Intelligent landscaping plant maintenance method and system, electronic equipment and storage medium

Abstract

The invention relates to the field of intelligent agriculture, and discloses an intelligent landscaping plant maintenance method and system, electronic equipment and a storage medium, and the method comprises the steps: deploying an environment sensor, and collecting data through the sensor; transmitting data acquired by the sensor to a central control system; analyzing and processing the received data; generating a dynamic maintenance plan; a maintenance plan is sent to an execution device, the system comprising: an environmental sensor network, a central control system and an automated execution system, a computer device comprising: a memory, a processor and a computer program stored on the memory and operable on the processor. The technical scheme of multi-source data analysis and self-adaptive regulation and control based on artificial intelligence is adopted, and the technical effects that the water and nutrient requirements of plants are accurately recognized, and irrigation and fertilization are dynamically adjusted according to real-time feedback are achieved. Compared with the technical scheme of irrigation and fertilization depending on a fixed schedule or manual judgment in the prior art, the maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart agriculture, and specifically to an intelligent landscaping plant maintenance method, system, electronic equipment and storage medium. Background Art

[0002] With the rapid development of urban greening, the need for plant maintenance is increasing. Modern landscaping must not only meet aesthetic and ecological needs but also address sustainable management requirements, such as water and fertilizer conservation, as well as pest and disease control. Furthermore, extreme weather events brought on by climate change, such as high temperatures, droughts, heavy rains, and sudden disease outbreaks, have further exacerbated the complexity of garden maintenance. Therefore, a plant maintenance method is needed that improves water and fertilizer utilization, reduces human intervention, and optimizes pest and disease control while ensuring effective greening.

[0003] Existing garden maintenance primarily relies on traditional methods such as regular irrigation, fertilization, and pest inspections. Some areas have introduced automated irrigation systems or sensor networks to improve management efficiency. Drip and sprinkler irrigation systems are widely used in many urban parks and green belts. Some intelligent irrigation systems also incorporate soil moisture sensors and timing controls to automatically adjust irrigation levels to a certain extent. Meanwhile, pest and disease control still relies primarily on manual inspections. However, some smart agriculture sectors are beginning to use computer vision and machine learning technologies for disease identification.

[0004] However, existing garden maintenance technologies are mostly based on fixed schedules or simple humidity threshold controls, which cannot accurately match the real-time needs of plants. After rainfall, irrigation systems may still operate according to schedule, resulting in over-irrigation and even root diseases. Manual inspections for pests and diseases are also relied upon, but due to labor costs and work efficiency, inspections are infrequent. Furthermore, the use of fixed rule-based control logic makes it difficult to adapt to complex and changing garden environments. Therefore, the present invention provides an intelligent garden plant maintenance method, system, electronic device, and storage medium to address the shortcomings of the existing technology. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides an intelligent landscaping plant maintenance method, system, electronic equipment and storage medium, which solves the problems that the existing garden maintenance technology cannot accurately match the real-time needs of plants, relies on manual inspections of pests and diseases, is limited by labor costs and work efficiency, has a low inspection frequency, and uses control logic based on fixed rules, which makes it difficult to adapt to the complex and changing garden environment.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent landscaping plant maintenance method, comprising the following steps: Deploy an environmental sensor network to collect real-time data on soil moisture, light intensity, air temperature and humidity, and plant physiology; The data collected by the sensor is transmitted to the central control system through the wireless communication module; The central control system analyzes and processes the received data, using artificial intelligence algorithm models and physical modeling methods to predict the spatial distribution of soil moisture and the water and nutrient requirements of plants, and assess potential pest and disease risks; Automatically generate dynamic maintenance plans based on predictions from artificial intelligence algorithm models, including precise irrigation amounts, personalized fertilization formulas, and targeted pest and disease control measures; Send dynamic maintenance plan instructions to the on-site automated execution equipment to perform the corresponding maintenance tasks.

[0007] Preferably, the physical modeling is a soil moisture migration equation, which is: where θ represents the soil moisture content, t is the time, K(θ) is the soil hydraulic conductivity, ψ is the soil water potential, and S is the source term.

[0008] Preferably, the artificial intelligence algorithm model combines plant physiological data, including chlorophyll content and photosynthesis rate, and uses photosynthesis and plant growth models to predict plant water and nutrient requirements and potential pest and disease risks.

[0009] Preferably, the central control system analyzes and processes the received sensor data through the following steps: The collected soil moisture, light intensity, air temperature and humidity, and plant physiological data were preprocessed to remove noise data and standardize them; Using photosynthesis and plant growth models, combined with chlorophyll content and photosynthesis rate, calculate plant photosynthesis efficiency and predict plant water and nutrient requirements; Based on environmental factors, including light intensity, temperature and humidity, plant growth is assessed and plant needs and growth risks are predicted; through artificial intelligence algorithm models, the plant water and nutrient requirements are accurately determined, and the risk of pests and diseases is predicted.

[0010] Preferably, the process of generating the dynamic maintenance plan is: Calculate irrigation needs and precisely allocate water based on predicted plant needs; Generate personalized fertilizer formulas based on soil fertility, plant species and growth stage to ensure adequate nutrients; Formulate pest and disease control measures based on predicted pest and disease risks; Adjust maintenance plans in real time to ensure plants are in optimal growth condition.

[0011] Preferably, the instruction execution process of the dynamic maintenance plan is: Send maintenance instructions to automated equipment, including intelligent sprinkler systems, unmanned fertilizer vehicles, and drone sprayers; the intelligent sprinkler system adjusts irrigation volume based on plant water needs; Unmanned fertilizer spreading vehicles accurately apply fertilizer according to the fertilizer formula; The drone spraying device applies pesticides precisely according to the needs of pest control; Automated equipment monitors task execution in real time and adjusts maintenance tasks based on feedback to ensure smooth completion of tasks.

[0012] Preferably, the automated execution equipment is adjusted according to the following manner: Monitor plant conditions and environmental data in real time and feed back to the central control system; The control system analyzes feedback data and evaluates the performance of the task; Based on the analysis results, adjustment instructions are issued to optimize the maintenance plan; The automated equipment dynamically adjusts the execution task parameters according to the adjustment instructions; Self-optimize maintenance tasks through feedback mechanism.

[0013] It also provides intelligent landscaping plant maintenance electronic equipment system, including: Environmental sensor networks for real-time collection of soil moisture, light intensity, air temperature and humidity, and plant physiological data; A central control system receives sensor data and uses artificial intelligence algorithms to predict plant water and nutrient needs and potential pest and disease risks; The automated execution system is used to execute maintenance tasks according to the dynamic maintenance plan generated by the central control system. The automated execution equipment includes an intelligent sprinkler system, an unmanned fertilizer vehicle and a drone spraying device.

[0014] A computer device is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, an intelligent landscaping plant maintenance method can be implemented.

[0015] Also provided is an intelligent landscaping plant maintenance storage medium storing a computer program. When the computer program is executed by a processor, an intelligent landscaping plant maintenance method can be implemented.

[0016] The present invention provides an intelligent landscaping plant maintenance method, system, electronic equipment and storage medium. Beneficial effects: 1. The present invention adopts artificial intelligence-based multi-source data analysis and adaptive control technology solutions to achieve the technical effect of accurately identifying the water and nutrient needs of plants and dynamically adjusting irrigation and fertilization based on real-time feedback. Compared with the existing technical solutions that rely on fixed schedules or manual judgment for irrigation and fertilization, this solves the problems of water resource waste and insufficient or excessive nutrient supply, and improves maintenance efficiency.

[0017] 2. The present invention adopts a technical solution for disease and insect pest risk prediction that combines deep learning with computer vision, achieving the technical effect of identifying possible diseases in advance and accurately adjusting prevention and control measures. Compared with the technical solutions in the existing technology that rely on manual inspections or simple threshold alarms, it solves the shortcomings of low inspection efficiency, insufficient recognition accuracy, and easy missing of early disease prevention windows, effectively reducing the use of pesticides and reducing the risk of environmental pollution.

[0018] 3. The present invention adopts an intelligent control technology solution that combines reinforcement learning and feedback optimization, which achieves the technical effect of dynamically adjusting parameters according to the maintenance effect, so that the system continuously learns and optimizes; compared with the technical solution in the existing technology that relies on static rules to set irrigation and fertilization parameters, it solves the problem of inaccurate control caused by its inability to adapt to seasonal changes and sudden environmental changes, making plant maintenance more flexible and efficient.

[0019] 4. The present invention adopts a technical solution that combines cloud database with big data analysis to achieve the technical effect of storing and analyzing historical maintenance data and optimizing future management strategies; compared with the technical solution in the existing technology that only makes decisions based on current monitoring data, it solves the shortcomings of being unable to use long-term data optimization models and difficult to form accurate management experience, making garden maintenance more scientific and systematic, and managers can improve the quality of decision-making based on data. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the method steps of the present invention; Figure 2 This is a system architecture diagram of the present invention; Figure 3 Schematic diagram of the computer device structure of the present invention.

[0021] Among them, 40, computer equipment; 41, processor; 42, memory; 43, storage medium. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. 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 making creative efforts are within the scope of protection of the present invention.

[0023] Please see the attached Figure 1 , an embodiment of the present invention provides an intelligent landscaping plant maintenance method, comprising the following steps: S1. Deploy an environmental sensor network to collect soil moisture, light intensity, air temperature and humidity, and plant physiological data in real time. S2, transmit the data collected by the sensor to the central control system through the wireless communication module; S3. The central control system analyzes and processes the received data, using artificial intelligence algorithm models and physical modeling methods to predict the spatial distribution of soil moisture and the water and nutrient requirements of plants, and assess potential pest and disease risks; S4. Automatically generate a dynamic maintenance plan based on the prediction results of the artificial intelligence algorithm model, wherein the dynamic maintenance plan includes precise irrigation amount, personalized fertilization formula and targeted pest and disease control measures; S5. Send the dynamic maintenance plan instructions to the on-site automated execution equipment to execute the corresponding maintenance tasks.

[0024] In step S1, in this embodiment, a network of environmental sensors is deployed to collect various environmental data required for plant growth, including soil moisture, light intensity, air temperature and humidity, and plant physiological data. This data provides the basis for subsequent intelligent analysis and the precise execution of maintenance tasks.

[0025] In this embodiment, a complete environmental sensing network is first constructed by deploying multiple high-precision environmental sensors throughout the landscaped area. This network, composed of different types of sensors, collects various environmental data in real time, tailored to the specific needs of plants. These sensors include soil moisture sensors, light intensity sensors, air temperature and humidity sensors, chlorophyll meters, and photosynthetic rate sensors. These sensors enable the acquisition of precise plant growth data.

[0026] In some embodiments, soil moisture sensors utilize capacitive or frequency-domain reflectometry technologies, which can accurately measure soil moisture content with minimal error, ensuring the reliability of the collected data. Specifically, capacitive soil moisture sensors operate based on changes in the electric field. When soil moisture changes, the electric field strength changes, and the soil moisture content is measured through changes in capacitance. Frequency-domain reflectometry sensors, on the other hand, utilize the propagation characteristics of electromagnetic waves to detect soil moisture content.

[0027] Light intensity sensors utilize a wide-spectrum, high-sensitivity design, capable of accurately sensing light intensity across different wavelengths. These sensors not only detect light intensity across the entire spectrum but also analyze the light requirements of different plants, providing them with optimal lighting environments. Trees and lawns have different light requirements, and sensors can provide tailored data support based on these needs.

[0028] Air temperature and humidity sensors offer fast response and long-term stability, collecting real-time air temperature and humidity information to help central control systems analyze the impact of environmental conditions on plant growth. These sensors are densely distributed throughout landscaping areas to ensure accurate temperature and humidity data is available in diverse microclimate zones.

[0029] Additionally, plant physiological data, including chlorophyll content and photosynthesis rate, will be measured using non-contact chlorophyll meters and photosynthesis meters. The chlorophyll meter measures the leaf reflectance spectrum, analyzing chlorophyll content and thereby assessing the plant's photosynthetic capacity. The photosynthesis meter can measure the plant's photosynthesis rate in real time, providing a basis for further water and nutrient prediction.

[0030] To ensure real-time and accurate data transmission, the sensor network communicates with the central control system via wireless communication modules. These modules utilize low-power wide area network (LPWAN) technologies, such as LoRa and NB-IoT protocols. These technologies offer long-range transmission, low energy consumption, and interference resistance, enabling stable transmission of sensor data from various locations across the campus to the central control system. Furthermore, the sensors are designed with environmental adaptability in mind, ensuring stable operation under varying temperatures, humidity, wind speeds, and other environmental conditions, ensuring the long-term, efficient operation of the system.

[0031] In some embodiments, the sensor also features a self-calibration function, enabling periodic self-calibration to ensure long-term measurement accuracy. This function uses internal standard materials or reference environmental parameters for self-calibration, reducing measurement errors caused by device aging or changes in the external environment. Furthermore, the sensor is equipped with a fault monitoring function. In the event of a fault, the system will issue an alarm and provide maintenance personnel with fault diagnostic information, enabling rapid repair or replacement of the device.

[0032] Collected environmental data undergoes real-time preprocessing, including noise removal, outlier detection, and standardization, to ensure high-quality data input into the central control system. This data serves as input to artificial intelligence (AI) algorithms, providing an accurate basis for subsequent plant demand forecasts. This preprocessed data includes sensor output signals, sensor operating status information, and environmental trends.

[0033] For soil moisture measurement, in some embodiments, the Hydraulic Conductivity Equation can be used as a basis for analyzing soil moisture distribution. The equation is: Here, θ represents soil moisture content, t is time, K(θ) is soil hydraulic conductivity, ψ is soil water potential, and S is the source term. This equation helps the system analyze soil moisture variations and provides the central control system with accurate water demand data, thus supporting subsequent irrigation and water resource allocation decisions.

[0034] In step S2, in this embodiment, the data is transmitted to the central control system via a wireless communication module. The wireless communication module plays a crucial role in this process, ensuring that data can be smoothly transmitted from the sensor nodes to the control system. This requires not only stable and real-time transmission, but also low power consumption and high-efficiency transmission quality.

[0035] In this embodiment, data transmission is achieved through a wireless communication module. After the sensor network is deployed, the raw data collected by each sensor is transmitted to the central control system via a pre-defined wireless communication network. Wireless communication modules typically use low-power wide area network (LPWAN) technologies such as LoRa and NB-IoT. These technologies offer advantages such as long distance, large scale, and low power consumption, making them well-suited for large-scale landscaping applications.

[0036] In some embodiments, LoRa technology is used, which effectively supports long-distance data transmission, ensuring stable data transmission to the central control system even in remote areas. The protocol used by the LoRa communication module supports wide-area coverage and multi-device communication, ensuring timely transmission of sensor data within large landscaping areas. Furthermore, the LoRa communication module has low power consumption, which can extend the battery life of sensor nodes and reduce maintenance costs.

[0037] Specifically, the communication module transmits data via wireless signals to a data aggregation node, which then transmits the data to a central control system via high-speed communication networks such as 4G or 5G. To ensure the stability and reliability of the communication network, the system can be equipped with signal boosters or repeaters as needed. This ensures timely and stable data transmission even in areas with weak network signals.

[0038] In one possible implementation, the system uses a data caching and retransmission mechanism to ensure data transmission reliability. When a communication network experiences a brief outage or data congestion, sensor nodes and data aggregation nodes temporarily store data. Once the network is restored, the cached data is automatically retransmitted to the central control system in chronological order. This prevents data loss or delays caused by temporary network issues and ensures the continuity and integrity of data transmission.

[0039] To further enhance data security, communication modules often integrate data encryption technology to ensure the security and integrity of data during transmission. Encryption technology can effectively prevent data from being illegally stolen or tampered with. Data security is particularly important in large-scale wireless communication networks.

[0040] In some embodiments, the communication module uses the LoRa or NB-IoT communication protocol, whose transmission rate and communication delay have clear parameter definitions. LoRa technology generally has a lower transmission rate and a longer communication distance, while NB-IoT provides a higher data transmission rate. Based on the requirements of different application scenarios, the central control system can select the appropriate communication technology to optimize data transmission efficiency and timeliness. Assuming that the amount of data transmitted by each sensor node is D (unit: bytes), its transmission time T can be calculated using the following formula: Where T is the time required for data to be transmitted from the sensor to the receiver, D is the size of the data being transmitted, and R is the communication rate in bytes per second (B / s). This formula describes the time required for data to be transmitted from a sensor node to a central control system at a given communication rate.

[0041] In step S3, in this embodiment, the data collected by the sensors is deeply analyzed and processed. The central control system uses artificial intelligence algorithm models and combines multi-source environmental data to predict the water and nutrient needs of plants and identify potential pest and disease risks in advance, providing an accurate basis for subsequent maintenance decisions.

[0042] In this embodiment, the central control system first preprocesses the received sensor data. Typically, raw data contains noise, outliers, or incomplete information, requiring data cleaning, interpolation, and standardization to improve data usability and analysis accuracy. Air temperature and humidity data may be affected by sudden weather events, while soil moisture data may produce outliers due to localized water accumulation or sensor errors. Therefore, data preprocessing employs denoising filtering, outlier removal, and interpolation algorithms to ensure data stability and continuity.

[0043] Specifically, in some embodiments, the central control system uses Kalman filter or local weighted regression (LOWESS) algorithm to smooth the data of continuous time series to reduce the impact of measurement errors. t , the predicted state variable is X t , the system status update can be expressed as: X t =AX t-1 +BU t +W t ; Among them, X t The state vector of the system at time t, A is the state transfer matrix, B is the input influence matrix, U t is the control input, W t is the process noise. The measurement update equation is: Z t =HX t +V t ; Among them, Z t is the measured value (observation value), which is the data obtained by the sensor or measuring device, H is the measurement matrix, V t This method can effectively filter out random errors caused by environmental factors and improve the stability of the prediction model.

[0044] As an option, after data preprocessing, the system will predict the water and nutrient requirements of plants. This prediction is based on the soil water transport equation (Richards equation) and the plant nutrient balance model. The calculation of plant water requirements can be expressed as: Here, θ represents soil moisture content, t is time, K(θ) is soil hydraulic conductivity, ψ is soil water potential, and S is the source term. This equation can simulate the dynamic changes in moisture under different soil types, providing data support for precision irrigation.

[0045] In one possible implementation, the central control system combines plant physiological data, including chlorophyll content and photosynthesis rate, with photosynthesis and plant growth models to assess the water and nutrient needs of plants. The photosynthesis rate is affected by multiple factors such as light intensity, carbon dioxide concentration, and leaf water potential, and can be calculated using the Farquhar photosynthesis model: Where A is the photosynthetic rate, V cmax is the maximum carboxylation rate, C i is the intercellular CO2 concentration, Γ * is the CO2 compensation point, K c and K o are the CO2 and O2 affinities of Rubisco, respectively, and O is the oxygen concentration. Based on this model, the system can calculate the carbon fixation rate of the plant and further predict the plant's water and nutrient requirements.

[0046] Furthermore, for pest and disease risk prediction, the central control system utilizes deep learning algorithms to analyze data from multiple sources. In some embodiments, the system trains a convolutional neural network (CNN) or recurrent neural network (RNN) based on historical data to identify abnormal plant growth signals and match them with existing pest and disease databases. When the system detects abnormal leaf color or a low chlorophyll index, the model automatically assesses whether there is a pest and disease risk and generates an early warning.

[0047] As an optimization solution, the system can incorporate expert systems, incorporating the experience and knowledge of plant care experts into the algorithm model to further improve prediction accuracy. Certain diseases are more likely to break out in specific seasons and environmental conditions. The system can combine expert rules and machine learning models to conduct a comprehensive risk assessment. This approach not only improves the accuracy of pest and disease predictions but also reduces the possibility of misjudgments and false alarms.

[0048] In one expansion, the system employs online learning to continuously update and adjust algorithm parameters to optimize the model's adaptability and accuracy. Whenever new maintenance data is input into the system, the model adapts to better align predictions with reality. For example, if the irrigation needs of a particular plant in a specific area deviate from the initial model predictions, the system can use this feedback to adjust the parameters of the water migration model to optimize subsequent predictions.

[0049] In step S4, in this embodiment, the central control system analyzes the prediction results to generate specific maintenance recommendations and automatically adjusts irrigation, fertilization, and other maintenance measures based on these recommendations. The key to this process is translating the analysis results into actual maintenance actions, ensuring that plants receive precise water and nutrient supplies while reducing the risk of pests and diseases. The system's automated adjustment mechanism adjusts maintenance parameters based on real-time data and prediction results, thereby achieving precise landscaping management.

[0050] In this embodiment, the system automatically generates maintenance recommendations using a comprehensive algorithm model based on water and nutrient requirements and pest and disease risk assessments. Specifically, the system first calculates appropriate irrigation and fertilization rates based on factors such as soil moisture, light intensity, and temperature, combined with the needs of the plant species and growth stage. If the system predicts a plant's water needs are high, it automatically increases irrigation frequency to ensure the soil maintains optimal moisture.

[0051] In some embodiments, the calculation of irrigation amount can be based on a soil water transport model and a plant transpiration demand model. The plant transpiration demand E can be estimated by the following formula: Among them, E is the transpiration demand of plants, K t is the conductivity coefficient of the plant species, T is the current temperature, T0 is the reference temperature, T m is the maximum temperature, RH is the relative humidity, represents the relative impact of temperature on evaporation. Based on this formula, the system can adjust the plant's water supply strategy in real time according to changes in the external environment.

[0052] As an optimization method, system-generated maintenance recommendations adjust irrigation and fertilization rates based on dynamic feedback from real-time monitoring and forecast data. When the system receives weather forecast data, it predicts rainfall over the next few days and adjusts irrigation plans in advance. This mechanism effectively avoids resource waste caused by over-irrigation or over-fertilization, while also improving plant growth.

[0053] Automatic adjustment measures typically involve linkage with irrigation systems, fertilization equipment, and pest and disease control systems. Typically, the system connects to the irrigation system through an interface, enabling real-time adjustments to irrigation equipment and water flow control. When the system detects low soil moisture or increased water demand, it automatically turns on irrigation equipment and adjusts water flow based on irrigation needs. Furthermore, when the system identifies potential pest and disease risks, it can precisely apply pesticides through automated spraying equipment, preventing the spread of pests and diseases that might otherwise be missed during traditional manual inspections.

[0054] In some embodiments, irrigation and fertilization are adjusted based not on fixed parameters but on adaptive learning from historical data. Specifically, the central control system continuously updates its understanding of plant maintenance needs through machine learning algorithms. In some areas, the system may adjust its response curve to soil moisture based on historical irrigation records, thereby improving irrigation efficiency and avoiding over-irrigation. Specifically, the automatic adjustment of irrigation volume can be expressed as: I=K s ·(S m -S act )+α·E; Where I is the irrigation amount, K s is the irrigation sensitivity, S m is the target soil moisture, S act is the current soil moisture, α is the adjustment coefficient, and E is the plant transpiration requirement. This formula is used to calculate the amount of water the irrigation system needs to provide under different soil moisture conditions.

[0055] For pest control, the system not only generates early warnings based on predicted pest and disease risks but also implements precise spraying via automated pesticide application equipment. When the system detects abnormalities in plant leaves, which, combined with environmental conditions, indicate potential pests and diseases, it automatically adjusts the application plan, selecting the appropriate pesticide type, spray concentration, and spraying time. Fertilization adjustments are also based on predicted plant nutrient needs and current soil fertility.

[0056] As an extension, the system can also integrate a pest control expert system, which optimizes pesticide application plans by combining expert rules with machine learning algorithms. The expert system provides the best control plan based on plant species, environmental factors, and historical pest and disease data, ensuring that low-risk biological or environmentally friendly pesticides are used.

[0057] In step S5, in this embodiment, the system continuously monitors plant growth and environmental parameters through a distributed sensor network. Typically, monitoring data includes soil moisture, temperature, humidity, light intensity, leaf color index (Chlorophyll Index), gas concentrations (such as CO2 and O2), and pest and disease identification information. Sensor data is transmitted to the central control system via a wireless communication module. The system adjusts the next maintenance strategy based on the difference between the latest monitoring data and the expected maintenance effect.

[0058] In some embodiments, the system uses a data fitting method to evaluate the effectiveness of maintenance measures. The mean square error (MSE) can be used to evaluate the deviation between the predicted plant moisture value and the actual measured value: Among them, MSE represents the mean square error between the true value and the predicted value, X iTo actually measure the moisture value, is the system prediction value, N is the number of measurement points, The square of the error represents the square of the prediction error for each data point. If the error exceeds the preset threshold, the system will adjust the irrigation strategy to improve irrigation accuracy.

[0059] Alternatively, the system can optimize maintenance strategies based on machine learning methods. For example, a recurrent neural network (RNN) can be used to analyze historical monitoring data to predict the impact of future environmental conditions on plant growth. In some embodiments, the system can combine long-term monitoring data to construct an environmental-growth factor regression model: Y=f(W,N,T,H,L); Where Y represents plant growth (e.g., leaf growth rate), W is soil moisture, N is soil nutrient concentration, T is air temperature, H is relative humidity, and L is light intensity. This regression model can be used to optimize irrigation and fertilization decisions.

[0060] In one possible implementation, the system sets adaptive feedback parameters for different plant types, making maintenance strategies more precise. For some plants, such as succulents, which are more sensitive to water, a rapid drop in leaf water potential may indicate over-irrigation. The system uses leaf moisture sensors to detect changes in plant water potential. If the measured data falls below a safe threshold, irrigation is automatically reduced. Conversely, for drought-tolerant plants, the system may only trigger water replenishment when it detects a prolonged drought.

[0061] In some embodiments, pest and disease monitoring incorporates computer vision algorithms to automatically identify plant leaf lesions. The system may employ a convolutional neural network (CNN) to analyze leaf image data and identify the probability of a specific disease: P(Disease) = σ(W·X+b); Where P (Disease) is the disease probability, σ is the activation function, W is the feature weight, X is the leaf feature vector, and b is the bias term. If the system predicts a high probability of plant disease in a certain area, it will automatically adjust the pesticide application strategy to improve prevention and control efficiency.

[0062] As an optimization approach, the system can also employ reinforcement learning (RL) algorithms to optimize maintenance strategies based on maintenance outcomes. In this approach, the system considers each maintenance action as a decision-making step and calculates rewards and penalties based on feedback data, gradually refining the decision-making process. For example, if plant growth improves, the system strengthens the current maintenance plan; otherwise, it adjusts parameters to find a more optimal solution.

[0063] In another possible implementation, the system stores monitoring data in a cloud database to support long-term data analysis and model optimization. Based on years of accumulated monitoring data, the system can analyze plant growth patterns in different seasons and environmental conditions and optimize maintenance strategies accordingly. This mechanism can continuously improve the level of intelligent landscaping and make the system more adaptable.

[0064] In some embodiments, monitoring data is not only used for real-time feedback, but also for early warning mechanisms. If the plant growth rate in a certain area is lower than the historical average, the system can trigger an abnormal alarm and prompt managers to check for possible environmental problems, such as poor soil, spread of pests and diseases, etc.

[0065] The intelligent landscaping plant maintenance system described below and the intelligent landscaping plant maintenance method described above can be referenced to each other.

[0066] Please see the attached Figure 2 The present invention also provides an intelligent landscaping plant maintenance system, including: Environmental sensor networks for real-time collection of soil moisture, light intensity, air temperature and humidity, and plant physiological data; A central control system receives sensor data and uses artificial intelligence algorithms to predict plant water and nutrient needs and potential pest and disease risks; The automated execution system is used to execute maintenance tasks according to the dynamic maintenance plan generated by the central control system. The automated execution equipment includes an intelligent sprinkler system, an unmanned fertilizer vehicle and a drone spraying device.

[0067] The system of this embodiment can be used to execute the above method embodiments, and its principles and technical effects are similar, so they will not be repeated here.

[0068] The computer device described below and the intelligent landscaping plant maintenance method described above can be used in correspondence with each other.

[0069] Please see the attached Figure 3 The present invention further provides a computer device 40, comprising: a processor 41 and a memory 42, wherein the memory 42 stores a computer program executable by the processor, and when the computer program is executed by the processor, the above method is performed.

[0070] The present invention further provides a storage medium 43 on which a computer program is stored. When the computer program is run by the processor 41 , the above method is executed.

[0071] Among them, the storage medium 43 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as 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.

[0072] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent landscaping plant maintenance method, characterized in that: The following steps are involved: Deploy an environmental sensor network to collect real-time data on soil moisture, light intensity, air temperature and humidity, and plant physiology; The data collected by the sensor is transmitted to the central control system through the wireless communication module; The central control system analyzes and processes the received data, using artificial intelligence algorithm models and physical modeling methods to predict the spatial distribution of soil moisture and the water and nutrient requirements of plants, and assess potential pest and disease risks; Automatically generate dynamic maintenance plans based on predictions from artificial intelligence algorithm models, including precise irrigation amounts, personalized fertilization formulas, and targeted pest and disease control measures; Send dynamic maintenance plan instructions to the on-site automated execution equipment to perform the corresponding maintenance tasks.

2. The intelligent landscaping plant maintenance method according to claim 1, characterized in that: The physical modeling is the soil moisture migration equation, which is: where θ represents the soil moisture content, t is the time, K(θ) is the soil hydraulic conductivity, ψ is the soil water potential, and S is the source term.

3. The intelligent landscaping plant maintenance method according to claim 1, characterized in that: The artificial intelligence algorithm model combines plant physiological data, including chlorophyll content and photosynthesis rate, with photosynthesis and plant growth models to predict plant water and nutrient requirements and potential pest and disease risks.

4. The intelligent landscaping plant maintenance method according to claim 1, characterized in that: The central control system analyzes and processes the received sensor data through the following steps: The collected soil moisture, light intensity, air temperature and humidity, and plant physiological data were preprocessed to remove noise data and standardize them; Using photosynthesis and plant growth models, combined with chlorophyll content and photosynthesis rate, calculate plant photosynthesis efficiency and predict plant water and nutrient requirements; Based on environmental factors, including light intensity, temperature and humidity, plant growth is assessed and plant needs and growth risks are predicted; through artificial intelligence algorithm models, the plant water and nutrient requirements are accurately determined, and the risk of pests and diseases is predicted.

5. The intelligent landscaping plant maintenance method according to claim 1, characterized in that: The generation process of the dynamic maintenance plan is as follows: Calculate irrigation needs and precisely allocate water based on predicted plant needs; Generate personalized fertilizer formulas based on soil fertility, plant species and growth stage to ensure adequate nutrients; Formulate pest and disease control measures based on predicted pest and disease risks; Adjust maintenance plans in real time to ensure plants are in optimal growth condition.

6. The intelligent landscaping plant maintenance method according to claim 1, characterized in that: The instruction execution process of the dynamic maintenance plan is as follows: Send maintenance instructions to automated equipment, including intelligent sprinkler systems, unmanned fertilizer vehicles, and drone sprayers; the intelligent sprinkler system adjusts irrigation volume based on plant water needs; Unmanned fertilizer spreading vehicles accurately apply fertilizer according to the fertilizer formula; The drone spraying device applies pesticides precisely according to the needs of pest control; Automated equipment monitors task execution in real time and adjusts maintenance tasks based on feedback to ensure smooth completion of tasks.

7. The intelligent landscaping plant maintenance method according to claim 1, characterized in that: The automated execution equipment is adjusted in the following manner: Monitor plant conditions and environmental data in real time and feed back to the central control system; The control system analyzes feedback data and evaluates the performance of the task; Based on the analysis results, adjustment instructions are issued to optimize the maintenance plan; The automated equipment dynamically adjusts the execution task parameters according to the adjustment instructions; Self-optimize maintenance tasks through feedback mechanism.

8. An intelligent landscaping plant maintenance system, applied to the intelligent landscaping plant maintenance method according to any one of claims 1 to 7, characterized in that: include: Environmental sensor networks for real-time collection of soil moisture, light intensity, air temperature and humidity, and plant physiological data; A central control system receives sensor data and uses artificial intelligence algorithms to predict plant water and nutrient needs and potential pest and disease risks; The automated execution system is used to execute maintenance tasks according to the dynamic maintenance plan generated by the central control system. The automated execution equipment includes an intelligent sprinkler system, an unmanned fertilizer vehicle and a drone spraying device.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the intelligent landscaping plant maintenance method according to any one of claims 1 to 7.

10. Intelligent landscaping plant maintenance storage medium, characterized by: A computer program is stored, and when the computer program is executed by a processor, the intelligent landscaping plant maintenance method according to any one of claims 1 to 7 is implemented.

Images