Ecological garden intelligent management method and system

Abstract

The invention discloses an ecological garden intelligent management method and system, and belongs to the technical field of landscaping management, and the method specifically comprises the steps: monitoring environmental parameters in real time through multiple sensors, and uploading the environmental parameters to a cloud server; at the cloud end, a dynamic data analysis model is constructed by utilizing historical irrigation data, a plant growth model and real-time monitoring parameters, the water demand of plants is predicted, and an irrigation decision is made; an irrigation threshold value is set according to the decision, and an irrigation program is automatically started and executed through remote control equipment; after irrigation, detailed information is recorded and fed back to the data analysis model, the irrigation effect is evaluated by adopting a data analysis method, and an irrigation decision is finely adjusted accordingly; intelligent and precise irrigation management is realized, and the utilization efficiency of water resources and the growth quality of plants are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of garden greening management, and specifically relates to an ecological garden intelligent management method and system. Background Art

[0002] With the acceleration of urbanization, the area of ​​urban green space is gradually decreasing. The importance of ecological gardens as the green lungs of cities is becoming increasingly prominent. Among them, the smart management methods of ecological gardens rely on the rapid development of modern information technology and data processing technology, aiming to solve many problems in traditional garden management. However, traditional garden management methods usually rely on manual inspections and manual records, which is not only inefficient, but also difficult to achieve comprehensive and real-time monitoring of the garden environment. In terms of garden irrigation methods, traditional garden irrigation methods often rely on manual experience. Although automated management has been achieved to a certain extent, there is still room for improvement in terms of precise control of irrigation volume and reduction of water waste. There are problems such as serious water waste and low efficiency.

[0003] For example, the Chinese patent with authorization announcement number CN113034323B discloses a smart garden management platform based on GIS and big data technology, including: an ecological garden spatiotemporal database, a comprehensive information visualization system, a monitoring and control system, a big data dynamic management GIS system, a business management system, and an auxiliary decision-making system; using the ecological garden spatiotemporal database to provide data support, using the comprehensive information visualization system to assist in refined management and macro-decision-making, using the monitoring and control system to conduct real-time early warning monitoring, using the big data dynamic management GIS system to instantly update garden landscaping data, using the business management system to manage garden business, and using the auxiliary decision-making system to provide data support for decision-making; realizing a "smart garden" with data informatization, intelligent management, and automated supervision.

[0004] For example, a Chinese patent with authorization announcement number CN116843276B discloses a smart garden maintenance management system and method based on the Internet of Things, including: a wetland environment monitoring and analysis module, a wetland ecological extraction and analysis module, a wetland blockage monitoring module, a wetland blockage analysis module, a wetland terminal control module and a wetland database. By monitoring the environmental information, extracting historical information and monitoring the infiltration information of the target wetland garden area, the winter overwintering problem of the target wetland garden area is solved, the biodiversity and regional ecological balance of the wetland garden in winter are maintained, and the winter biological community structure of the wetland garden is avoided. To a certain extent, the hydraulic performance of the wetland is guaranteed to avoid the problem of wetland degradation, thereby improving the treatment effect and service life of the wetland. At the same time, the climate regulation function of the wetland is improved, the water resource supply security is guaranteed, and the flood storage and waterlogging prevention capacity along the river is enhanced.

[0005] The above existing technologies all have the following problems: high system complexity and cost; functional targeting and limitations; and insufficient precision in irrigation management. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes an intelligent management method and system for ecological gardens, which monitors environmental parameters in real time through multiple sensors and uploads them to a cloud server; in the cloud, a dynamic data analysis model is constructed using historical irrigation data, plant growth models and real-time monitoring parameters to predict plant water requirements and make irrigation decisions; irrigation thresholds are set according to the decisions, and the irrigation program is automatically started and executed through a remote control device; after irrigation, detailed information is recorded and fed back to the data analysis model, and the irrigation effect is evaluated using data analysis methods, and the irrigation decisions are fine-tuned accordingly; the intelligent and precise irrigation management is realized, and the water resource utilization efficiency and plant growth quality are improved.

[0007] To achieve the above object, the present invention provides the following technical solutions: An ecological garden intelligent management method, comprising: Step S1: Real-time monitoring of environmental parameters by multiple sensors, and uploading the environmental parameters collected by the multiple sensors to a cloud server using the Internet of Things; Step S2: On the cloud server, a dynamic data analysis model is constructed using historical irrigation data, plant growth models, and currently monitored environmental parameters in real time. The dynamic data analysis model is used to predict the water requirements of plants in different time periods, and irrigation decisions are made based on the prediction results. Step S3: according to the irrigation decision, the irrigation threshold is set. If the monitored environmental parameters reach the preset irrigation threshold, the system automatically starts the irrigation program and performs irrigation operations according to the irrigation decision through remote control of the irrigation equipment; Step S4: Record detailed information of each irrigation and feed the irrigation records back to the dynamic data analysis model. At the same time, use data analysis methods to analyze the irrigation effect and fine-tune the irrigation decision based on the irrigation effect and plant growth model.

[0008] Specifically, the environmental parameters in step S1 include but are not limited to temperature, humidity, light intensity, and soil moisture.

[0009] Specifically, the specific steps of step S2 include: S2.1: Obtain historical irrigation data from the cloud database and pre-process the historical irrigation data. At the same time, obtain a plant growth model suitable for local climate and soil conditions from the cloud; S2.2: Based on the preprocessed historical irrigation data and plant growth model, a dynamic data analysis model is constructed, and the dynamic data analysis model is trained using the preprocessed historical irrigation data and plant growth model comprehensive data set to find the optimal dynamic data analysis model parameters; S2.3: The sensor network deployed in the farmland collects the environmental parameters currently monitored in real time, performs preprocessing, and inputs the preprocessed environmental parameters into the trained dynamic data analysis model to predict the plant water requirement in different time periods; S2.4: Obtain the current soil moisture conditions through the soil sensor network deployed in the farmland, combine it with the plant water requirement predicted in step S2.3, use intelligent algorithms to make irrigation decisions, and generate the optimal irrigation amount and irrigation time.

[0010] Specifically, the specific steps of S2.2 include: S2.21: Obtain the preprocessed historical irrigation data and plant growth model in step S2.1, and establish a data interface between the historical irrigation data and the output of the plant growth model according to the data format of the preprocessed historical irrigation data and the output of the plant growth model; S2.22: According to the data interface, the pre-processed historical irrigation data is timestamped with the plant growth model, and based on the timestamp matching result, the features of the historical irrigation data and the data output by the plant growth model are extracted, and the features of the historical irrigation data and the output features of the plant growth model are integrated by feature splicing; S2.23: Construct the structure of the comprehensive irrigation data set according to the integrated data characteristics, and divide the comprehensive irrigation data set after forming the comprehensive irrigation data set; S2.24: Determine the input features and output targets of the model, use the random forest algorithm to build the model framework, and obtain the random forest model; S2.25: Use the training set in the comprehensive irrigation data set to train the random forest model, and adjust the parameters of the random forest model through an iterative training process to obtain a trained dynamic data analysis model; S2.26: Use the validation set in the comprehensive irrigation dataset to evaluate the performance of the trained dynamic data analysis model, and optimize the dynamic data analysis model based on the evaluation results to obtain the optimal dynamic data analysis model parameters.

[0011] The calculation formula for the optimal irrigation amount and irrigation time in S2.4 is: ; in, Indicates the required irrigation amount, represents the plant species coefficient, represents the plant species coefficient, represents the weather forecast coefficient, represents the comprehensive adjustment factor, represents the optimal soil moisture content, Indicates the current soil moisture content. The maximum water holding capacity of the soil. Indicates the thickness of the garden soil layer. represents irrigation efficiency, represents the water demand deviation coefficient, It indicates the water requirement of plants per unit time. represents the historical average water demand, t Indicates the irrigation interval time, represents the water requirement function of plants per unit time, g represents light intensity, T represents temperature, v Indicates wind speed, w Indicates humidity.

[0012] Specifically, the specific steps of step S3 include: S3.1: Obtain irrigation decision information and set irrigation thresholds based on irrigation decisions h ; S3.2: Configure an irrigation system and connect the environmental monitoring device to the irrigation system, wherein the irrigation system includes irrigation equipment and a control system; S3.3: When new environmental parameters are monitored When the new environmental parameters are compared with the set irrigation thresholds; like , the control system automatically starts the irrigation program, and at the same time, the irrigation status can be checked and remotely controlled through the remote monitoring platform; S3.4: After irrigation is completed, the control system automatically turns off the irrigation equipment.

[0013] Specifically, a user interface is included that allows managers to view real-time data and adjust irrigation settings.

[0014] An ecological garden intelligent management system, comprising: an environmental monitoring module, a decision-making module, an irrigation execution module, and an irrigation effect evaluation module; The environmental monitoring module is used to collect environmental parameters in the ecological garden in real time and upload the environmental parameter data to the cloud server through the Internet of Things technology; The decision-making module is used to predict the water requirement of plants through the constructed dynamic data analysis model, and make irrigation decisions based on the prediction results; The irrigation execution module is used to determine whether to execute the irrigation operation by judging according to the irrigation decision and the preset irrigation threshold value; The irrigation effect evaluation module is used to record irrigation information, analyze irrigation effects, and adjust and optimize irrigation decisions based on irrigation effects and plant growth models.

[0015] Specifically, the decision module includes: a preprocessing unit, a model unit, and a decision making unit; The pre-processing unit is used to clean, integrate and standardize the collected environmental parameters; The model unit is used to construct a dynamic data analysis model to predict plant water requirements based on historical irrigation data, plant growth models, and current real-time monitored environmental parameters; The decision-making unit is used to make irrigation decisions based on the prediction results of the dynamic data analysis model.

[0016] Specifically, the irrigation execution module includes: a threshold setting unit, a program starting unit, and a remote control unit; The threshold setting unit is used to set the irrigation threshold according to the irrigation decision; The program starting unit is used to automatically start the irrigation program when the monitored environmental parameter reaches a preset irrigation threshold; The remote control unit is used to perform irrigation operations according to irrigation decisions by remotely controlling the irrigation equipment.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes an intelligent management method for ecological gardens. By integrating multiple sensors and Internet of Things technology, environmental parameters are monitored in real time and uploaded to the cloud. A dynamic data analysis model is constructed using historical data and plant growth models. Accurate prediction of plant water requirements in different time periods and intelligent formulation of irrigation decisions are achieved, thereby improving the scientificity and efficiency of irrigation management.

[0018] The present invention proposes an intelligent management method for ecological gardens. By setting irrigation thresholds and automatically starting irrigation programs, the present invention can remotely control irrigation equipment to accurately execute irrigation decisions, while recording irrigation information and feeding it back to a data analysis model for effect evaluation and decision fine-tuning, forming a closed-loop optimization mechanism for irrigation management, effectively improving water resource utilization efficiency and plant growth quality, and promoting the sustainable development of ecological gardens. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of an ecological garden intelligent management method of the present invention; Figure 2 This is a principle flow chart of an ecological garden intelligent management method of the present invention; Figure 3 This is a structural framework diagram of an ecological garden intelligent management system of the present invention. DETAILED DESCRIPTION

[0020] Example 1: Please refer to Figure 1 and Figure 2 , an embodiment provided by the present invention: an ecological garden intelligent management method, comprising the following steps: Step S1: Real-time monitoring of environmental parameters by multiple sensors, and uploading the environmental parameters collected by the multiple sensors to a cloud server using the Internet of Things; Environmental parameters in S1 include but are not limited to temperature, humidity, light intensity, soil moisture and soil pH.

[0021] Specifically, the specific steps of step S1 include: (1) Sensor deployment and initialization: Deploy sensors in the monitoring area and perform initialization settings. Sensors include temperature sensors, humidity sensors, gas sensors, etc. These sensors are reasonably deployed in the area to be monitored to ensure that environmental data can be collected comprehensively and accurately. (2) Data collection and preprocessing: The sensor collects environmental parameter data in real time and performs preprocessing, such as filtering, denoising, and unit conversion; (3) Data transmission: The pre-processed data is transmitted to the cloud server through the IoT communication protocol, where the IoT communication protocol uses a low-power wide area network; (4) Data storage and management: The cloud server receives and stores data and provides data management functions; (5) Data analysis and presentation: Analyze and process data in the cloud, and present the results to users in the form of charts and reports.

[0022] Step S2: On the cloud server, a dynamic data analysis model is constructed using historical irrigation data, plant growth models, and currently monitored environmental parameters in real time. The dynamic data analysis model is used to predict the water requirements of plants in different time periods, and irrigation decisions are made based on the prediction results. Step S3: according to the irrigation decision, the irrigation threshold is set. If the monitored environmental parameters reach the preset irrigation threshold, the system automatically starts the irrigation program and performs irrigation operations according to the irrigation decision through remote control of the irrigation equipment; Step S4: Record detailed information of each irrigation and feed the irrigation records back to the dynamic data analysis model. At the same time, use data analysis methods to analyze the irrigation effect and fine-tune the irrigation decision based on the irrigation effect and plant growth model.

[0023] Specifically, the specific steps of step S4 include: (1) After each irrigation operation, record in detail the date, time, irrigation volume, irrigation method (such as drip irrigation and sprinkler irrigation), irrigation area, irrigation equipment used and other key information to ensure that the recorded information is accurate and facilitate subsequent data analysis and processing; (2) Feedback irrigation record data to the dynamic data analysis model through the data interface to ensure the timeliness and accuracy of data feedback so that the dynamic data analysis model can perform data analysis and processing in a timely manner; (3) Analyze the irrigation records using statistical analysis methods to evaluate the irrigation effect, wherein the statistical analysis method is the prior art content in this field and is not an inventive solution of the present application, and will not be described in detail here; (4) Analyze indicators such as crop growth, soil moisture changes, and water use efficiency after irrigation to evaluate the rationality of irrigation decisions; (5) Loading the plant growth model in step S2, using the plant growth model to predict key indicators such as crop water demand and growth rate, to provide a basis for adjusting irrigation decisions; (6) Fine-tune irrigation decisions based on the irrigation effect and the predicted results of the plant growth model, including adjusting parameters such as irrigation amount, irrigation frequency, and irrigation time to optimize irrigation effects and improve crop yield and quality; (7) Apply the fine-tuned irrigation decisions to actual irrigation operations, observe crop growth and irrigation effects, and verify and iterate based on actual results to optimize irrigation decisions and dynamic data analysis models.

[0024] The specific steps of step S2 include: S2.1: Obtain historical irrigation data from the cloud database and pre-process the historical irrigation data. At the same time, obtain a plant growth model suitable for local climate and soil conditions from the cloud; Among them, historical irrigation data includes information such as irrigation time, irrigation amount, plant type, growth stage, etc.; the plant growth model can predict plant growth and water requirements based on environmental parameters.

[0025] Furthermore, the plant growth model is obtained by: (1) Clarify requirements and conditions: It is necessary to clarify the specific requirements of the required plant growth model, including plant species, growth stage, parameters to be predicted, such as growth rate, biomass, water requirement, and application scenarios of the model, such as agricultural management, scientific research and teaching; at the same time, it is necessary to understand the local climate type, such as cold, mild, hot, dry, and soil conditions, such as soil type, pH value, drainage performance, which are important bases for selecting or customizing plant growth models; Search and filter models (2) Using professional websites or databases: Visit authoritative agricultural research websites, botanical databases, or crop model summary websites. These platforms usually provide a wealth of plant growth model resources. Then, filter them according to plant species, growth stages, and parameters to be predicted to find models that meet your needs. (3) Consider the open source and free nature of the model: Give priority to open source and free plant growth models to reduce the cost of use. If the model is not open source or requires payment, you need to evaluate its cost-effectiveness and consider whether it is worth investing in; (4) Focus on the applicability and accuracy of the model: Check the model’s scope of application to ensure that it can adapt to local climate and soil conditions. Also, check the model’s validation report or user reviews to understand its accuracy and reliability in actual applications. (5) Download and install the model If the model is open source and provides a free download link, you can download the model file directly from the relevant website. After downloading, install and configure it according to the model documentation.

[0026] (6) Verify and adjust the model After installation, the model is verified using local historical climate and soil data to ensure that its predictions are consistent with actual observation data. If there are deviations in the predictions, the model parameters need to be adjusted or optimized, and the key parameters in the model need to be calibrated according to local climate and soil conditions to improve the accuracy and applicability of the model.

[0027] S2.2: Based on the preprocessed historical irrigation data and plant growth model, a dynamic data analysis model is constructed, and the dynamic data analysis model is trained using the preprocessed historical irrigation data and plant growth model comprehensive data set to find the optimal dynamic data analysis model parameters; S2.3: The sensor network deployed in the farmland collects the environmental parameters currently monitored in real time, performs preprocessing, and inputs the preprocessed environmental parameters into the trained dynamic data analysis model to predict the plant water requirement in different time periods; Furthermore, the specific steps of the dynamic data analysis model in S2.3 for prediction include: Load the previously trained dynamic data analysis model from the storage medium; The pre-processed environmental parameters are input into the model, and the model will infer according to the input features and the internally learned rules, and output the predicted values ​​of plant water requirements in different time periods. The model inference process is the prior art content in this field, and is not the inventive solution of this application, and will not be described in detail here; The plant water requirement results predicted by the dynamic data analysis model are output in visual or text form.

[0028] S2.4: Obtain the current soil moisture conditions through the soil sensor network deployed in the farmland, combine it with the plant water requirement predicted in step S2.3, use intelligent algorithms to make irrigation decisions, and generate the optimal irrigation amount and irrigation time.

[0029] Among them, irrigation decisions are made based on crop type, growth stage, soil conditions, and climate conditions, mainly including determining irrigation volume and irrigation time parameters.

[0030] The specific steps of S2.2 include: S2.21: Obtain the preprocessed historical irrigation data and plant growth model in step S2.1, and establish a data interface between the historical irrigation data and the output of the plant growth model according to the data format of the preprocessed historical irrigation data and the output of the plant growth model; It should be noted that when designing the data interface based on the data format output by the historical irrigation data and the plant growth model, the data interface should be able to ensure the integrity, accuracy and consistency of the data during the transmission process. Then, the data interface is implemented using the Python programming language, and the interface is unit tested and integrated tested to ensure that the interface functions correctly and has stable performance.

[0031] S2.22: According to the data interface, the pre-processed historical irrigation data is timestamped with the plant growth model, and based on the timestamp matching result, the features of the historical irrigation data and the data output by the plant growth model are extracted, and the features of the historical irrigation data and the output features of the plant growth model are integrated by feature splicing; Specifically, the specific steps of S2.22 include: (1) Use the designed data interface to connect the pre-processed historical irrigation data and the data source output by the plant growth model, and read the data to ensure the integrity and accuracy of the data; (2) The preprocessed historical irrigation data and the data output by the plant growth model are matched according to their respective timestamps using a matching method with exactly the same timestamp. The successfully matched data pairs and any unmatched data that may exist are recorded.

[0032] (3) For the historical irrigation data that has been successfully matched, extract the features related to plant growth, such as irrigation amount, irrigation frequency, and irrigation duration. For the data output by the plant growth model, extract the features reflecting the plant growth status, such as growth rate, biomass, and leaf area index. (4) splicing the extracted historical irrigation data features and the output features of the plant growth model to form a new feature set. In the present invention, the splicing method selects simple feature vector splicing. Feature vector splicing is a prior art content in this field and is not an inventive solution of the present application, so it will not be described in detail here; (5) Verify the spliced ​​feature set to ensure the accuracy and consistency of the data, and store the verified feature set in a designated data storage medium, such as a database or file system.

[0033] S2.23: Construct the structure of the comprehensive irrigation data set according to the integrated data characteristics, and divide the comprehensive irrigation data set after forming the comprehensive irrigation data set; For example, based on the feature data, assume that a simple comprehensive irrigation data set has the following structure: Crop table: contains fields such as crop ID, crop name, planting date, etc. Irrigation event table: contains fields such as irrigation event ID, crop ID, irrigation date, irrigation amount, irrigation method, etc. Soil moisture table: contains fields such as humidity record ID, crop ID, measurement date, soil moisture value, etc. Meteorological conditions table: contains fields such as meteorological record ID, measurement date, temperature, humidity, precipitation, etc.

[0034] S2.24: Determine the input features and output targets of the model, use the random forest algorithm to build a model framework, and obtain a random forest model, wherein the random forest algorithm and its model building process are prior art contents in this field, are not the inventive solution of the present application, and are not described in detail here; S2.25: Use the training set in the comprehensive irrigation data set to train the random forest model, and adjust the parameters of the random forest model through an iterative training process to obtain a trained dynamic data analysis model, wherein the random forest model training process is the prior art content in this field, is not the inventive solution of the present application, and is not described in detail here; S2.26: Use the validation set in the comprehensive irrigation dataset to evaluate the performance of the trained dynamic data analysis model, and optimize the dynamic data analysis model based on the evaluation results to obtain the optimal dynamic data analysis model parameters.

[0035] Specifically, the specific steps of S2.26 include: (1) A validation set was separated from the comprehensive irrigation dataset to ensure that the validation set was representative and independent of the training set; (2) Load the trained dynamic data analysis model to ensure that the parameters and structure of the dynamic data analysis model are correct; (3) Use the validation set to predict the dynamic data analysis model and calculate the performance indicators of the dynamic data analysis model, such as accuracy, recall, and F1 score. The calculation formulas for accuracy, recall, and F1 score are prior art in this field and are not the inventive solution of the present application, so they are not described in detail here. (4) Based on the evaluation results, analyze the advantages and disadvantages of the dynamic data analysis model and identify the direction of improvement; (5) According to the evaluation results, adjust the parameters of the dynamic data analysis model, such as learning rate, number of iterations, regularization parameters, etc.; (6) Use the optimized parameters to retrain the dynamic data analysis model to ensure that the dynamic data analysis model performs well on the training set. If the performance of the dynamic data analysis model still does not meet expectations, repeat steps (5) to (6) for iterative optimization.

[0036] The calculation formula for the optimal irrigation amount and irrigation time in S2.4 is: ; in, Indicates the required irrigation amount, represents the plant species coefficient, represents the plant species coefficient, represents the weather forecast coefficient, represents the comprehensive adjustment factor, represents the optimal soil moisture content, Indicates the current soil moisture content. The maximum water holding capacity of the soil. Indicates the thickness of the garden soil layer. represents irrigation efficiency, represents the water demand deviation coefficient, It indicates the water requirement of plants per unit time. represents the historical average water demand, t Indicates the irrigation interval time, represents the water requirement function of plants per unit time, g represents light intensity, T represents temperature, v Indicates wind speed, w represents humidity, and , , The configuration mode is determined by those skilled in the art through a large number of experiments.

[0037] It should be noted that different plants have different water requirements, and a plant species coefficient can be set To reflect this difference, for example, drought-tolerant plants have a lower coefficient and moisture-loving plants have a higher coefficient; different soil types have different water retention capacities, so soil type coefficients can be set For example, sandy soil has a lower water retention capacity, while clay soil has a higher water retention capacity; considering the rainfall and evaporation in the next few days, the weather forecast coefficient can be set For example, if there is rainfall in the next few days, the irrigation amount can be appropriately reduced; set the comprehensive adjustment factor Balance the influence of various parameters to ensure the rationality of irrigation volume; water demand deviation coefficient Used to adjust the impact when water demand deviates from the average value, and to amplify or reduce the impact of water demand deviation.

[0038] For example, assuming that the plant's daily water requirement is , historical average water demand , current soil moisture content , optimal soil moisture content , maximum soil water holding capacity , soil thickness , irrigation efficiency ,and , , , , ,but, Calculate soil water deficit: ; Calculate water demand deviation: ; Calculate the amount of irrigation needed: ; Calculate irrigation intervals: .

[0039] The specific steps of S3 include: S3.1: Obtain irrigation decision information and set irrigation thresholds based on irrigation decisions h ,The irrigation threshold includes soil moisture threshold, air humidity threshold, and temperature threshold; S3.2: Configure the irrigation system and connect the environmental monitoring equipment to the irrigation system, wherein the irrigation system includes irrigation equipment and a control system to ensure that the irrigation system can perform accurate irrigation operations according to control signals, the irrigation equipment includes sprinklers and drip irrigation pipes, and the control system includes a controller and a solenoid valve; S3.3: When new environmental parameters are monitored When the new environmental parameters are compared with the set irrigation thresholds; like , the control system automatically starts the irrigation program, and at the same time, the irrigation status can be checked and remotely controlled through the remote monitoring platform; S3.4: After irrigation is completed, the control system automatically turns off the irrigation equipment.

[0040] An intelligent management method for ecological gardens also includes a user interface that allows managers to view real-time data and adjust irrigation settings.

[0041] Example 2: Please refer to Figure 3 Another embodiment provided by the present invention is an ecological garden intelligent management system, comprising: Environmental monitoring module, decision-making module, irrigation execution module, irrigation effect evaluation module; Environmental monitoring module, which is used to collect environmental parameters in the ecological garden in real time, such as temperature, humidity, light intensity, soil moisture, etc., and upload the environmental parameter data to the cloud server through the Internet of Things technology; The decision-making module is used to predict the water demand of plants through the constructed dynamic data analysis model and make irrigation decisions based on the prediction results; The irrigation execution module is used to determine whether to execute the irrigation operation through judgment according to the irrigation decision and the preset irrigation threshold value; The irrigation effect evaluation module is used to record irrigation information, analyze irrigation effects, and adjust and optimize irrigation decisions based on irrigation effects and plant growth models.

[0042] The environmental monitoring module includes: a sensor unit and an IoT communication unit; Sensor units are used to collect environmental parameters such as temperature, humidity, light intensity, and soil moisture to provide real-time and accurate environmental data, providing a basis for data analysis and decision-making; The IoT communication unit is used to upload the data collected by the sensors to the cloud server to achieve real-time data transmission and ensure the timeliness and accuracy of data analysis.

[0043] The decision module includes: pre-processing unit, model unit, and decision-making unit; A pre-processing unit is used to clean, integrate and standardize the collected environmental parameters to improve data quality; The model unit is used to construct a dynamic data analysis model to predict plant water requirements based on historical irrigation data, plant growth models, and current real-time monitored environmental parameters; The decision-making unit is used to make irrigation decisions based on the prediction results of the dynamic data analysis model, including determining key parameters such as irrigation time and water volume to ensure that plants receive the right amount of water.

[0044] The irrigation execution module includes: a threshold setting unit, a program starting unit, and a remote control unit; A threshold setting unit is used to set the irrigation threshold according to the irrigation decision, so as to provide a judgment basis for starting the irrigation program; A program start unit is used to automatically start the irrigation program when the monitored environmental parameters reach the preset irrigation threshold value, so as to realize automatic control of irrigation; The remote control unit is used to remotely control the irrigation equipment to perform irrigation operations according to irrigation decisions, ensuring the accurate execution of irrigation operations.

[0045] The irrigation effect evaluation module includes: irrigation recording unit, data analysis unit, and decision fine-tuning unit; Irrigation recording unit, used to record detailed information of each irrigation, such as irrigation time, water volume, and plant species, to provide data support for the evaluation of irrigation effects; A data analysis unit, used to analyze irrigation effects using data analysis methods and evaluate the execution effects of irrigation decisions; The decision fine-tuning unit is used to fine-tune irrigation decisions based on irrigation effects and plant growth models, and to improve the intelligence level of irrigation management by continuously optimizing irrigation decisions.

[0046] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

Claims

1. An ecological garden intelligent management method, characterized in that: include: Step S1: Real-time monitoring of environmental parameters by multiple sensors, and uploading the environmental parameters collected by the multiple sensors to a cloud server using the Internet of Things; Step S2: On the cloud server, a dynamic data analysis model is constructed using historical irrigation data, plant growth models, and currently monitored environmental parameters in real time. The dynamic data analysis model is used to predict the water requirements of plants in different time periods, and irrigation decisions are made based on the prediction results. Step S3: according to the irrigation decision, the irrigation threshold is set. If the monitored environmental parameters reach the preset irrigation threshold, the system automatically starts the irrigation program and performs irrigation operations according to the irrigation decision through remote control of the irrigation equipment; Step S4: Record detailed information of each irrigation and feed the irrigation records back to the dynamic data analysis model. At the same time, use data analysis methods to analyze the irrigation effect and fine-tune the irrigation decision based on the irrigation effect and plant growth model.

2. The ecological garden intelligent management method according to claim 1, characterized in that: The environmental parameters in step S1 include but are not limited to temperature, humidity, light intensity, and soil moisture.

3. The ecological garden intelligent management method according to claim 2, characterized in that: The specific steps of step S2 include: S2.1: Obtain historical irrigation data from the cloud database and pre-process the historical irrigation data. At the same time, obtain a plant growth model suitable for local climate and soil conditions from the cloud; S2.2: Based on the preprocessed historical irrigation data and plant growth model, a dynamic data analysis model is constructed, and the dynamic data analysis model is trained using the preprocessed historical irrigation data and plant growth model comprehensive data set to find the optimal dynamic data analysis model parameters; S2.3: The sensor network deployed in the farmland collects the environmental parameters currently monitored in real time, performs preprocessing, and inputs the preprocessed environmental parameters into the trained dynamic data analysis model to predict the plant water requirement in different time periods; S2.4: Obtain the current soil moisture conditions through the soil sensor network deployed in the farmland, combine it with the plant water requirement predicted in step S2.3, use intelligent algorithms to make irrigation decisions, and generate the optimal irrigation amount and irrigation time.

4. The ecological garden intelligent management method according to claim 3, characterized in that: The specific steps of S2.2 include: S2.21: Obtain the preprocessed historical irrigation data and plant growth model in step S2.1, and establish a data interface between the historical irrigation data and the output of the plant growth model according to the data format of the preprocessed historical irrigation data and the output of the plant growth model; S2.22: According to the data interface, the pre-processed historical irrigation data is timestamped with the plant growth model, and based on the timestamp matching result, the features of the historical irrigation data and the data output by the plant growth model are extracted, and the features of the historical irrigation data and the output features of the plant growth model are integrated by feature splicing; S2.23: Construct the structure of the comprehensive irrigation data set according to the integrated data characteristics, and divide the comprehensive irrigation data set after forming the comprehensive irrigation data set; S2.24: Determine the input features and output targets of the model, use the random forest algorithm to build the model framework, and obtain the random forest model; S2.25: Use the training set in the comprehensive irrigation data set to train the random forest model, and adjust the parameters of the random forest model through an iterative training process to obtain a trained dynamic data analysis model; S2.26: Use the validation set in the comprehensive irrigation dataset to evaluate the performance of the trained dynamic data analysis model, and optimize the dynamic data analysis model based on the evaluation results to obtain the optimal dynamic data analysis model parameters.

5. The ecological garden intelligent management method according to claim 4, characterized in that: The calculation formula for the optimal irrigation amount and irrigation time in S2.4 is: ； in, Indicates the required irrigation amount, represents the plant species coefficient, represents the plant species coefficient, represents the weather forecast coefficient, represents the comprehensive adjustment factor, represents the optimal soil moisture content, Indicates the current soil moisture content. The maximum water holding capacity of the soil. Indicates the thickness of the garden soil layer. represents irrigation efficiency, represents the water demand deviation coefficient, It indicates the water requirement of plants per unit time. represents the historical average water demand, t Indicates the irrigation interval time, represents the water requirement function of plants per unit time, g represents light intensity, T represents temperature, v Indicates wind speed, w Indicates humidity.

6. The ecological garden intelligent management method according to claim 5, characterized in that: The specific steps of step S3 include: S3.1: Obtain irrigation decision information and set irrigation thresholds based on irrigation decisions h ; S3.2: Configure an irrigation system and connect the environmental monitoring device to the irrigation system, wherein the irrigation system includes irrigation equipment and a control system; S3.3: When new environmental parameters are monitored When the new environmental parameters are compared with the set irrigation thresholds; like , the control system automatically starts the irrigation program, and at the same time, the irrigation status can be checked and remotely controlled through the remote monitoring platform; S3.4: After irrigation is completed, the control system automatically turns off the irrigation equipment.

7. The ecological garden intelligent management method according to claim 6, characterized in that: Also included is a user interface that allows managers to view real-time data and adjust irrigation settings.

8. An ecological garden smart management system, which is used to implement an ecological garden smart management method according to any one of claims 1 to 7, characterized in that: include: Environmental monitoring module, decision-making module, irrigation execution module, irrigation effect evaluation module; The environmental monitoring module is used to collect environmental parameters in the ecological garden in real time and upload the environmental parameter data to the cloud server through the Internet of Things technology; The decision-making module is used to predict the water requirement of plants through the constructed dynamic data analysis model, and make irrigation decisions based on the prediction results; The irrigation execution module is used to determine whether to execute the irrigation operation by judging according to the irrigation decision and the preset irrigation threshold value; The irrigation effect evaluation module is used to record irrigation information, analyze irrigation effects, and adjust and optimize irrigation decisions based on irrigation effects and plant growth models.

9. An ecological garden intelligent management system as claimed in claim 8, characterized in that: The decision module includes: a pre-processing unit, a model unit, and a decision-making unit; The pre-processing unit is used to clean, integrate and standardize the collected environmental parameters; The model unit is used to construct a dynamic data analysis model to predict plant water requirements based on historical irrigation data, plant growth models, and current real-time monitored environmental parameters; The decision-making unit is used to make irrigation decisions based on the prediction results of the dynamic data analysis model.

10. An ecological garden intelligent management system as claimed in claim 9, characterized in that: The irrigation execution module includes: a threshold setting unit, a program starting unit, and a remote control unit; The threshold setting unit is used to set the irrigation threshold according to the irrigation decision; The program starting unit is used to automatically start the irrigation program when the monitored environmental parameter reaches a preset irrigation threshold; The remote control unit is used to perform irrigation operations according to irrigation decisions by remotely controlling the irrigation equipment.

Images