Landscape design identification method and system based on neural network model

Abstract

The invention provides a landscape design identification method and system based on a neural network model. The method comprises the following steps: by acquiring landscape design data, lighting equipment data and energy supply network real-time load data in a target area, establishing an optical model to analyze a spatial attenuation effect of vegetation shielding and artificial structure reflectivity on a lighting beam; calculating an energy consumption mapping relation between the lamp power distribution and the energy network load based on an energy transfer model; generating a dynamic dimming strategy in combination with a spatial attenuation effect and an energy consumption mapping relation, coupling the dynamic dimming strategy with a tourist distribution thermodynamic diagram and environment illumination intensity data which are acquired in real time, inputting the dynamic dimming strategy into a neural network model for iterative optimization, and dynamically adjusting lamp power distribution, a light beam angle coverage range and a light source color temperature parameter; dynamic optimization of the landscape lighting effect and minimization of energy consumption are achieved, and meanwhile the visual experience and comfort of tourists are improved. The invention provides an intelligent dynamic optimization technical scheme of a landscape lighting effect.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a landscape design recognition method and system based on a neural network model. Background Art

[0002] In modern urban landscape lighting projects, there are technical challenges in how to efficiently manage energy consumption and optimize lighting effects. As cities expand and the demand for environmentally friendly solutions increases, a technical solution is needed that can intelligently adjust lighting equipment parameters based on real-time environmental data and dynamically changing pedestrian density. This solution must not only support basic control functions for lighting equipment, but also be able to process complex input data sets to achieve precise lighting control, ensure the best lighting experience in different usage scenarios, and minimize unnecessary energy consumption.

[0003] The existing solution provides a smart lighting system based on a sensor network. The system deploys a series of environmental sensors to monitor the light level and human flow in the surrounding environment in real time. Based on this data, the system can automatically adjust the working status of the lamps, such as reducing the brightness or changing the color temperature of the light source during low-flow periods to save electricity.

[0004] However, intelligent lighting systems based on sensor networks rely on fixed algorithms or preset rules to make decisions and lack sufficient adaptive capabilities to cope with complex and changing actual application environments, which affects their overall performance and user satisfaction in different application scenarios. Summary of the invention

[0005] The embodiments of the present application provide a landscape design recognition method and system based on a neural network model to solve the problems in the prior art of poor accuracy of landscape lighting effects and energy consumption management in complex and changeable actual application environments, resulting in high energy consumption and poor landscape lighting effects.

[0006] In a first aspect, an embodiment of the present application provides a landscape design recognition method based on a neural network model, comprising: Acquire landscape design data, lighting equipment data and real-time load data of the energy supply network in the target area, wherein the landscape design data includes vegetation shading outline and artificial structure surface reflectivity, and the lighting equipment data includes lamp power distribution, beam angle coverage and light source color temperature parameters; An optical model is established based on the landscape design data and the lighting equipment data, and the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment is analyzed by the optical model; Establishing an energy transfer model based on the lighting equipment data and the real-time load data of the energy supply network, and calculating the energy consumption mapping relationship between the power distribution of the lamps and the real-time load data of the energy supply network through the energy transfer model; A dynamic dimming strategy is generated by combining the spatial attenuation effect with the energy consumption mapping relationship, and the dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, which is input into a neural network model to iteratively optimize the lamp power distribution, the beam angle coverage range and the light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

[0007] Optionally, the combining of the spatial attenuation effect and the energy consumption mapping relationship to generate a dynamic dimming strategy, coupling the dynamic dimming strategy with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and inputting the coupling result into a neural network model to iteratively optimize the lamp power distribution, the beam angle coverage range and the light source color temperature parameters through the neural network model, including: Building an objective function based on the mapping relationship between the spatial attenuation effect and the energy consumption, and generating a dynamic dimming strategy through an optimization algorithm based on the objective function; The dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, wherein the coupling result is a multi-dimensional feature vector; The multidimensional feature vector is input into a neural network model, a lighting effect prediction value is calculated by a forward propagation algorithm of the neural network model, and the lamp power distribution, beam angle coverage and light source color temperature parameters are iteratively optimized based on a preset loss function and a back propagation algorithm of the neural network model; The optimized lamp power distribution, beam angle coverage and light source color temperature parameters are output to the lighting control system to adjust the lighting equipment data in the target area in real time according to the optimized lamp power distribution, beam angle coverage and light source color temperature parameters.

[0008] Optionally, the multidimensional feature vector is input into a neural network model, a lighting effect prediction value is calculated by a forward propagation algorithm of the neural network model, and a lamp power distribution, a beam angle coverage range and a light source color temperature parameter are iteratively optimized based on a preset loss function and a back propagation algorithm of the neural network model, including: The multidimensional feature vector is standardized to obtain a preprocessed multidimensional feature vector, wherein the multidimensional features include the high-density area coordinates and dynamic change trends of the tourist distribution heat map, the time series characteristics of the ambient light intensity data, and the spatial distribution characteristics of the vegetation shading contour and the surface reflectivity of the artificial structure; Inputting the preprocessed multidimensional feature vector into a neural network model, combining the forward propagation algorithm in the neural network model, performing nonlinear transformation through the hidden layer of the neural network model, and generating a lighting effect prediction value at the output layer; Based on the difference between the lighting effect prediction value and the preset target value, the function value of the preset loss function is calculated. Based on the function value, the lamp power distribution, beam angle coverage and light source color temperature parameters are iteratively optimized and adjusted through the back propagation algorithm until the function value of the loss function converges to a preset threshold.

[0009] Optionally, the preprocessed multidimensional feature vector is input into a neural network model, combined with a forward propagation algorithm in the neural network model, a nonlinear transformation is performed through a hidden layer of the neural network model, and a lighting effect prediction value is generated at an output layer, including: Designing a structure of a neural network model, wherein the structure of the neural network model includes an input layer, a hidden layer and an output layer, the number of nodes in the input layer is consistent with the dimension of the multidimensional feature vector, the hidden layer adopts a multi-layer structure, and the number of nodes in the output layer is consistent with the dimension of the lighting effect prediction value; Input the preprocessed multidimensional feature vector to the input layer, combine the forward propagation algorithm in the neural network model, perform weighted summation on the multidimensional features corresponding to the preprocessed multidimensional feature vector in the hidden layer, perform nonlinear transformation on the weighted summation result through an activation function, and calculate the multidimensional feature mapping result layer by layer; In the output layer, the multidimensional feature mapping results output by the last hidden layer are weighted and summed, and the lighting effect prediction value is generated through the activation function of the output layer. The lighting effect prediction value includes the light intensity, total energy consumption and visual comfort score of each location in the target area.

[0010] Optionally, the establishing of an optical model based on the landscape design data and the lighting equipment data, and analyzing the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment through the optical model, includes: The vegetation shielding contour is digitally processed to obtain the spatial distribution characteristics and shielding intensity parameters of the vegetation, and the surface reflectivity of the artificial structure is divided into regions to generate a reflectivity distribution map; Generate an optical model based on the spatial distribution characteristics and shading intensity parameters of the vegetation, and the reflectivity distribution diagram, combined with the lamp power distribution, the beam angle coverage range and the light source color temperature parameters; Based on the optical model, the propagation process of the light beam emitted by the lighting device in the target area is simulated, the influence of the vegetation blocking outline and the reflectivity of the surface of the artificial structure on the light beam is calculated, and the attenuation parameter of the light beam is generated; Based on the attenuation parameters of the light beam, a spatial attenuation effect distribution diagram is generated, and the spatial attenuation effect distribution diagram is used to characterize the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting device.

[0011] Optionally, based on the optical model, simulating the propagation process of the light beam emitted by the lighting device in the target area, calculating the influence of the vegetation blocking contour and the surface reflectivity of the artificial structure on the light beam, and generating the attenuation parameter of the light beam, includes: Constructing a beam propagation path model according to the optical model, the lamp power distribution, the beam angle coverage range and the light source color temperature parameter, and dividing the target area into a plurality of grid units based on the beam propagation path model; In the light beam propagation path model, the attenuation effect of the vegetation shading contour on the light beam is calculated grid unit by grid unit, a vegetation shading attenuation coefficient is generated, and the light intensity value of each grid unit is updated according to the vegetation shading attenuation coefficient; Identify the grid cells that intersect with the surface of the artificial structure in the light beam propagation path model, calculate the reflection path and reflection intensity of the light beam on the surface of the artificial structure, and update the light intensity value of the grid cells covered by the reflection path according to the reflection intensity; According to the light intensity value of each grid cell, a beam attenuation parameter of each grid cell is generated.

[0012] Optionally, in the light beam propagation path model, calculating the attenuation effect of the vegetation occlusion contour on the light beam grid by grid unit, generating a vegetation occlusion attenuation coefficient, and updating the light intensity value of each grid unit according to the vegetation occlusion attenuation coefficient, including: Extracting the height, density and distribution range parameters of vegetation from the vegetation occlusion contour, and mapping the height, density and distribution range parameters of vegetation to the grid cells of the target area; In the beam propagation path model, for each grid unit, according to the vegetation shielding intensity value, the mapping data corresponding to the vegetation height, density and distribution range parameters, the attenuation coefficient of the beam after penetrating the vegetation is calculated to generate the vegetation shielding attenuation coefficient of each grid unit; Combined with the scattering effect of vegetation on the light beam, the scattering path of the light beam after penetrating the vegetation is simulated, the propagation direction and intensity distribution of the scattered light beam are calculated, and the light intensity value of the grid unit covered by the scattering path is updated according to the propagation direction and the intensity distribution; The vegetation shading attenuation coefficient of each grid unit and the light intensity value of the grid unit covered by the scattering path are applied to the light beam propagation path model to update the light intensity value of each grid unit through the light beam propagation path model.

[0013] In a second aspect, the embodiment of the present application provides a landscape design recognition system based on a neural network model, comprising: An acquisition module is used to acquire landscape design data, lighting equipment data and real-time load data of the energy supply network in the target area, wherein the landscape design data includes vegetation shading contours and artificial structure surface reflectivity, and the lighting equipment data includes lamp power distribution, beam angle coverage and light source color temperature parameters; Establishing an analysis module for establishing an optical model based on the landscape design data and the lighting equipment data, and analyzing the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment through the optical model; Establishing a calculation module, for establishing an energy transfer model based on the lighting equipment data and the real-time load data of the energy supply network, and calculating the energy consumption mapping relationship between the power distribution of the lamps and the real-time load data of the energy supply network through the energy transfer model; A coupling module is generated to generate a dynamic dimming strategy by combining the spatial attenuation effect with the energy consumption mapping relationship, and the dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and the coupling result is input into a neural network model to iteratively optimize the lamp power distribution, the beam angle coverage range and the light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

[0014] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a landscape design recognition method based on a neural network model as described in any one of the first aspects.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a landscape design identification method based on a neural network model as described in any one of the first aspects.

[0016] In an embodiment of the present application, a landscape design recognition method based on a neural network model is provided, the method comprising: obtaining landscape design data, lighting equipment data and real-time load data of an energy supply network in a target area, the landscape design data comprising vegetation shading contours and artificial structure surface reflectivity, and the lighting equipment data comprising lamp power distribution, beam angle coverage and light source color temperature parameters; establishing an optical model based on the landscape design data and the lighting equipment data, and analyzing the spatial attenuation effect of the vegetation shading contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment through the optical model; establishing an energy transfer model based on the lighting equipment data and the real-time load data of the energy supply network, and calculating the energy consumption mapping relationship between the lamp power distribution and the real-time load data of the energy supply network through the energy transfer model; generating a dynamic dimming strategy in combination with the spatial attenuation effect and the energy consumption mapping relationship, coupling the dynamic dimming strategy with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and inputting the coupling result into the neural network model to iteratively optimize the lamp power distribution, beam angle coverage and light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

[0017] The embodiment of the present application provides a comprehensive data basis for subsequent modeling and optimization by obtaining vegetation occlusion contours, artificial structure surface reflectivity, lamp power distribution, beam angle coverage, light source color temperature parameters, and real-time load data of the energy supply network, ensuring that the regulation of the lighting system can accurately adapt to environmental characteristics and energy requirements. By analyzing the spatial attenuation effect of vegetation occlusion contours and artificial structure surface reflectivity on the lighting beam through optical models, the impact of environmental factors on the lighting effect can be quantified, providing a basis for the generation of subsequent dimming strategies. By calculating the energy consumption mapping relationship between lamp power distribution and real-time load data of the energy supply network through the energy transfer model, the energy consumption of the lighting system can be accurately predicted and optimized, providing support for efficient energy utilization. By comprehensively considering the spatial attenuation effect and the energy consumption mapping relationship, a dynamic dimming strategy is generated, which can achieve a preliminary balance between lighting effects and energy consumption, providing a basis for subsequent refined optimization. By coupling the heat map of tourist distribution and ambient light intensity data, the lighting strategy can be dynamically adjusted to make it more in line with actual scene requirements and enhance the visual experience and comfort of tourists. Through the iterative optimization of the neural network model, the lighting parameters can be finely adjusted, the lighting effect can be dynamically optimized and the energy consumption can be minimized, while the intelligence level of the system can be improved. Furthermore, through the construction of the objective function, the generation of multi-dimensional feature vectors and the iterative optimization of the neural network model, the dynamic and fine adjustment of the lighting parameters can be achieved, so that the lighting effect and energy consumption can be optimally balanced, while improving the visual experience and comfort of tourists, reflecting the efficiency and adaptability of intelligent lighting control.

[0018] These and other aspects of the present application will become more apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flowchart of a landscape design identification method based on a neural network model provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a landscape design recognition system based on a neural network model provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0022] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The sequence numbers of the operations, such as 11, 12, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to different types.

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0024] The existing technology has poor accuracy in landscape lighting effects and energy consumption management in complex and changeable actual application environments, resulting in high energy consumption and poor landscape lighting effects. The embodiments of the present application achieve dynamic optimization and efficient energy utilization of landscape lighting systems through multi-source data fusion and intelligent modeling. Specifically, it includes: by acquiring landscape design data, lighting equipment data and real-time load data of the energy supply network, establishing an optical model to analyze the spatial attenuation effect of the light beam, and calculating the energy consumption mapping relationship through the energy transfer model. Combining dynamic dimming strategies with real-time environmental data, the neural network model is used to iteratively optimize the lighting parameters to achieve dynamic optimization of landscape lighting effects and minimize energy consumption, while improving the visual experience and comfort of tourists.

[0025] Figure 1 A flowchart of a landscape design recognition method based on a neural network model is provided in an embodiment of the present application, such as Figure 1 As shown, the method includes: S11. Obtain the landscape design data, lighting equipment data and real-time load data of the energy supply network in the target area. The landscape design data includes the vegetation shading outline and the surface reflectivity of artificial structures. The lighting equipment data includes the lamp power distribution, beam angle coverage and light source color temperature parameters.

[0026] The target area can be a city park, city square, greenway, commercial block, tourist attraction, industrial park, etc. The real-time load data of the energy supply network includes electrical parameters such as voltage, current, power factor, and the real-time load of the entire network.

[0027] The vegetation occlusion profile refers to the distribution of vegetation (such as trees, shrubs, etc.) in space and its blocking effect on light. Specifically, the vegetation occlusion profile includes parameters such as the height, density, and distribution range of vegetation, which together determine the degree of attenuation of the light beam after penetrating the vegetation. By digitally processing the vegetation occlusion profile, the spatial distribution characteristics and occlusion intensity parameters of the vegetation can be obtained, providing data support for quantifying the impact of vegetation on the intensity attenuation of the light beam after penetration. For example, in night lighting scenes, vegetation may cause insufficient light in some areas. Understanding its occlusion profile can help adjust the position or power of the lamp to compensate for this effect. In addition, the surface reflectivity of artificial structures involves the ability of the surface material of non-natural construction objects (such as buildings, sculptures, roads, etc.) to reflect light. Different materials have different reflective properties. Therefore, when the same intensity of light is irradiated on different surfaces, the intensity of the reflected light generated will also be different. The power distribution of lamps refers to the power configuration scheme of each lighting device in the target area at different spatial positions, including the power value of a single lamp, the power adjustment range, and its coordinated distribution relationship in the overall lighting network.

[0028] S12. An optical model is established based on the landscape design data and the lighting equipment data. The optical model is used to analyze the spatial attenuation effect of the vegetation shading contour and the surface reflectivity of the artificial structure on the light beam emitted by the lighting equipment.

[0029] The optical model is used to simulate the process of light beams starting from lamps and propagating in the target area, while taking into account the influence of factors such as vegetation occlusion and reflection from artificial structures. The spatial attenuation effect refers to the phenomenon that the intensity of the light beam emitted by the lighting equipment gradually weakens as the spatial distance increases due to the influence of environmental factors during the propagation process. The spatial attenuation effect can be displayed through the spatial attenuation effect distribution diagram.

[0030] S13. Establish an energy transfer model based on lighting equipment data and real-time load data of the energy supply network, and calculate the energy consumption mapping relationship between the power distribution of lamps and the real-time load data of the energy supply network through the energy transfer model.

[0031] Among them, the energy transfer model may include an electric power calculation formula, an active power calculation formula, and an energy consumption calculation formula. The energy transfer model can determine the power demand of each lamp in the target area, such as the power value of a single lamp and its adjustment range, according to the lighting design requirements and environmental conditions (such as vegetation shading outline, reflectivity of artificial structures, etc.). The actual power consumption of each lamp is calculated by using the above electric power calculation formula in combination with the working voltage and working current of each lamp. If the power factor is considered, the active power formula is used for correction. The energy loss from the power supply to the lamp is calculated based on the wire resistance and other electrical characteristics on the power transmission path. The power consumption of all lamps is summed up, and the loss during the power transmission process is added to obtain the total energy consumption of the entire lighting system. The total energy consumption calculated above is combined with the real-time load data of the energy supply network to establish an energy consumption mapping relationship between the power distribution of the lamps and the real-time load data of the energy supply network.

[0032] Exemplarily, the energy transfer model can be expressed by the following formula: ; in, is the total energy consumption, N is the number of lamps in the target area; is the actual power of the i-th lamp, which is determined by the working current of the lamp, is the working voltage of the lamp, is the internal resistance of the lamp, t is the working time, M is the number of line segments on the power transmission path, is the resistance of the jth line on the power transmission path, I j is the current of the jth line on the power transmission path.

[0033] S14. Generate a dynamic dimming strategy based on the spatial attenuation effect and energy consumption mapping relationship, couple the dynamic dimming strategy with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and input the coupling result into the neural network model to iteratively optimize the lamp power distribution, beam angle coverage and light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

[0034] Among them, the tourist distribution heat map is used to reflect the density and distribution of people in a specific area. This kind of chart usually uses different colors to represent the density of people in different areas. The darker the color (such as red or warm tones), the greater the flow of people in the area, while the lighter the color (such as blue or cold tones), the less the flow of people. Coupling can be achieved through data fusion technology. Ambient light intensity data is used to reflect the brightness level of natural light or artificial light sources at a specific location or area at a specific time. Dynamic dimming strategy refers to an intelligent control scheme that dynamically adjusts the power distribution of lamps, beam angle coverage, and light source color temperature parameters based on real-time environmental data (such as tourist distribution, ambient light intensity, vegetation occlusion contour, artificial structure reflectivity, etc.) and preset optimization goals (such as minimizing energy consumption and improving visual experience).

[0035] Here is a specific example: In the landscape lighting system of a city park, the vegetation occlusion outline and the surface reflectivity of artificial structures are first obtained through LiDAR (Light Detection and Ranging, LiDAR) scanning and spectral analysis, and the lighting equipment data and energy load data are obtained from the lamp manufacturers and smart meters. Based on these data, an optical model and an energy transfer model are established to analyze the spatial attenuation effect of the light beam and the energy consumption mapping relationship respectively. Subsequently, a dynamic dimming strategy is generated and input into the neural network model for optimization by combining the real-time collected tourist distribution heat map (through infrared sensors and cameras) and ambient light intensity data. Finally, the system dynamically adjusts the lamp power, beam angle and color temperature according to the optimization results, achieving energy-saving lighting at night while providing tourists with a comfortable visual experience.

[0036] By executing S11~S14, the embodiment of the present application provides a comprehensive data basis for subsequent modeling and optimization by obtaining vegetation occlusion contours, artificial structure surface reflectivity, lamp power distribution, beam angle coverage, light source color temperature parameters and real-time load data of the energy supply network, ensuring that the regulation of the lighting system can accurately adapt to environmental characteristics and energy requirements. By analyzing the spatial attenuation effect of vegetation occlusion contours and artificial structure surface reflectivity on the lighting beam through optical models, the influence of environmental factors on the lighting effect can be quantified, providing a basis for the generation of subsequent dimming strategies. By calculating the energy consumption mapping relationship between lamp power distribution and real-time load data of the energy supply network through the energy transfer model, the energy consumption of the lighting system can be accurately predicted and optimized, providing support for efficient energy utilization. By comprehensively considering the spatial attenuation effect and the energy consumption mapping relationship, a dynamic dimming strategy is generated, which can achieve a preliminary balance between lighting effects and energy consumption, providing a basis for subsequent refined optimization. By coupling the heat map of tourist distribution and the ambient light intensity data, the lighting strategy can be dynamically adjusted to make it more in line with the actual scene requirements and enhance the visual experience and comfort of tourists. Through iterative optimization of the neural network model, it is possible to achieve fine-grained adjustment of lighting parameters, dynamically optimize lighting effects and minimize energy consumption, while improving the intelligence level of the system.

[0037] In a possible embodiment, S14, a dynamic dimming strategy is generated by combining the spatial attenuation effect with the energy consumption mapping relationship, the dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and the coupling result is input into a neural network model to iteratively optimize the lamp power distribution, the beam angle coverage range and the light source color temperature parameters through the neural network model to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists, including: Step 141: construct an objective function based on the mapping relationship between the spatial attenuation effect and the energy consumption, and generate a dynamic dimming strategy through an optimization algorithm based on the objective function.

[0038] Among them, the objective function usually contains multiple variables and constraints, which are used to minimize or maximize certain key indicators (such as energy consumption, visual comfort score, etc.). For example, in a landscape lighting scenario, the objective function may be designed to minimize total energy consumption while maximizing the visual experience of visitors. Alternatively, in order to minimize energy consumption while maintaining a certain level of illumination, the objective function may comprehensively consider factors such as lamp power distribution, beam angle coverage, light source color temperature parameters, and ambient light intensity, and calculate the overall score through a weighted formula. The optimization algorithm can be a genetic algorithm, ant colony algorithm, gradient descent method, simulated annealing algorithm, etc. The dynamic dimming strategy customizes exclusive dimming strategies according to the characteristics of different areas (such as trail areas, sculpture areas, etc.) to ensure that each area can obtain appropriate lighting effects.

[0039] Exemplarily, the optimization algorithm can be a multi-objective particle swarm optimization, and the objective function is: Etotal−Scomfort; where Etotal is the energy consumption, Scomfort is the visual comfort score, energy consumption refers to the total energy consumption, which can be calculated by the energy transfer model, and the visual comfort score is ∑||I pred (x,y)−I target (x,y)|| 2 , I pred (x, y) is the predicted light intensity, I target (x,y) is the target light intensity.

[0040] Step 142: Couple the dynamic dimming strategy with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, which is a multi-dimensional feature vector.

[0041] Among them, multidimensional feature vector refers to the integration of multiple different types of data (such as dynamic dimming strategies, tourist distribution heat maps, ambient light intensity data, vegetation occlusion contours, surface reflectivity of artificial structures, etc.) into a high-dimensional mathematical representation through data fusion technology.

[0042] Step 143: input the multidimensional feature vector into the neural network model, calculate the lighting effect prediction value through the forward propagation algorithm of the neural network model, and iteratively optimize the lamp power distribution, beam angle coverage and light source color temperature parameters based on the preset loss function and the back propagation algorithm of the neural network model.

[0043] Among them, the preset loss function is a mathematical expression used to quantify the difference between the model prediction value and the true target value during the neural network training process.

[0044] Step 144: output the optimized lamp power distribution, beam angle coverage and light source color temperature parameters to the lighting control system to adjust the lighting equipment data in the target area in real time according to the optimized lamp power distribution, beam angle coverage and light source color temperature parameters.

[0045] Among them, the beam angle coverage is the horizontal / vertical divergence angle range formed by the light emitted by the lighting device in space, usually expressed in full angle or half angle form.

[0046] Here is a specific example: In the landscape lighting system of a city square, the objective function is first constructed based on the spatial attenuation effect and energy consumption mapping relationship to generate a dynamic dimming strategy (such as 60W power in the trail area and 120W power in the sculpture area). Subsequently, the dimming strategy is coupled with the real-time collected tourist distribution heat map (dense pedestrian flow in the trail area) and ambient light intensity data (nighttime light intensity is 0 lux) to generate a multidimensional feature vector. Next, the multidimensional feature vector is input into the neural network model, and the lamp parameters are iteratively optimized through forward propagation and back propagation algorithms (such as the power in the trail area is increased to 70W, and the power in the sculpture area is reduced to 100W). Finally, the optimized parameters are output to the lighting control system to adjust the lamp power, beam angle and light source color temperature parameters in real time to achieve a balance between energy-saving lighting and tourist visual experience.

[0047] By executing steps 141 to 144, the embodiment of the present application realizes intelligent dynamic dimming of the landscape lighting system through objective function construction, data coupling, neural network optimization and real-time control. Combining the spatial attenuation effect, energy consumption mapping relationship and real-time environmental data, the dynamic adaptability and energy utilization efficiency of the lighting effect are improved, while optimizing the visual experience and comfort of tourists, providing an efficient and intelligent solution for landscape lighting management in smart cities.

[0048] In a possible embodiment, step 143, inputting the multidimensional feature vector into the neural network model, calculating the lighting effect prediction value through the forward propagation algorithm of the neural network model, and iteratively optimizing the lamp power distribution, beam angle coverage and light source color temperature parameters based on the preset loss function and the back propagation algorithm of the neural network model, including: Step a1, standardize the multidimensional feature vector to obtain a preprocessed multidimensional feature vector, wherein the multidimensional features include the high-density area coordinates and dynamic change trends of the tourist distribution heat map, the time series characteristics of the ambient light intensity data, and the spatial distribution characteristics of the vegetation occlusion contour and the surface reflectivity of the artificial structure.

[0049] Among them, time series characteristics can refer to the statistical laws, periodic patterns and dynamic trends presented by the changes in ambient light intensity data over time.

[0050] Step a2: input the preprocessed multidimensional feature vector into the neural network model, combine the forward propagation algorithm in the neural network model, perform nonlinear transformation through the hidden layer of the neural network model, and generate a lighting effect prediction value at the output layer.

[0051] Among them, nonlinear transformation refers to the process of converting a linear combination of input data into a nonlinear output through a mathematical function. In the embodiment of the present application, this process occurs in the hidden layer of the neural network.

[0052] Exemplarily, the formula used by the forward propagation algorithm in the neural network model is as follows: Z (l) =W (l) a (l−1) +b (l) ,a (l) =σ(z (l) ); Among them, Z (l) is the lighting effect prediction value output by the neural network model, a (l−1) is the multidimensional feature vector extracted from the l-1th layer, a (0) is the preprocessed multidimensional feature vector, l is the lth layer in the neural network model, W (l) is the weight of the lth layer, b (l) is the bias of the lth layer. σ is the activation function (such as ReLU).

[0053] Step a3: Based on the difference between the lighting effect prediction value and the preset target value, the function value of the preset loss function is calculated. Based on the function value, the lamp power distribution, beam angle coverage and light source color temperature parameters are iteratively optimized and adjusted through the back propagation algorithm until the function value of the loss function converges to the preset threshold.

[0054] Among them, the function value converges to the preset threshold value can mean that during the neural network training process, the model parameters are continuously adjusted through the back propagation algorithm, so that the value of the loss function gradually approaches the preset target value or target range, and finally stabilizes within the target range, indicating that the model training is completed.

[0055] Exemplarily, the preset loss function may adopt the following formula: ; in, is the function value of the preset loss function, is the energy consumption predicted by the neural network, is the light intensity predicted by the neural network, is the comfort level predicted by the neural network, is the actual energy consumption, is the actual light intensity, is the target comfort score, λ1,λ2,λ3 are the weights corresponding to each loss item.

[0056] Here is a specific example: Processing and optimization of multi-dimensional feature vectors in the landscape lighting system of an urban park. Visitor distribution heat map: the trail area is densely populated (density 0.9), and the sculpture area is sparsely populated (density 0.3). Ambient light intensity: The night light intensity is 0 lux. Vegetation occlusion profile: The occlusion degree of the trail area is 50%. Reflectivity data: The reflectivity of the trail area is 0.6, and the reflectivity of the sculpture area is 0.8. Standardization processing: All data are normalized to the interval [0,1] to generate feature vectors. Input the feature vector to the neural network model and generate the lighting effect prediction value through forward propagation. Calculate the loss function value and optimize the lamp parameters through the back propagation algorithm. Output the optimized parameters to the lighting control system to adjust the lamp power and beam angle in real time.

[0057] By executing steps a1 to a3, the embodiment of the present application realizes intelligent dynamic dimming of the landscape lighting system through standardized processing of multi-dimensional feature vectors and optimization of forward propagation and back propagation of neural network models. Combining real-time environmental data with preset optimization goals, the dynamic adaptability and energy efficiency of the lighting effect are improved, while optimizing the visual experience and comfort of tourists, providing an efficient and intelligent solution for landscape lighting management in smart cities.

[0058] In a possible embodiment, step a2 inputs the preprocessed multidimensional feature vector into the neural network model, combines the forward propagation algorithm in the neural network model, performs nonlinear transformation through the hidden layer of the neural network model, and generates a lighting effect prediction value at the output layer, including: Step b1, design the structure of the neural network model. The structure of the neural network model includes an input layer, a hidden layer and an output layer. The number of nodes in the input layer is consistent with the dimension of the multidimensional feature vector. The hidden layer adopts a multi-layer structure. The number of nodes in the output layer is consistent with the dimension of the lighting effect prediction value.

[0059] Among them, the hidden layer is a parameterizable layer located between the input layer and the output layer in the neural network. Its core function is to extract high-order abstract representations from the input features through nonlinear transformation to capture the complex mapping relationship between the input data and the output target.

[0060] Step b2: input the preprocessed multidimensional feature vector into the input layer, combine the forward propagation algorithm in the neural network model, perform weighted summation on the multidimensional features corresponding to the preprocessed multidimensional feature vector in the hidden layer, perform nonlinear transformation on the weighted summation result through the activation function, and calculate the multidimensional feature mapping result layer by layer.

[0061] Among them, the neural network model is a machine learning model based on a multi-dimensional feature input-nonlinear transformation-output prediction architecture. Its core function is to learn complex mapping relationships from input data through hierarchical abstraction and output optimized lighting equipment parameters.

[0062] Step b3: In the output layer, the multi-dimensional feature mapping results output by the last hidden layer are weighted and summed, and the lighting effect prediction value is generated through the activation function of the output layer. The lighting effect prediction value includes the light intensity, total energy consumption and visual comfort score of each location in the target area.

[0063] The total energy consumption refers to the total electrical energy consumed by all lighting equipment in the target area within a specific time period.

[0064] The following is a specific example: the design and prediction process of a neural network model in a landscape lighting system in a city square. Input layer: 8 nodes (corresponding to 8-dimensional feature vectors). Hidden layer: 2 layers, 16 nodes and 8 nodes respectively. Output layer: 3 nodes (corresponding to light intensity, total energy consumption, and visual comfort score). Input the feature vector to the input layer, perform nonlinear transformation through the hidden layer, and generate a multidimensional feature mapping result. Perform weighted summation on the hidden layer output to generate a lighting effect prediction value. Light intensity: [0.8, 0.6, 0.9]; total energy consumption: 0.7; visual comfort score: 0.85. Output the predicted value to the lighting control system to adjust the lighting parameters in real time.

[0065] By executing steps b1 to b3, the embodiment of the present application realizes intelligent prediction and optimization of landscape lighting effects through structural design of neural network model, forward propagation calculation and output layer prediction. Combining multi-dimensional feature vectors with real-time environmental data, the dynamic adaptability and energy efficiency of the lighting system are improved, while optimizing the visual experience and comfort of tourists, providing an efficient and intelligent solution for landscape lighting management in smart cities.

[0066] In a possible embodiment, S12, an optical model is established based on the landscape design data and the lighting equipment data, and the spatial attenuation effect of the vegetation blocking contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment is analyzed by the optical model, including: Step 121, digitally process the vegetation shielding contour to obtain the spatial distribution characteristics and shielding intensity parameters of the vegetation, and divide the surface reflectivity of the artificial structure into regions to generate a reflectivity distribution map.

[0067] Among them, the reflectivity distribution map is a two-dimensional visualization chart generated by regional division technology, which is used to characterize the spatial distribution characteristics of the reflectivity of the surface of artificial structures in the target area. In the reflectivity distribution map, higher reflectivity means more light is reflected back into the environment, which is very important for increasing the brightness of certain areas or creating specific visual effects.

[0068] Step 122: Generate an optical model based on the spatial distribution characteristics and shading intensity parameters of vegetation and the reflectivity distribution diagram, combined with the lamp power distribution, beam angle coverage and light source color temperature parameters.

[0069] Among them, the optical model is a light propagation simulation framework constructed by numerical simulation methods based on the landscape design data and lighting equipment parameters of the target area.

[0070] Step 123: Based on the optical model, simulate the propagation process of the light beam emitted by the lighting device in the target area, calculate the influence of the vegetation shading outline and the surface reflectivity of the artificial structure on the light beam, and generate the attenuation parameter of the light beam.

[0071] The attenuation parameter of the light beam is a physical quantity that quantifies the intensity attenuation of the light beam caused by vegetation occlusion, reflection from artificial structures, and scattering effects when the light beam propagates in the target area through an optical model. Its core purpose is to provide precise constraints on spatial light intensity changes for dynamic dimming strategies to ensure a balance between lighting effects and energy consumption.

[0072] Step 124: Generate a spatial attenuation effect distribution map based on the attenuation parameters of the light beam. The spatial attenuation effect distribution map is used to characterize the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting device.

[0073] Among them, the spatial attenuation effect refers to the phenomenon that the light intensity of the light beam emitted by the lighting equipment decays nonlinearly with spatial distance or environmental characteristics during the propagation process due to physical effects such as vegetation obstruction, reflection and scattering of artificial structures.

[0074] Here is a specific example: In the landscape lighting system of an urban park, the construction and application process of the optical model obtains the vegetation occlusion contour through LiDAR scanning and calculates the occlusion intensity parameters (such as the occlusion rate of the trail area is 50%). The reflectivity of artificial structures is measured by a spectrometer to generate a reflectivity distribution map (such as the reflectivity of the trail area is 0.6, and the reflectivity of the sculpture area is 0.8). The optical model is constructed by combining the vegetation occlusion contour, reflectivity distribution map and lamp parameters (such as power 60W, beam angle 90°). The beam propagation path is simulated to calculate the light intensity attenuation of 50% in the trail area and the reflected light intensity increase of 20% in the sculpture area. A distribution map is generated to show the light intensity attenuation in the trail area and the reflected light intensity increase in the sculpture area. The distribution map is output to the lighting control system to adjust the lamp power in the trail area to 80W to compensate for the light intensity attenuation.

[0075] By executing steps 121 to 124, the embodiment of the present application generates a spatial attenuation effect distribution map through digitization of vegetation occlusion contours, reflectivity area division, optical model construction and beam propagation simulation, providing a basis for the dynamic dimming strategy of the landscape lighting system. Combining real-time environmental data with optical models, the dynamic adaptability and energy efficiency of the lighting effect are improved, while optimizing the visual experience and comfort of tourists, providing an efficient and intelligent solution for landscape lighting management in smart cities.

[0076] In a possible embodiment, step 123 simulates the propagation process of the light beam emitted by the lighting device in the target area based on the optical model, calculates the influence of the vegetation shading contour and the reflectivity of the surface of the artificial structure on the light beam, and generates the attenuation parameters of the light beam.

[0077] Step 1231: construct a beam propagation path model according to the optical model, lamp power distribution, beam angle coverage and light source color temperature parameters, and divide the target area into multiple grid units based on the beam propagation path model.

[0078] The beam propagation path model is a numerical calculation model based on a grid method to simulate the propagation process of the beam in the target area. Its core function is to generate beam attenuation parameters and spatial attenuation effect distribution maps by analyzing vegetation occlusion, surface reflection and scattering effects on a grid-by-grid basis, thus providing physical constraints for dynamic dimming strategies.

[0079] Step 1232: In the light beam propagation path model, the attenuation effect of the vegetation occlusion contour on the light beam is calculated for each grid cell, a vegetation occlusion attenuation coefficient is generated, and the light intensity value of each grid cell is updated according to the vegetation occlusion attenuation coefficient.

[0080] Among them, the vegetation attenuation coefficient is a physical quantity that quantifies the intensity attenuation of a light beam after it penetrates the vegetation, reflecting the absorption, scattering and blocking effects of vegetation density, height and other characteristics on light energy.

[0081] Step 1233, identifying the grid cells in the light beam propagation path model that intersect with the surface of the artificial structure, calculating the reflection path and reflection intensity of the light beam on the surface of the artificial structure, and updating the illumination intensity value of the grid cells covered by the reflection path according to the reflection intensity.

[0082] Among them, the illumination intensity value of the grid unit covered by the reflection path refers to the illumination intensity of the grid unit after the light beam is reflected on the surface of the artificial structure and propagated through the reflection path to the target area. Its calculation needs to be combined with the initial intensity of the light beam, surface reflectivity, incident angle, effective area of ​​the reflection surface, propagation distance of the reflection path, etc. The reflection intensity is used as the illumination intensity value of the grid unit covered by the reflection path to correct the influence of the secondary light path on the illumination distribution in the light beam propagation model.

[0083] Exemplarily, the formula used to calculate the reflection intensity of a light beam on the surface of an artificial structure is as follows: I(x,y)=I0×γ(x,y)×cosθ(x,y)×[Ar(x,y) / r2(x,y)]; Where I(x,y) is the reflection intensity of the light beam on the surface of the artificial structure, I0 is the initial intensity of the incident light beam, γ(x,y) is the surface reflectivity, θ(x,y) is the incident angle, Ar(x,y) is the effective area of ​​the reflecting surface, in square meters, and r(x,y) is the propagation distance of the reflection path, in meters.

[0084] Step 1234: Generate a beam attenuation parameter for each grid unit according to the light intensity value of each grid unit.

[0085] Among them, the beam attenuation parameter is a quantitative indicator that characterizes the intensity attenuation of the light beam during its propagation in the target area after comprehensively considering multiple factors such as vegetation occlusion, reflection from artificial structures, and scattering effects.

[0086] Here is a specific example: In the landscape lighting system of a city square, the construction and application process of the beam propagation path model, the beam propagation path model is constructed according to the lamp parameters (power 60W, beam angle 90°), and the target area is divided into 1m×1m grid units. The vegetation shading attenuation coefficient of the grid unit in the trail area is calculated (such as 0.5), and the light intensity value is updated (from 100 lux to 50 lux). The grid units intersecting with the sculpture surface are identified, the reflection path and reflection intensity are calculated (such as reflectivity 0.8, reflection intensity 40 lux), and the light intensity value of the grid unit covered by the reflection path is updated (from 50 lux to 90 lux). The beam attenuation parameters of each grid unit are calculated (such as 50% attenuation rate in the trail area and 10% attenuation rate in the sculpture area).

[0087] By executing steps 1231 to 1234, the embodiment of the present application realizes accurate modeling of the beam propagation path and quantification of the attenuation effect in the landscape lighting system through the construction of the beam propagation path model, the calculation of the vegetation shading attenuation effect, the calculation of the reflection effect, and the generation of beam attenuation parameters. Combining real-time environmental data with optical models, the dynamic adaptability and energy efficiency of the lighting effect are improved, while optimizing the visual experience and comfort of tourists, providing an efficient and intelligent solution for landscape lighting management in smart cities.

[0088] In a possible embodiment, step 1232, in the light beam propagation path model, calculates the attenuation effect of the vegetation occlusion contour on the light beam for each grid unit, generates a vegetation occlusion attenuation coefficient, and updates the light intensity value of each grid unit according to the vegetation occlusion attenuation coefficient, including: Step c1: extracting the height, density and distribution range parameters of vegetation from the vegetation occlusion contour, and mapping the height, density and distribution range parameters of vegetation to the grid cells of the target area.

[0089] Step c2: In the beam propagation path model, for each grid unit, the attenuation coefficient of the beam after penetrating the vegetation is calculated according to the vegetation shading intensity value, the mapping data corresponding to the vegetation height, density and distribution range parameters, and the vegetation shading attenuation coefficient of each grid unit is generated.

[0090] Exemplarily, the calculation formula of the attenuation coefficient of the light beam after penetrating the vegetation is as follows: α(x,y)=1−exp(−β×h(x,y)×ρ(x,y)×d(x,y)); Among them, α(x,y) is the vegetation occlusion attenuation coefficient of the grid unit (x,y), β is the vegetation occlusion intensity value, which can be understood as the vegetation type coefficient. For example, β=0.05 for trees and β=0.03 for shrubs. h(x,y) is the mapping data corresponding to the vegetation height of the grid unit (x,y), in meters. ρ(x,y) is the mapping data corresponding to the density. d(x,y) is the mapping data corresponding to the distribution range parameter, for example, the proportion of vegetation distribution range.

[0091] The distribution range parameters refer to a set of parameters that describe the spatial distribution characteristics of vegetation in the target area, including the horizontal distribution range and the vertical distribution range.

[0092] Step c3: Apply the vegetation shading attenuation coefficient of each grid cell and the light intensity value of the grid cell covered by the scattering path to the light beam propagation path model to update the light intensity value of each grid cell through the light beam propagation path model.

[0093] Among them, the attenuation coefficient of the light beam after penetrating the vegetation is a parameter that quantifies the intensity attenuation of the light beam after penetrating the vegetation, reflecting the absorption and scattering effects of vegetation density, height and scattering characteristics on light energy.

[0094] Here is a specific example: In the landscape lighting system of an urban park, the calculation and application process of the vegetation occlusion attenuation effect is to obtain the vegetation height (2m), density (0.6) and distribution range (50%) through LiDAR scanning, and map them to 1m×1m grid cells. Calculate the occlusion intensity value of the grid cell in the trail area (such as 0.6) and generate the attenuation coefficient (such as 0.45). Update the light intensity value of the grid cell in the trail area according to the attenuation coefficient (from 100 lux to 55 lux). Calculate the scattering path of the light beam in the vegetation, and update the light intensity value of the grid cell covered by the scattering path (from 55 lux to 70 lux).

[0095] By executing steps c1 to c3, the embodiment of the present application realizes accurate modeling and quantification of vegetation occlusion effect in landscape lighting system through vegetation parameter extraction and mapping, vegetation occlusion attenuation coefficient calculation and light intensity update. Combining the beam propagation path model with real-time environmental data, the dynamic adaptability and energy efficiency of lighting effects are improved, while optimizing the visual experience and comfort of tourists, providing an efficient and intelligent solution for landscape lighting management in smart cities.

[0096] Figure 2 A schematic diagram of the structure of a landscape design recognition system based on a neural network model provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the system includes: The acquisition module 21 is used to obtain the landscape design data, lighting equipment data and real-time load data of the energy supply network in the target area. The landscape design data includes the vegetation shading outline and the surface reflectivity of artificial structures. The lighting equipment data includes the lamp power distribution, beam angle coverage and light source color temperature parameters.

[0097] An analysis module 22 is established to establish an optical model based on the landscape design data and the lighting equipment data, and to analyze the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment through the optical model.

[0098] A calculation module 23 is established to establish an energy transfer model based on lighting equipment data and real-time load data of the energy supply network, and calculate the energy consumption mapping relationship between the lamp power distribution and the real-time load data of the energy supply network through the energy transfer model.

[0099] A coupling module 24 is generated, which is used to generate a dynamic dimming strategy by combining the spatial attenuation effect with the energy consumption mapping relationship, and the dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, which is input into the neural network model to iteratively optimize the lamp power distribution, beam angle coverage and light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

[0100] Figure 2 The landscape design recognition system based on the neural network model can perform Figure 1 The implementation principle and technical effect of the landscape design recognition method based on the neural network model described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the landscape design recognition system based on the neural network model in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0101] In one possible design, Figure 2 The landscape design recognition system based on the neural network model of the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32 .

[0102] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0103] The processing component 32 is used to: obtain landscape design data, lighting equipment data and real-time load data of the energy supply network in the target area, the landscape design data includes vegetation shading contours and artificial structure surface reflectivity, and the lighting equipment data includes lamp power distribution, beam angle coverage and light source color temperature parameters; establish an optical model based on the landscape design data and the lighting equipment data, and analyze the spatial attenuation effect of the vegetation shading contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment through the optical model; establish an energy transfer model based on the lighting equipment data and the real-time load data of the energy supply network, and calculate the energy consumption mapping relationship between the lamp power distribution and the real-time load data of the energy supply network through the energy transfer model; generate a dynamic dimming strategy in combination with the spatial attenuation effect and the energy consumption mapping relationship, couple the dynamic dimming strategy with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and input the coupling result into the neural network model to iteratively optimize the lamp power distribution, beam angle coverage and light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

[0104] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0105] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as random access memory (RAM), static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0106] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0107] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0108] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0109] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0110] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a landscape design identification method based on a neural network model.

[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A landscape design recognition method based on a neural network model, characterized in that: include: Acquire landscape design data, lighting equipment data and real-time load data of the energy supply network in the target area, wherein the landscape design data includes vegetation shading outline and artificial structure surface reflectivity, and the lighting equipment data includes lamp power distribution, beam angle coverage and light source color temperature parameters; An optical model is established based on the landscape design data and the lighting equipment data, and the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment is analyzed by the optical model; Establishing an energy transfer model based on the lighting equipment data and the real-time load data of the energy supply network, and calculating the energy consumption mapping relationship between the power distribution of the lamps and the real-time load data of the energy supply network through the energy transfer model; A dynamic dimming strategy is generated by combining the spatial attenuation effect with the energy consumption mapping relationship, and the dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, which is input into a neural network model to iteratively optimize the lamp power distribution, the beam angle coverage range and the light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

2. The method according to claim 1, characterized in that The dynamic dimming strategy is generated by combining the spatial attenuation effect with the energy consumption mapping relationship, the dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and the coupling result is input into a neural network model to iteratively optimize the lamp power distribution, the beam angle coverage range and the light source color temperature parameters through the neural network model, including: Building an objective function based on the mapping relationship between the spatial attenuation effect and the energy consumption, and generating a dynamic dimming strategy through an optimization algorithm based on the objective function; The dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, wherein the coupling result is a multi-dimensional feature vector; The multidimensional feature vector is input into a neural network model, a lighting effect prediction value is calculated by a forward propagation algorithm of the neural network model, and the lamp power distribution, beam angle coverage and light source color temperature parameters are iteratively optimized based on a preset loss function and a back propagation algorithm of the neural network model; The optimized lamp power distribution, beam angle coverage and light source color temperature parameters are output to the lighting control system to adjust the lighting equipment data in the target area in real time according to the optimized lamp power distribution, beam angle coverage and light source color temperature parameters.

3. The method according to claim 2, characterized in that The multidimensional feature vector is input into the neural network model, the lighting effect prediction value is calculated by the forward propagation algorithm of the neural network model, and the lamp power distribution, beam angle coverage and light source color temperature parameters are iteratively optimized based on a preset loss function and the back propagation algorithm of the neural network model, including: The multidimensional feature vector is standardized to obtain a preprocessed multidimensional feature vector, wherein the multidimensional features include the high-density area coordinates and dynamic change trends of the tourist distribution heat map, the time series characteristics of the ambient light intensity data, and the spatial distribution characteristics of the vegetation shading contour and the surface reflectivity of the artificial structure; Inputting the preprocessed multidimensional feature vector into a neural network model, combining the forward propagation algorithm in the neural network model, performing nonlinear transformation through the hidden layer of the neural network model, and generating a lighting effect prediction value at the output layer; Based on the difference between the lighting effect prediction value and the preset target value, the function value of the preset loss function is calculated. Based on the function value, the lamp power distribution, beam angle coverage and light source color temperature parameters are iteratively optimized and adjusted through the back propagation algorithm until the function value of the loss function converges to a preset threshold.

4. The method according to claim 3, characterized in that The preprocessed multidimensional feature vector is input into the neural network model, combined with the forward propagation algorithm in the neural network model, a nonlinear transformation is performed through the hidden layer of the neural network model, and a lighting effect prediction value is generated at the output layer, including: Designing a structure of a neural network model, wherein the structure of the neural network model includes an input layer, a hidden layer and an output layer, the number of nodes in the input layer is consistent with the dimension of the multidimensional feature vector, the hidden layer adopts a multi-layer structure, and the number of nodes in the output layer is consistent with the dimension of the lighting effect prediction value; The preprocessed multidimensional feature vector is input into the input layer, and in combination with the forward propagation algorithm in the neural network model, the multidimensional features corresponding to the preprocessed multidimensional feature vector are weighted summed in the hidden layer, and the weighted summation result is nonlinearly transformed by an activation function, and the multidimensional feature mapping result is calculated layer by layer; In the output layer, the multidimensional feature mapping results output by the last hidden layer are weighted and summed, and the lighting effect prediction value is generated through the activation function of the output layer. The lighting effect prediction value includes the light intensity, total energy consumption and visual comfort score of each location in the target area.

5. The method according to claim 1, characterized in that: The optical model is established based on the landscape design data and the lighting equipment data, and the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment is analyzed by the optical model, including: The vegetation shielding contour is digitally processed to obtain the spatial distribution characteristics and shielding intensity parameters of the vegetation, and the surface reflectivity of the artificial structure is divided into regions to generate a reflectivity distribution map; Based on the spatial distribution characteristics and shading intensity parameters of the vegetation, and the reflectivity distribution diagram, combined with the lamp power distribution, the beam angle coverage range and the light source color temperature parameters, an optical model is generated; Based on the optical model, the propagation process of the light beam emitted by the lighting device in the target area is simulated, the influence of the vegetation blocking contour and the reflectivity of the surface of the artificial structure on the light beam is calculated, and the attenuation parameter of the light beam is generated; Based on the attenuation parameters of the light beam, a spatial attenuation effect distribution diagram is generated, and the spatial attenuation effect distribution diagram is used to characterize the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting device.

6. The method according to claim 5, characterized in that Based on the optical model, the propagation process of the light beam emitted by the lighting device in the target area is simulated, the influence of the vegetation blocking outline and the surface reflectivity of the artificial structure on the light beam is calculated, and the attenuation parameters of the light beam are generated, including: Constructing a beam propagation path model according to the optical model, the lamp power distribution, the beam angle coverage range and the light source color temperature parameter, and dividing the target area into a plurality of grid units based on the beam propagation path model; In the light beam propagation path model, the attenuation effect of the vegetation shading contour on the light beam is calculated grid unit by grid unit, a vegetation shading attenuation coefficient is generated, and the light intensity value of each grid unit is updated according to the vegetation shading attenuation coefficient; Identify the grid cells that intersect with the surface of the artificial structure in the light beam propagation path model, calculate the reflection path and reflection intensity of the light beam on the surface of the artificial structure, and update the light intensity value of the grid cells covered by the reflection path according to the reflection intensity; According to the light intensity value of each grid cell, a beam attenuation parameter of each grid cell is generated.

7. The method according to claim 6, characterized in that In the light beam propagation path model, the attenuation effect of the vegetation occlusion contour on the light beam is calculated grid by grid unit, a vegetation occlusion attenuation coefficient is generated, and the light intensity value of each grid unit is updated according to the vegetation occlusion attenuation coefficient, including: Extracting the height, density and distribution range parameters of vegetation from the vegetation occlusion contour, and mapping the height, density and distribution range parameters of vegetation to the grid cells of the target area; In the beam propagation path model, for each grid unit, according to the vegetation shielding intensity value, the mapping data corresponding to the vegetation height, density and distribution range parameters, the attenuation coefficient of the beam after penetrating the vegetation is calculated to generate the vegetation shielding attenuation coefficient of each grid unit; Combined with the scattering effect of vegetation on the light beam, the scattering path of the light beam after penetrating the vegetation is simulated, the propagation direction and intensity distribution of the scattered light beam are calculated, and the light intensity value of the grid unit covered by the scattering path is updated according to the propagation direction and the intensity distribution; The vegetation shading attenuation coefficient of each grid unit and the light intensity value of the grid unit covered by the scattering path are applied to the light beam propagation path model to update the light intensity value of each grid unit through the light beam propagation path model.

8. A landscape design recognition system based on a neural network model, characterized in that: include: An acquisition module is used to acquire landscape design data, lighting equipment data and real-time load data of the energy supply network in the target area, wherein the landscape design data includes vegetation shading contours and artificial structure surface reflectivity, and the lighting equipment data includes lamp power distribution, beam angle coverage and light source color temperature parameters; Establishing an analysis module for establishing an optical model based on the landscape design data and the lighting equipment data, and analyzing the spatial attenuation effect of the vegetation shielding contour and the artificial structure surface reflectivity on the light beam emitted by the lighting equipment through the optical model; Establishing a calculation module, for establishing an energy transfer model based on the lighting equipment data and the real-time load data of the energy supply network, and calculating the energy consumption mapping relationship between the power distribution of the lamps and the real-time load data of the energy supply network through the energy transfer model; A coupling module is generated to generate a dynamic dimming strategy by combining the spatial attenuation effect with the energy consumption mapping relationship, and the dynamic dimming strategy is coupled with the real-time collected tourist distribution heat map and ambient light intensity data to obtain a coupling result, and the coupling result is input into a neural network model to iteratively optimize the lamp power distribution, the beam angle coverage range and the light source color temperature parameters through the neural network model, so as to achieve dynamic optimization of landscape lighting effects and minimization of energy consumption, while improving the visual experience and comfort of tourists.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a landscape design recognition method based on a neural network model as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a landscape design recognition method based on a neural network model as described in any one of claims 1 to 7 is implemented.

Images