer program 311 is executed by a processor, an intelligent flat panel heat dissipation control method is implemented.

[0144] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0145] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0146] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0147] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0149] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0150] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A method for controlling heat dissipation of an intelligent flat panel, characterized in that: Applied to a heat dissipation control system of a smart tablet, the system is embedded in the smart tablet, and the smart tablet has an ambient temperature sensor, including: When the smart tablet is running, the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature are received, until the Nth flat plate heat source state and the Nth flat plate heat source initial temperature, wherein the first flat plate heat source state, the second flat plate heat source state until the Nth flat plate heat source state are the flat plate heat source operation states at the current moment, and the first flat plate heat source initial temperature, the second flat plate heat source initial temperature until the Nth flat plate heat source initial temperature are the predicted temperatures of the flat plate heat source at the previous moment; Collecting ambient temperature signals through ambient temperature sensors; Using a heat source temperature prediction model of an intelligent flat-panel heat dissipation control system, based on the ambient temperature signal, temperature prediction is performed on the first flat-panel heat source state and the first flat-panel heat source initial temperature, the second flat-panel heat source state and the second flat-panel heat source initial temperature, up to the Nth flat-panel heat source state and the Nth flat-panel heat source initial temperature, to obtain the first flat-panel heat source temperature, the second flat-panel heat source temperature, up to the Nth flat-panel heat source temperature; Performing target heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature, and the ambient temperature signal to obtain a target heat dissipation rate; Performing a threshold heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature, and the ambient temperature signal to obtain a heat dissipation rate threshold; When the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to the preset heat dissipation rate deviation, an overheating risk signal is generated and sent to the smart tablet visual interface for overheating warning reminder; Further, performing a target heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature and the ambient temperature signal to obtain a target heat dissipation rate includes: Tablet model is used as a fixed constraint; Based on the temperature deviation tolerance interval, constructing dynamic constraints on the first flat plate heat source temperature, the second flat plate heat source temperature up to the Nth flat plate heat source temperature and the ambient temperature signal; According to the fixed constraint and the dynamic constraint, a data set of heat production records per unit time is collected, and a mode analysis is performed to obtain a mode heat production per unit time; Calculate the mean of the heat generated per unit time to obtain the target heat dissipation rate; Further, performing a threshold heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature and the ambient temperature signal to obtain a heat dissipation rate threshold includes: According to the fixed constraint and the dynamic constraint, a data set of heat dissipation records per unit time is collected, and a mode analysis is performed to obtain a mode heat dissipation per unit time; The heat dissipation rate threshold is obtained by calculating the mean of the mode heat dissipation per unit time.

2. The method according to claim 1, characterized in that When the smart panel is running, receiving the first panel heat source status, the second panel heat source status, and the Nth panel heat source status, including: When the plate heat source is the CPU, the plate heat source status attribute is the CPU occupancy rate; When the flat plate heat source is a GPU, the flat plate heat source state attribute is the GPU occupancy rate; When the plate heat source is memory, the plate heat source state attribute is memory occupancy; When the flat panel heat source is the screen, the flat panel heat source state attribute is the screen brightness; When the flat plate heat source is in a non-charging state, the flat plate heat source state attribute is the battery discharge rate; When the flat plate heat source is in a charging state, the flat plate heat source state attributes are a battery discharge rate and a battery charge rate.

3. The method according to claim 1, characterized in that The method uses a heat source temperature prediction model of an intelligent flat plate heat dissipation control system to predict the temperature of the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, and finally the Nth flat plate heat source state and the Nth flat plate heat source initial temperature based on the ambient temperature signal, and obtains the first flat plate heat source temperature, the second flat plate heat source temperature, and finally the Nth flat plate heat source temperature, including: The heat source temperature prediction model includes a charging mode heat source temperature prediction model and a non-charging mode heat source temperature prediction model; When in the charging mode, according to the charging mode heat source temperature prediction model, the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, until the Nth flat plate heat source state and the Nth flat plate heat source initial temperature are predicted to obtain the first flat plate heat source temperature, the second flat plate heat source temperature, until the Nth flat plate heat source temperature; When in non-charging mode, according to the non-charging mode heat source temperature prediction model, temperature prediction is performed on the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, until the Nth flat plate heat source state and the Nth flat plate heat source initial temperature, to obtain the first flat plate heat source temperature, the second flat plate heat source temperature, until the Nth flat plate heat source temperature.

4. The method according to claim 3, characterized in that The heat source temperature prediction model construction step comprises: Collect non-charging mode tablet operation logs and charging mode tablet operation logs; Wherein, the non-charging mode flat panel operation log includes a first flat panel heat source state non-charging mode record data set and a first flat panel heat source initial temperature non-charging mode record data set, a second flat panel heat source state non-charging mode record data set and a second flat panel heat source initial temperature non-charging mode record data set, until the Nth flat panel heat source state non-charging mode record data set and the Nth flat panel heat source initial temperature non-charging mode record data set, and a first flat panel heat source temperature non-charging mode identification data set, a second flat panel heat source temperature non-charging mode identification data set, until the Nth flat panel heat source temperature non-charging mode identification data set; Wherein, the charging mode tablet operation log includes a first tablet heat source state charging mode record data set and a first tablet heat source initial temperature charging mode record data set, a second tablet heat source state charging mode record data set and a second tablet heat source initial temperature charging mode record data set, until the Nth tablet heat source state charging mode record data set and the Nth tablet heat source initial temperature charging mode record data set, and a first tablet heat source temperature charging mode identification data set, a second tablet heat source temperature charging mode identification data set, until the Nth tablet heat source temperature charging mode identification data set; The first flat plate heat source temperature non-charging mode identification data set, the second flat plate heat source temperature non-charging mode identification data set, and the Nth flat plate heat source temperature non-charging mode identification data set are used as supervision data, and the first flat plate heat source state non-charging mode record data set and the first flat plate heat source initial temperature non-charging mode record data set, the second flat plate heat source state non-charging mode record data set, and the second flat plate heat source initial temperature non-charging mode record data set, and the Nth flat plate heat source state non-charging mode record data set and the Nth flat plate heat source initial temperature non-charging mode record data set are used as input data to train a BP neural network to generate the non-charging mode heat source temperature prediction model; The first flat plate heat source temperature charging mode identification data set, the second flat plate heat source temperature charging mode identification data set, and the Nth flat plate heat source temperature charging mode identification data set are used as supervision data, and the first flat plate heat source state charging mode record data set and the first flat plate heat source initial temperature charging mode record data set, the second flat plate heat source state charging mode record data set, and the second flat plate heat source initial temperature charging mode record data set, and the Nth flat plate heat source state charging mode record data set and the Nth flat plate heat source initial temperature charging mode record data set are used as input data to train a BP neural network and generate the charging mode heat source temperature prediction model.

5. The method according to claim 4, characterized in that The first flat plate heat source temperature non-charging mode identification data set, the second flat plate heat source temperature non-charging mode identification data set, and the Nth flat plate heat source temperature non-charging mode identification data set are used as supervision data, and the first flat plate heat source state non-charging mode record data set and the first flat plate heat source initial temperature non-charging mode record data set, the second flat plate heat source state non-charging mode record data set, and the second flat plate heat source initial temperature non-charging mode record data set, and the Nth flat plate heat source state non-charging mode record data set and the Nth flat plate heat source initial temperature non-charging mode record data set are used as input data to train a BP neural network to generate the non-charging mode heat source temperature prediction model, including: Construct the training loss function: ， ， in, Represents the global loss function, Represents the mean loss function, Characterizes the predicted temperature of the non-charging mode of the i-th flat plate heat source, Characterize the non-charging mode identification data of the temperature of the i-th plate heat source, represents the temperature deviation threshold, Q represents the number of heat sources on the plate; Based on the global loss threshold and the mean loss threshold, the training loss function is called up, and the first flat plate heat source temperature non-charging mode identification dataset, the second flat plate heat source temperature non-charging mode identification dataset, and the Nth flat plate heat source temperature non-charging mode identification dataset are used as supervision data; the first flat plate heat source state non-charging mode record dataset and the first flat plate heat source initial temperature non-charging mode record dataset, the second flat plate heat source state non-charging mode record dataset, and the second flat plate heat source initial temperature non-charging mode record dataset, and the Nth flat plate heat source state non-charging mode record dataset and the Nth flat plate heat source initial temperature non-charging mode record dataset are used as input data to train the BP neural network and generate the non-charging mode heat source temperature prediction model.

6. An intelligent flat-panel heat dissipation control system, characterized in that: A method for controlling heat dissipation of a smart tablet computer according to any one of claims 1 to 5, wherein the system is embedded in the smart tablet computer, and the smart tablet computer has an ambient temperature sensor, including: A heat source data receiving module, the heat source data receiving module is used to receive a first flat plate heat source state and a first flat plate heat source initial temperature, a second flat plate heat source state, and a second flat plate heat source initial temperature, until an Nth flat plate heat source state and an Nth flat plate heat source initial temperature when the smart flat plate is running, wherein the first flat plate heat source state, the second flat plate heat source state, until the Nth flat plate heat source state are the flat plate heat source running states at the current moment, and the first flat plate heat source initial temperature, the second flat plate heat source initial temperature, until the Nth flat plate heat source initial temperature are the predicted temperatures of the flat plate heat source at the previous moment; An ambient temperature acquisition module, wherein the ambient temperature acquisition module is used to acquire an ambient temperature signal through an ambient temperature sensor; A temperature prediction and analysis module, the temperature prediction and analysis module is used to perform temperature prediction on the first flat plate heat source state and the first flat plate heat source initial temperature, the second flat plate heat source state and the second flat plate heat source initial temperature, up to the Nth flat plate heat source state and the Nth flat plate heat source initial temperature through the heat source temperature prediction model of the intelligent flat plate heat dissipation control system based on the ambient temperature signal, and obtain the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature; a target heat dissipation analysis module, the target heat dissipation analysis module being used to perform a target heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature, and the ambient temperature signal to obtain a target heat dissipation rate; A threshold heat dissipation analysis module, the threshold heat dissipation analysis module is used to perform a threshold heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature until the Nth flat plate heat source temperature and the ambient temperature signal to obtain a heat dissipation rate threshold; An overheating warning and reminder module, wherein the overheating warning and reminder module is used to generate an overheating risk signal and send it to the smart tablet visual interface for overheating warning reminder when the target heat dissipation rate is greater than or equal to the heat dissipation rate threshold, and the heat dissipation rate deviation between the target heat dissipation rate and the heat dissipation rate threshold is greater than or equal to a preset heat dissipation rate deviation; Further, performing a target heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature and the ambient temperature signal to obtain a target heat dissipation rate includes: Tablet model is used as a fixed constraint; Based on the temperature deviation tolerance interval, constructing dynamic constraints on the first flat plate heat source temperature, the second flat plate heat source temperature up to the Nth flat plate heat source temperature and the ambient temperature signal; According to the fixed constraint and the dynamic constraint, a data set of heat production records per unit time is collected, and a mode analysis is performed to obtain a mode heat production per unit time; Calculate the mean of the heat generated per unit time to obtain the target heat dissipation rate; Further, performing a threshold heat dissipation rate analysis according to the first flat plate heat source temperature, the second flat plate heat source temperature, up to the Nth flat plate heat source temperature and the ambient temperature signal to obtain a heat dissipation rate threshold includes: According to the fixed constraint and the dynamic constraint, a data set of heat dissipation records per unit time is collected, and a mode analysis is performed to obtain a mode heat dissipation per unit time; The heat dissipation rate threshold is obtained by calculating the mean of the mode heat dissipation per unit time.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; The processor is used to read and execute the computer software program, thereby implementing the intelligent flat panel heat dissipation control method described in any one of claims 1-5.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the intelligent flat panel heat dissipation control method according to any one of claims 1 to 5 is implemented.

Images