Intelligent environment sensing method and system based on outdoor waterproof television

Abstract

The invention relates to an intelligent environment sensing method and system based on an outdoor waterproof television. The method comprises the following steps: acquiring an environment monitoring data set of the outdoor waterproof television; carrying out nonlinear transformation and multi-dimensional feature extraction, and obtaining a fusion feature matrix through feature fusion; calculating a temperature parameter weight coefficient, a humidity parameter weight coefficient, an illumination intensity parameter weight coefficient and a rainfall parameter weight coefficient for the fusion feature matrix, and performing weighted calculation with the fusion feature matrix to obtain an environmental risk factor; inputting the environmental risk factor and the fusion feature matrix into a deep neural network based on near-end strategy optimization PPO to carry out strategy iteration optimization calculation, and generating a protection control instruction set; a driving signal of the display module and a control signal of the waterproof actuator are generated respectively, and the driving signal and the control signal are executed through the execution unit. According to the invention, through cooperative control of the display parameters and the waterproof level, the display effect is optimized while the equipment safety is ensured, and the watching experience of a user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of television environment sensing, and in particular to an intelligent environment sensing method and system based on an outdoor waterproof television. Background Art

[0002] With the widespread use of outdoor electronic display devices, outdoor waterproof TVs play an important role in public places, advertising displays, etc. However, outdoor environmental conditions are complex and changeable, and factors such as temperature, humidity, light intensity and rainfall will have a significant impact on the normal operation and display effect of TV equipment.

[0003] Traditional outdoor waterproof TVs generally adopt a fixed threshold protection strategy and a single display parameter adjustment solution, which cannot respond accurately to different environmental conditions. This static protection mechanism has a delayed response when facing sudden weather changes, which can easily cause insufficient or excessive equipment protection, affecting the service life of the equipment and the viewing experience. Most of the environmental sensing solutions on the market currently rely on simple single-parameter monitoring and preset rule judgments, and lack the ability to comprehensively analyze multiple environmental factors. In practical applications, there are complex interactions between various environmental parameters, and it is necessary to establish an intelligent environmental perception mechanism to achieve dynamic weight optimization of environmental parameters and adaptive adjustment of protection strategies. Summary of the invention

[0004] The main purpose of the present invention is to provide an intelligent environment sensing method and system based on an outdoor waterproof television. The present invention optimizes the display effect while ensuring the safety of the equipment through the coordinated control of display parameters and waterproof level, thereby improving the user's viewing experience.

[0005] To achieve the above object, the present invention provides an intelligent environment sensing method based on an outdoor waterproof television, comprising the following steps:

[0006] Collect environmental monitoring data sets of outdoor waterproof TVs through environmental sensor arrays;

[0007] Inputting the environmental monitoring data set into the environmental sensor network for nonlinear transformation and multidimensional feature extraction, and obtaining a fused feature matrix through feature fusion;

[0008] The temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient are calculated for the fusion feature matrix by using the Bayesian optimization algorithm, and weighted calculation is performed with the fusion feature matrix to obtain the environmental risk factor;

[0009] Input the environmental risk factor and the fusion feature matrix into a deep neural network based on proximal policy optimization (PPO) to perform policy iteration optimization calculation to generate a protection control instruction set, wherein the protection control instruction set includes a display parameter adjustment instruction and a waterproof level control instruction;

[0010] A driving signal of the display module and a control signal of the waterproof actuator are respectively generated according to the protection control instruction set, and the driving signal and the control signal are executed by the execution unit.

[0011] The present invention also provides an intelligent environment sensing system based on an outdoor waterproof television, comprising:

[0012] A collection module, used to collect environmental monitoring data sets of outdoor waterproof TVs through an environmental sensor array;

[0013] A feature extraction module is used to input the environmental monitoring data set into the environmental sensor network for nonlinear transformation and multi-dimensional feature extraction, and obtain a fused feature matrix through feature fusion;

[0014] A weighted calculation module, used to calculate the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient for the fused feature matrix through a Bayesian optimization algorithm, and perform weighted calculation with the fused feature matrix to obtain an environmental risk factor;

[0015] A generation module, used for inputting the environmental risk factor and the fusion feature matrix into a deep neural network based on proximal policy optimization (PPO) to perform policy iteration optimization calculation, and generating a protection control instruction set, wherein the protection control instruction set includes a display parameter adjustment instruction and a waterproof level control instruction;

[0016] An execution module is used to generate a drive signal of the display module and a control signal of the waterproof actuator according to the protection control instruction set, and execute the drive signal and the control signal through an execution unit.

[0017] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0018] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0019] In summary, the technical solution provided by the present invention realizes the real-time collection and feature extraction of multi-dimensional environmental parameters through the cooperation of the environmental sensor array and the environmental sensor network, thereby improving the accuracy and comprehensiveness of environmental monitoring; the Bayesian optimization algorithm is used to dynamically calculate the weights of environmental parameters, solving the problem that the traditional fixed weight scheme cannot adapt to environmental changes; the policy optimization mechanism based on the PPO deep neural network realizes the intelligent generation of protection control instructions, significantly reducing the system response delay; through the coordinated control of display parameters and waterproof level, the display effect is optimized while ensuring the safety of the equipment, thereby improving the user viewing experience; the multi-layer feature extraction structure of the environmental sensor network enhances the system's perception and feature expression capabilities of complex environmental changes; the self-attention mechanism is used for feature fusion to improve the system's recognition and response capabilities to key environmental factors; the policy gradient calculation method based on importance sampling ratio clipping ensures the stability and convergence of the control strategy update. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the steps of an intelligent environment sensing method based on an outdoor waterproof television in one embodiment of the present invention;

[0021] Figure 2 is a front view schematic diagram of an outdoor waterproof television in one embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of the back side of an outdoor waterproof television in one embodiment of the present invention;

[0023] Figure 4 It is a structural block diagram of an intelligent environment sensing system based on an outdoor waterproof TV in one embodiment of the present invention;

[0024] Figure 5 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0025] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0027] Reference Figure 1 This embodiment provides an intelligent environment sensing method based on an outdoor waterproof television, comprising the following steps:

[0028] S1, collects the environmental monitoring dataset of outdoor waterproof TV through environmental sensor array;

[0029] Among them, a preset sampling voltage is applied to the input end of the temperature sensor in the environmental sensor array, and the voltage can ensure that the temperature sensor works stably and captures the real temperature change signal in the environment. The output of the temperature sensor is processed by the signal conditioning circuit, which includes the amplification and filtering steps of the analog signal. The design of the amplification circuit needs to take into account the sensitivity of the sensor and the range of the output signal to ensure that the small signal can be accurately amplified to a voltage range suitable for subsequent processing, and the filtering circuit is used to remove environmental noise and other interference signals to obtain a stable temperature signal. Through this step, the temperature signal after analog-to-digital conversion is converted into a corresponding temperature digital signal. At the same time, an excitation signal is input to the detection end of the humidity sensor in the environmental sensor array. The excitation signal is a carefully designed sine wave or pulse signal, and its frequency and amplitude need to match the optimal working parameters of the sensor. After passing through the humidity sensor, the signal will respond to the change in environmental humidity. On this basis, the signal conversion circuit is used to perform impedance matching processing to reduce the energy loss in signal transmission and improve the quality of the signal. In the process of signal stabilization, the designed filter and buffer circuit will further eliminate environmental interference, so that the output signal can more accurately reflect the actual humidity change. The processed humidity signal is converted into a corresponding humidity digital signal. For the light intensity sensor in the environmental sensor array, the characteristics of its photosensitive element are utilized, and the photoelectric conversion circuit is used to realize the conversion of light signal to electrical signal under the condition of applying reverse bias voltage. When the photosensitive element is exposed to light, a current signal proportional to the light intensity is generated. This signal is relatively weak, and is amplified by the current amplifier circuit to enhance the signal strength. In order to make the light intensity signal output by the sensor have better linear characteristics, the signal is corrected by the linearization circuit to ensure that the output light intensity signal can accurately reflect the changes in the light intensity of the environment. These amplified and linearized light intensity signals are converted into light intensity digital signals. In the signal processing process of the rain sensor, an AC excitation signal is applied to its detection electrode. The selection of this signal should take into account the working characteristics and environmental conditions of the rain sensor, and a high-frequency and low-amplitude AC signal is used to improve the sensitivity. After the sensor receives the external rainfall information and generates the corresponding response signal, the signal is waveform-shaped by the signal processing circuit to correct the amplitude and frequency drift problems of the rainfall signal to ensure the standardization and readability of the signal. The processed rainfall signal is converted into a rainfall digital signal by analog-to-digital conversion to indicate the real-time changes in rainfall intensity. The temperature digital signal, humidity digital signal, light intensity digital signal and rainfall digital signal are collected into the data acquisition module, which realizes signal switching and sampling and holding processing through a multiplexer. The design of the multiplexer can effectively coordinate the input of various sensor signals to ensure that each signal can be accurately collected during the multi-channel sampling process, and the sampling and holding circuit improves the accuracy of subsequent digital conversion by maintaining the stability of the signal voltage value.By converting multi-channel sampling data into digital quantities, using a high-precision analog-to-digital converter to convert analog signals into digital signals, and combining algorithms for data compensation to correct measurement errors caused by differences in sensor characteristics or environmental interference, a complete and accurate environmental monitoring data set is generated.

[0030] In this embodiment, Figure 2 This is a front view of an outdoor waterproof TV, including: a front shell 1, a liquid crystal glass 2, and a glue application area between the front shell 1 and the liquid crystal glass 2. Figure 3 It is a schematic diagram of the back of an outdoor waterproof TV, including a rear shell 3 and a rear backpack 4. There is a gap between the rear shell 3 and the rear backpack 4 for gluing after the rear shell and the rear backpack are assembled. The gap is 1 mm and is used for gluing.

[0031] S2, input the environmental monitoring data set into the environmental sensor network for nonlinear transformation and multi-dimensional feature extraction, and obtain the fused feature matrix through feature fusion;

[0032] Specifically, the environmental monitoring data set is input into the input layer of the environmental sensor network, where the data is standardized and time-aligned. Standardization is to map environmental data of different dimensions and ranges, such as temperature, humidity, light intensity, and rainfall data, to a unified numerical range (such as [0,1] or [-1,1]) to eliminate the impact of dimension differences and improve the model's adaptability to data. At the same time, the time dimension misalignment problem caused by different sampling frequencies or data delays in the sensor data acquisition process is solved by the time alignment method to ensure the time consistency of multidimensional data and generate a standardized data sequence with a unified scale and time alignment. The standardized data sequence is input into the reservoir layer of the environmental sensor network for dynamic feature mapping. The reservoir layer consists of 128 neuron nodes, and each node uses the hyperbolic tangent function as the activation function. The hyperbolic tangent function has good nonlinear mapping capabilities and effectively captures the complex nonlinear relationships in the input data. At the same time, the input weight matrix of the reservoir layer adopts a sparse connection structure to reduce the parameter scale of the network, reduce the computational complexity, and improve the generalization performance of the reservoir. Under the action of the reservoir layer, the standardized data sequence is mapped into a high-dimensional space to generate a reservoir state matrix. The reservoir state matrix can retain the dynamic characteristics of the input data and reflect the potential association between the data through the internal state evolution of the reservoir. The reservoir state matrix is ​​input into the time feature extraction unit, and the dynamic information in the time dimension is mined through the recursive neural network structure. In this process, the recursive neural network can capture the characteristic patterns of data changing over time through its cyclic connection mechanism, such as the long-term trend of temperature change, the short-term fluctuation characteristics of humidity, the periodic change pattern of light intensity, and the cumulative change law of rainfall. These features are gradually encoded into a set of time feature vectors through recursive calculation. The time feature vector not only contains the independent feature information of various types of environmental data, but also integrates the time correlation between them. The time series feature vector is input into the output layer of the environmental sensor network for feature mapping to obtain a set of environmental feature vectors. The environmental feature vector is input into the feature fusion network for feature enhancement. In the feature fusion network, the nonlinear interaction between features is realized through the multi-layer perceptron (MLP) or convolutional neural network (CNN) structure, the expression ability and discrimination ability of the features are improved, and an enhanced feature matrix is ​​generated. The enhanced feature matrix is ​​weighted by self-attention to generate an attention feature matrix. The self-attention mechanism is used to evaluate the importance of each dimension of the enhanced feature matrix and calculate the importance weights of different features to the overall environment description. The self-attention mechanism can dynamically adjust the weight distribution of features so that the model pays more attention to the feature information that is most important to the current task. The attention feature matrix is ​​generated by weighted summing of each feature. The attention feature matrix is ​​transformed to generate a fusion feature matrix.The process of dimensionality transformation includes dimensionality reduction or rearrangement of feature dimensions, so that the final fused feature matrix can not only maintain the integrity of the original feature information, but also adapt to the specific needs of subsequent application scenarios.

[0033] S3, using the Bayesian optimization algorithm to calculate the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient for the fusion feature matrix, and performing weighted calculation with the fusion feature matrix to obtain the environmental risk factor;

[0034] It should be noted that the objective function of the Bayesian optimization algorithm is established based on the fusion feature matrix. This function optimizes the weight distribution of each parameter so that the risk factor finally calculated can accurately reflect the comprehensive impact of different environmental conditions on the operation of outdoor waterproof TVs. After constructing the objective function, Gaussian process regression is used to model the weight space of temperature, humidity, light intensity and rainfall parameters. Gaussian process regression constructs a joint distribution model of these parameters based on existing data, and describes the potential correlation and uncertainty between the parameters in the weight space through dynamic adjustment of the mean and covariance, thereby providing data-driven probabilistic inference support for weight optimization. The four-dimensional joint distribution model generated by the Gaussian process is input into the Bayesian optimization algorithm, and the sampling points are selected according to the principle of maximizing expected improvement. This principle balances the contradiction between exploring new weight combinations and using existing weight information, ensuring that the optimization process can cover the entire parameter space and focus on the possible optimal area. In each iteration, the Bayesian optimization algorithm predicts the parameter combination that brings the maximum optimization benefit based on the current distribution model, and evaluates and samples it. The sampling results are used to update the posterior model of the weight distribution, and the step-by-step iteration method can ensure that the weight optimization process continues to converge to the global optimal solution. As sampling proceeds, the generated weight parameter sample set is used to calculate the sample mean and confidence interval of each parameter. The sample mean reflects the overall trend of the weight parameter, while the confidence interval quantifies the uncertainty of different parameters in the optimization process. Based on the sample mean and confidence interval, the weight parameters are updated using the posterior probability maximization criterion to obtain the optimized temperature parameter weight, humidity parameter weight, light intensity parameter weight and rainfall parameter weight. The optimized weights are used to weight the features of each dimension in the fusion feature matrix, and the importance of different features is integrated into a comprehensive score vector according to the optimized weight ratio. The vector expresses the comprehensive risk impact of various environmental features in a quantitative form. In order to convert the comprehensive score vector into an actually usable environmental risk factor, a piecewise linear mapping processing method is introduced. By setting multiple risk level intervals, the score vector is divided into risk categories of different levels such as low risk, medium risk and high risk. The scores in each risk interval are converted according to a linear ratio. The environmental risk factor finally generated can effectively reflect the potential impact of the current environmental conditions on outdoor waterproof TVs and provide a clear guiding basis for the protection strategy of the equipment.

[0035] The joint distribution model of the four-dimensional parameters is input into the Gaussian kernel function, and the probability density value of each point in the parameter space is calculated by the transformation of the kernel function. The Gaussian kernel function uses its nonlinear mapping ability to transform the input weight parameter space into a high-dimensional feature space, thereby capturing the potential complex relationship between the parameters. In this process, each data point in the joint distribution model is mapped by the kernel function to generate the corresponding probability density value, which is arranged in the form of a matrix to form a probability density distribution matrix. The matrix defines the probability weight of each point in the space, reflecting the potential possibility of different parameter combinations. The probability density distribution matrix is ​​gridded in the parameter space to generate an initial set of sampling points for the four-dimensional parameters. The purpose of gridding is to create an initial sampling point framework in the parameter space so that the entire space is evenly covered. The initial set of sampling points is input into the expected lift calculation module to calculate the expected lift value of each sampling point. The expected lift value calculation evaluates the importance of the point by comprehensively considering the optimization benefits brought by the current sampling point and the contribution of the point to the exploration of the parameter space. After the calculation is completed, a set of expected lift value sequences is generated to reflect the priority of each point in the parameter space. The expected improvement value sequence is sorted in descending order, and the top E points with the highest expected improvement value are selected to form a set of candidate sampling points. These candidate sampling point sets contain parameter points that have potential contributions to the target optimization and represent the areas in the current space that are most worthy of further exploration. After the candidate sampling points are input into the local search module, a preset search radius is defined around each candidate point, and gradient calculation is performed within this radius. The goal of gradient calculation is to capture the changing trend of the candidate points in the local area, and a local gradient vector is generated through this process. According to the local gradient vector, the parameters of the candidate sampling points are updated to generate optimized sampling points. During the update process, the parameters of each candidate point will move in the direction indicated by the gradient, and the amplitude of the movement is determined by the preset learning rate and the gradient size. This update method can ensure that the sampling points gradually approach the optimal solution area while avoiding falling into local extreme values. The optimized sampling points are input into the Gaussian process regression model again to update the model parameters and recalculate the posterior distribution. Through this process, the prediction ability of the Gaussian process model is further enhanced, and it can more accurately describe the current parameter space distribution. Iterate the above steps many times to converge to a set of weight parameter sample sets.

[0036] S4, inputting the environmental risk factors and the fusion feature matrix into the deep neural network based on the proximal policy optimization PPO to perform policy iteration optimization calculation, and generating a protection control instruction set, which includes display parameter adjustment instructions and waterproof level control instructions;

[0037] Specifically, the environmental risk factors and the fusion feature matrix are input into the input layer of the deep neural network based on proximal policy optimization (PPO). The input layer is designed as a fully connected layer containing 256 neurons, which are nonlinearly transformed by the ReLU activation function. The ReLU function is selected to enhance the expressive power of the network while avoiding the gradient vanishing problem and generating the initial feature vector. The initial feature vector is input into the shared layer of the deep neural network. The shared layer consists of three fully connected layers, each with 128, 64 and 32 neurons, and each neuron is also processed by the ReLU activation function. The role of the shared layer is to generate a high-level shared feature representation by gradually extracting the feature hierarchy. The shared layer is designed to capture the potential correlation features and environmental impact patterns in the input data, while ensuring that the key basic features are shared between different task branches to reduce network redundancy and computational complexity. The shared feature representation is input into the display parameter optimization branch and the waterproof level optimization branch respectively. Each branch contains two fully connected layers, each with 16 neurons, and also uses the ReLU activation function. This branch design enables the network to process features related to display parameter adjustment and features related to waterproof level control at the same time, and generate corresponding display branch feature vectors and waterproof branch feature vectors. The display branch feature vector and waterproof branch feature vector are respectively input into the value function network for state value calculation. The main task of the value function network is to evaluate the value distribution in the current state, and generate display state value evaluation and waterproof state value evaluation through this evaluation. The display state value evaluation and waterproof state value evaluation are input into the policy gradient calculation unit, and the display parameter adjustment probability distribution and protection action probability distribution are calculated through the core of the PPO algorithm - the importance sampling ratio clipping method. The role of the clipping method is to limit the amplitude of the policy update, thereby ensuring the stability and efficiency of the policy optimization. The two probability distributions represent the priority of the display parameter adjustment action and the protection action in the current state. The display parameter adjustment strategy and the waterproof level control strategy are generated according to the display parameter adjustment probability distribution and the protection action probability distribution. These strategies are input into the action mapping module, and the mapping of discrete actions to continuous control quantities is realized through the lookup table. The design of the lookup table is adjusted according to the control requirements of the specific hardware device, so as to ensure that the generated display parameter adjustment instructions and waterproof level control instructions can accurately match the operation requirements of the actual control device. The display parameter adjustment instructions and waterproof level control instructions are packaged to form a complete protection control instruction set. The instruction set includes specific display parameter adjustment schemes, such as adjustment of screen brightness, contrast and display mode, and also includes waterproof level control measures, such as triggering the sealing system, drainage device or opening the protective cover.

[0038] Based on the display state value evaluation and waterproof state value evaluation, the ratio of the new strategy to the old strategy is calculated respectively. This ratio measures the degree of improvement of the current strategy compared with the previous strategy, and also reflects the magnitude of the strategy change during the optimization process. By dynamically calculating the optimization weights of display parameter adjustment and waterproof level control, the display parameter adjustment weight and waterproof level adjustment weight are obtained, which reflect the contribution of different strategies to the target optimization in the current state. The display parameter adjustment weight and waterproof level adjustment weight are compared with the preset clipping range. The clipping range is to limit the magnitude of the strategy update and prevent the training instability caused by excessive strategy changes. In this process, the display parameter adjustment weight and waterproof level adjustment weight are truncated by the minimum function to obtain the clipped display adjustment weight and clipped waterproof adjustment weight. The core of clipping is to ensure the stability of the optimization process by balancing exploration and utilization while maintaining the adaptability of the strategy in the parameter space. Based on the clipped display adjustment weight and waterproof adjustment weight, the strategy objective function is calculated. The design of the strategy objective function aims to maximize the reward signal, while constraining the scope of the strategy update by clipping weights. In this process, the display parameter policy gradient and the waterproof level policy gradient are calculated respectively as directional guidance for policy optimization. After obtaining the policy gradient, the display parameter policy gradient and the waterproof level policy gradient are constrained to limit their variation range and ensure the rationality and feasibility of the update direction, and the display parameter update direction and the waterproof level update direction are generated. The display parameter update direction and the waterproof level update direction are projected into the constraint space through the proximal mapping function. The role of the proximal mapping function is to ensure that the update direction is always within the defined constraint space to avoid the parameter instability problem caused by excessive gradient update. After this projection process, the display parameter update amount and the waterproof level update amount in the constraint space are obtained. According to the display parameter update amount and the waterproof level update amount in the constraint space, the parameters of the policy network are updated to generate the updated display policy network and the waterproof policy network. The updated policy network has stronger environmental adaptability and optimization ability, and can handle dynamically changing environmental conditions more efficiently. In order to calculate the actual control action, the updated display policy network and the waterproof policy network are input into the Actor network for forward calculation. The Actor network is responsible for extracting the display parameter action space and the waterproof level action space from the policy network. These action spaces define all possible control actions and their corresponding priorities. The display parameter action space and the waterproof level action space are probabilistically normalized to ensure that the sum of the probability distributions of all control actions is 1, and the display parameter adjustment probability distribution and the protection action probability distribution are obtained.

[0039] S5, generating a driving signal of the display module and a control signal of the waterproof actuator respectively according to the protection control instruction set, and executing the driving signal and the control signal through the execution unit.

[0040] Among them, the protection control instruction set is generated by the system's deep neural network and optimization algorithm, including display parameter adjustment instructions and waterproof level control instructions. These instructions have been logically optimized by intelligent algorithms and have dynamic adaptability to the current environment. After receiving the instructions, the instruction parsing stage is entered, and the parsing module maps each instruction in the protection control instruction set to a specific hardware operation logic. For example, the display parameter adjustment instruction contains multiple adjustment parameters such as screen brightness, contrast, and color temperature, while the waterproof level control instruction involves specific actions such as opening and closing the waterproof cover, starting the drainage device, and pressurizing the sealing system. The parsing module converts these instruction contents into specific signal types, signal amplitudes, and addresses of target devices to ensure that the hardware devices can respond correctly. The instruction parsing results are input into the signal generation module. In the signal generation stage, corresponding control signals are generated for different execution devices according to the parsed parameter contents. For the drive signal of the display module, by adjusting the parameter values ​​in the display parameter instructions, such as the percentage of brightness or the set value of contrast, it is mapped to a PWM (pulse width modulation) signal or a digital level signal. These signals are matched with the drive circuit of the display module, so that the brightness, color temperature, and display effect of the screen can be dynamically adjusted according to user expectations or environmental requirements. During the signal generation process, filtering and calibration are performed to ensure that the generated drive signal meets the specifications of the hardware device in terms of amplitude and frequency to avoid overload or invalid operation. For the control signal of the waterproof actuator, the signal generation module generates the corresponding control logic signal according to the grade requirements in the waterproof grade control instruction. These signals include switch-type signals (such as relay control signals) to trigger the opening and closing operation of the waterproof cover; analog signals (such as voltage or current signals) to control the pressure regulation of the hydraulic or pneumatic sealing system. For waterproof equipment that requires continuous adjustment, such as intelligent drainage systems, control signals are generated in the form of proportional regulation to accurately control the operating speed or drainage volume of the equipment. At this stage, the signal is corrected according to the response characteristics of the equipment, such as considering delay compensation or dynamic range limitation, to ensure that the signal can drive the equipment quickly and accurately. The generated drive signal and control signal are input to the execution unit. The execution unit converts the signal generated by the system into a physical action that can be performed by the actual device. During the execution of the display module, the execution unit converts the PWM signal into a current or voltage drive signal and loads it into the LED backlight system or LCD panel of the display module through the driver chip. At the same time, the status monitoring circuit in the execution unit monitors the response status of the display module in real time to ensure that the result of parameter adjustment is consistent with expectations. For waterproof actuators, the execution unit adapts the control signal according to the device type. For example, when controlling an electric waterproof cover, the execution unit converts the digital signal into the switch operation of the device through the relay module, and uses the position sensor to feedback the current status to prevent excessive operation or jamming.For the hydraulic sealing system, the execution unit adjusts the operating state of the hydraulic pump according to the input analog signal to keep the pressure within the specified range. The execution unit also has a protection mechanism. When an abnormal signal or abnormal equipment operating state is detected, the fault protection logic will be triggered immediately to avoid further damage to the equipment or affect the normal operation of the system. The entire system ensures the consistency of the response of the display module and the waterproof actuator with the protection control instruction set through signal closed-loop control. The status feedback of the execution unit is transmitted back to the system main control unit for dynamic adjustment of the generation logic of subsequent signals. For example, when environmental conditions change drastically, the system can update the protection control instruction set in real time based on the latest environmental sensing data, and generate new drive signals and control signals, thereby achieving adaptive dynamic response to the environment.

[0041] In one example, an environmental monitoring dataset of an outdoor waterproof TV is collected through an environmental sensor array, including:

[0042] Apply a preset sampling voltage to the input end of the temperature sensor in the environmental sensor array, perform analog signal amplification and filtering through the signal conditioning circuit, and obtain a temperature digital signal;

[0043] An excitation signal is input to the detection end of the humidity sensor in the environmental sensor array, and impedance matching and signal stabilization are performed through a signal conversion circuit to obtain a humidity digital signal;

[0044] Apply a reverse bias voltage to the photosensitive element of the light intensity sensor in the environment sensor array, perform current amplification and linearization processing through the photoelectric conversion circuit, and obtain a light intensity digital signal;

[0045] Applying an AC excitation signal to the detection electrode of the rain sensor in the environmental sensor array, performing waveform shaping and digital processing through a signal processing circuit to obtain a rain digital signal;

[0046] The temperature digital signal, humidity digital signal, light intensity digital signal and rainfall digital signal are input into the data acquisition module, and the signal switching and sampling and holding processing are performed through the multiplexer to obtain multi-channel sampling data;

[0047] The multi-channel sampling data is converted into digital quantities and compensated to obtain the environmental monitoring data set of the outdoor waterproof TV.

[0048] In this example, a stable preset sampling voltage is applied to the input of the temperature sensor, represented by the symbol This indicates that this is the driving voltage for the sensor to work, and its size is selected according to the specifications of the sensor, such as The output signal of the temperature sensor is a signal that is proportional to the ambient temperature. Linearly related analog voltage , whose expression is ;

[0049] in, Indicates the sensitivity of the sensor, which indicates the magnitude of voltage change caused by temperature change; is the zero point offset, that is, the temperature is The signal is amplified and filtered by the signal conditioning circuit. The gain of the amplifier circuit is used It means that its function is to increase the weak signal output by the sensor to a range suitable for the analog-to-digital converter (ADC) input: ;

[0050] The filter module removes high-frequency noise from the signal by designing an appropriate cutoff frequency. The processed signal is converted into a digital signal through ADC. The calculation formula is: ;

[0051] in, is the reference voltage of ADC, is the resolution of the ADC (e.g. 12 bits ), digital signal The humidity sensor needs to input an excitation signal at its detection end. , using a sine wave signal, expressed as: ;

[0052] in, is the amplitude of the signal, is the frequency of the signal. The output signal of the humidity sensor Relative humidity of the environment It is a linear relationship, and its expression is: ;

[0053] in, is the sensitivity of the humidity sensor; is the offset voltage value. The signal is processed by the impedance matching circuit to reduce the signal source impedance to adapt to the subsequent signal processing circuit, and the stabilization circuit eliminates noise and signal fluctuations. After analog-to-digital conversion, a humidity digital signal is generated. :

[0054] ;

[0055] For the light intensity sensor, the photosensitive element needs to be reverse biased , which is used to enhance the response sensitivity of the photosensitive element. The output of the sensor is the photocurrent , whose size and light intensity Proportional, expressed as: ;

[0056] in, is the photoelectric response coefficient of the sensor. The photocurrent is converted into a voltage signal by the current amplifier. : ;

[0057] in is the gain of the amplifier. After linearization, the signal is digitized by the analog-to-digital converter into a digital signal of light intensity. : ;

[0058] For the rain sensor, the detection electrode needs to be applied with an AC excitation signal. , expressed as: ;

[0059] in is the signal amplitude, is the signal frequency. The output signal of the rain sensor and rainfall The relationship is: ;

[0060] in is the sensitivity of the rain sensor; The signal is converted into a rainfall digital signal through the ADC after the nonlinear component is removed by the waveform shaping circuit. : ;

[0061] All generated digital signals , , and Input to the data acquisition module. Signal switching and sampling and holding processing are performed through the multiplexer. The multiplexer collects the signals of each channel one by one according to the preset time sequence, and the sampling and holding circuit ensures that the voltage value of the sampling point is kept stable during the switching process. The collected multi-channel data is corrected for the nonlinear deviation and system error of the sensor by the digital compensation algorithm to generate an environmental monitoring data set: ;

[0062] This dataset serves as the core input for environmental analysis and provides accurate environmental information for intelligent control of equipment.

[0063] In one example, an environmental monitoring data set is input into an environmental sensor network for nonlinear transformation and multidimensional feature extraction, and a fused feature matrix is ​​obtained through feature fusion, including:

[0064] Input the environmental monitoring data set into the input layer of the environmental sensor network for data standardization and time series alignment to obtain a standardized data sequence;

[0065] The standardized data sequence is input into the reservoir layer of the environmental sensor network for dynamic feature mapping. The reservoir layer contains 128 neuron nodes, each of which uses the hyperbolic tangent function as the activation function. The input weight matrix uses a sparse connection structure to obtain the reservoir state matrix.

[0066] The state matrix of the reservoir is input into the time feature extraction unit, and the temperature change trend, humidity fluctuation characteristics, light intensity change pattern and rainfall accumulation characteristics are extracted through the recursive neural network structure to obtain the time series feature vector;

[0067] Input the time series feature vector into the output layer of the environment sensor network for feature mapping to obtain the environment feature vector, and input the environment feature vector into the feature fusion network for feature enhancement to obtain the enhanced feature matrix;

[0068] The enhanced feature matrix is ​​self-attention weighted combined to obtain the attention feature matrix, and the attention feature matrix is ​​dimensionally transformed to generate a fusion feature matrix.

[0069] In this example, the environmental monitoring dataset Contains sampled data of various environmental parameters, such as temperature, humidity, light intensity, and rainfall, recorded as These data need to be standardized and time-aligned before being input into the environmental sensor network to eliminate the impact of data dimension differences and sampling delays. The value range of each variable is mapped to [0,1] or standard normal distribution, which is achieved through the following formula: ;

[0070] in, represents the standardized data, and are the mean and standard deviation of the data respectively. For time series alignment, interpolation or dynamic time warping algorithms are used to align the time series of different sensors to the same time step to form a standardized data series . Standardize the data series Input to the pooling layer of the environment sensor network. The pooling layer contains There are neuron nodes, and the activation function of each node uses the hyperbolic tangent function (tanh), which is expressed as: ;

[0071] Weight matrix input to the reserve pool is a sparse connection structure matrix, where the sparsity rate The proportion of non-zero elements is controlled to improve computational efficiency and prevent overfitting. The calculation formula is: ;

[0072] in, is the bias vector. The reservoir state matrix The high-dimensional dynamic features of the input data are extracted while retaining the temporal correlation. Enter the time feature extraction unit, which uses a recursive neural network structure to extract time series features, such as temperature change trends, humidity fluctuation characteristics, light intensity change patterns, and rainfall accumulation characteristics. The recursive neural network captures dependencies in the time series through recurrent connections, and its state update formula is: ;

[0073] in, It's time The hidden state vector of and are the weight matrices for input and hidden states, respectively, is the activation function, choose Sigmoid or ReLU. The final output time series feature vector Represents the key pattern of the time series. Input the output layer of the environmental sensor network and generate the environmental feature vector through feature mapping The feature mapping process is implemented through a fully connected layer, and the formula is: ;

[0074] in, is the activation function, such as ReLU, and are weights and biases respectively. In order to enhance the feature expression capability, the environment feature vector Input feature fusion network to generate enhanced feature matrix through nonlinear combination The fusion network contains multiple hidden layers. The output of each layer is activated by ReLU and then input into the next layer. The calculation formula is: ;

[0075] The final output enhanced feature matrix The information of multi-dimensional features is integrated. Apply the self-attention mechanism for weighted combination. The attention weight is calculated by the following formula: ;

[0076] in, and They are query vector and key vector, attention weight Used for each element of the weighted matrix. Weighted combined attention feature matrix for: ;

[0077] in, Is a value vector. For the attention feature matrix Perform dimension transformation and generate a fusion feature matrix by reducing dimension or rearranging For example, the principal component analysis method is used to select the main feature components, and the formula is: ;

[0078] in, is the projection matrix of principal component analysis, and the final output is It is a fusion feature matrix with stronger feature expression ability and discrimination power.

[0079] In one example, the Bayesian optimization algorithm is used to calculate the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient for the fusion feature matrix, and weighted calculation is performed with the fusion feature matrix to obtain the environmental risk factors, including:

[0080] The objective function of the Bayesian optimization algorithm is constructed based on the fusion feature matrix. The weighted spatial modeling of temperature parameters, humidity parameters, light intensity parameters and rainfall parameters is carried out through Gaussian process regression to obtain the joint distribution model of the four-dimensional parameters.

[0081] The joint distribution model of the four-dimensional parameters is input into the Bayesian optimization algorithm, sampling points are selected based on the principle of maximizing expected improvement, and the weight parameter space is iteratively sampled to obtain a weight parameter sample set;

[0082] The sample mean and confidence interval are calculated according to the weight parameter sample set, and the weight coefficient is updated by the posterior probability maximization criterion to obtain the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient;

[0083] Based on the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient, the fusion feature matrix is ​​weighted and combined with multiple parameters to obtain a comprehensive score vector.

[0084] The comprehensive score vector is hierarchically mapped through a piecewise linear mapping function to obtain the environmental risk factor.

[0085] In this example, according to the fusion feature matrix , construct the objective function of the Bayesian optimization algorithm to optimize the weight distribution of each feature parameter. Fusion feature matrix is a multidimensional matrix whose rows represent samples and columns represent feature dimensions, corresponding to temperature ,humidity , light intensity and rainfall Objective function It is defined as the combined effect of parameter weights and is used to describe the contribution of weights to environmental risks, expressed as: ;

[0086] in, are the weight coefficients of temperature, humidity, light intensity and rainfall, It is The corresponding eigenvalues ​​of samples, is the number of samples. To optimize the weight coefficients, the objective function is modeled by Gaussian process regression. The Gaussian process assumes that the weight distribution of each feature follows a joint Gaussian distribution with a mean of , the covariance matrix is The joint distribution is expressed as: ;

[0087] in, . Through the Gaussian kernel function , defines the similarity between input data points, and the kernel function form is: ;

[0088] in, is a data point, is the kernel width parameter. The Gaussian process uses the kernel function to calculate the covariance matrix , and update the posterior distribution based on the observed data. The joint distribution model of the Gaussian process is input into the Bayesian optimization algorithm, and the sampling points are selected based on the principle of maximizing the expected improvement. The goal of expected improvement is to find the point in the weight space that is most likely to improve the value of the objective function. For each candidate point , its expected improvement Defined as: ;

[0089] in, is the current optimal value, represents the expected value. , select the next sampling point. During the sampling process, the algorithm iteratively updates the posterior distribution of the weight parameter and generates a weight parameter sample set through each sampling. ,in is the number of sampling times. Calculate the sample mean based on the sample set and confidence interval , the confidence interval is defined as: ;

[0090] in, and are the sample mean and standard deviation, respectively. is the confidence coefficient. Finally, the weight coefficient is updated by maximizing the posterior probability criterion Based on the optimized weight coefficient, the fusion feature matrix is ​​weighted by multiple parameters to generate a comprehensive score vector :

[0091] ;

[0092] in, , each element Indicates The comprehensive score vector is transformed into the comprehensive score vector by piecewise linear mapping function. Mapped to environmental risk factors. The piecewise linear mapping function is defined as follows:

[0093] ;

[0094] in, and is the mapping coefficient for different risk intervals, is the segment boundary value. The final output environmental risk factor Used to assess the risk level of the current environment.

[0095] In one example, the joint distribution model of the four-dimensional parameters is input into the Bayesian optimization algorithm, sampling points are selected based on the principle of maximizing expected improvement, and the weight parameter space is iteratively sampled to obtain a weight parameter sample set, including:

[0096] The joint distribution model of the four-dimensional parameters is input into the Gaussian kernel function, and the probability density value of each point in the parameter space is calculated through the kernel function transformation to obtain the probability density distribution matrix;

[0097] Perform parameter space grid division on the probability density distribution matrix to generate an initial sampling point set of four-dimensional parameters, and input the initial sampling point set into the expected lift calculation module to calculate the expected lift value of each sampling point to obtain an expected lift value sequence;

[0098] Arrange the expected lift value sequence in descending order, select the first E points with the highest expected lift value as candidate sampling points, obtain a set of candidate sampling points, and input the set of candidate sampling points into the local search module, perform gradient calculation around each candidate point with a preset search radius, and obtain a local gradient vector;

[0099] The parameters of the candidate sampling points are updated according to the local gradient vector to obtain the optimized sampling points, and the optimized sampling points are input into the Gaussian process regression model, the model parameters are updated and the posterior distribution is recalculated to obtain the weight parameter sample set.

[0100] In this example, the joint distribution model of the four-dimensional parameters is input into the Gaussian kernel function for processing to calculate the probability density value of each point in the parameter space. Assume that the four-dimensional parameters are temperature, weight, , humidity weight , light intensity weight and rainfall weight , which together form the joint distribution model . Gaussian kernel function Defined as: ;

[0101] in, and are any two sets of parameters, is the kernel width, which controls the sensitivity of the kernel function to distance. By calculating the kernel function values ​​of all parameter combinations, the probability density distribution matrix K is constructed, whose elements Indicates and The similarity of the parameter points. For the probability density distribution matrix Perform parameter space grid division to generate an initial set of sampling points. is discretized into a multidimensional grid, assuming that each dimension is divided into points, the total number of sampling points is Grid points It is expressed as: ;

[0102] The probability density value corresponding to each grid point The normalized calculation of the Gaussian kernel function matrix is ​​obtained: ;

[0103] The initial set of sampling points is input into the expected improvement calculation module to evaluate the optimization potential of each point. , its expected improvement Defined as: ;

[0104] in, is the objective function value, is the current optimal value, Represents the expected value. Prediction by Gaussian process The mean and standard deviation , It is expressed as: ;

[0105] in, , is the cumulative distribution function of the standard normal distribution, is the probability density function of the standard normal distribution. Calculate the expected lift values ​​of all initial sampling points, generate an expected lift value sequence, and arrange them in descending order, and select the first one with the highest expected lift value. points as a set of candidate sampling points. Each candidate point Represents a potential efficient sampling point. The candidate sampling point set is input into the local search module, and a preset search radius is set around each candidate point. Perform gradient calculation. Gradient vector It means that the objective function is at point The local change direction of is calculated as:

[0106] ;

[0107] Update the candidate sampling point position according to the gradient vector, and the updated point It is expressed as: ;

[0108] in, is the learning rate, which controls the update step size. The optimized sampling points are input into the Gaussian process regression model, the posterior distribution of the model is updated, and the mean and covariance matrix of the parameters are recalculated. By iterating the above process, a sample set of weight parameters is generated. , where each sample point represents a set of optimized parameter weights. The distribution of the weight parameter sample set reflects the optimization results of the parameter space for further analysis or decision-making.

[0109] In one example, the environmental risk factor and the fusion feature matrix are input into a deep neural network based on proximal policy optimization (PPO) for policy iteration optimization calculation to generate a protection control instruction set, which includes display parameter adjustment instructions and waterproof level control instructions, including:

[0110] The environmental risk factors and fusion feature matrix are input into the input layer of the deep neural network based on the proximal strategy optimization PPO. The input layer contains 256 neurons and is nonlinearly transformed through the ReLU activation function to obtain the initial feature vector.

[0111] The initial feature vector is input into the shared layer of the deep neural network based on the proximal strategy optimization PPO. The shared layer contains three fully connected layers, each of which contains 128, 64, and 32 neurons respectively. Each neuron uses the ReLU activation function to obtain the shared feature representation.

[0112] The shared feature representation is input into the display parameter optimization branch and the waterproof level optimization branch respectively. The display parameter optimization branch and the waterproof level optimization branch contain 2 fully connected layers, each of which contains 16 neurons. The ReLU activation function is used to obtain the display branch feature vector and the waterproof branch feature vector.

[0113] The display branch feature vector and the waterproof branch feature vector are respectively input into the value function network to calculate the state value, and the display state value evaluation and the waterproof state value evaluation are obtained;

[0114] The display state value evaluation and waterproof state value evaluation are respectively input into the policy gradient calculation unit, and the policy gradient is calculated by the importance sampling ratio clipping method to obtain the display parameter adjustment probability distribution and the protection action probability distribution;

[0115] Generate a display parameter adjustment strategy and a waterproof level control strategy based on the display parameter adjustment probability distribution and the protection action probability distribution, input the display parameter adjustment strategy and the waterproof level control strategy into the action mapping module, map the discrete action into a continuous control quantity through a lookup table, and obtain the display parameter adjustment instruction and the waterproof level control instruction;

[0116] The display parameter adjustment instructions and the waterproof level control instructions are packaged to generate a protection control instruction set.

[0117] In this example, the environmental risk factor And the fusion feature matrix Input to the input layer of the deep neural network based on proximal policy optimization. The fused feature matrix The multidimensional features including different environmental parameters (such as temperature, humidity, light intensity and rainfall) are expressed as , where each line is a feature vector. The input layer contains 256 neurons, which are used to perform preliminary nonlinear transformation on the input data. The output of each neuron is calculated by the ReLU activation function, whose formula is:

[0118] ;

[0119] in, is the input vector, and They are the input layer The weights and biases of the neurons, is the weighted input of the neuron. After passing through the input layer, an initial feature vector is output , as the input of the subsequent network layer. Enter the shared layer, which contains three fully connected layers, each with 128, 64, and 32 neurons, and the output of each layer is calculated by the ReLU activation function. The goal of the shared layer is to extract global feature representations and gradually compress the high-dimensional feature space of the input while retaining important information. The output formula of the shared layer is:

[0120] ;

[0121] in, and It is The weights and biases of the layers. Get the shared feature representation , used for task branching. The shared features are represented as The output is respectively input to the display parameter optimization branch and the waterproof level optimization branch. These two branches contain two fully connected layers, each with 16 neurons, and the output is the display branch feature vector and waterproof branch feature vector . Input the value function network to calculate the state value. The value function network estimates the value of each state , the formula is:

[0122] ;

[0123] ;

[0124] Get display status value evaluation and waterproof status value assessment The state value evaluation is input into the policy gradient calculation unit, and the policy gradient is calculated by combining the importance sampling ratio clipping method. The sampling ratio is defined as: ;

[0125] in, is the probability distribution of the current strategy, is the probability distribution of the old policy. Clipping the policy gradient constrains the policy update range to prevent unstable optimization. By optimizing the policy objective function, we can get the probability distribution of display parameter adjustment. And the probability distribution of protective actions Based on the probability distribution, the display parameter adjustment strategy and the waterproof level control strategy are generated and input into the action mapping module. The action mapping module converts the discrete actions into Mapping to continuous control quantity : ;

[0126] The display parameter adjustment instructions and waterproof level control instructions are obtained. These instructions are packaged to form a protection control instruction set. The instruction set is directly used to drive the device to adjust the display parameters (such as brightness, contrast) and waterproof protection measures (such as sealing pressure or drainage device) in real time.

[0127] In one example, the display state value evaluation and the waterproof state value evaluation are respectively input into the policy gradient calculation unit, and the policy gradient is calculated by the importance sampling ratio clipping method to obtain the display parameter adjustment probability distribution and the protection action probability distribution, including:

[0128] Based on the display status value evaluation and the waterproof status value evaluation, the ratio of the new and old strategies is calculated respectively to obtain the display parameter adjustment weight and the waterproof level adjustment weight;

[0129] Compare the display parameter adjustment weight and the waterproof level adjustment weight with the preset clipping range, perform truncation processing through the minimum value function, and obtain the clipped display adjustment weight and the clipped waterproof adjustment weight;

[0130] The policy objective function is calculated based on the clipped display adjustment weight and the clipped waterproof adjustment weight to obtain the display parameter policy gradient and the waterproof level policy gradient, and the display parameter policy gradient and the waterproof level policy gradient are constrained to obtain the display parameter update direction and the waterproof level update direction;

[0131] The display parameter update direction and the waterproof level update direction are projected by the proximal mapping function to obtain the display parameter update amount in the constraint space and the waterproof level update amount in the constraint space;

[0132] The policy network parameters are updated according to the display parameter update amount in the constraint space and the waterproof level update amount in the constraint space to obtain an updated display policy network and an updated waterproof policy network;

[0133] The updated display strategy network and the updated waterproof strategy network are input into the Actor network for forward calculation to obtain the display parameter action space and the waterproof level action space, and the display parameter action space and the waterproof level action space are probability normalized to obtain the display parameter adjustment probability distribution and the protection action probability distribution.

[0134] In this example, the display state value is evaluated and waterproof status value assessment , respectively calculate the current strategy and the old strategy The ratio, namely the importance sampling ratio, is expressed as:

[0135] ;

[0136] in, Is the current strategy in state Take action The probability distribution of Represents the parameters of the policy network; and They are the actions of display parameter adjustment and waterproof level control. The importance sampling ratio is calculated to obtain the display parameter adjustment weight and waterproof level adjustment weight , which characterize the degree of deviation of the current strategy compared to the old strategy. In order to limit the magnitude of the strategy update and avoid instability caused by too large or too small a ratio, the parameter adjustment weight and waterproof level adjustment weight are displayed with the preset clipping range. For comparison, is a small positive number used to control the range of policy changes. The adjustment weight is truncated by the minimum function, and the formula is:

[0137] ;

[0138] ;

[0139] in, and are the clipped display adjustment weights and waterproof adjustment weights. Clipping ensures that the policy update remains within a safe range to prevent instability caused by large updates. Based on the clipped weights, the policy objective function is calculated. The policy objective function is in the form of maximizing the reward plus a regularization term to balance exploration and exploitation. The formula is:

[0140] ;

[0141] ;

[0142] in, and It is the advantage function of display and waterproof, indicating the superiority of the current action compared with the average strategy. The objective function is solved by a gradient optimization algorithm (such as Adam optimizer) to obtain the display parameter policy gradient and waterproof level policy gradient The policy gradient is constrained to ensure that the update direction of the gradient does not exceed the preset range. The constraint mechanism is implemented by introducing the proximal mapping function, which is expressed as:

[0143] ;

[0144] ;

[0145] in, is the maximum allowed value of the gradient, and is the gradient update direction for display and waterproofing. The update direction is projected into the constraint space through the proximal mapping function, and the display parameter update amount in the constraint space is calculated. and waterproof level update , the formula is:

[0146] ;

[0147] ;

[0148] in, is the learning rate, which is used to control the update step size. The update amount is used to update the policy network parameters to obtain the updated display policy network and waterproof policy network. The updated policy network is input into the Actor network for forward calculation to generate the display parameter action space and waterproof level action space To ensure that the sum of the action probabilities is 1, the action space is probability normalized, and the formula is:

[0149] ;

[0150] The normalized action space generates the display parameter adjustment probability distribution and the protection action probability distribution respectively, which provides a basis for the actual control of the equipment.

[0151] Reference Figure 4 This embodiment provides an intelligent environment sensing system based on an outdoor waterproof television, including:

[0152] The collection module 401 is used to collect the environmental monitoring data set of the outdoor waterproof TV through the environmental sensor array;

[0153] The feature extraction module 402 is used to input the environmental monitoring data set into the environmental sensor network for nonlinear transformation and multi-dimensional feature extraction, and obtain a fused feature matrix through feature fusion;

[0154] The weighted calculation module 403 is used to calculate the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient for the fused feature matrix through the Bayesian optimization algorithm, and perform weighted calculation with the fused feature matrix to obtain the environmental risk factor;

[0155] A generation module 404 is used to input the environmental risk factor and the fusion feature matrix into a deep neural network based on proximal policy optimization (PPO) to perform policy iteration optimization calculations and generate a protection control instruction set, which includes a display parameter adjustment instruction and a waterproof level control instruction;

[0156] The execution module 405 is used to generate a driving signal of the display module and a control signal of the waterproof actuator according to the protection control instruction set, and execute the driving signal and the control signal through the execution unit.

[0157] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0158] Reference Figure 5 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0159] Those skilled in the art will understand that Figure 5 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0160] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0161] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0162] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0163] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent environment sensing method based on outdoor waterproof television, characterized in that: The following steps are involved: Collect environmental monitoring data sets of outdoor waterproof TVs through environmental sensor arrays; Inputting the environmental monitoring data set into the environmental sensor network for nonlinear transformation and multidimensional feature extraction, and obtaining a fused feature matrix through feature fusion; The temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient are calculated for the fusion feature matrix by using the Bayesian optimization algorithm, and weighted calculation is performed with the fusion feature matrix to obtain the environmental risk factor; Input the environmental risk factor and the fusion feature matrix into a deep neural network based on proximal policy optimization (PPO) to perform policy iteration optimization calculation to generate a protection control instruction set, wherein the protection control instruction set includes a display parameter adjustment instruction and a waterproof level control instruction; A driving signal of the display module and a control signal of the waterproof actuator are respectively generated according to the protection control instruction set, and the driving signal and the control signal are executed by the execution unit.

2. The intelligent environment sensing method based on outdoor waterproof television according to claim 1 is characterized in that: The environmental monitoring data set of the outdoor waterproof TV is collected by the environmental sensor array, including: Apply a preset sampling voltage to the input end of the temperature sensor in the environmental sensor array, perform analog signal amplification and filtering through the signal conditioning circuit, and obtain a temperature digital signal; An excitation signal is input to the detection end of the humidity sensor in the environmental sensor array, and impedance matching and signal stabilization are performed through a signal conversion circuit to obtain a humidity digital signal; Apply a reverse bias voltage to the photosensitive element of the light intensity sensor in the environment sensor array, perform current amplification and linearization processing through the photoelectric conversion circuit, and obtain a light intensity digital signal; Applying an AC excitation signal to the detection electrode of the rain sensor in the environmental sensor array, performing waveform shaping and digital processing through a signal processing circuit to obtain a rain digital signal; Input the temperature digital signal, the humidity digital signal, the light intensity digital signal and the rainfall digital signal into a data acquisition module, perform signal switching and sample-hold processing through a multiplexer, and obtain multi-channel sampling data; The multi-channel sampling data is subjected to digital quantity conversion and data compensation to obtain an environmental monitoring data set of an outdoor waterproof television.

3. The intelligent environment sensing method based on outdoor waterproof television according to claim 2 is characterized in that: The step of inputting the environmental monitoring data set into the environmental sensor network for nonlinear transformation and multidimensional feature extraction, and obtaining a fused feature matrix by feature fusion, includes: Inputting the environmental monitoring data set into the input layer of the environmental sensor network for data standardization and time series alignment to obtain a standardized data sequence; Input the standardized data sequence into the reservoir layer of the environmental sensor network for dynamic feature mapping, wherein the reservoir layer includes 128 neuron nodes, each neuron node uses a hyperbolic tangent function as an activation function, and the input weight matrix uses a sparse connection structure to obtain a reservoir state matrix; The state matrix of the storage tank is input into the time feature extraction unit, and the temperature change trend, humidity fluctuation characteristics, light intensity change pattern and rainfall accumulation characteristics are extracted through a recursive neural network structure to obtain a time series feature vector; Input the time series feature vector into the output layer of the environment sensor network for feature mapping to obtain an environment feature vector, and input the environment feature vector into a feature fusion network for feature enhancement to obtain an enhanced feature matrix; The enhanced feature matrix is ​​self-attention weighted combined to obtain an attention feature matrix, and the attention feature matrix is ​​dimensionally transformed to generate a fusion feature matrix.

4. The intelligent environment sensing method based on outdoor waterproof television according to claim 3 is characterized in that: The Bayesian optimization algorithm is used to calculate the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient of the fused feature matrix, and weighted calculation is performed with the fused feature matrix to obtain the environmental risk factor, including: The objective function of the Bayesian optimization algorithm is constructed according to the fusion feature matrix, and the temperature parameter, humidity parameter, light intensity parameter and rainfall parameter are weighted spatially modeled by Gaussian process regression to obtain a joint distribution model of the four-dimensional parameters; Inputting the joint distribution model of the four-dimensional parameters into the Bayesian optimization algorithm, selecting sampling points based on the principle of maximizing expected lift, and iteratively sampling the weight parameter space to obtain a weight parameter sample set; Calculating the sample mean and confidence interval according to the weight parameter sample set, and updating the weight coefficients by maximizing the posterior probability criterion to obtain the temperature parameter weight coefficient, the humidity parameter weight coefficient, the light intensity parameter weight coefficient, and the rainfall parameter weight coefficient; Based on the temperature parameter weight coefficient, the humidity parameter weight coefficient, the light intensity parameter weight coefficient and the rainfall parameter weight coefficient, a multi-parameter weighted combination is performed on the fusion feature matrix to obtain a comprehensive scoring vector; The comprehensive score vector is hierarchically mapped through a piecewise linear mapping function to obtain an environmental risk factor.

5. The intelligent environment sensing method based on outdoor waterproof television according to claim 4 is characterized in that: The joint distribution model of the four-dimensional parameters is input into the Bayesian optimization algorithm, sampling points are selected based on the principle of maximizing expected lift, and the weight parameter space is iteratively sampled to obtain a weight parameter sample set, including: The joint distribution model of the four-dimensional parameters is input into a Gaussian kernel function, and the probability density value of each point in the parameter space is calculated by kernel function transformation to obtain a probability density distribution matrix; Performing parameter space grid division on the probability density distribution matrix to generate an initial sampling point set of four-dimensional parameters, and inputting the initial sampling point set into an expected lift calculation module to calculate the expected lift value of each sampling point to obtain an expected lift value sequence; Arrange the expected lift value sequence in descending order, select the first E points with the highest expected lift value as candidate sampling points, obtain a set of candidate sampling points, input the set of candidate sampling points into a local search module, perform gradient calculation around each candidate point with a preset search radius, and obtain a local gradient vector; The parameters of the candidate sampling points are updated according to the local gradient vector to obtain optimized sampling points, and the optimized sampling points are input into the Gaussian process regression model, the model parameters are updated and the posterior distribution is recalculated to obtain a weight parameter sample set.

6. The intelligent environment sensing method based on outdoor waterproof television according to claim 5, characterized in that: The environmental risk factor and the fusion feature matrix are input into a deep neural network based on proximal policy optimization (PPO) for policy iteration optimization calculation to generate a protection control instruction set, wherein the protection control instruction set includes display parameter adjustment instructions and waterproof level control instructions, including: Input the environmental risk factor and the fused feature matrix into the input layer of the deep neural network based on the proximal strategy optimization PPO, wherein the input layer includes 256 neurons, and performs nonlinear transformation through the ReLU activation function to obtain an initial feature vector; The initial feature vector is input into a shared layer in a deep neural network based on proximal strategy optimization PPO, wherein the shared layer comprises three fully connected layers, each layer comprises 128, 64 and 32 neurons respectively, and each neuron adopts a ReLU activation function to obtain a shared feature representation; The shared feature representation is input into the display parameter optimization branch and the waterproof level optimization branch respectively, wherein the display parameter optimization branch and the waterproof level optimization branch include 2 fully connected layers, each fully connected layer includes 16 neurons, and a ReLU activation function is used to obtain a display branch feature vector and a waterproof branch feature vector; Inputting the display branch feature vector and the waterproof branch feature vector into a value function network to perform state value calculation respectively, to obtain a display state value evaluation and a waterproof state value evaluation; The display state value evaluation and the waterproof state value evaluation are respectively input into a policy gradient calculation unit, and the policy gradient is calculated by an importance sampling ratio clipping method to obtain a display parameter adjustment probability distribution and a protection action probability distribution; Generate a display parameter adjustment strategy and a waterproof level control strategy based on the display parameter adjustment probability distribution and the protection action probability distribution, input the display parameter adjustment strategy and the waterproof level control strategy into an action mapping module, map discrete actions into continuous control quantities through a lookup table, and obtain display parameter adjustment instructions and waterproof level control instructions; The display parameter adjustment instruction and the waterproof level control instruction are packaged to generate the protection control instruction set.

7. The intelligent environment sensing method based on outdoor waterproof television according to claim 6, characterized in that: The display state value evaluation and the waterproof state value evaluation are respectively input into the policy gradient calculation unit, and the policy gradient is calculated by the importance sampling ratio clipping method to obtain the display parameter adjustment probability distribution and the protection action probability distribution, including: Based on the display status value evaluation and the waterproof status value evaluation, respectively calculating the new and old strategy ratios to obtain the display parameter adjustment weight and the waterproof level adjustment weight; Compare the display parameter adjustment weight and the waterproof level adjustment weight with a preset clipping range, perform truncation processing through a minimum value function, and obtain a clipped display adjustment weight and a clipped waterproof adjustment weight; Calculating a policy objective function based on the cropped display adjustment weight and the cropped waterproof adjustment weight to obtain a display parameter policy gradient and a waterproof level policy gradient, and constraining the display parameter policy gradient and the waterproof level policy gradient to obtain a display parameter update direction and a waterproof level update direction; Projecting the display parameter update direction and the waterproof level update direction through a proximal mapping function to obtain a display parameter update amount within the constraint space and a waterproof level update amount within the constraint space; The policy network parameters are updated according to the display parameter update amount in the constraint space and the waterproof level update amount in the constraint space to obtain an updated display policy network and an updated waterproof policy network; The updated display strategy network and the updated waterproof strategy network are input into the Actor network for forward calculation to obtain a display parameter action space and a waterproof level action space, and the display parameter action space and the waterproof level action space are probability normalized to obtain a display parameter adjustment probability distribution and a protection action probability distribution.

8. An intelligent environment sensing system based on outdoor waterproof television, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: A collection module, used to collect environmental monitoring data sets of outdoor waterproof TVs through an environmental sensor array; A feature extraction module is used to input the environmental monitoring data set into the environmental sensor network for nonlinear transformation and multi-dimensional feature extraction, and obtain a fused feature matrix through feature fusion; A weighted calculation module, used to calculate the temperature parameter weight coefficient, humidity parameter weight coefficient, light intensity parameter weight coefficient and rainfall parameter weight coefficient for the fused feature matrix through a Bayesian optimization algorithm, and perform weighted calculation with the fused feature matrix to obtain an environmental risk factor; A generation module, used for inputting the environmental risk factor and the fusion feature matrix into a deep neural network based on proximal policy optimization (PPO) to perform policy iteration optimization calculation, and generating a protection control instruction set, wherein the protection control instruction set includes a display parameter adjustment instruction and a waterproof level control instruction; An execution module is used to generate a drive signal of the display module and a control signal of the waterproof actuator according to the protection control instruction set, and execute the drive signal and the control signal through an execution unit.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images