Family planting assembly and control system based on fourth-generation residence

Abstract

The invention provides a home planting assembly and control system based on a fourth-generation residence, and relates to the technical field of intelligent gardening planting, the home planting assembly comprises a balcony plane, a planting area and a vine climbing area, a cushion table is placed at the bottom of the inner back of the balcony plane, and square side piles are clamped to one side and the middle of the top of the cushion table; a bearing plate is connected between the side piles on the two sides in a mortise and tenon joint mode, embedded blocks are embedded in the two sides of the bearing plate, clamping openings are formed in the side edges of the embedded blocks, and the clamping openings are matched with the side piles. Through organic combination of the data acquisition module, the environment regulation and control module, the irrigation management module, the illumination optimization module, the pest control module, the remote monitoring module and the power supply support module, the problems of single function, lack of systematicness, resource waste, low management efficiency and the like in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent gardening planting, and in particular to a household planting component and a control system based on a fourth-generation house. Background Art

[0002] In terms of balcony functional requirements, according to market research, the order of the number of people who need it is planting, reading, drinking tea, drying clothes, fitness, and meeting guests, while the actual functional use of balconies is drying clothes, planting, storing sundries, reading, drinking tea, and meeting guests. It can be seen that although planting is one of the core needs of consumers, the functions of most balconies are still mainly drying and storing sundries, and the planting function remains at a relatively basic level, which is difficult to meet consumers' needs for refined, technological and intelligent planting. Especially in the urban balcony environment, due to the limitations of space, environmental conditions, time and energy, users have a poor experience in realizing pastoral planting functions.

[0003] The fourth generation of housing, also known as three-dimensional garden ecological housing or urban forest garden building, is a derivative of green building. Its core is that every household has a garden and every family has a courtyard, returning to the traditional Chinese living style and life scene.

[0004] However, with gardens and courtyards in every household, how to use and build them will face the following problems in actual creation: 1. First, these devices have single functions and lack systematic design. It is difficult to effectively integrate the environmental control and management functions such as lighting, humidity, and temperature related to planting. The existing planting products on the market cannot meet the diverse planting needs. The operation is complicated, difficult to take care of, and difficult to maintain; 2. Secondly, most of the current intelligent planting equipment can only realize the detection or feedback of a single condition, and cannot dynamically adjust various conditions according to environmental changes and plant growth stages. The planting effect still depends on the user's experience and operation; 3. In addition, the existing irrigation and pest control devices usually consume a lot of water and lack precise control capabilities, resulting in serious waste of resources. At the same time, the remote monitoring capabilities of these devices are limited, and users need to frequently manage manually, making it difficult to achieve a fully automated and intelligent planting experience. The most critical thing is that the current technology lacks a multi-functional integrated design and fails to make full use of the limited space of the balcony, resulting in the difficulty of compatibility between the planting function and other functions, thereby limiting the overall utilization and comfort of the balcony.

[0005] Therefore, home planting components and control systems based on the fourth-generation residence are needed to solve the above problems. Summary of the invention

[0006] Technical issues solved In view of the deficiencies of the prior art, the present invention provides a home planting component and control system based on the fourth-generation house, which solves the problems mentioned in the above background technology.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a home planting component and control system based on the fourth-generation residence, including a balcony plane, a planting area and a climbing vine area, a pad is placed at the bottom of the back side of the balcony plane, one side and the middle of the top of the pad are clamped with side piles, the shape of the side piles is square, and a support plate is connected by mortise and tenon joints between the side piles on both sides, both sides of the support plate are embedded with embedded blocks, the side edges of the embedded blocks are provided with card interfaces, the card interfaces and the side piles are adapted to each other, a back plate is clamped on the back side of the top of the pad, the planting area is composed of a back plate and side piles on both sides, a total of five groups of support plates are installed inside the planting area, a vine side board is clamped on the other side of the top of the pad, the shape of the vine side board is L-shaped, the climbing area is composed of side piles in the middle and vine side boards, and the back side of the climbing side board is provided with openings.

[0009] Preferably, the middle part of the bottom end of the supporting board is snap-connected with a connecting bottom block, a mosquito repellent nozzle is provided on one side of the bottom end of the connecting bottom block, a shower head is provided in the middle part of the bottom end of the connecting bottom block, a fill light is installed on the other side of the bottom end of the connecting bottom block, a drain pipe is provided on the side close to the pad in the balcony plane, a suction head is installed on the top of the drain pipe, the suction head is bonded to the wall, the bottom of the drain pipe is connected to the drain outlet of the balcony plane, one side of the drain pipe is connected to a drain manifold, there are five groups of drain manifolds in total, the drain manifolds are all located at the bottom of the supporting board, and a pipe head is provided on one side of the top of the drain manifold.

[0010] Preferably, a drain hole is provided on one side of the bottom of the supporting board, a water supply hole is provided on the other side of the bottom of the supporting board, the end of the pipe head passes through the drain hole and is connected to the bottom of the potted plant on the supporting board, a cover plate is clamped on the front of the pad, a mosquito repellent device is placed on one side of the pad, a storage box is placed on the other side of the pad, a blower fan is installed on one side of the top of the balcony plane, a monitoring device is installed on the other side of the top of the balcony plane, and a data collector is installed on the balcony plane near the front of the monitoring device.

[0011] Preferably, a control system is provided in the data collector, and the control system includes a data acquisition module, an environment control module, an irrigation management module, a lighting optimization module, a pest control module, a remote monitoring module and a power support module. The data acquisition module collects real-time environmental data of the planting area through temperature sensors, humidity sensors and light sensors. The environment control module adopts the intelligent temperature fluid optimization algorithm ITFOA to adjust the temperature of the planting area. The irrigation management module controls the operation of the water pump in the storage tank based on the dynamic multi-objective irrigation control algorithm DMO-ICA, and accurately irrigates the potted plants through the sprinkler head. The lighting optimization module adopts the multi-dimensional dynamic lighting optimization algorithm MDL-OA to dynamically adjust the light intensity and duration of the fill light, thereby providing suitable lighting conditions and promoting plant growth.

[0012] The formula of Intelligent Temperature Fluid Optimization Algorithm (ITFOA) is:

[0013] Parameter Description: : The optimal temperature of the environment, output results, used to adjust the fan speed or start the cooling system; Controlled volume of planting area; Thermal conductivity of air, used to calculate heat conduction; The Laplace operator of the temperature gradient represents the spatial distribution of heat transfer diffusion; The density of air, which describes the distribution of mass per unit volume; The specific heat capacity of air indicates the ability of air per unit mass to absorb heat; Convection term, describing the effect of air flow on the temperature field, where is the velocity vector field; The temperature regulation coefficient determines the importance of external control; : Weight factor, which is related to the accuracy of each sensor data; The temperature difference measured by each sensor indicates how much the current temperature deviates from the target temperature.

[0014] Preferably, the pest control module adopts a multi-mode pest barrier generation algorithm MM-PGA, transports the mosquito repellent liquid to the mosquito repellent nozzle through an efficient water pump in the mosquito repellent device, uses a generative adversarial network GAN to simulate pest invasion behavior, combines a gradient boosting decision tree GBDT to predict pest risks, and optimizes the spraying range and concentration of the liquid through a multi-objective optimization algorithm to achieve targeted pest control and protect the healthy growth of plants.

[0015] Preferably, the remote monitoring module collects image data of the planting area in real time through a monitoring device, adopts a dynamic multimodal visual analysis algorithm DMVA to identify plant status, uses a convolutional neural network CNN to extract leaf morphological features, combines an attention mechanism model to analyze key areas, and generates treatment suggestions for abnormal conditions such as yellowing leaves through a Monte Carlo tree search MCTS; users can remotely control fill lights, sprinkler heads and other equipment through a mobile phone to adjust the planting environment.

[0016] Preferably, the power support module includes a power supply device, which provides power support for the control system and all electronic devices; the power supply device has overvoltage protection, overcurrent protection, waterproofing and leakage protection functions to ensure the safe operation of the planting components; the power support module is also equipped with a multi-module joint self-learning optimization algorithm MM-JSLA, which models the power usage pattern through the variational autoencoder VAE, and combines the adaptive neural fuzzy inference system ANFIS to optimize the power distribution strategy to ensure system stability and energy saving.

[0017] Preferably, the lighting optimization module utilizes the multi-dimensional dynamic lighting optimization algorithm MDL-OA, optimizes the balcony lighting conditions through the particle swarm optimization algorithm PSO and the adaptive genetic algorithm AGA, and combines the time series prediction algorithm LSTM to analyze the historical change trend of the light intensity, and adjusts the luminous power, spectral distribution and irradiation time of the fill light 26 in real time, so that the plants are under suitable lighting conditions and the photosynthesis efficiency is improved.

[0018] Preferably, the data acquisition module works in coordination with the environment control module, the irrigation management module and the pest control module through an efficient multi-source data fusion and prediction algorithm HMD-FPA. The efficient multi-source data fusion and prediction algorithm extracts features of multi-dimensional data such as temperature, humidity and light based on a multi-scale deep neural network MS-DNN, uses a conditional random field CRF to analyze the time series dependency between data, and dynamically adjusts the data fusion strategy through a quantum adaptive neural network QANN to provide accurate environmental parameter support and prediction results for system operation. The CRF model constructs a conditional probability model between data to mine the mutual influence of data such as temperature, humidity and light on the time axis, such as humidity usually decreases after high temperature continues for a period of time, and dynamically adjusts the data fusion strategy through a quantum adaptive neural network QANN. The QANN model adaptively adjusts the weight distribution of different data in the fusion process according to the real-time changes in the data and the system operation status, so as to provide accurate environmental parameter support and prediction results for system operation. For example, when predicting pest risks, more emphasis is placed on the weight adjustment of the impact of recent changes in temperature and humidity data on the pest model.

[0019] Beneficial Effects

[0020] The present invention provides a home planting component and control system based on the fourth generation house. It has the following beneficial effects: 1. The present invention proposes an intelligent and multifunctional balcony planting system, which solves the problems of single function, lack of systematicity, waste of resources and low management efficiency in the prior art through the organic combination of data acquisition module, environmental control module, irrigation management module, lighting optimization module, pest control module, remote monitoring module and power support module.

[0021] 2. The data acquisition module of the present invention realizes the real-time collection of environmental parameters such as temperature, humidity, and light intensity. Combined with multi-dimensional intelligent algorithms, it can dynamically adjust irrigation, lighting and environmental control strategies to provide more accurate plant planting conditions. The environmental control module uses intelligent fans and electric heating devices to realize automatic adjustment of temperature and humidity in the planting area without human intervention; the irrigation management module adopts high-efficiency water pumps and intelligent management and control systems to ensure the water required for normal plant growth while greatly reducing water resource waste; the lighting optimization module further improves the utilization rate of light energy through LED fill lights with adjustable spectrum and intensity to meet the needs of plants at different growth stages; the pest control module realizes low-dose, high-efficiency insect repellent function, reduces the use of chemical agents, and ensures green planting of plants; the remote monitoring module combines high-definition cameras and mobile applications to provide users with real-time monitoring and remote operation functions, greatly improving the convenience of planting experience; the stable power supply and power-off protection design of the power support module ensure that the system can operate stably under various conditions.

[0022] 3. The present invention makes the balcony planting function compatible with other functions such as reading, tea drinking, fitness, etc. through modular and integrated design, effectively improving the space utilization and overall comfort of the balcony. The overall system has the characteristics of diverse functions, high integration and high resource utilization, providing users with a new pastoral planting experience and meeting the needs of modern urban people for a balance between nature and life. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is the overall structure diagram of the present invention; Figure 2 It is a plan view schematic diagram of the present invention; Figure 3 It is the internal main structure diagram of the present invention; Figure 4 This is a disassembled diagram of the internal main structure of the present invention; Figure 5 It is a structural diagram of a support plate of the present invention; Figure 6 This is a diagram showing the structure of the control system of the present invention.

[0024] Legend: 1. Balcony plan; 2. Blowing fan; 3. Data collector; 4. Monitoring device; 5. Pad; 6. Side piles; 7. Climbing area; 8. Support board; 9. Embossed block; 10. Card interface; 11. Connecting bottom block; 12. Drain hole; 13. Water supply hole; 14. Drain branch; 15. Pipe head; 16. Suction head; 17. Drain main pipe; 18. Cover plate; 19. Mosquito repellent device; 20. Storage box; 21. Back plate; 22. Planting area; 23. Opening; 24. Mosquito repellent nozzle; 25. Sprinkler head; 26. Fill light; 27. Climbing side board. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Specific embodiment 1

[0027] like Figure 1-6 As shown, a household planting component and control system based on the fourth generation of housing includes a balcony plane 1, a planting area 22 and a climbing area 7. A pad 5 is placed at the bottom of the back of the balcony plane 1. Side piles 6 are clamped on one side and the middle of the top of the pad 5. The shape of the side piles 6 is square. A support plate 8 is connected between the side piles 6 on both sides by mortise and tenon joints. Both sides of the support plate 8 are embedded with embedded blocks 9. The side edges of the embedded blocks 9 are provided with card interfaces 10. The card interfaces 10 and the side piles 6 are adapted to each other. A back plate 21 is clamped on the back of the top of the pad 5. The planting area 22 is composed of the back plate 21 and the two The balcony is composed of side piles 6 on the side, and five groups of supporting boards 8 are installed inside the planting area 22. A vine side board 27 is clamped on the other side of the top of the pad 5. The shape of the vine side board 27 is L-shaped. The climbing area 7 is composed of a middle side pile 6 and a climbing side board 27. An opening 23 is provided on the back of the climbing side board 27. The entire planting assembly is placed on the inside of the balcony, and intelligent planting can be realized. Each part of the planting assembly can be disassembled and spliced, which is very portable. If the connection between the side pile 6 and the supporting board 8 needs to be more stable, screws can be screwed into the connection.

[0028] The middle part of the bottom end of the supporting board 8 is snap-connected with the connecting bottom block 11, a mosquito repellent nozzle 24 is provided on one side of the bottom end of the connecting bottom block 11, a shower head 25 is provided in the middle part of the bottom end of the connecting bottom block 11, and a fill light 26 is installed on the other side of the bottom end of the connecting bottom block 11. A drainage pipe 17 is provided on one side of the balcony plane 1 close to the pad 5, and a suction head 16 is installed on the top of the drainage pipe 17. The suction head 16 is bonded to the wall, and the bottom of the drainage pipe 17 is connected to the drain of the balcony plane 1, and one side of the drainage pipe 17 is connected to the drainage manifold 14. There are five groups of drainage manifolds 14, which are all located at the bottom of the supporting board 8, and a pipe head 15 is provided on one side of the top of the drainage manifold 14. The structures of the five layers of supporting boards 8 in the planting area 22 are similar. The mosquito repellent nozzle 24, the shower head 25 and the fill light 26 at the bottom of the supporting board 8 will repel mosquitoes, spray water and fill light for the plants on the bottom layer of the supporting board 8.

[0029] A drainage hole 12 is provided on one side of the bottom of the supporting plate 8, and a water supply hole 13 is provided on the other side of the bottom of the supporting plate 8. The end of the pipe head 15 passes through the drainage hole 12 and is connected to the bottom of the potted plant on the supporting plate 8. A cover plate 18 is clamped on the front of the pad 5. A mosquito repellent device 19 is placed on one side of the pad 5, and a storage box 20 is placed on the other side of the pad 5. A blower fan 2 is installed on one side of the top of the balcony plane 1, and a monitoring device 4 is installed on the other side of the top of the balcony plane 1. A data collector 3 is installed near the front of the monitoring device 4 in the balcony plane 1. The potted plants on the supporting plate 8 are drained from the drainage hole 12 through the pipe head 15 and the drainage manifold 14 to the drainage main 17, and then flow into the sewer from the drainage main 17. The mosquito repellent liquid is stored in the mosquito repellent device 19, which will be connected to the mosquito repellent nozzle 24 through a pipeline passing through the bottom block 11. A high-efficiency water pump is used for suction. Similarly, the storage box 20 stores clean water or nutrient solution, which is connected to the bottom block 11 and the spray head 25 through a pipe. The spray head 25 is retractable and can be adjusted as needed. The fill light 26 can adjust the light intensity according to actual conditions. At the same time, the fan 2 equipped in the balcony plane 1 will cool down the plants. The monitoring device 4 can remotely check the situation through a mobile phone. If the leaves of the plants are found to be yellow, the fill light 26 is remotely controlled to turn on. It should be noted that the entire planting component will be equipped with a power supply device to provide separate power supply for all electronic devices. It can be placed on a pad 5 and can also be installed on the top of the balcony. A temperature sensor is configured in the planting area 22, and a humidity sensor can be placed in each group of potted plants. The data collector 3 will collect these two sets of data, identify and calculate, and then control the addition of water and the start of the fan.

[0030] After the planting assembly is installed on the balcony plane 1, each component works together to achieve intelligent planting. In terms of lighting, the fill light 26 can be adjusted according to the lighting requirements of different plants and the actual lighting conditions of the balcony. When the data collector 3 receives the data collected by the temperature sensor in the planting area 22 and the humidity sensor in the potted plant, and determines that the light intensity is insufficient, it will send a signal to the fill light 26, and the fill light 26 will adjust the luminous power and lighting duration according to the signal to provide suitable lighting conditions for the plants and promote photosynthesis.

[0031] For the irrigation function, when the humidity sensor detects that the soil humidity in the potted plant is lower than the preset suitable humidity range, the data collector 3 will start the water pump in the storage box 20. The water pump transports the clean water or nutrient solution in the storage box 20 to the sprinkler head 25 connected to the bottom block 11 through a pipeline. The sprinkler head 25 accurately sprinkles water or nutrient solution on the potted soil according to the set spray mode such as uniform spray, drip irrigation, etc. and the retractable structural characteristics, ensuring that the plant roots can fully absorb water and nutrients. Excess irrigation water will eventually flow into the sewer main 17 through the drainage hole 12 at the bottom of the support plate 8, the pipe head 15, and the drainage branch 14 and be discharged to the sewer to prevent water accumulation from causing plant root rot.

[0032] In terms of temperature regulation, when the temperature sensor detects that the ambient temperature of the planting area is too high, the data collector 3 will trigger the fan 2 on the top of the balcony plane 1 to start. The fan 2 accelerates the air flow, takes away the heat around the plants, lowers the local ambient temperature, and keeps the plants in a relatively suitable growth temperature range, thereby avoiding high temperature from inhibiting or damaging plant growth.

[0033] For pest control, when the system starts the mosquito repellent device 19 according to a preset time cycle or according to a manual instruction of the user, the mosquito repellent liquid stored in the mosquito repellent device 19 will be transported to the mosquito repellent nozzle 24 connected to the bottom block 11 through a pipeline under the action of a high-efficiency water pump. The mosquito repellent nozzle 24 atomizes the mosquito repellent liquid and sprays it around the planting area 22 to form a protective barrier, drive away mosquitoes and other pests, protect plants from pests, and ensure the healthy growth of plants.

[0034] The monitoring device 4 takes images of the planting area in real time and transmits the image data to the user's mobile phone or the home intelligent central control system. The user can check the growth status of the plant at any time through the mobile phone or the central control system, such as leaf color, shape, plant height, etc. Once an abnormal situation such as yellowing leaves is found, the user can remotely control the relevant equipment through the mobile phone, such as manually turning on the fill light 26 to increase the lighting duration or intensity, or adjusting the irrigation water volume and frequency, etc., to timely intervene and optimize the plant growth environment to ensure that the plant can continue to grow healthily.

[0035] The whole system is powered by a specially configured power supply device that provides stable power support, which can ensure the normal operation of all electronic devices, whether placed in the pad 5 or on the top of the balcony. At the same time, the overvoltage and overcurrent protection functions of the power supply device, as well as the waterproofing, insulation treatment and leakage protection switch settings of the electrical circuits, ensure the safety and reliability of the entire planting component and control system during use, avoid safety accidents caused by electrical failures, and create a safe operating environment for family planting activities. Specific embodiment 2

[0037] like Figure 1-6As shown, in the present invention, a control system is provided in the data collector 3, and the control system includes a data acquisition module, an environment control module, an irrigation management module, a lighting optimization module, a pest control module, a remote monitoring module and a power supply support module. The data acquisition module collects the environmental data of the planting area in real time through the temperature sensor, the humidity sensor and the light sensor. The environment control module adopts the intelligent temperature fluid optimization algorithm (ITFOA) to adjust the temperature of the planting area. The irrigation management module controls the operation of the water pump in the storage box 20 based on the dynamic multi-objective irrigation control algorithm (DMO-ICA), and accurately irrigates the potted plants through the sprinkler head 25. The lighting optimization module adopts the multi-dimensional dynamic lighting optimization algorithm (MDL-OA) to dynamically adjust the light intensity and duration of the fill light 26, so as to provide suitable lighting conditions and promote plant growth. It should be noted that the frequency of data collection can be flexibly set in the system, ranging from once every 10 minutes to once every hour, to meet the needs of data accuracy at different plant growth stages. The environmental control module uses the intelligent temperature fluid optimization algorithm (ITFOA) to adjust the temperature of the planting area. The algorithm builds a temperature field model based on the spatial layout of the planting area and the air flow characteristics. By simulating the heat conduction and convection process, it accurately calculates the fan speed and angle adjustment strategy to achieve a fast and uniform temperature regulation effect, with an error control within ±1°C. The irrigation management module controls the operation of the water pump in the storage tank 20 based on the dynamic multi-objective irrigation control algorithm (DMO-ICA), and accurately irrigates the potted plants through the sprinkler head 25. The algorithm takes into account soil moisture, plant water demand, and weather forecast information (such as rainfall and evaporation forecast data). The data can be connected through the network. The module optimizes the irrigation water volume and time interval in real time based on multiple factors such as water supply, water quality, and irrigation water intake. For example, it increases the irrigation frequency on sunny days with high temperatures, and reduces or suspends irrigation on rainy days, so as to achieve the dual goals of saving water and ensuring good plant growth. The lighting optimization module adopts a multi-dimensional dynamic lighting optimization algorithm (MDL-OA) to dynamically adjust the light intensity and duration of the fill light 26, so as to provide suitable lighting conditions and promote plant growth. The algorithm is based on the plant species database (which stores the light requirement curves of common household plants) and real-time light sensor data. By analyzing the differences in light intensity, spectral composition and photosynthetic active radiation requirements of plants in different time periods, the algorithm uses a linear programming method to determine the optimal start-up combination of the fill light and the light parameter adjustment plan, so that plants receive artificial light supplements close to the natural optimal light conditions within a day.

[0038] The pest control module adopts a multi-mode pest barrier generation algorithm (MM-PGA), which transports the mosquito repellent liquid to the mosquito repellent nozzle 24 through an efficient water pump in the mosquito repellent device 19, uses a generative adversarial network (GAN) to simulate pest invasion behavior, combines a gradient boosting decision tree (GBDT) to predict pest risks, and optimizes the spraying range and concentration of the liquid through a multi-objective optimization algorithm to achieve targeted pest control and protect the healthy growth of plants.

[0039] When using generative adversarial networks (GANs) to simulate pest invasion behavior, the GAN model is trained based on a large amount of historical pest occurrence data and environmental factor data (such as temperature, humidity and pest correlation data) to generate realistic pest simulation scenarios, and combined with the gradient boosting decision tree (GBDT) to predict pest risks. The GBDT model accurately judges the probability and severity of pest occurrence under different time periods and conditions by analyzing multivariate factors such as plant species, seasons, and surrounding environmental ecology, and optimizes the spraying range and concentration of the liquid medicine through a multi-objective optimization algorithm. The multi-objective optimization algorithm takes minimizing the amount of liquid medicine used, maximizing the pest control effect, and minimizing the negative impact on the environment and plants as the objective function, and uses a genetic algorithm to solve the optimal spraying parameter combination to achieve targeted pest control and protect the healthy growth of plants.

[0040] The remote monitoring module collects real-time image data of the planting area through the monitoring device 4, adopts the dynamic multimodal visual analysis algorithm (DMVA) to identify the plant status, uses the convolutional neural network (CNN) to extract the leaf morphological characteristics, combines the attention mechanism model to analyze the key areas, and generates processing suggestions for abnormal conditions (such as yellowing leaves) through the Monte Carlo tree search (MCTS); users can remotely control the fill light 26, sprinkler head 25 and other equipment through the mobile phone to adjust the planting environment. When using a convolutional neural network (CNN) to extract leaf morphological features, the CNN model uses a deep residual network structure, which can effectively extract subtle features such as leaf texture, color, and shape, and is combined with an attention mechanism model to analyze key areas. The attention mechanism model learns the importance weights of different plant parts in judging the growth status, focuses on the leaves, stems and other areas that are most critical to judging the health status of plants, and generates processing suggestions for abnormal conditions (such as yellowing leaves) through Monte Carlo tree search (MCTS). When generating processing suggestions, the MCTS model comprehensively considers factors such as the current plant status, historical processing records, and environmental conditions, and selects the optimal processing strategy by simulating the changes in plant growth after different processing operations (such as increasing light, adjusting irrigation, etc.); users can remotely control devices such as fill lights 26 and sprinkler heads 25 through mobile phones to adjust the planting environment. The mobile phone application provides an intuitive operation interface. Users can start preset plant growth modes (such as vegetable growth modes, flower growth modes, etc.) with one click, or manually fine-tune the parameters of each device.

[0041] The power supply support module includes a power supply device, which provides power support for the control system and all electronic devices; the power supply device has overvoltage protection, overcurrent protection, waterproof treatment and leakage protection functions to ensure the safe operation of the implant component; the power supply support module is also equipped with a multi-module joint self-learning optimization algorithm (MM-JSLA), which models the power usage mode through a variational autoencoder (VAE), and optimizes the power distribution strategy in combination with an adaptive neural fuzzy inference system (ANFIS) to ensure system stability and energy saving. The power supply device has overvoltage protection, overcurrent protection, waterproof treatment and leakage protection functions. The overvoltage protection uses a combination circuit of a varistor and a transient suppression diode, which can quickly conduct shunt when the voltage instantly rises to more than 1.2 times the rated value. The overcurrent protection uses a self-recovery fuse, which automatically blows when the current exceeds 1.5 times the rated value and automatically recovers after the fault is eliminated. The waterproof treatment uses a special sealant and waterproof shell design to ensure the normal operation of the power supply device in a humid environment. The leakage protection uses a high-precision leakage protector, which cuts off the power within 0.1 seconds when the leakage current exceeds 30mA, ensuring the safe operation of the implant component. The power support module is also equipped with a multi-module joint self-learning optimization algorithm (MM-JSLA), which models the power usage pattern through a variational autoencoder (VAE). The VAE model maps the power usage data to a low-dimensional latent space, extracts the main features and changing trends of the data, and optimizes the power distribution strategy in combination with an adaptive neural-fuzzy inference system (ANFIS). The ANFIS system dynamically adjusts the supply voltage and current of each device according to the operating priority, real-time power demand and power supply status of different devices to ensure system stability and energy saving. For example, when the light demand is low, the supply voltage of the fill light can be appropriately reduced, and the power supply of the water pump can be cut off during the non-working period.

[0042] The lighting optimization module uses the multi-dimensional dynamic lighting optimization algorithm (MDL-OA) to optimize the balcony lighting conditions through the particle swarm optimization algorithm (PSO) and the adaptive genetic algorithm (AGA). It combines the time series prediction algorithm (LSTM) to analyze the historical change trend of light intensity, and adjusts the luminous power, spectral distribution and irradiation time of the fill light 26 in real time to put the plants in suitable lighting conditions and improve the photosynthesis efficiency. The PSO algorithm is used to quickly search for the approximate optimal solution of lighting parameters. By simulating the foraging behavior of bird flocks, multiple particles search in parallel in the parameter space such as light intensity and spectral distribution. The AGA algorithm further optimizes the search results of the PSO algorithm, improves the global search ability and convergence speed of the algorithm by adaptively adjusting the genetic operators (such as crossover probability and mutation probability), and combines the time series prediction algorithm (LSTM) to analyze the historical change trend of light intensity. The LSTM model predicts the light changes in the next day based on the light intensity data of the past week, and adjusts the luminous power, spectral distribution and irradiation time of the fill light 26 in real time to put the plants in suitable lighting conditions and improve the photosynthesis efficiency. For example, when the light is weak in the morning and evening, the red spectrum component of the fill light should be appropriately increased to promote the initiation of plant photosynthesis. When the light is too strong at noon, the power of the fill light should be reduced and the spectrum should be adjusted to shift toward the blue light direction to avoid plant light inhibition.

[0043] The data acquisition module works with the environmental control module, irrigation management module and pest control module through the efficient multi-source data fusion and prediction algorithm (HMD-FPA); the efficient multi-source data fusion and prediction algorithm extracts features from multi-dimensional data such as temperature, humidity, and light based on the multi-scale deep neural network (MS-DNN), uses the conditional random field (CRF) to analyze the time series dependency between data, and dynamically adjusts the data fusion strategy through the quantum adaptive neural network (QANN) to provide accurate environmental parameter support and prediction results for system operation. The CRF model constructs a conditional probability model between data to explore the mutual influence of data such as temperature, humidity, and light on the time axis. For example, humidity usually decreases after high temperature continues for a period of time, and dynamically adjusts the data fusion strategy through the quantum adaptive neural network (QANN). The QANN model adaptively adjusts the weight distribution of different data in the fusion process according to the real-time changes in data and the operating status of the system, providing accurate environmental parameter support and prediction results for system operation. For example, when predicting pest risks, it focuses more on the weight adjustment of the recent change trend of temperature and humidity data on the pest model. Specific embodiment three: like Figure 1-6 As shown, the key algorithms mentioned in Example 1 are analyzed in detail below: The formula of Intelligent Temperature Fluid Optimization Algorithm (ITFOA) is:

[0045] Parameter Description: : The optimal temperature of the environment, output results, used to adjust the fan speed or start the cooling system; Controlled volume of planting area; Thermal conductivity of air, used to calculate heat conduction; The Laplace operator of the temperature gradient represents the spatial distribution of heat transfer diffusion; The density of air, which describes the distribution of mass per unit volume; The specific heat capacity of air indicates the ability of air per unit mass to absorb heat; Convection term, describing the effect of air flow on the temperature field, where is the velocity vector field; The temperature regulation coefficient determines the importance of external control; : Weight factor, which is related to the accuracy of each sensor data; The temperature difference measured by each sensor indicates how much the current temperature deviates from the target temperature.

[0046] This formula achieves precise optimization of the temperature field in the planting area by solving the heat transfer equation of fluid dynamics and combining it with multi-sensor data fusion (the second term is weighted summation). The first term calculates the overall temperature distribution in the area, and the second term introduces the temperature difference measured at each point to comprehensively determine the target control value.

[0047] The dynamic multi-objective irrigation control algorithm (DMO-ICA) formula is as follows:

[0048] Parameter Description: irrigation amount (variable); Time step, used to describe the real-time control process; : weight coefficients, balancing the optimization importance of soil moisture and irrigation cost respectively; :Current time Next The moisture content of the potting soil; Target moisture value of soil, the optimal moisture range for plant growth; :No. Irrigation water volume per sprinkler head; Water penetration area; :No. The water retention capacity coefficient of the potting soil indicates the efficiency of soil water penetration; :No. Evaporation loss of a potted plant.

[0049] In this formula group, the first formula is used as the objective function to balance soil moisture deviation and irrigation water consumption. The second formula is the water balance equation, which dynamically updates the soil moisture status. Through optimization and solution, the irrigation mode can achieve precise water supply according to humidity requirements.

[0050] The multi-mode pest barrier generation algorithm (MM-PGA) algorithm is as follows:

[0051] Parameter Description: The effectiveness index of the mosquito repellent spraying area is used to control the spraying amount and range; The mosquito repellent strength coefficient of the liquid medicine; Probability of the liquid medicine driving away target pests Environmental diffusion coefficient, which indicates the diffusion rate of the liquid during spraying; The distance between the sprinkler head and the target area; The influencing factors of each pest behavior model in the Generative Adversarial Network (GAN); The loss attenuation coefficient is used to describe the effect of distance on the repelling effect; Nozzle and Pest Model The distance of samples.

[0052] The first term of the formula combines the environment and the characteristics of the liquid medicine to calculate the basic mosquito repellent effect, and the second term generates a variety of pest behavior patterns through GAN to predict the range of their optimal protective barrier and spraying concentration.

[0053] The formula of dynamic multimodal visual analysis algorithm (DMVA) is as follows:

[0054] Parameter Description: Plant abnormality score; Number of data samples (number of image frames); : Weight factor, related to sample quality; : Classification model prediction function, output abnormal probability, where are model parameters; The feature vector of the current image sample is extracted by CNN; CNN Convolutional neural network from images Extract global features from : Attention mechanism module, used to strengthen key area features; Regional features of the image.

[0055] The algorithm extracts global features of plant images through CNN, combines the attention mechanism to strengthen key area information, uses a classification model to predict abnormal conditions, and outputs a score to determine whether the plant needs intervention.

[0056] The formula of multi-module joint self-learning optimization algorithm (MM-JSLA) is as follows

[0057] Parameter Description: Optimal power distribution vector; : The actual power requirement of the current module; : Power demand based on VAE prediction; : Regularization weight, used to balance error and distribution smoothness; The power distribution matrix represents the collaborative relationship between modules.

[0058] VAE predicts module power demand, and the optimization objective ensures power stability by minimizing prediction error and allocation smoothness.

[0059] The formula of efficient multi-source data fusion and prediction algorithm (HMD-FPA) is as follows:

[0060] Parameter Description: Current time The prediction results (environmental parameters); Multi-source data samples ; : Feature weight; :Multi-scale feature extraction function, implemented by MS-DNN; Bias term, used to correct the prediction results.

[0061] The algorithm extracts multi-source data features through MS-DNN and uses CRF to model time series dependencies to achieve high-precision prediction. Specific embodiment four: like Figure 1-6 As shown, the following is a description of the specific application logic steps of each module and algorithm in the home planting component and control system based on the fourth-generation residential building: The Intelligent Temperature Fluid Optimization Algorithm (ITFOA) is applied in the environmental control module to dynamically adjust the temperature and humidity of the planting area and optimize the plant growth environment through the air flow and temperature control system.

[0063] Specific steps: Environmental data collection: Temperature and humidity sensors collect current environmental data and upload the data to the control system.

[0064] Temperature and humidity status assessment: The system compares the actual data with the set target range to determine whether adjustment is needed.

[0065] Control strategy generation: Based on environmental data and flow optimization algorithms, an adjustment strategy for air flow is generated, such as controlling the fan speed or turning on the heating device.

[0066] To perform air flow control: Fans and heaters are used to control and optimize air circulation and temperature and humidity distribution.

[0067] Feedback and self-learning: By real-time monitoring of the regulation effect, the next regulation strategy can be optimized.

[0068] The dynamic multi-objective irrigation control algorithm (DMO-ICA) is applied in the irrigation management module to accurately calculate the irrigation amount and frequency according to plant growth requirements and soil moisture, thereby achieving water-saving and efficient irrigation.

[0069] Specific steps: Soil moisture collection: Moisture sensors are used to monitor soil moisture content and transmit data to the control system.

[0070] Analysis of plant water requirements: Calculate the current water requirement based on the plant type, growth stage and environmental conditions.

[0071] Irrigation strategy optimization: The system generates irrigation strategies, including irrigation duration and irrigation method (drip irrigation, sprinkler, etc.).

[0072] To perform irrigation: Start irrigation equipment according to the strategy to accurately supply water to the root area of ​​​​the plants and avoid wasting water resources.

[0073] Effect monitoring and adjustment: Monitor irrigation results in real time and automatically adjust irrigation strategies if humidity exceeds the target range.

[0074] The multi-mode pest barrier generation algorithm (MM-PGA) is applied in the pest control module. By monitoring and analyzing the distribution of pest activities, it dynamically generates mosquito repellent protection barriers and effectively reduces pest infestation.

[0075] Specific steps: Pest activity monitoring: The system monitors the density and distribution of pests around plants through image recognition modules.

[0076] Pest risk assessment: Analyze the monitoring data to determine the potential threat level of pests to plants.

[0077] Barrier parameter settings: Dynamically adjust the strength of the insect repellent barrier (such as the concentration or range of spraying insect repellent) based on the risk assessment results.

[0078] Execute barrier generation: Activate protective equipment, such as spraying insect repellents and turning on physical barriers (such as ultrasonic devices).

[0079] Results tracking and improvement: Update and optimize pest control strategies by monitoring pest populations in real time.

[0080] The dynamic multimodal visual analysis algorithm (DMVA) is applied in the remote monitoring module to analyze the plant status in real time and detect abnormalities (such as leaf yellowing, lesions, etc.) by fusing multimodal data such as images and environment.

[0081] Specific steps: Multimodal data acquisition: The camera collects images of plant growth and combines them with environmental data such as temperature and humidity.

[0082] Plant status analysis: The system analyzes the collected images, such as determining changes in leaf color and shape, and combines environmental data to further confirm whether the plant is abnormal.

[0083] Abnormal information extraction: If anomalies are detected, such as yellowing leaves, insect infestation or disease, the system will locate the problem area and mark the possible cause.

[0084] User warning: The system sends an early warning message to the remote user, including a specific description of the anomaly and recommended countermeasures.

[0085] Monitor status updates: Continuously track the status of abnormal areas, update diagnosis results and optimize visual analysis models.

[0086] The multi-module joint self-learning optimization algorithm (MM-JSLA) is applied to the overall control system. It integrates the data of each sub-module through self-learning to optimize the operation efficiency and decision-making effect of the overall control system.

[0087] Specific steps: System data integration: Collect the operating data of each module (such as ambient temperature, irrigation volume, monitoring images, etc.) and store and analyze them in a unified manner.

[0088] Multi-module collaboration optimization: The system uses a self-learning algorithm to analyze the linkage between modules and formulate the optimal coordination strategy (such as the linkage between environmental control and irrigation).

[0089] Dynamically adjust parameters: Adjust the operating parameters of each module according to real-time data and target status to achieve intelligent optimization control.

[0090] Effect feedback and self-learning: Monitor the overall operating results and continuously optimize the system decision-making model based on historical data.

[0091] Update the model regularly: Self-learning algorithms are regularly trained to adapt to new environments and changes in demand.

[0092] The efficient multi-source data fusion and prediction algorithm (HMD-FPA) is applied in the data acquisition module. It generates accurate prediction results by fusing multiple sensor data to provide support for other modules.

[0093] Specific steps: Multi-source data collection: Sensors such as temperature, humidity, and light intensity continuously collect data and upload it to the control system.

[0094] Data cleaning and fusion: The data is cleaned, outliers are removed, and then merged into a unified data set to ensure accuracy.

[0095] Trend prediction: The system analyzes the processed data and predicts environmental trends (such as changes in temperature and humidity) over the next period of time.

[0096] Application of prediction results: The prediction results are provided to various modules (such as environmental control, irrigation management, etc.) to optimize their operation strategies.

[0097] Dynamically adjust the collection strategy: Optimize sensor collection frequency and data processing methods based on prediction accuracy and real-time conditions. Specific embodiment five

[0099] like Figure 1-6 As shown, based on the above content, the detailed hardware composition and hardware in each module are explained.

[0100] (1) Data acquisition module hardware composition: Temperature Sensor: It is mainly used to monitor the real-time temperature of the planting area environment. It usually adopts high-precision digital temperature sensors (such as DS18B20 or DHT22). Its advantages are high accuracy and support for long-distance transmission.

[0101] Humidity Sensor: For detecting the air humidity and soil humidity in the planting area, soil humidity sensors (such as YL-69) and ambient humidity sensors (such as AM2302) can be used. These sensors have strong anti-interference ability and are suitable for long-term work.

[0102] Light intensity sensor: Using photoresistors or light sensor modules (such as TSL2561) to detect the light intensity of sunlight and artificial light sources, supporting high dynamic range measurement, can help the system determine whether additional light is needed.

[0103] Multifunctional data acquisition board: The data acquisition board integrates input interfaces of multiple sensors, has high-speed data transmission capability, and communicates directly with the control system to ensure accurate collection and transmission of real-time data.

[0104] Hardware Description: The hardware of the module is designed with low power consumption to ensure long-term stability and connect to the control system wirelessly or wired. Sensors are arranged in different locations in the planting area to ensure the coverage and accuracy of environmental data.

[0105] (2) Hardware composition of the environmental control module: Blowing fan: Responsible for temperature control through air flow, using DC brushless fans or variable speed axial flow fans, supporting multi-speed adjustment and low noise operation. Fans are generally installed above or to the side of the planting area to ensure even airflow distribution.

[0106] Electric heating module: It includes ceramic heating plates or PTC heaters, which are used to locally heat the planting area in a low-temperature environment, quickly raise the temperature to an appropriate range, and have a built-in overheating protection function to ensure safe operation.

[0107] Temperature and humidity feedback controller: As the control center of the fan and heating module, it receives data from temperature and humidity sensors to dynamically adjust the operating status of the equipment to ensure the accuracy and energy saving of environmental control.

[0108] Hardware Description: The environmental control module works closely with the data acquisition module and can respond quickly to environmental changes. It also adopts a modular design, which is convenient for installation and maintenance and is suitable for various balcony planting environments.

[0109] (3) Hardware composition of irrigation management module: Storage box: A water tank of moderate capacity, which can store clean water or nutrient solution. It is made of high-density polyethylene to prevent liquid contamination and leakage, and is equipped with a liquid level sensor to monitor the remaining liquid.

[0110] High efficiency water pump: Small brushless DC pumps with high head and low power consumption for transferring water or nutrient solution from storage tanks to sprinkler heads.

[0111] Pipeline system: The pipes are made of pressure-resistant hoses, PVC pipes and other materials, which are responsible for connecting storage boxes, high-efficiency water pumps, sprinkler heads and other components. The inner surface of the pipes is treated with anti-clogging and anti-corrosion treatments to ensure long-term use.

[0112] Sprinkler head: Equipped with a retractable design, it can adjust the spraying angle and spraying mode (such as mist spraying, drip irrigation), providing precise water supply services according to plant types.

[0113] Hardware Description: The irrigation module adopts intelligent design, which can control the irrigation frequency according to humidity data, ensuring that each plant can get the right amount of water, avoiding over-watering or water waste. (4) Hardware composition of the lighting optimization module: Fill light: High-efficiency LED plant growth lights can emit light of specific wavelengths (such as red light and blue light) to promote photosynthesis. The lamp body supports the adjustment of light intensity and duration, and has the characteristics of high energy efficiency and low heat output.

[0114] Light Controller: Built-in microprocessor is used to receive data from the light intensity sensor and adjust the power of the fill light in real time to meet the needs of plants at different growth stages.

[0115] Reflector: Attached around the fill light, it is used to improve the utilization rate of light and irradiate the light more concentratedly on the plants.

[0116] Hardware Description: The lighting module focuses on the scientific nature and energy saving of the spectrum. It can also be remotely adjusted through the control system, which is suitable for the refined planting needs of various plants. (5) Hardware composition of pest control module: Mosquito repellent spray head: The micro-atomizing nozzle can evenly spray mosquito repellent liquid, and the diameter of the atomized particles can be controlled to form an effective insect repellent barrier in the planting area.

[0117] Fluid reservoir: Used to store mosquito repellent liquid, the tank has sealing properties and a built-in liquid level monitoring device.

[0118] Liquid medicine delivery pipeline: The corrosion-resistant hose connects the liquid storage tank and the mosquito repellent nozzle to ensure stability during the liquid delivery process.

[0119] High efficiency water pump: Provide sufficient pressure to drive the delivery and spraying of the liquid medicine, while ensuring the coverage of the spraying range.

[0120] Hardware Description: The selection of mosquito repellent module hardware is based on safety and environmental protection as the main considerations, ensuring that the liquid medicine is harmless to plants while reducing the impact on the environment.

[0121] (6) Hardware composition of remote monitoring module: Camera: The high-definition wide-angle camera supports real-time video transmission and pan / tilt control functions, can cover the entire planting area, and capture the plant growth status in real time.

[0122] Communication module: Includes a Wi-Fi module or a 4G module for uploading video data to the user terminal device.

[0123] Storage devices: Built-in or external memory card is used to save surveillance video records for users to review later.

[0124] Mobile applications: Provides a connection interface with the camera, users can view the monitoring screen in real time through the mobile phone and remotely control the device.

[0125] Hardware Description: The remote monitoring module can achieve seamless monitoring around the clock and provide users with a friendly interactive experience through the mobile terminal, improving the intelligence level of the system. (7) Power supply support module hardware composition: Power Adapter: The voltage-stabilized power adapter is used to convert AC power into low-voltage DC power to ensure stable operation of the system.

[0126] Lithium battery pack: As a backup power source, it provides uninterrupted power support for the system in the event of a power outage.

[0127] Circuit protection device: Including over-current protection, over-voltage protection and leakage protection switch to ensure the safety of the system under abnormal conditions.

[0128] Wiring system: Use high-quality insulated wires and waterproof connectors to connect all devices to the power module to ensure the reliability of power supply.

[0129] Hardware Description: The design of the power module fully considers the power safety and efficiency of the system, while the backup power supply ensures continuous power supply in emergency situations.

[0130] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprising a reference structure" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0131] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A fourth-generation residential home planting component and control system, characterized by: The balcony comprises a balcony plane (1), a planting area (22) and a climbing area (7), wherein a cushion platform (5) is placed at the bottom of the inner back of the balcony plane (1), and side piles (6) are clamped on one side and the middle of the top of the cushion platform (5), and the side piles (6) are in the shape of a square, and a support plate (8) is connected between the side piles (6) on both sides by mortise and tenon joints, and both sides of the support plate (8) are embedded with an inlay block (9), and a clamping interface (10) is provided on the side of the inlay block (9), and the clamping interface (10) and the side pile (6) are mutually adapted. The back of the top of the cushion platform (5) is clamped with a rear plate (21), the planting area (22) is composed of the rear plate (21) and side piles (6) on both sides, a total of five groups of support plates (8) are installed inside the planting area (22), the other side of the top of the cushion platform (5) is clamped with a vine side plate (27), the shape of the vine side plate (27) is L-shaped, the vine area (7) is composed of a middle side pile (6) and a vine side plate (27), and an opening (23) is opened on the back of the vine side plate (27).

2. The fourth generation residential home planting component and control system according to claim 1 is characterized in that: The middle part of the bottom end of the supporting plate (8) is snap-connected with a connecting bottom block (11), one side of the bottom end of the connecting bottom block (11) is provided with a mosquito repellent nozzle (24), the middle part of the bottom end of the connecting bottom block (11) is provided with a shower head (25), and the other side of the bottom end of the connecting bottom block (11) is provided with a fill light (26). A drainage pipe (17) is provided on the side of the balcony plane (1) close to the pad (5), a suction head (16) is installed on the top of the drainage pipe (17), and the suction head (16) is bonded to the wall. The bottom of the drainage pipe (17) is connected to the drainage outlet of the balcony plane (1), and one side of the drainage pipe (17) is connected to a drainage manifold (14). There are five groups of drainage manifolds (14), all of which are located at the bottom of the supporting plate (8), and a pipe head (15) is provided on one side of the top of the drainage manifold (14).

3. The fourth generation residential home planting component and control system according to claim 2 is characterized in that: A water discharge hole (12) is provided on one side of the bottom of the support plate (8), and a water supply hole (13) is provided on the other side of the bottom of the support plate (8). The end of the pipe head (15) passes through the water discharge hole (12) and is connected to the bottom of the potted plant on the support plate (8). A cover plate (18) is clamped on the front of the support platform (5). A mosquito repellent device (19) is placed on one side of the support platform (5), and a storage box (20) is placed on the other side of the support platform (5). A fan (2) is installed on one side of the top of the balcony plane (1), and a monitoring device (4) is installed on the other side of the top of the balcony plane (1). A data collector (3) is installed on the balcony plane (1) near the front of the monitoring device (4).

4. The fourth generation residential home planting component and control system according to claim 3 is characterized by: The data collector (3) is provided with a control system, and the control system includes a data collection module, an environmental control module, an irrigation management module, a lighting optimization module, a pest control module, a remote monitoring module and a power supply support module. The data collection module collects the environmental data of the planting area in real time through a temperature sensor, a humidity sensor and a light sensor. The environmental control module uses an intelligent temperature fluid optimization algorithm to adjust the temperature of the planting area. The irrigation management module controls the operation of the water pump in the storage box (20) based on a dynamic multi-objective irrigation control algorithm, and accurately irrigates the potted plants through a sprinkler head (25). The lighting optimization module uses a multi-dimensional dynamic lighting optimization algorithm to dynamically adjust the lighting intensity and duration of the fill light (26), thereby providing suitable lighting conditions and promoting plant growth. The formula of the intelligent temperature fluid optimization algorithm (ITFOA) is: ； Parameter Description: : The optimal temperature of the environment, output results, used to adjust the fan speed or start the cooling system; Controlled volume of planting area; Thermal conductivity of air, used to calculate heat conduction; The Laplace operator of the temperature gradient represents the spatial distribution of heat transfer diffusion; The density of air, which describes the distribution of mass per unit volume; The specific heat capacity of air indicates the ability of air per unit mass to absorb heat; Convection term, describing the effect of air flow on the temperature field, where is the velocity vector field; The temperature regulation coefficient determines the importance of external control; : Weight factor, which is related to the accuracy of each sensor data; The temperature difference measured by each sensor indicates how much the current temperature deviates from the target temperature.

5. The fourth generation residential home planting component and control system according to claim 4 is characterized in that: The pest control module adopts a multi-mode pest barrier generation algorithm, transports mosquito repellent liquid to the mosquito repellent nozzle (24) through a high-efficiency water pump in the mosquito repellent device (19), simulates pest invasion behavior using a generative adversarial network, predicts pest risk in combination with a gradient boosting decision tree, and optimizes the spraying range and concentration of the liquid through a multi-objective optimization algorithm to achieve targeted pest control and protect the healthy growth of plants. When using a generative adversarial network to simulate pest invasion behavior, a GAN model is trained based on historical pest occurrence data and environmental factor data to generate a pest simulation scenario.

6. The fourth generation residential home planting component and control system according to claim 5 is characterized in that: The remote monitoring module collects image data of the planting area in real time through the monitoring device (4), uses a dynamic multimodal visual analysis algorithm to identify the plant state, uses a convolutional neural network to extract leaf morphological features, combines an attention mechanism model to analyze key areas, and generates processing suggestions for abnormal states through Monte Carlo tree search. The user can remotely control the fill light (26) and the sprinkler head (25) through a mobile phone to adjust the planting environment. When the convolutional neural network is used to extract the leaf morphological features, the CNN model adopts a deep residual network structure to effectively extract the subtle features of the texture, color and shape of the leaves.

7. The fourth generation residential home planting component and control system according to claim 6 is characterized in that: The power support module includes a power supply device, which provides power support for the control system and all electronic devices. The power supply device has overvoltage protection, overcurrent protection, waterproofing and leakage protection functions to ensure the safe operation of the implant components. The power support module is also equipped with a multi-module joint self-learning optimization algorithm. The power usage pattern is modeled through a variational autoencoder, and the power distribution strategy is optimized in combination with an adaptive neural fuzzy inference system to ensure system stability and energy saving. The overvoltage protection adopts a combination circuit of a varistor and a transient suppression diode, which quickly turns on the shunt when the voltage instantly rises to more than 1.2 times the rated value.

8. The fourth generation residential home planting component and control system according to claim 7 is characterized in that: The lighting optimization module uses a multi-dimensional dynamic lighting optimization algorithm to optimize the balcony lighting conditions through a particle swarm optimization algorithm and an adaptive genetic algorithm, and combines a time series prediction algorithm to analyze the historical change trend of the light intensity, and adjusts the luminous power, spectral distribution and irradiation time of the fill light (26) in real time, so that the plants are under suitable lighting conditions and the photosynthesis efficiency is improved.

9. The fourth generation residential home planting component and control system according to claim 8 is characterized in that: The data acquisition module works in collaboration with the environmental control module, the irrigation management module and the pest control module through an efficient multi-source data fusion and prediction algorithm. The efficient multi-source data fusion and prediction algorithm is based on a multi-scale deep neural network, extracts features from multi-dimensional data of temperature, humidity and light, uses conditional random fields to analyze the time series dependency between data, and dynamically adjusts the data fusion strategy through a quantum adaptive neural network, providing accurate environmental parameter support and prediction results for system operation.

Images