Intelligent management system for modern agricultural demonstration park

Abstract

The invention discloses an intelligent management system for a modern agricultural demonstration park. Relates to the technical field of agricultural park management. Comprising an intelligent sensing layer, a data processing layer, an application service layer and a decision support layer, the intelligent sensing layer is used for collecting park environment data, crop growth data and equipment state data; the data processing layer analyzes the park data collected by the intelligent sensing layer by using an AI model, outputs multi-source data, analyzes the environment of the park by fusing the multi-source data and performs risk prediction on the park environment to obtain a risk prediction result; the application service layer gives a management suggestion according to the park environment and the risk prediction result; and the decision support layer generates a dynamic decision scheme according to the management suggestions. The deployment cost and the adaptation difficulty of the agricultural demonstration park are reduced, the park operation efficiency and the anti-risk capability are greatly improved, and the large-scale application of digital management of the modern agricultural park is promoted.

Description

Technical Field

[0001] This invention relates to the field of agricultural park management technology, and more specifically to an intelligent management system for modern agricultural demonstration parks. Background Technology

[0002] Modern agricultural demonstration parks, as core carriers of agricultural modernization, are continuously improving in terms of scale and intensification. However, deep-seated contradictions in their management and operation are also becoming increasingly prominent. Currently, most demonstration parks are still in a decentralized management model with multiple scenarios. Planting areas, breeding areas, and tourism areas operate independently, environmental monitoring relies on manual inspections, and production control depends on experience-based judgment. This results in low efficiency of cross-regional collaboration, delayed response to emergencies, and difficulty in meeting the precision management needs of modern agriculture.

[0003] At the data application level, the demonstration park suffers from a severe "data silo" phenomenon. Environmental data from weather stations, soil sensors, and irrigation equipment, data from the production process (seedling, fertilization, and harvesting), and order and logistics information from the transaction process are scattered across different systems. The data formats are inconsistent, and the correlations are weak, failing to form a complete data chain and hindering the in-depth mining of data value. Simultaneously, the application of intelligent technologies is limited to single aspects, such as achieving automatic irrigation in only certain areas, lacking intelligent coverage of the entire process including production, transactions, and tourism. This results in a low overall level of intelligence within the park, failing to fully leverage the driving role of technology in improving agricultural quality and efficiency.

[0004] Furthermore, the existing management systems have significant shortcomings in their functional coverage, with most focusing only on production control or environmental monitoring, neglecting the needs for convenient transaction services, experiential smart tourism, and scientific decision support. Regulatory authorities also struggle to monitor the park's operational dynamics in real time, hindering precise supervision and optimization.

[0005] Therefore, developing a fully intelligent system that integrates environmental monitoring, production control, transaction services, smart tourism, decision support, and regulatory optimization has become a key path to solving the management challenges of modern agricultural demonstration parks and promoting high-quality agricultural development. Summary of the Invention

[0006] In view of this, the present invention provides an intelligent management system for modern agricultural demonstration parks, which can effectively reduce the deployment cost and adaptation difficulty of agricultural demonstration parks, significantly improve the park's operational efficiency and risk resistance, and promote the large-scale application of digital management in modern agricultural parks.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent management system for modern agricultural demonstration parks, comprising: an intelligent sensing layer, a data processing layer, an application service layer, and a decision support layer;

[0008] The intelligent sensing layer is used to collect park environmental data, crop growth data, and equipment status data;

[0009] The data processing layer uses an AI model to analyze the park data collected by the intelligent sensing layer, outputs multi-source data, analyzes the park environment by integrating multi-source data, and makes risk predictions for the park environment to obtain environmental risk prediction results.

[0010] The application service layer provides management suggestions based on the park environment and environmental risk prediction results;

[0011] The decision support layer generates dynamic decision-making schemes based on management recommendations.

[0012] Preferably, the intelligent sensing layer includes an Internet of Things (IoT) sensor network and image acquisition equipment; the IoT sensor network includes soil parameter sensors, climate parameter sensors, water quality parameter sensors, and equipment status sensors, which respectively collect data on saturated soil bulk density, soil particle density, soil moisture content, air temperature and humidity, water vapor partial pressure in the air, daily precipitation, types and concentrations of water pollutants, as well as the operating status and energy consumption data of irrigation equipment and aquaculture equipment in the park; the image acquisition equipment is used to collect crop growth images and extract data on crop growth cycle stages, leaf health, and appearance characteristics of pests and diseases.

[0013] Preferably, the process of using AI models to analyze the park data collected by the intelligent sensing layer includes: the AI ​​models include a soil fertility assessment model, a crop disease and pest prediction model, a crop growth progress model, and a park environmental comprehensive assessment model, wherein the soil fertility assessment model, the crop disease and pest prediction model, the crop growth progress model, and the park environmental comprehensive assessment model respectively output the corresponding soil state coefficient, disease and pest occurrence risk level, crop expected maturity time, and park comprehensive environmental index.

[0014] Preferably, the process of risk prediction for the park environment includes:

[0015] Construct an environmental risk prediction model;

[0016] By inputting air temperature and humidity, water vapor pressure in the air, daily precipitation, and soil moisture content into the risk prediction model, the type of disaster is predicted, and the environmental risk prediction results are obtained.

[0017] Preferably, the soil fertility assessment model adopts a multiple linear regression model; the crop disease and pest prediction model uses a random forest model; the crop growth progress model adopts a Logistic model to simulate the S-shaped curve of crop growth; and the park environment comprehensive assessment model is implemented using the analytic hierarchy process.

[0018] Preferably, the specific implementation process of the comprehensive environmental assessment model for the park includes:

[0019] The system incorporates dynamic weighting factors for crop growth stages. It dynamically adjusts the calculation weights of soil state coefficient, pest and disease risk level, and expected crop maturity time based on the current crop growth stage, and corrects the weight allocation in real time through reinforcement learning.

[0020] Preferably, the soil fertility assessment model, crop disease and pest prediction model, crop growth progress model, and park environmental comprehensive assessment model are interconnected and coordinated through a multi-model fusion decision network. The specific process includes:

[0021] The multi-model fusion decision network includes a knowledge graph of soil-crop-pests association based on graph neural network (GNN). Soil state coefficient, pest risk level, expected crop maturity time and comprehensive environmental index of the park are used as nodes of the knowledge graph. Hidden relationships between nodes are mined to generate a coupled assessment report of crop growth and environmental parameters.

[0022] Preferably, the application service layer includes an intelligent production management subsystem, an intelligent transaction subsystem, a park supervision subsystem, and an intelligent tourism subsystem. Based on the analysis results and risk prediction results of the data processing layer, it provides management suggestions for the entire industrial chain of the park and feeds back the data on the implementation effect of the management suggestions to the multi-model fusion decision network of the data processing layer.

[0023] Preferably, the decision support layer generates a dynamic decision-making scheme based on the management suggestions output by the application service layer, combined with the park's historical operation data and agricultural product market data. The execution effect data of the decision-making scheme is transmitted back to the intelligent sensing layer through a dynamic calibration interface to adjust the sampling frequency of the sensors in the intelligent sensing layer.

[0024] As can be seen from the above technical solution, compared with the prior art, the present invention discloses an intelligent management system for modern agricultural demonstration parks, with the following beneficial effects:

[0025] This system constructs a closed-loop collaborative architecture through a dynamic calibration interface and a model co-evolution module. The decision support layer can adjust the sampling frequency of the perception layer based on the execution effect, and the data processing layer can optimize the AI ​​model weights based on application feedback. The system's decision accuracy is improved compared to traditional solutions, and the AI ​​model analysis is aligned with actual operational needs, solving the problems of data silos and decision lag, and enabling the system to self-iterate and upgrade.

[0026] Multi-model fusion assessment solves the problem of assessment distortion in complex environments. This system relies on the knowledge graph of soil-crop-pests and dynamic weighting mechanism to explore the coupling relationship between multiple environmental parameters and crop growth, which greatly improves the accuracy of comprehensive environmental assessment.

[0027] The entire industry chain is linked to improve the park's operational efficiency and risk resistance: Through a dynamic linkage engine across the entire industry chain, the system achieves dynamic matching of production capacity, demand, and tourism experience. When there is a surplus of crops, tourism picking promotions are automatically triggered; when disasters occur, the production, trading, and tourism subsystems are simultaneously dispatched to respond, effectively reducing disaster losses and effectively solving the industry pain points of disconnect between production and sales and conflicts between tourism enterprises in traditional parks.

[0028] Customized decision-making for regional crops reduces system deployment costs and adaptation difficulties: With the help of adaptive decision knowledge graphs and transfer learning modules, decision-making experience from similar regions / crops can be transferred and adapted without training the model from scratch. This significantly reduces the threshold for system implementation in different agricultural scenarios, meets the management needs of diverse regions and crop types, and promotes the large-scale application of digital management in modern agricultural parks. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of the system structure provided by the present invention.

[0031] Figure 2 This is a schematic diagram of the intelligent sensing layer structure provided by the present invention.

[0032] Figure 3 This is a schematic diagram of the application service layer structure provided by the present invention. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] like Figure 1 As shown in the figure, an embodiment of the present invention discloses an intelligent management system for modern agricultural demonstration parks, including: an intelligent sensing layer, a data processing layer, an application service layer, and a decision support layer;

[0035] The intelligent sensing layer is used to collect park environmental data, crop growth data, and equipment status data;

[0036] The data processing layer uses AI models to analyze the park data collected by the intelligent perception layer, outputs multi-source data, analyzes the park environment by integrating multi-source data, and makes risk predictions for the park environment to obtain risk prediction results.

[0037] The application service layer provides management suggestions based on the park environment and risk prediction results;

[0038] The decision support layer generates dynamic decision-making schemes based on management recommendations.

[0039] In a specific embodiment of the present invention, the specific process of the data processing layer performing analysis includes:

[0040] The data collected by the intelligent perception layer is preprocessed, including data cleaning, deduplication, outlier removal, and missing value completion.

[0041] Specifically, such as Figure 2 As shown, the intelligent sensing layer includes an Internet of Things (IoT) sensor network and image acquisition equipment. The IoT sensor network includes soil parameter sensors, climate parameter sensors, water quality parameter sensors, and equipment status sensors, which respectively collect data on saturated soil bulk density, soil particle density, soil moisture content, air temperature and humidity, water vapor partial pressure in the air, daily precipitation, types and concentrations of water pollutants, and the operating status and energy consumption data of irrigation and aquaculture equipment in the park. The image acquisition equipment is used to collect crop growth images and extract data on crop growth cycle stages, leaf health, and appearance characteristics of pests and diseases.

[0042] Specifically, the process of using AI models to analyze the park data collected by the intelligent sensing layer includes: the AI ​​models include a soil fertility assessment model, a crop disease and pest prediction model, a crop growth progress model, and a comprehensive park environment assessment model. The soil fertility assessment model, the crop disease and pest prediction model, the crop growth progress model, and the comprehensive park environment assessment model respectively output the corresponding soil state coefficient, disease and pest occurrence risk level, crop expected maturity time, and comprehensive park environment index.

[0043] Specifically, the process of risk prediction for the park environment includes:

[0044] Construct an environmental risk prediction model;

[0045] By inputting air temperature and humidity, water vapor pressure in the air, daily precipitation, and soil moisture content into the risk prediction model, the type of disaster is predicted, and the environmental risk prediction results are obtained.

[0046] In a specific embodiment of this invention, a random forest model is used to predict the risks of the park environment. The input data includes collected climate, soil, and water quality data (such as precipitation over three consecutive days and duration of soil waterlogging). The output is the predicted disaster type, such as the probability of occurrence (85%) of disasters like rainstorms, droughts, and frosts, and the affected area (e.g., the eastern planting area of ​​the park).

[0047] Specifically, the soil fertility assessment model adopts a multiple linear regression model; the crop disease and pest prediction model uses a random forest model; the crop growth progress model adopts a Logistic model to simulate the S-shaped curve of crop growth; and the park environment comprehensive assessment model is implemented using the analytic hierarchy process.

[0048] In a specific embodiment of the present invention, in soil fertility assessment, a multiple linear regression model is used to assess soil fertility. The dependent variable is the soil state coefficient, while the independent variables may include the content of nutrients such as nitrogen, phosphorus, and potassium in the soil, as well as the soil's pH value, organic matter content, texture, and other physicochemical properties.

[0049] In another specific embodiment of the present invention, the specific process for predicting crop diseases and pests includes:

[0050] Key factors influencing crop pest and disease occurrence, such as weather conditions, crop variety, and crop growth stage, are identified. These factors serve as input features for the model. A large amount of pest and disease occurrence data is collected, and the corresponding pest and disease occurrence risk levels are labeled using observation and other methods. This data is divided into training and testing sets, and the model is trained using the training set. During training, the model constructs multiple decision trees through random sampling and feature selection, and synthesizes the prediction results of the random forest model through voting and other methods.

[0051] The trained model is evaluated using a test set, focusing primarily on classification accuracy, such as precision and recall. Based on the evaluation results, the model is optimized, such as adjusting model parameters (e.g., the number of decision trees, tree depth), or further filtering and processing of features.

[0052] In another specific embodiment of the present invention, the crop growth progress assessment process includes: identifying key factors affecting crop growth progress, such as crop morphological indicators, physiological indicators, and agricultural operation information. These factors serve as input features for the model. A Logistic model (a nonlinear regression model suitable for simulating the S-shaped curve of crop growth) is selected.

[0053] In another specific embodiment of the invention, key factors affecting the environmental quality of the park are identified, such as air quality, water quality, soil quality, noise level, and light intensity. These factors serve as input features for the model. The Analytic Hierarchy Process (AHP) is a multi-criteria decision analysis method that decomposes complex problems into multiple levels and factors by constructing a hierarchical model, and determines the weight of each factor through methods such as expert scoring.

[0054] Specifically, the implementation process of the comprehensive environmental assessment model for the park includes:

[0055] The system includes dynamic weighting factors for crop growth stages. The calculation weights of soil state coefficient, pest and disease risk level, and expected crop maturity time are dynamically adjusted according to the current crop growth stage. The weight allocation is also dynamically adjusted according to the crop growth stage.

[0056] In another specific embodiment of the present invention, the comprehensive environmental assessment model of the park first presets the basic weights for different growth stages: during the seedling stage, the soil condition coefficient (affecting root development) is set to 0.5, and the weights of the climate and water quality coefficients are 0.3 and 0.2, respectively; during the flowering stage, the weight of the climate humidity coefficient (affecting pollination) is increased to 0.5, and the weights of the soil and water quality coefficients are reduced to 0.3 and 0.2, respectively; during the harvest stage, the weight of the water quality coefficient (affecting fruit quality) is increased to 0.4, and the weights of the soil and climate coefficients are adjusted to 0.35 and 0.25, respectively.

[0057] The soil condition coefficient, pest and disease risk level, and expected crop maturity time were normalized using the following formula:

[0058] Assessment result = Soil state coefficient * 0.5 + Climate * 0.3 + Water quality * 0.2 + Risk level of pests and diseases + Expected maturity time of crops.

[0059] The values ​​of 0.5, 0.3, and 0.2 in the formula are dynamically adjusted according to the growth stage of the crop.

[0060] Meanwhile, the model incorporates a reinforcement learning module to track the effects of weight allocation in real time: if increasing the climate weight at a certain stage improves crop pollination success, the system automatically increases the climate weight for that stage by 5%-10%; if the soil weight is too high but crop root development does not show significant improvement, the soil weight is reduced by 3%-5%. Through "basic weight adaptation stage + reinforcement learning dynamic correction," the system ensures that the comprehensive environmental index calculation always aligns with the current core needs of the crops, avoiding assessment biases caused by fixed weights, and providing a more accurate quantitative basis for environmental regulation in the park.

[0061] Specifically, the soil fertility assessment model, crop disease and pest prediction model, crop growth progress model, and park environmental comprehensive assessment model achieve collaborative linkage through a multi-model fusion decision network. The specific process includes:

[0062] The multi-model fusion decision network includes a knowledge graph of soil-crop-pests association based on graph neural network (GNN). Soil state coefficient, pest risk level, expected crop maturity time and comprehensive environmental index of the park are used as nodes of the knowledge graph. Hidden relationships between nodes are mined to generate a coupled assessment report of crop growth and environmental parameters.

[0063] In a specific embodiment of the present invention, the association knowledge graph constructed by the graph neural network (GNN) transforms the originally independent assessment results such as soil state coefficient, pest and disease risk level, environmental risk prediction results, and crop maturity time into interconnected nodes, and uncovers hidden associations that cannot be identified by a single model (such as the coupled assessment report of crop growth-environmental parameters-risk parameters, clarifying the specific impact of risks on park operations), thus solving the problem of one-sided assessment caused by neglecting the coupling relationship of multiple factors in traditional single-model analysis.

[0064] Enhancing the reliability of decision-making and reducing production risks: The coupled assessment report integrates the correlation logic between multi-dimensional environmental and crop data, enabling managers to clearly understand the synergistic impact of various factors on crop growth (e.g., how insufficient soil fertility exacerbates susceptibility to pests and diseases), avoiding the blindness of decisions based on a single indicator. Experimental data shows that it can reduce the error rate of agricultural operations. Providing precise knowledge support for the entire industry chain linkage: The correlation relationships between nodes in the knowledge graph (e.g., "increased pest and disease risk → delayed maturity time") provide the underlying logic for the dynamic linkage engine of the entire industry chain in the application service layer, enabling decisions such as capacity adjustment, market pricing, and tourism activity arrangements to be made based on the coupling effect of multiple factors, further improving the overall operational efficiency of the park.

[0065] Specifically, such as Figure 3 As shown, the application service layer includes an intelligent production management subsystem, an intelligent transaction subsystem, a park supervision subsystem, and an intelligent tourism subsystem. Based on the analysis results of the data processing layer and the environmental risk prediction results, it provides management suggestions for the entire industrial chain of the park and feeds back the data on the implementation effect of the management suggestions to the multi-model fusion decision network of the data processing layer.

[0066] In a specific embodiment of the present invention, disaster prevention and pre-treatment suggestions are output based on environmental disaster risk prediction, such as 85% risk of rainstorm → shutting down irrigation equipment 4 hours in advance and reinforcing the support frame of the eastern greenhouse.

[0067] Based on equipment failure risk prediction, the system outputs equipment pre-inspection and maintenance recommendations. For example, if the irrigation equipment has a high failure risk, the motor can be replaced within 24 hours to avoid affecting watering the next day.

[0068] Specifically, the decision support layer generates dynamic decision-making schemes based on the management suggestions output by the application service layer, combined with historical operational data of the park and market data of agricultural products. The execution effect data of the decision-making schemes is transmitted back to the intelligent perception layer through the dynamic calibration interface to adjust the sampling frequency of the sensors in the intelligent perception layer.

[0069] In a specific embodiment of the present invention, the risk response effect and risk prediction accuracy are fed back to the intelligent perception layer through a dynamic calibration interface. For example, if the rainstorm prediction is accurate, the sampling frequency of the climate parameter sensor will be increased from 1 hour / time to 15 minutes / time during high-risk periods to improve the subsequent prediction accuracy.

[0070] Model optimization involves feeding back risk prediction deviation data (such as the prediction that equipment failure did not occur) to the data processing layer, adjusting the risk prediction model parameters, and optimizing the feature weights of the random forest model.

[0071] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0072] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent management system for modern agricultural demonstration parks, characterized in that, include: Intelligent sensing layer, data processing layer, application service layer, and decision support layer; The intelligent sensing layer is used to collect park environmental data, crop growth data, and equipment status data; The data processing layer uses AI models to analyze the park data collected by the intelligent sensing layer, outputs multi-source data, analyzes the park environment by integrating multi-source data and makes risk predictions for the park environment, and obtains environmental risk prediction results. The application service layer provides management suggestions based on the park environment and environmental risk prediction results; The decision support layer generates dynamic decision-making schemes based on management recommendations.

2. The intelligent management system for modern agricultural demonstration parks according to claim 1, characterized in that, The intelligent sensing layer includes an Internet of Things (IoT) sensor network and image acquisition equipment. The IoT sensor network includes soil parameter sensors, climate parameter sensors, water quality parameter sensors, and equipment status sensors, which respectively collect data on saturated soil bulk density, soil particle density, soil moisture content, air temperature and humidity, water vapor partial pressure in the air, daily precipitation, types and concentrations of water pollutants, as well as the operating status and energy consumption data of irrigation and aquaculture equipment in the park. The image acquisition equipment is used to collect crop growth images and extract data on crop growth cycle stages, leaf health, and appearance characteristics of pests and diseases.

3. The intelligent management system for modern agricultural demonstration parks according to claim 2, characterized in that, The process of analyzing park data collected by the intelligent sensing layer using AI models includes: The AI ​​model includes a soil fertility assessment model, a crop disease and pest prediction model, a crop growth progress model, and a comprehensive park environment assessment model. The soil fertility assessment model, the crop disease and pest prediction model, the crop growth progress model, and the comprehensive park environment assessment model respectively output the corresponding soil state coefficient, disease and pest occurrence risk level, crop expected maturity time, and comprehensive park environment index.

4. The intelligent management system for modern agricultural demonstration parks according to claim 2, characterized in that, The process of risk prediction for the park environment includes: Construct an environmental risk prediction model; By inputting air temperature and humidity, water vapor pressure in the air, daily precipitation, and soil moisture content into the risk prediction model, the type of disaster is predicted, and the environmental risk prediction results are obtained.

5. The intelligent management system for modern agricultural demonstration parks according to claim 2, characterized in that, The soil fertility assessment model adopts a multiple linear regression model; the crop disease and pest prediction model uses a random forest model; the crop growth progress model adopts a logistic model to simulate the S-shaped curve of crop growth; and the park environment comprehensive assessment model is implemented using the analytic hierarchy process.

6. The intelligent management system for modern agricultural demonstration parks according to claim 5, characterized in that, The specific implementation process of the comprehensive environmental assessment model for the park includes: The system incorporates dynamic weighting factors for crop growth stages. It dynamically adjusts the calculation weights of soil state coefficient, pest and disease risk level, and expected crop maturity time based on the current crop growth stage, and corrects the weight allocation in real time through reinforcement learning.

7. The intelligent management system for modern agricultural demonstration parks according to claim 3, characterized in that, The soil fertility assessment model, crop disease and pest prediction model, crop growth progress model, and park environmental comprehensive assessment model are interconnected and coordinated through a multi-model fusion decision network. The specific process includes: The multi-model fusion decision network includes a knowledge graph of soil-crop-pests association based on graph neural network (GNN). Soil state coefficient, pest risk level, expected crop maturity time and comprehensive environmental index of the park are used as nodes of the knowledge graph. Hidden relationships between nodes are mined to generate a coupled assessment report of crop growth and environmental parameters.

8. The intelligent management system for modern agricultural demonstration parks according to claim 7, characterized in that, The application service layer includes an intelligent production management subsystem, an intelligent transaction subsystem, a park supervision subsystem, and an intelligent tourism subsystem. Based on the analysis results of the data processing layer and the environmental risk prediction results, it provides management suggestions for the entire industrial chain of the park and feeds back the data on the implementation effect of the management suggestions to the multi-model fusion decision network of the data processing layer.

9. The intelligent management system for modern agricultural demonstration parks according to claim 8, characterized in that, The decision support layer generates dynamic decision-making schemes based on the management suggestions output by the application service layer, combined with historical operation data of the park and market data of agricultural products. The execution effect data of the decision-making schemes is transmitted back to the intelligent perception layer through the dynamic calibration interface to adjust the sampling frequency of the sensors in the intelligent perception layer.

Images