System and method for intelligently analyzing and importing greening industry plant information

Abstract

The invention provides a system and method for intelligently analyzing and importing greening industry plant information, and the method comprises the steps: obtaining plant growth data, environment data and historical maintenance records in real time, carrying out the preprocessing, normalization and standardization processing of the obtained multi-source data, building a plant demand prediction model based on a machine learning algorithm, and carrying out the prediction of the plant demand. Real-time moisture and nutrient requirements are predicted in combination with plant types, growth stages and environmental parameters, a personalized maintenance scheme is dynamically generated according to an output result of a plant requirement prediction model and weather forecast data, an executable instruction is pushed through a mobile terminal or a Web terminal, and the personalized maintenance scheme is provided based on real-time data and individual differences; automatic data acquisition and analysis are achieved, manual intervention is reduced, excessive maintenance is avoided, and waste of water, fertilizer and other resources is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of plant maintenance. More specifically, it relates to a system and method for intelligently analyzing and importing plant information in the greening industry. Background Art

[0002] Currently, plant maintenance management mainly relies on manual experience or preset rules with fixed cycles. For example, traditional systems may recommend activities such as watering and fertilizing based on seasons or fixed schedules, but they cannot dynamically respond to real-time environmental changes (such as sudden rainfall, high temperature and drought, etc.) or plant individual differences (such as growth stage, health status). In the prior art, although some systems can collect basic environmental data, they lack the ability to comprehensively analyze multi-dimensional data, resulting in strong generality and insufficient personalization of maintenance plans, and it is difficult to meet the precise maintenance needs of plants.

[0003] However, the following problems exist in the prior art:

[0004] 1. Static recommendation: relying on fixed cycles or manual experience, unable to dynamically adjust to adapt to real-time environmental changes;

[0005] 2. Data singularity: only considering some environmental parameters (such as soil humidity), ignoring key factors such as plant growth stage, historical maintenance records, etc.;

[0006] 3. Resource waste: excessive or insufficient maintenance activities may cause damage to plant health or waste of resources. Summary of the Invention

[0007] Therefore, in order to solve the above technical problems, the present invention proposes an intelligent system that can integrate environmental data, plant growth status and historical maintenance records in real time, and generate personalized maintenance plans through dynamic analysis, so as to solve the deficiencies of traditional methods in terms of efficiency, accuracy and resource utilization rate, a system and method for intelligently analyzing and importing plant information in the greening industry.

[0008] An intelligent system for analyzing and importing plant information in the greening industry, comprising:

[0009] A data acquisition module, used to obtain plant growth data, environmental data and historical maintenance records in real time, wherein:

[0010] The plant growth data is obtained by periodically scanning the greening area with a drone equipped with a high-resolution spectral imager, and combining image recognition technology to obtain plant physiological indicators, and the plant physiological indicators include tree height, leaf area and pest and disease characteristics;

[0011] The environmental data is used to monitor air temperature, humidity, light intensity and soil moisture in real time through a weather station and soil sensors;

[0012] The historical maintenance records are extracted from a database or a maintenance log, including watering time and fertilization amount;

[0013] A data analysis module, which is used to preprocess, normalize, and standardize the multi-source data obtained by the data acquisition module, and build a plant demand prediction model based on machine learning algorithms, and predict real-time water and nutrient requirements in combination with plant species, growth stages, and environmental parameters;

[0014] A recommendation algorithm module: which is used to dynamically generate a personalized maintenance plan according to the output results of the data analysis module and weather forecast data, and push executable instructions through a mobile terminal or a Web terminal;

[0015] Among them, the system realizes the adaptive adjustment of the maintenance plan by dynamically integrating real-time weather data, plant growth status, and historical records.

[0016] Further, in the data acquisition module, the drone transmits the collected data to the cloud platform in real time through a 5G network, and combines edge computing technology to perform local preprocessing on the spectral imaging data to reduce data transmission latency.

[0017] Further, the machine learning algorithm adopted in the data analysis module is a hybrid model architecture. The random forest model is used to process structured data, and the convolutional neural network (CNN) is used to analyze the pest and disease characteristics in the spectral imaging data. Among them, the outputs of the two types of models are fused through weighting to generate a comprehensive demand prediction result.

[0018] Further, according to the biological characteristics of plant species, the model weights are dynamically adjusted. For example, for plants with large water requirements, the sensitivity of water demand prediction is increased in arid environments; combined with the correlation between fertilization amount and plant growth rate in historical maintenance records, the model is trained to optimize the nutrient recommendation accuracy.

[0019] Further, the recommendation algorithm module constructs a neural network model through the TensorFlow framework, dynamically optimizes the maintenance plan in combination with the weather forecast data for the next 48 hours, and real-time corrects the watering or fertilization plan in the maintenance plan.

[0020] Further, the recommendation algorithm module further includes a meteorological event response mechanism. When the predicted rainfall probability exceeds 70% within the next 48 hours, the watering plan is automatically postponed, and the fertilization time window is recalculated to reduce nutrient loss.

[0021] Further, the recommendation algorithm module introduces resource optimization constraint conditions, specifically: when generating a maintenance plan, a watering strategy with a water saving rate ≥ 30% is preferentially selected; combined with the peak and valley periods of regional electricity prices, it is recommended to perform automated fertilization operations during low energy consumption periods.

[0022] Furthermore, the sensors in the data acquisition module are replaced with LoRa or NB-IoT Internet of Things devices for low-cost data acquisition, and an adaptive sampling strategy is deployed: automatically shortening the sampling interval of the soil moisture sensor to 10 minutes in high-temperature weather; increasing the drone scanning frequency to once a day during the rapid growth period of plants (such as spring).

[0023] A method for intelligently analyzing and importing plant information in the greening industry includes the following steps:

[0024] Step S1: Periodically scan the greening area through a drone equipped with a spectral imager and image recognition technology to obtain plant physiological indicators;

[0025] Step S2: Real-time collect environmental data through a weather station and soil sensors, including temperature, humidity, light intensity, and soil moisture;

[0026] Step S3: Extract historical maintenance records from the database or maintenance logs;

[0027] Step S4: Clean, normalize, and standardize the multi-source data obtained in Steps S1 to S3 to construct a standardized data set;

[0028] Step S5: Based on the plant species and growth stage, use machine learning algorithms combined with environmental parameters to predict real-time water and nutrient requirements;

[0029] Step S6: Integrate weather forecast data, dynamically adjust the maintenance plan, generate executable instructions, and push them to users through the mobile or Web side;

[0030] Step S7: Update the parameters of the machine learning model according to the real-time feedback of plant health data to form a closed-loop optimization mechanism.

[0031] Furthermore, in Step S5, a transfer learning model is established for the growth data of the same plant in different geographical regions to quickly adapt to the maintenance requirements of the new region; adversarial training is introduced to enhance the robustness of the model to extreme weather events.

[0032] Furthermore, in Step S6, when sudden pests and diseases are detected, an emergency maintenance mode is automatically triggered, and a pesticide spraying plan is preferentially pushed; combined with the maintenance preferences manually input by the user (such as giving priority to organic fertilizers), the priority of the recommended instructions is dynamically adjusted.

[0033] Furthermore, in Step S1, the drone uses multi-spectral imaging technology to distinguish the chlorophyll content and water stress index of plant leaves; real-time compressed sensing processing is performed on the scanned data to reduce the occupancy of the 5G network transmission bandwidth.

[0034] Further, in step S2, a grid monitoring network is constructed in the deployment area of the soil sensor, and a high-precision soil moisture distribution map is generated through a spatial interpolation algorithm; the light intensity data is combined with the three-dimensional model of the plant canopy to calculate the actual light-receiving area to optimize the photosynthesis efficiency analysis.

[0035] Advantages of the present invention: The present invention provides a system and method for intelligently analyzing and importing plant information in the greening industry. Through the data acquisition module, plant growth data, environmental data, and historical maintenance records are obtained in real time. The data analysis module is used to preprocess, normalize, and standardize the multi-source data obtained by the data acquisition module, and construct a plant demand prediction model based on machine learning algorithms to predict the real-time water and nutrient requirements in combination with plant species, growth stages, and environmental parameters; the recommendation algorithm module: is used to dynamically generate a personalized maintenance plan according to the output results of the data analysis module and weather forecast data, and push executable instructions through the mobile terminal or the Web terminal; provide a personalized maintenance plan based on real-time data and individual differences; automate data acquisition and analysis, reduce manual intervention, and at the same time avoid over-maintenance and reduce waste of resources such as water and fertilizer. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flowchart of a system and method for intelligently analyzing and importing plant information in the greening industry according to the present invention.

[0037] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. SPECIFIC EMBODIMENTS

[0038] The following embodiments are described to assist in understanding the present application. The embodiments are not and should not be construed in any way as limiting the scope of protection of the present application.

[0039] In the following description, those skilled in the art will recognize that throughout this discussion, components may be described as separate functional units (which may include sub-units), but those skilled in the art will recognize that various components or portions thereof may be divided into separate components, or may be integrated together (including integration within a single system or component).

[0040] At the same time, the connections between components or systems are not intended to be limited to direct connections. Instead, the data between these components may be modified, reformatted, or otherwise changed by intermediate components. Additionally, additional or fewer connections may be used. It should also be noted that the terms "coupled", "connected", or "input" should be understood to include direct connections, indirect connections through one or more intermediate devices, and wireless connections. Embodiment 1:

[0041] As Figure 1As shown in the figure, it is a flowchart of a system and method for intelligently analyzing and importing plant information in the greening industry according to the present invention.

[0042] An intelligent analysis and import system for plant information in the greening industry includes:

[0043] A data acquisition module for obtaining plant growth data, environmental data, and historical maintenance records in real time, where:

[0044] The plant growth data is obtained by periodically scanning the greening area with a drone equipped with a high-resolution spectral imager and combining image recognition technology to obtain plant physiological indicators, including tree height, leaf area, and pest and disease characteristics;

[0045] The environmental data is obtained by real-time monitoring of temperature, humidity, light intensity, and soil moisture through a weather station and soil sensors;

[0046] The historical maintenance records are extracted from a database or maintenance log and include watering time and fertilization amount;

[0047] A data analysis module for preprocessing, normalizing, and standardizing the multi-source data obtained by the data acquisition module, and constructing a plant demand prediction model based on machine learning algorithms to predict real-time water and nutrient requirements in combination with plant species, growth stages, and environmental parameters;

[0048] A recommendation algorithm module: for dynamically generating a personalized maintenance plan according to the output result of the data analysis module and weather forecast data, and pushing executable instructions through a mobile terminal or a Web terminal;

[0049] Among them, the system realizes the adaptive adjustment of the maintenance plan by dynamically integrating real-time weather data, plant growth status, and historical records.

[0050] In the data acquisition module, the drone transmits the collected data to the cloud platform in real time through a 5G network, and combines edge computing technology to perform local preprocessing on the spectral imaging data to reduce data transmission latency.

[0051] The machine learning algorithm used in the data analysis module is a hybrid model architecture. The random forest model is used to process structured data, and the convolutional neural network (CNN) is used to analyze pest and disease characteristics in spectral imaging data. Among them, the outputs of the two types of models are fused by weighting to generate a comprehensive demand prediction result.

[0052] According to the biological characteristics of plant species, the model weights are dynamically adjusted. For example, for plants with high water requirements, the sensitivity of water demand prediction is increased in arid environments; combined with the correlation between fertilization amount and plant growth rate in historical maintenance records, the model is trained to optimize the nutrient recommendation accuracy.

[0053] The recommended algorithm module constructs a neural network model through the TensorFlow framework, dynamically optimizes the maintenance plan by combining the weather forecast data for the next 48 hours, and real-time corrects the watering or fertilization plan in the maintenance plan.

[0054] The recommended algorithm module further includes a meteorological event response mechanism. When the predicted rainfall probability exceeds 70% within the next 48 hours, it automatically postpones the watering plan and recalculates the fertilization time window to reduce nutrient loss.

[0055] The recommended algorithm module introduces resource optimization constraints, specifically: when generating a maintenance plan, it preferentially selects watering strategies with a water saving rate ≥ 30%; in combination with the peak and valley periods of regional electricity prices, it recommends performing automated fertilization operations during low-energy consumption periods.

[0056] The sensors in the data acquisition module are replaced with LoRa or NB-IoT Internet of Things devices for low-cost data acquisition, and an adaptive sampling strategy is deployed: automatically shortening the sampling interval of the soil moisture sensor to 10 minutes in high-temperature weather; increasing the drone scanning frequency to once a day during the rapid growth period of plants (such as spring).

[0057] A method for intelligently analyzing and importing plant information in the greening industry includes the following steps:

[0058] Step S1: Periodically scan the greening area through a drone equipped with a spectral imager and image recognition technology to obtain plant physiological indicators;

[0059] Step S2: Real-time collect environmental data through a weather station and soil sensors, including temperature, humidity, light intensity, and soil moisture;

[0060] Step S3: Extract historical maintenance records from the database or maintenance logs;

[0061] Step S4: Clean, normalize, and standardize the multi-source data obtained in Steps S1 to S3 to construct a standardized data set;

[0062] Step S5: Based on the plant species and growth stage, use machine learning algorithms combined with environmental parameters to predict real-time water and nutrient requirements;

[0063] Step S6: Integrate weather forecast data, dynamically adjust the maintenance plan, generate executable instructions, and push them to users through the mobile or Web side;

[0064] Step S7: Update the parameters of the machine learning model according to the real-time feedback of plant health data to form a closed-loop optimization mechanism.

[0065] In step S5, a transfer learning model is established for the growth data of the same plant in different geographical regions to quickly adapt to the maintenance requirements of the new region; adversarial training is introduced to enhance the robustness of the model against extreme weather events.

[0066] In step S6, when sudden pests and diseases are detected, an emergency maintenance mode is automatically triggered, and a pesticide spraying plan is preferentially pushed; combined with the maintenance preferences manually input by the user (such as organic fertilizers being preferred), the priority of the recommended instructions is dynamically adjusted.

[0067] In step S1, the drone uses multi-spectral imaging technology to distinguish the chlorophyll content and water stress index of plant leaves; the scanned data is processed by compressive sensing in real time to reduce the occupancy of the 5G network transmission bandwidth.

[0068] In step S2, a grid monitoring network is constructed in the area where the soil sensors are deployed, and a high-precision soil moisture distribution map is generated through a spatial interpolation algorithm; the light intensity data is combined with the three-dimensional model of the plant canopy to calculate the actual light-receiving area to optimize the analysis of photosynthesis efficiency.

[0069] Advantages of the present invention: The present invention proposes a system and method for intelligently analyzing and importing plant information in the greening industry. Through the data acquisition module, plant growth data, environmental data, and historical maintenance records are obtained in real time. The data analysis module is used to preprocess, normalize, and standardize the multi-source data obtained by the data acquisition module, and a plant demand prediction model is constructed based on machine learning algorithms to predict the real-time water and nutrient requirements in combination with the plant species, growth stage, and environmental parameters. The recommendation algorithm module: is used to dynamically generate a personalized maintenance plan according to the output result of the data analysis module and the weather forecast data, and push executable instructions through the mobile terminal or the Web terminal; provide a personalized maintenance plan based on real-time data and individual differences; automated data acquisition and analysis reduce manual intervention, while avoiding over-maintenance and reducing waste of resources such as water and fertilizer.

[0070] The above embodiments only represent several implementation manners of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent should be subject to the appended claims.

Claims

1. An intelligent system for analyzing and importing plant information in the greening industry, characterized in that: A data acquisition module for obtaining plant growth data, environmental data, and historical maintenance records in real time, where: The plant growth data is obtained by periodically scanning the greening area with a drone equipped with a high-resolution spectral imager and combining image recognition technology to obtain plant physiological indicators, including tree height, leaf area, and pest and disease characteristics; The environmental data is obtained by a weather station and soil sensors to monitor temperature, humidity, light intensity, and soil moisture in real time; The historical maintenance records are extracted from a database or maintenance log, including watering time and fertilization amount; A data analysis module for preprocessing, normalizing, and standardizing the multi-source data obtained by the data acquisition module, and constructing a plant demand prediction model based on machine learning algorithms to predict real-time water and nutrient requirements in combination with plant species, growth stage, and environmental parameters; A recommendation algorithm module: for dynamically generating a personalized maintenance plan according to the output result of the data analysis module and weather forecast data, and pushing executable instructions through a mobile terminal or a Web terminal; Among them, the system realizes the adaptive adjustment of the maintenance plan by dynamically integrating real-time weather data, plant growth status, and historical records.

2. The system for intelligently analyzing and importing plant information in the greening industry according to claim 1, wherein: In the data acquisition module, the drone transmits the collected data to the cloud platform in real time through a 5G network, and combines edge computing technology to perform local preprocessing on the spectral imaging data to reduce data transmission latency.

3. The system for intelligently analyzing and importing plant information in the greening industry according to claim 1, wherein: The machine learning algorithm adopted in the data analysis module is a hybrid model architecture. The random forest model is used to process structured data, and the convolutional neural network (CNN) is used to analyze pest and disease characteristics in spectral imaging data. Among them, the outputs of the two types of models are fused by weighting to generate a comprehensive demand prediction result.

4. The system for intelligently analyzing and importing plant information in the greening industry according to claim 1, wherein: According to the biological characteristics of plant species, dynamically adjust the model weights. For example, for plants with high water requirements, increase the sensitivity of water demand prediction in arid environments; combine the correlation between fertilization amount and plant growth rate in historical maintenance records to train the model to optimize nutrient recommendation accuracy.

5. The system for intelligently analyzing and importing plant information in the greening industry according to claim 1, wherein: The recommendation algorithm module constructs a neural network model through the TensorFlow framework, dynamically optimizes the maintenance plan in combination with weather forecast data for the next 48 hours, and real-time corrects the watering or fertilization plan in the maintenance plan.

6. The system for intelligently analyzing and importing plant information in the greening industry according to claim 5, characterized in that: The recommendation algorithm module further includes a meteorological event response mechanism. When the predicted rainfall probability exceeds 70% within the next 48 hours, automatically postpone the watering plan and recalculate the fertilization time window to reduce nutrient loss.

7. The system for intelligently analyzing and importing plant information in the greening industry according to claim 1, characterized in that: The recommendation algorithm module introduces resource optimization constraints, specifically: when generating a maintenance plan, preferentially select a watering strategy with a water saving rate ≥ 30%; combine the peak and valley periods of regional electricity prices to recommend automated fertilization operations during low energy consumption periods.

8. The system for intelligently analyzing and importing plant information in the greening industry according to claim 1, characterized in that: The sensors in the data acquisition module are replaced with LoRa or NB-IoT Internet of Things devices for low-cost data acquisition, and an adaptive sampling strategy is deployed: automatically shorten the sampling interval of the soil moisture sensor to 10 minutes in high-temperature weather; increase the drone scanning frequency to once a day during the rapid growth period of plants (such as spring).

9. A method for intelligently analyzing and importing plant information in the greening industry, characterized in that: Including the following steps: Step S1: Periodically scan the greening area by using a drone equipped with a spectral imager and image recognition technology to obtain plant physiological indicators; Step S2: Real-time collect environmental data through a weather station and soil sensors, including air temperature, humidity, light intensity, and soil moisture; Step S3: Extract historical maintenance records from the database or maintenance logs; Step S4: Clean, normalize, and standardize the multi-source data obtained in Steps S1 to S3 to construct a standardized data set; Step S5: Based on the plant species and growth stage, use machine learning algorithms combined with environmental parameters to predict the real-time water and nutrient requirements; Step S6: Integrate weather forecast data, dynamically adjust the maintenance plan, generate executable instructions, and push them to the user through the mobile or Web side; Step S7: According to the real-time feedback of plant health data, update the parameters of the machine learning model to form a closed-loop optimization mechanism.

10. The method for intelligently analyzing and importing plant information in the greening industry according to claim 9, wherein: In Step S5, establish a transfer learning model for the growth data of the same plant in different geographical regions to quickly adapt to the maintenance requirements of the new region; introduce adversarial training to enhance the robustness of the model to extreme weather events.

Images