Plant germplasm resource intelligent cultivation system based on Internet of Things and digital technology

Abstract

The invention discloses a plant germplasm resource intelligent cultivation system based on the Internet of Things and the digital technology, and the system comprises a cultivation information collection and fusion module, a plant growth state judgment module, a pest and disease distribution sample collection module, a photosynthesis state cultivation module, and a photosynthesis state evaluation module. The system can realize acquisition and supervision of unit time cultivation information in different plant growth environments, and analysis of plant growth states and digital monitoring, thereby completing photosynthesis cultivation of biophysical information and physiological and ecological information in different plant growth environments. According to the invention, germplasm resource plant growth state pest and disease distribution management and systematic photosynthesis cultivation and evaluation capability can be realized, and the digital monitoring efficiency of different plant growth environments is ensured, so that layered effective cultivation of plants in different plant growth environments is realized; and the gene stress tolerance modeling accuracy of different plant growth environments is improved.

Description

Technical Field

[0001] The present invention relates to the field of germplasm resource cultivation, and in particular to an intelligent plant germplasm resource cultivation system based on the Internet of Things and digital technologies. Background Art

[0002] With the continuous development of agricultural technology, the Internet of Things (IoT) and digital technologies are increasingly being applied in agriculture, particularly in the intelligent cultivation of germplasm resources, where they demonstrate tremendous potential. These technologies, through the integration of sensors, remote sensing, and intelligent devices, enable real-time monitoring of environmental changes, soil conditions, and plant growth, providing refined and intelligent management solutions for agricultural production. Traditional agricultural cultivation methods rely primarily on experience and manual observation. While these methods guarantee crop growth to a certain extent, they suffer from low efficiency and accuracy. Intelligent cultivation methods for germplasm resources based on the IoT are becoming a new trend in agricultural technology development. Through intelligent devices and systems, agricultural management no longer relies solely on experience and casual observation, but instead relies on big data and precise models, improving the sustainability and efficiency of agricultural production. However, despite significant technological progress in this field, many challenges remain, particularly in assessing plant growth status, assessing environmental adaptability, monitoring pests and diseases, and modeling genetic stress tolerance.

[0003] Although the Internet of Things and digital technologies have provided strong support for agricultural production, existing intelligent breeding methods for germplasm resources still face many challenges, especially in the judgment and management of plant growth status. Most current technologies can only be optimized for specific environments or single crops, and cannot form a universal, unified solution that can adapt to different plant growth environments. The plant growth environment varies due to various factors such as region, climate, and soil, which makes it impossible for most existing technologies to provide accurate plant growth status judgment in diverse agricultural production environments. For example, different types of plants have different requirements for temperature, humidity, and light, and existing intelligent systems often only make judgments based on fixed rules and cannot dynamically adjust the growth status analysis model according to factors such as plant variety differences and environmental changes.

[0004] Furthermore, current intelligent systems have significant shortcomings in pest and disease monitoring and management. Although IoT technology has achieved breakthroughs in environmental monitoring and data collection, the occurrence of plant pests and diseases is often influenced by multiple factors (such as climate change, soil conditions, and crop varieties), making it difficult for existing systems to accurately predict and control pests and diseases in a comprehensive, multi-layered environment. To improve the accuracy of plant growth status, it is necessary to combine diversified data analysis methods and incorporate variables from different environments, crops, and growth stages into the model, thereby achieving more refined planting management.

[0005] While intelligent germplasm breeding methods based on the Internet of Things and digital technologies hold significant potential in agriculture, existing technologies still suffer from shortcomings such as limited versatility, low monitoring efficiency, difficulty in hierarchical plant growth cultivation, and inaccurate modeling of genetic stress tolerance. Addressing these issues requires further efforts in optimizing technical architecture, strengthening data processing capabilities, and improving model accuracy. Summary of the Invention

[0006] The present invention aims to provide an intelligent cultivation system and method for plant germplasm resources based on the Internet of Things and digital technology, and to build a photosynthesis monitoring system for different plant growth environments, so as to solve the technical problems in the existing technology of poor versatility, difficult maintenance and low evolution efficiency of photosynthesis monitoring methods for different plant growth environments.

[0007] To this end, the present invention provides a plant germplasm resource intelligent cultivation system based on the Internet of Things and digital technology, comprising:

[0008] A cultivation information collection and fusion module is used to collect the unit time cultivation information of different plant growth environments and fuse the cultivation information to form chart conversion information;

[0009] A plant growth status judgment module is used to use the chart conversion information and different plant growth status judgment methods in the IoT edge computing gateway to complete digital monitoring work in different plant growth environments and judge the plant growth status of germplasm resources and form judgment parameters;

[0010] The pest and disease distribution sample collection module is used to collect analytical samples for digital monitoring of different plant growth environments and the growth status of germplasm resources based on judgment parameters at different time points. It also analyzes the various lodging states within the distribution of pests and diseases in germplasm resources to form analytical sample collection parameters for the distribution of pests and diseases in germplasm resources.

[0011] A photosynthesis state cultivation module is used to model germplasm resources in different plant growth environments to form photosynthesis models, wherein the photosynthesis model includes a biophysical model, a physiological and ecological model, and a crop growth model; photosynthesis cultivation is performed on the corresponding biophysical information, physiological and ecological information, and crop growth information based on the photosynthesis model and the chart conversion information, and photosynthesis efficiency is calculated, thereby completing photosynthesis state cultivation in different plant growth environments;

[0012] The photosynthesis state evaluation module is used to associate the genome with the phenotype and evaluate the photosynthesis state in different plant growth environments through the photosynthesis state cultivation parameters of different plant growth environments, and to perform gene stress tolerance modeling optimization.

[0013] Preferably, the cultivation information collection and fusion module includes:

[0014] Information collection component, used to collect in real time the unit time cultivation information generated by various quality resources in different plant growth environments;

[0015] An information fusion component, configured to fuse the unit time cultivation information into corresponding physical parameters according to a predetermined protocol format;

[0016] Information cleaning component, used to clean the fused physical parameters to obtain standardized cultivation information; cleaning includes but is not limited to K-means algorithm, Canopy algorithm and proximity sorting algorithm processing;

[0017] An indicator labeling component is used to label core cultivation information from the standardized cultivation information, and to fuse multiple types of core cultivation information according to building planning indicators to obtain core indicator parameters that are consistent with the building planning indicators;

[0018] An information desensitization component, configured to align the core indicator parameters by time to form standardized indicator coefficients as the chart conversion information;

[0019] The information clustering conversion component is used to cluster the standardized index coefficients and convert the standardized index coefficients according to the cluster centers.

[0020] Preferably, the plant growth status judgment module includes:

[0021] AI supervision components, used for AI configuration and scheduling of different functions and digital monitoring supervision, as well as collecting and analyzing supervision information and generating supervision parameters;

[0022] IoT edge computing gateway component, used to implement parameter setting, model building, process optimization, and method adjustment for different plant growth status judgment methods in the IoT edge computing gateway;

[0023] A germplasm resource plant growth status judgment component is used to perform real-time plant growth status judgment on the germplasm resource based on the plant growth status judgment method, the chart conversion information and the supervision parameters, and generate germplasm resource plant growth status judgment parameters;

[0024] The digital monitoring work plant growth status judgment component is used for artificial intelligence analysis of the calibration status of the digital monitoring work, to judge and analyze the digital monitoring work of the plant growth status, and to generate digital monitoring work plant growth status judgment parameters. The digital monitoring work plant growth status judgment parameters and germplasm resource plant growth status judgment parameters form the judgment parameters.

[0025] Preferably, the pest distribution sample collection module includes:

[0026] Plant growth status analysis component, used to track plant growth status judgment parameters for digital monitoring work and germplasm resource plant growth status judgment parameters, including but not limited to plant growth status reporting, plant growth status disposal process and plant growth status disposal parameters;

[0027] Plant growth status knowledge annotation component, used to cluster, count and analyze plant growth status judgment parameters and plant growth status information in germplasm resource plant growth status judgment parameters and obtain corresponding treatment methods for plant growth status information, forming plant growth status cases, edges, nodes and growth evolution decision trees in plant growth status graph neural networks;

[0028] The germplasm resource indicator component is used to detect the lodging of the entire pest and disease distribution of the germplasm resources, and statistically analyze the core indicators of the germplasm resources to form the analysis sample collection parameters of the pest and disease distribution of the germplasm resources.

[0029] Preferably, the photosynthesis state cultivation module includes:

[0030] Photosynthesis model management component, used to build and manage biophysical models, physiological and ecological models, and crop growth models;

[0031] The photosynthesis evaluation component is used to evaluate the photosynthesis status of germplasm resources, planting environment, and artificial integrated management platform based on unit time cultivation information, biophysical models, physiological and ecological models, and crop growth models, using a preset attention mechanism and evaluation algorithm to obtain photosynthesis evaluation parameters;

[0032] A digital monitoring evaluation component is used to quantitatively evaluate the digital monitoring of germplasm resources, planting environments, and different plant growth environments based on the photosynthesis state evaluation parameters and core digital monitoring indicators and obtain digital monitoring evaluation parameters;

[0033] A photosynthesis efficiency calculation component is used to automatically complete the photosynthesis status evaluation of germplasm resources, planting environment and artificial integrated management platform regularly or based on the photosynthesis evaluation parameters and digital monitoring evaluation parameters, and generate a photosynthesis efficiency calculation document;

[0034] The photosynthesis status display component is used to display the photosynthesis status of the system.

[0035] Preferably, the photosynthesis status assessment module includes:

[0036] The document generation component is used to continuously cultivate the working status of germplasm resources and the core digital monitoring indicators of the system, form documents on the status of germplasm resources and the digital monitoring of the system, and compare the status of germplasm resources in the same region and in different regions with the same climate to obtain horizontal document generation parameters;

[0037] The digital monitoring and calibration component of germplasm resources is used to determine the photosynthetic state of germplasm resources or systems in advance to obtain photosynthetic state cultivation parameters, evaluate the time for normal evolution of germplasm resources or systems, and evaluate the calibration efficiency of germplasm resources or systems for future digital monitoring work;

[0038] The genetic stress tolerance modeling optimization component is used to optimize genetic stress tolerance modeling based on the photosynthetic status of the germplasm resources or systems, and combined with the calibration efficiency of the germplasm resources or systems for future digital monitoring work.

[0039] The present invention also provides a method for intelligent cultivation of plant germplasm resources based on the Internet of Things and digital technology using the above system, comprising the following steps:

[0040] S1. Collecting unit-time cultivation information of different plant growth environments, and fusing the cultivation information to form chart conversion information;

[0041] S2. Using the chart conversion information and different plant growth status judgment methods in the IoT edge computing gateway to complete digital monitoring work in different plant growth environments and plant growth status judgment of germplasm resources and form judgment parameters;

[0042] S3. Analyze and collect samples of digital monitoring of different plant growth environments and the growth status of germplasm resources based on judgment parameters at different time points. Simultaneously, analyze the various lodging states within the distribution of germplasm pests and diseases to form analysis sample collection parameters for the distribution of germplasm pests and diseases.

[0043] S4. Modeling the digital monitoring work and photosynthesis status of germplasm resources in different plant growth environments to form a photosynthesis model, wherein the photosynthesis model includes a biophysical model, a physiological and ecological model, and a crop growth model;

[0044] S5. Based on the photosynthesis model and the chart conversion information, the corresponding biophysical information, physiological and ecological information, and crop growth information are photosynthesized and cultivated, and the photosynthesis efficiency is calculated to complete the photosynthesis state cultivation in different plant growth environments; the photosynthesis state of different plant growth environments is associated with the genome and phenotype and the photosynthesis state is evaluated through the photosynthesis state cultivation parameters of different plant growth environments, and genetic stress tolerance modeling optimization is performed.

[0045] Preferably, the step of collecting the unit time cultivation information of different plant growth environments and fusing the cultivation information to form chart conversion information specifically includes:

[0046] Real-time collection of unit-time cultivation information generated by various physical resources in different plant growth environments; fusing the unit-time cultivation information into corresponding physical parameter variables according to a predetermined protocol format; cleaning the fused physical parameter variables to obtain standardized cultivation information; the cleaning includes but is not limited to processing using a K-means algorithm, a Canopy algorithm, and a neighbor sorting algorithm; marking core cultivation information from the standardized cultivation information, fusing multiple types of core cultivation information according to building planning indicators to obtain core indicator parameter variables that are consistent with the building planning indicators; aligning the core indicator parameter variables by time to form standardized indicator coefficients as the chart conversion information; clustering the standardized indicator coefficients, and converting the standardized indicator coefficients according to cluster centers;

[0047] The steps of using the chart conversion information and different plant growth status judgment methods in the Internet of Things edge computing gateway to complete digital monitoring work in different plant growth environments and plant growth status judgment of germplasm resources and form judgment parameters specifically include: artificial intelligence configuration and scheduling of different functions and digital monitoring supervision, and collecting and analyzing supervision information to generate supervision parameters; realizing parameter setting, model establishment, process optimization, and method adjustment of different plant growth status judgment methods in the Internet of Things edge computing gateway; performing real-time plant growth status judgment on germplasm resources according to the plant growth status judgment method, the chart conversion information and the supervision parameters, and generating germplasm resource plant growth status judgment parameters; artificial intelligence analysis of the calibration status of the digital monitoring work, performing judgment analysis on the digital monitoring work of the plant growth status, and generating digital monitoring work plant growth status judgment parameters, the digital monitoring work plant growth status judgment parameters and the germplasm resource plant growth status judgment parameters form the judgment parameters.

[0048] Preferably, the steps of collecting analysis samples of the digital monitoring work of different plant growth environments and the growth status of germplasm resources plants based on the judgment parameters at different time points, and simultaneously analyzing the various lodging states within the distribution of germplasm resources pests and diseases, and forming analysis sample collection parameters for the distribution of germplasm resources pests and diseases specifically include:

[0049] Track the plant growth status judgment parameters of digital monitoring work and the plant growth status judgment parameters of germplasm resources, including but not limited to plant growth status reporting, plant growth status disposal process and plant growth status disposal parameters; cluster, count and analyze the plant growth status judgment parameters and the plant growth status judgment parameters of germplasm resources and the plant growth status information in the parameters and obtain the disposal method corresponding to the plant growth status information, forming plant growth status cases, edges, nodes and growth evolution decision trees in the plant growth status graph neural network; conduct lodging detection on the entire pest and disease distribution of germplasm resources, and statistically analyze the core indicators of germplasm resources to form analysis sample collection parameters for the distribution of pests and diseases of germplasm resources.

[0050] Modeling germplasm resources in different plant growth environments to form a photosynthesis model, the photosynthesis model including a biophysical model, a physiological-ecological model, and a crop growth model; photosynthetically cultivating the corresponding biophysical information, physiological-ecological information, and crop growth information based on the photosynthesis model and the chart conversion information, and calculating the photosynthesis efficiency, thereby completing the photosynthesis state cultivation of different plant growth environments. The steps specifically include: constructing and managing the biophysical model, the physiological-ecological model, and the crop growth model; evaluating the photosynthesis state of the germplasm resources, the planting environment, and the artificial integrated management platform based on the unit time cultivation information, the biophysical model, the physiological-ecological model, and the crop growth model, using a preset attention mechanism and an evaluation algorithm to obtain photosynthesis evaluation parameters; quantitatively evaluating the digital monitoring of the germplasm resources, the planting environment, and different plant growth environments based on the photosynthesis state evaluation parameters and core digital monitoring indicators to obtain digital monitoring evaluation parameters; regularly or automatically completing the photosynthesis state evaluation of the germplasm resources, the planting environment, and the artificial integrated management platform based on the photosynthesis evaluation parameters and the digital monitoring evaluation parameters, and forming a photosynthesis efficiency calculation document; and displaying the photosynthesis state of the system.

[0051] Preferably, the steps of performing genome-phenotype association and photosynthesis state evaluation on the photosynthesis state of different plant growth environments through photosynthesis state cultivation parameters of different plant growth environments, and performing gene stress tolerance modeling optimization specifically include:

[0052] Continuously cultivate the working status of germplasm resources and the core digital monitoring indicators of the system, form documents on the status of germplasm resources and the digital monitoring of the system, and compare the status of germplasm resources in the same region and in different regions with the same climate to obtain horizontal document generation parameters;

[0053] Determine the photosynthetic state of germplasm resources or systems in advance to obtain photosynthetic state cultivation parameters, evaluate the time for normal evolution of germplasm resources or systems, and evaluate the calibration efficiency of germplasm resources or systems for future digital monitoring work;

[0054] Genetic stress tolerance modeling optimization is carried out based on the photosynthetic status of the germplasm resources or systems, combined with the calibration efficiency of the germplasm resources or systems for future digital monitoring work.

[0055] Beneficial effects:

[0056] The plant germplasm resource intelligent cultivation system and method based on the Internet of Things and digital technology provided by the present invention can form a universal plant growth state judgment scheme for different plant growth environments, realize the distribution management of plant growth state pests and diseases of germplasm resources, systematically judge the growth state of different plants and cultivate photosynthesis during the evolution process, ensure the digital monitoring efficiency of different plant growth environments, and then achieve the purpose of effectively cultivating plants in different plant growth environments and improving the accuracy of gene stress tolerance modeling in different plant growth environments. The combination of Internet of Things technology and digital tools enables the automatic collection, processing and analysis of various data in the agricultural production process, greatly improving data processing efficiency and decision-making speed. In addition, this method can dynamically adjust the growth environment and cultivation strategy, optimize the photosynthesis and growth state of plants, and effectively improve crop yield and quality. More importantly, through genomics and big data analysis, it can provide a more scientific basis for crop breeding and achieve precise cultivation of stress resistance and high yield. The combination of Internet of Things and digital technology makes the monitoring and prediction of pests and diseases more accurate, helps to reduce the use of pesticides, reduce agricultural production costs, and promote sustainable agricultural development. In short, this intelligent cultivation method has improved the intelligence level and sustainability of agricultural production and promoted the efficient development of modern agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a schematic diagram of the composition of the plant germplasm resource intelligent cultivation system based on the Internet of Things and digital technology of the present invention;

[0058] Figure 2 The figure is a flow chart of the intelligent cultivation method of plant germplasm resources based on the Internet of Things and digital technology of the present invention. DETAILED DESCRIPTION

[0059] It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of this application can be combined with each other. The present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] Example 1

[0061] like Figure 1 As shown, one embodiment of the present invention provides a plant germplasm resource intelligent cultivation system based on the Internet of Things and digital technology, including:

[0062] The cultivation information collection and fusion module is used to collect, fuse and process the cultivation information per unit time, and form chart conversion information for use by the photosynthesis cultivation system. It is the information layer of the entire photosynthesis cultivation system.

[0063] The plant growth status judgment module is used to complete digital monitoring work and plant growth status judgment of germplasm resources based on the information converted from graphs and different customizable plant growth status disposal methods in the IoT edge computing gateway. This module is based on traditional plant growth status judgment technology and realizes flexible identification of plant growth status judgment by using graph conversion information and evolution judgment algorithm.

[0064] The pest and disease distribution sample collection module is used for digital monitoring, germplasm resource plant growth status and germplasm resource pest and disease distribution analysis sample collection. Through manual entry and automatic collection, it completes the pest and disease distribution cultivation of germplasm resources, and at the same time provides a plant growth status analysis platform to complete the analysis and processing of plant growth status.

[0065] The photosynthesis state cultivation module is used to perform photosynthesis modeling on germplasm resources and systems to form a photosynthesis model. The photosynthesis model includes a biophysical model, a physiological and ecological model, and a crop growth model. According to the photosynthesis model and the chart conversion information, the corresponding biophysical information, physiological and ecological information, and crop growth information are photosynthetically cultivated, and the photosynthesis efficiency is calculated to complete the photosynthesis state cultivation of the system. It is the generation and display layer of photosynthesis information.

[0066] The photosynthesis status assessment module is used to complete system document generation and digital monitoring calibration of germplasm resources through the system's photosynthesis status, and to optimize gene stress tolerance modeling for system photosynthesis problems. It is the application layer of photosynthesis information.

[0067] The above scheme provided in this embodiment can form a universal plant growth status judgment scheme for different plant growth environments, realize the distribution management of plant growth status and pests of germplasm resources, and the photosynthesis cultivation and evaluation capabilities of the system, ensure high digital monitoring efficiency of different plant growth environments, and thus achieve the purpose of reducing the maintenance workload and complexity of the system for different plant growth environments, and improving the accuracy of genetic stress tolerance modeling in different plant growth environments.

[0068] The cultivation information collection and fusion module includes information collection component, information fusion component, information cleaning component, indicator labeling component, information desensitization component and information clustering conversion component.

[0069] Specifically:

[0070] The information collection component is used to collect the unit time cultivation information generated by various systems in different plant growth environments in real time. In some embodiments of the present invention, the information collection component collects different germplasm resource status information via wireless signals, and the status information is encapsulated using a lossless compression information structure protocol.

[0071] The information fusion component is used to format the unit-time cultivation information collected by the information collection component according to the protocol format and fuse it into corresponding physical parameters. In this embodiment of the present invention, the information fusion component fuses losslessly compressed information structures and maps the fused parameters to the germplasm resource monitoring protocol one by one according to the germplasm resource type to obtain the corresponding physical quantity. Simultaneously, the information fusion component uses the cloud to complete the fusion of XML files such as digital monitoring work plan information and digital monitoring work process information.

[0072] The information cleaning component is used to clean the physical parameters obtained by fusion using K-means algorithm, Canopy algorithm, neighbor sorting algorithm, etc. to obtain standardized cultivation information.

[0073] The indicator labeling component is used to select core indicator parameters from standardized cultivation information, and fuse multiple types of parameters as needed to calculate the core indicator parameters; in the example of the present invention, core indicator parameters such as signal-to-noise ratio and loss of lock count are labeled from the germplasm resource status information, and at the same time, comprehensive core indicator parameters such as tracking progress, pointing accuracy, and signal strength curve are calculated by integrating different parameters.

[0074] The information desensitization component is used to align the marked indicator parameters by time to form standardized indicator coefficients; in the example of the present invention, different state parameters at the same time are formed into one-dimensional state coefficients according to the signal flow direction.

[0075] The information clustering and conversion component is used to cluster and convert standardized indicator coefficients on demand. The desensitized state coefficients are stored in the MYSQL database with the time stamp as the primary key. The state coefficients are also published to the software for use by other components.

[0076] The plant growth status judgment module includes an artificial intelligence supervision component, an IoT edge computing gateway component, a germplasm resource plant growth status judgment component, and a digital monitoring work plant growth status judgment component. Among them:

[0077] The artificial intelligence supervision component is used for artificial intelligence configuration, scheduling to complete different functions and digital monitoring supervision, and to collect and analyze supervision information to generate supervision parameters. In the example of the present invention, the artificial intelligence supervision component automatically generates and calibrates different supervisions based on the supervision applications of the germplasm resource plant growth status judgment component, the digital monitoring work plant growth status judgment component and the photosynthesis status cultivation module.

[0078] The IoT edge computing gateway component is used to implement parameter settings, model establishment, process optimization, and method adjustments for different plant growth status judgment methods in the IoT edge computing gateway, such as preset values ​​required for plant growth status judgment, standard knowledge, edges, nodes, and growth evolution decision trees in the plant growth state graph neural network. In the embodiment of the present invention, knowledge is abstracted into information structures and clustered and managed in the information library, wherein: the preset values ​​required for plant growth status judgment are stored in the information library in the form of key-value pairs, and the management of preset value knowledge can be completed by operating the information library; similarly, the edges and nodes in the plant growth state graph neural network are abstracted into the relationship between edges, nodes, and connections in the plant growth state graph neural network, and are clustered and managed in the information library.

[0079] The germplasm resource plant growth status judgment component is used to perform real-time plant growth status judgment on germplasm resources based on preset values, edges, nodes, growth evolution decision trees and supervision parameters in the plant growth status graph neural network, and generate a germplasm resource plant growth status judgment document; when it exceeds the preset value range, it is judged as the germplasm resource plant growth status; for other parameters, the edges and nodes in the plant growth status graph neural network are used for judgment, and the state coefficient converted by the cultivation information collection and fusion module is used as the base event. According to the corresponding edges and nodes in the plant growth status graph neural network, various logical operations (and, or, etc.) on the base events can be used to deduce the plant growth status of the germplasm resource module or component. If necessary, an artificial intelligence supervision application can also be initiated, and further combined with the supervision parameters to complete the plant growth status judgment of the germplasm resource.

[0080] The plant growth status judgment component of the digital monitoring work is used for artificial intelligence analysis of the calibration status of the digital monitoring work. For the digital monitoring work that finds the plant growth status, further judgment and analysis are performed through artificial intelligence supervision, and a digital monitoring work plant growth status judgment document is generated. In the example of the present invention, the digital monitoring work plant growth status judgment first analyzes and checks the digital monitoring work calibration steps, tracking status, reception status, cultivation point alarm status, core log and other different inspection items in the digital monitoring work through the growth evolution decision tree, and generates a reception status document; for the digital monitoring work with abnormal reception, the cause of the abnormality is further analyzed and judged through the edges and nodes in the plant growth status graph neural network, and when necessary, artificial intelligence supervision is initiated, and the cause of the plant growth status is analyzed and analyzed through the supervision parameters to generate a digital monitoring work plant growth status judgment document.

[0081] The pest and disease distribution sample collection module includes a plant growth status analysis component, a plant growth status knowledge annotation component, and a germplasm resource indicator component. Specifically:

[0082] The plant growth status analysis component is used for the interaction between digital monitoring and germplasm plant growth status information, including plant growth status reporting, plant growth status processing procedures, plant growth status processing parameters, and other information. In this example, the plant growth status analysis component includes three roles: urban digital monitoring decision-makers, decision trees, and breeding resource experts. Urban digital monitoring decision-makers convert problems encountered during system evolution and corresponding log information to a designated decision tree, which then provides answers. Finally, the breeding resource expert confirms the closed loop.

[0083] The plant growth state knowledge annotation component is used to count, analyze, and refine plant growth state information and treatment methods, forming plant growth state cases, edges, nodes, and growth evolution decision trees in the plant growth state graph neural network. In this embodiment of the present invention, the plant growth state knowledge annotation component statistically analyzes the plant growth state treatment information recorded in the plant growth state analysis component to form a knowledge set that is closely linked to specific business operations and can be used for overall system analysis and judgment. For typical plant growth states, this knowledge set can also be summarized as plant growth state cases and edges and nodes in the plant growth state graph neural network for use by the plant growth state judgment module.

[0084] The germplasm resource indicator component is used to detect lodging of pests and diseases throughout the entire process of germplasm resource deployment, upgrading, genetic stress tolerance modeling, and disposal. It also statistically analyzes core indicators such as the evolutionary status of germplasm resources, digital monitoring, and plant growth status mutation time nodes. In this example, the germplasm resource indicator component automatically stores information on the various stages of germplasm resource deployment, upgrading, genetic stress tolerance modeling, and disposal into an information database. It also statistically analyzes information such as the evolutionary time of different germplasm resources, the frequency of plant growth states, and the causes of plant growth states, and regularly generates germplasm resource indicator documents.

[0085] The photosynthesis state cultivation module includes photosynthesis model management component, photosynthesis evaluation component, digital monitoring evaluation component, photosynthesis efficiency calculation component and photosynthesis state display component. Specifically:

[0086] The photosynthesis model management component is used to construct and manage biophysical information, physiological and ecological information, and crop growth models. In this example, the cultivation sites of germplasm resources are modeled by category and component, using the edges and nodes in a plant growth state graph neural network. The relationship between each node value and the theoretical preset value is calculated to obtain the transfer node to the higher-level node, which is the photosynthesis model of the germplasm resource. The vegetation and crop growth model uses the germplasm resource photosynthesis model as a leaf node. The system and station architecture design are integrated to obtain the edges and nodes in the plant growth state graph neural network, which is its photosynthesis model.

[0087] The photosynthesis evaluation component is used to conduct a comprehensive analysis based on the cultivation information per unit time and the photosynthesis model, and uses an appropriate attention mechanism and evaluation algorithm to evaluate the photosynthesis status of germplasm resources, planting environments, and different plant growth environments. In the example of the present invention, the photosynthesis model constructed by the photosynthesis model management component is combined with the cultivation information per unit time to complete the evaluation of the photosynthesis status. The system photosynthesis status is divided into four levels: photosynthesis, sub-photosynthesis, plant growth status, and failure. Among them: photosynthesis means that all cultivation points of the germplasm resources are normal; sub-photosynthesis means that some cultivation points of the germplasm resources are abnormal, but have no impact on the germplasm resources; plant growth status means that some cultivation points of the germplasm resources are abnormal, and cause some clustering components to be abnormal, but the component has a backup or does not affect the normal operation of other components of the germplasm resources; failure means that the germplasm resources can no longer work normally. The above attention mechanism and evaluation algorithm can be given by a decision tree or determined based on historical experience.

[0088] The digital monitoring evaluation component is used to quantitatively evaluate the system digital monitoring of germplasm resources, planting environment and different plant growth environments based on the system's core digital monitoring indicators.

[0089] The photosynthesis efficiency calculation component is used to automatically organize and complete system monitoring periodically or based on photosynthesis assessment and digital monitoring assessment parameters, and generate photosynthesis efficiency calculation documents. In this embodiment of the present invention, when the photosynthesis efficiency calculation component detects a change in the system photosynthesis state or the system digital monitoring, it automatically initiates corresponding monitoring and generates photosynthesis efficiency calculation documents in combination with the photosynthesis model.

[0090] The photosynthesis status display component is used to display the system's photosynthesis status in graphical and tabular form. In this example, a bar chart is used to display the photosynthesis status of each germplasm resource, and a fitted curve is used to display the status of each digital monitoring indicator. A comprehensive interface is also provided to display the parameters for photosynthesis efficiency calculation.

[0091] The photosynthesis status assessment module includes a document generation component, a germplasm resource digital monitoring and calibration component, and a gene stress tolerance modeling and optimization component. More specifically:

[0092] The document generation component is used to continuously cultivate the working status of germplasm resources and the core digital monitoring indicators of the system, forming vertical document generation of germplasm resource status and system digital monitoring, and at the same time completing horizontal document generation between germplasm resources in the same region and different regions with the same climate.

[0093] The digital monitoring and calibration component for germplasm resources is used to pre-determine the photosynthetic status of a germplasm resource or system, assess the time it takes for normal evolution, and evaluate the calibration efficiency of future digital monitoring efforts. In this example, an information-driven digital monitoring and calibration technology for germplasm resources is employed. This technology does not require precise physical models or prior knowledge of the germplasm resource or system. Instead, it uses historically collected information as a foundation and uses machine learning, neural networks, and other information analysis and processing methods to mine implicit information for evaluation.

[0094] The genetic stress tolerance modeling optimization component is used to comprehensively judge and optimize the genetic stress tolerance modeling based on the system photosynthesis and digital monitoring evaluation parameters, combined with the digital monitoring and calibration of germplasm resources. In the example of the present invention, the genetic stress tolerance modeling optimization component collects the system photosynthesis information and digital monitoring and calibration parameters of germplasm resources generated by the photosynthesis state cultivation module in real time, and combines the preset growth evolution decision tree to give genetic stress tolerance modeling decision suggestions. At the same time, based on the parameters of document generation and digital monitoring and calibration of germplasm resources, it also warns in advance of possible plant growth conditions and provides maintenance suggestions.

[0095] See Figure 2 The present invention also provides a method for intelligent cultivation of germplasm resources based on the Internet of Things and digital technology, comprising the following steps:

[0096] S1. Collecting unit-time cultivation information of different plant growth environments, and fusing the cultivation information to form chart conversion information; the formed chart conversion information is used by the photosynthesis cultivation system.

[0097] During this step, various sensors and IoT devices collect information about the cultivation of different plant growth environments. This includes environmental parameters such as temperature, humidity, light intensity, and CO2 concentration, as well as information about plant growth, leaf area, and root health. This data is recorded over time using real-time monitoring and data acquisition equipment. This data is then processed through data fusion and converted into charts. This charted information is presented in graphical or tabular form to facilitate further analysis and decision-making. This information is subsequently used by the photosynthesis cultivation system, providing data support for plant photosynthesis regulation and environmental adaptation.

[0098] S2. Utilize the chart conversion information and different plant growth status judgment methods in the IoT edge computing gateway to complete digital monitoring work in different plant growth environments and plant growth status judgment of germplasm resources and form judgment parameters; on the basis of traditional plant growth status judgment technology, flexible identification of plant growth status judgment is achieved by using chart conversion information and evolution judgment algorithm.

[0099] In this step, combined with chart-based conversion information, intelligent algorithms and models within the IoT edge computing gateway are used to monitor and analyze plant status in real time across different plant growth environments. Edge computing enables local data processing, reducing data transmission latency, and allows for real-time calculation of plant growth status and generation of judgment parameters. This method utilizes a flexible, evolving judgment algorithm. Based on real-time data, historical data, and environmental changes, the model is dynamically adjusted to accurately determine plant growth status. This method is more adaptable than traditional plant growth status judgment technologies and can rapidly adjust strategies based on changes in the plant growth environment.

[0100] S3. Based on the judgment parameters at different time points, the digital monitoring work of different plant growth environments and the growth status of germplasm resources are analyzed and sample collection is carried out. At the same time, the various lodging states within the distribution of germplasm pests and diseases are analyzed to form the analysis sample collection parameters of the distribution of germplasm pests and diseases; through manual entry and automatic collection, the distribution cultivation of germplasm resources is completed, and a plant growth status analysis platform is provided to complete the analysis and processing of plant growth status.

[0101] In this step, based on the judgment parameters obtained in the previous step, the system digitally monitors the plant growth environment at different time points and collects corresponding sample data. These samples include information such as plant growth status, leaf health, stem stability, and the distribution of pests and diseases and the lodging status of germplasm resources. The system uses a combination of manual input and automatic collection to collect and analyze pest and disease distribution information, helping to identify plant areas with potential pest and disease risks or growth abnormalities. These analysis results provide data support for subsequent pest and disease control and plant health optimization.

[0102] S4. Model the digital monitoring work and photosynthesis status of germplasm resources in different plant growth environments to form a photosynthesis model, wherein the photosynthesis model includes a biophysical model, a physiological and ecological model, and a crop growth model; photosynthesis cultivation is performed on the corresponding biophysical information, physiological and ecological information, and crop growth information based on the photosynthesis model and the chart conversion information, and photosynthesis efficiency is calculated, thereby completing the photosynthesis status cultivation of different plant growth environments.

[0103] In this step, based on previously collected environmental data and plant growth status information, the system will establish a photosynthesis model through a combination of biophysical models, physiological and ecological models, and crop growth models. These models cover multiple aspects of plant biology, physics, and ecology, such as the impact of light, temperature, CO2 concentration, and soil moisture on photosynthesis. The model will calculate photosynthesis efficiency to guide plant cultivation and photosynthesis optimization. By updating and adjusting the model in real time, it can accurately predict the photosynthesis status of different plants in different growth environments, optimize growth conditions, and improve photosynthesis efficiency.

[0104] S5. Through the cultivation parameters of photosynthesis status in different plant growth environments, the genome-phenotype association and photosynthesis status evaluation of different plant growth environments are carried out, and genetic stress tolerance modeling optimization is carried out.

[0105] In this step, the system evaluates the photosynthetic performance of different plants under specific environments through genome-phenotype association analysis based on the photosynthetic state cultivation parameters in the previous step. By analyzing the relationship between plant genomic data and phenotype, gene regions related to photosynthetic efficiency are identified, and genetic stress tolerance modeling is performed. This process will help determine which genes are related to the environmental adaptability and stress resistance of plants, thereby optimizing the cultivation strategy of germplasm resources. Genetic stress tolerance modeling can effectively improve the growth performance of plants under different environmental conditions, enhance their stress resistance, and promote crop variety improvement and the sustainable development of agricultural production.

[0106] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical indicators therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The intelligent cultivation system of plant germplasm resources based on the Internet of Things and digital technology is characterized by: include: A cultivation information collection and fusion module is used to collect the unit time cultivation information of different plant growth environments and fuse the cultivation information to form chart conversion information; A plant growth status judgment module is used to use the chart conversion information and different plant growth status judgment methods in the IoT edge computing gateway to complete digital monitoring work in different plant growth environments and judge the plant growth status of germplasm resources and form judgment parameters; The pest and disease distribution sample collection module is used to collect analytical samples for digital monitoring of different plant growth environments and the growth status of germplasm resources based on judgment parameters at different time points. It also analyzes the various lodging states within the distribution of pests and diseases in germplasm resources to form analytical sample collection parameters for the distribution of pests and diseases in germplasm resources. A photosynthesis state cultivation module is used to model germplasm resources in different plant growth environments to form photosynthesis models, wherein the photosynthesis model includes a biophysical model, a physiological and ecological model, and a crop growth model; photosynthesis cultivation is performed on the corresponding biophysical information, physiological and ecological information, and crop growth information based on the photosynthesis model and the chart conversion information, and photosynthesis efficiency is calculated, thereby completing photosynthesis state cultivation in different plant growth environments; The photosynthesis state evaluation module is used to associate the genome with the phenotype and evaluate the photosynthesis state in different plant growth environments through the photosynthesis state cultivation parameters of different plant growth environments, and to perform gene stress tolerance modeling optimization.

2. The plant germplasm resource intelligent cultivation system based on the Internet of Things and digital technology according to claim 1 is characterized in that: The plant growth status judgment module includes: AI supervision components, used for AI configuration and scheduling of different functions and digital monitoring supervision, as well as collecting and analyzing supervision information and generating supervision parameters; IoT edge computing gateway component, used to implement parameter setting, model building, process optimization, and method adjustment for different plant growth status judgment methods in the IoT edge computing gateway; A germplasm resource plant growth status judgment component is used to perform real-time plant growth status judgment on the germplasm resource based on the plant growth status judgment method, the chart conversion information and the supervision parameters, and generate germplasm resource plant growth status judgment parameters; The digital monitoring work plant growth status judgment component is used for artificial intelligence analysis of the calibration status of the digital monitoring work, to judge and analyze the digital monitoring work of the plant growth status, and to generate digital monitoring work plant growth status judgment parameters. The digital monitoring work plant growth status judgment parameters and germplasm resource plant growth status judgment parameters form the judgment parameters.

3. The plant germplasm resource intelligent cultivation system based on the Internet of Things and digital technology according to claim 1 is characterized in that: The pest distribution sample collection module includes: Plant growth status analysis component, used to track the plant growth status judgment parameters of digital monitoring work and germplasm resource plant growth status judgment parameters, including plant growth status reporting, plant growth status disposal process and plant growth status disposal parameters; Plant growth status knowledge annotation component, used to cluster, count and analyze plant growth status judgment parameters and plant growth status information in germplasm resource plant growth status judgment parameters and obtain corresponding treatment methods for plant growth status information, forming plant growth status cases, edges, nodes and growth evolution decision trees in plant growth status graph neural networks; The germplasm resource indicator component is used to detect the lodging of the entire pest and disease distribution of the germplasm resources, and statistically analyze the core indicators of the germplasm resources to form the analysis sample collection parameters of the pest and disease distribution of the germplasm resources.

4. The plant germplasm resource intelligent cultivation system based on the Internet of Things and digital technology according to claim 1 is characterized in that: The photosynthesis state cultivation module includes: Photosynthesis model management component, used to build and manage biophysical models, physiological and ecological models, and crop growth models; The photosynthesis evaluation component is used to evaluate the photosynthesis status of germplasm resources, planting environment, and artificial integrated management platform based on unit time cultivation information, biophysical models, physiological and ecological models, and crop growth models, using a preset attention mechanism and evaluation algorithm to obtain photosynthesis evaluation parameters; A digital monitoring evaluation component is used to quantitatively evaluate the digital monitoring of germplasm resources, planting environments, and different plant growth environments based on the photosynthesis state evaluation parameters and core digital monitoring indicators and obtain digital monitoring evaluation parameters; The photosynthesis efficiency calculation component is used to automatically complete the photosynthesis status evaluation of germplasm resources, planting environment and artificial integrated management platform regularly or based on the photosynthesis evaluation parameters and digital monitoring evaluation parameters, and form a photosynthesis efficiency calculation document; the photosynthesis status display component is used to display the photosynthesis status of the system.

5. The plant germplasm resource intelligent cultivation system based on the Internet of Things and digital technology according to claim 1 is characterized in that: The photosynthesis status assessment module includes: The document generation component is used to continuously cultivate the working status of germplasm resources and the core digital monitoring indicators of the system, form documents on the status of germplasm resources and the digital monitoring of the system, and compare the status of germplasm resources in the same region and in different regions with the same climate to obtain horizontal document generation parameters; The digital monitoring and calibration component of germplasm resources is used to determine the photosynthetic state of germplasm resources or systems in advance to obtain photosynthetic state cultivation parameters, evaluate the time for normal evolution of germplasm resources or systems, and evaluate the calibration efficiency of germplasm resources or systems for future digital monitoring work; The genetic stress tolerance modeling optimization component is used to optimize genetic stress tolerance modeling based on the photosynthetic status of the germplasm resources or systems, and combined with the calibration efficiency of the germplasm resources or systems for future digital monitoring work.

6. A method for intelligent cultivation of plant germplasm resources based on the Internet of Things and digital technology using the system according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. Collecting unit-time cultivation information of different plant growth environments, and fusing the cultivation information to form chart conversion information; S2. Using the chart conversion information and different plant growth status judgment methods in the IoT edge computing gateway to complete digital monitoring work in different plant growth environments and plant growth status judgment of germplasm resources and form judgment parameters; S3. Analyze and collect samples of digital monitoring of different plant growth environments and the growth status of germplasm resources based on judgment parameters at different time points. Simultaneously, analyze the various lodging states within the distribution of germplasm pests and diseases to form analysis sample collection parameters for the distribution of germplasm pests and diseases. S4. Modeling the digital monitoring work and photosynthesis status of germplasm resources in different plant growth environments to form a photosynthesis model, wherein the photosynthesis model includes a biophysical model, a physiological and ecological model, and a crop growth model; S5. Based on the photosynthesis model and the chart conversion information, the corresponding biophysical information, physiological and ecological information, and crop growth information are photosynthesized and cultivated, and the photosynthesis efficiency is calculated to complete the photosynthesis state cultivation in different plant growth environments; the photosynthesis state of different plant growth environments is associated with the genome and phenotype and the photosynthesis state is evaluated through the photosynthesis state cultivation parameters of different plant growth environments, and genetic stress tolerance modeling optimization is performed.

7. The method for intelligent cultivation of germplasm resources based on Internet of Things and digital technology according to claim 6, characterized in that: The steps of collecting unit time cultivation information of different plant growth environments and fusing the cultivation information to form chart conversion information specifically include: Real-time collection of unit time cultivation information generated by various quality resources in different plant growth environments; fusing the unit time cultivation information into corresponding physical parameter variables according to a predetermined protocol format; cleaning the fused physical parameter variables to obtain standardized cultivation information; Cleaning includes processing using the K-means algorithm, the Canopy algorithm, and the neighbor sorting algorithm; marking core cultivation information from the standardized cultivation information, and fusing multiple types of core cultivation information according to the building planning indicators to obtain core indicator parameter variables that are consistent with the building planning indicators; Aligning the core indicator parameters by time to form standardized indicator coefficients as the chart conversion information; Clustering the standardized index coefficients and converting the standardized index coefficients according to cluster centers; The steps of using chart conversion information and different plant growth status judgment methods in the IoT edge computing gateway to complete digital monitoring work in different plant growth environments and judge the plant growth status of germplasm resources and form judgment parameters include: artificial intelligence configuration and scheduling of different functions and digital monitoring supervision, and collecting and analyzing supervision information to generate supervision parameters; Implement parameter setting, model building, process optimization, and method adjustment for different plant growth status judgment methods within the IoT edge computing gateway; According to the plant growth status judgment method, the chart conversion information and the supervision parameters, the plant growth status of the germplasm resources is judged in real time, and the plant growth status judgment parameters of the germplasm resources are generated; Artificial intelligence analyzes the calibration status of the digital monitoring work, performs judgment analysis on the digital monitoring work that discovers the plant growth status, and generates digital monitoring work plant growth status judgment parameters. The digital monitoring work plant growth status judgment parameters and germplasm resource plant growth status judgment parameters form the judgment parameters.

8. The method for intelligent cultivation of plant germplasm resources based on the Internet of Things and digital technology according to claim 6, characterized in that: The steps for collecting analysis samples of digital monitoring work on different plant growth environments and the growth status of germplasm resources based on judgment parameters at different time points, and analyzing the various lodging states within the distribution of germplasm pests and diseases, and forming analysis sample collection parameters for the distribution of germplasm pests and diseases include: Tracking of plant growth status judgment parameters for digital monitoring and germplasm resource plant growth status judgment parameters, including plant growth status reporting, plant growth status disposal process and plant growth status disposal parameters; Clustering, statistics, and analysis of plant growth status judgment parameters and plant growth status information in germplasm resource plant growth status judgment parameters, and obtaining treatment methods corresponding to the plant growth status information, forming plant growth status cases, edges, nodes, and growth evolution decision trees in plant growth status graph neural networks; lodging detection of the entire pest and disease distribution of germplasm resources, and statistical analysis of the core indicators of germplasm resources to form analysis sample collection parameters for the pest and disease distribution of germplasm resources; Modeling germplasm resources in different plant growth environments to form photosynthesis models, wherein the photosynthesis models include biophysical models, physiological and ecological models, and crop growth models; The steps of cultivating the photosynthesis state of different plant growth environments by photosynthesizing the corresponding biophysical information, physiological and ecological information, and crop growth information according to the photosynthesis model and the chart conversion information, and calculating the photosynthesis efficiency, specifically include: constructing and managing the biophysical model, the physiological and ecological model, and the crop growth model; Based on the unit time cultivation information, biophysical model, physiological and ecological model and crop growth model, a preset attention mechanism and evaluation algorithm are used to evaluate the photosynthesis status of germplasm resources, planting environment and artificial integrated management platform to obtain photosynthesis evaluation parameters; based on the photosynthesis status evaluation parameters and core digital monitoring indicators, the digital monitoring of germplasm resources, planting environment and different plant growth environments is quantitatively evaluated to obtain digital monitoring evaluation parameters; Regularly or automatically complete the photosynthesis status evaluation of germplasm resources, planting environment and artificial integrated management platform based on the photosynthesis evaluation parameters and digital monitoring evaluation parameters, and form a photosynthesis efficiency calculation document; display the photosynthesis status of the system.

9. The method for intelligent cultivation of plant germplasm resources based on Internet of Things and digital technology according to claim 6, characterized in that: The steps of performing genome-phenotype association and photosynthesis status evaluation in different plant growth environments through photosynthesis state cultivation parameters in different plant growth environments, and optimizing genetic stress tolerance modeling include: Continuously cultivate the working status of germplasm resources and the core digital monitoring indicators of the system, form documents on the status of germplasm resources and the digital monitoring of the system, and compare the status of germplasm resources in the same region and in different regions with the same climate to obtain horizontal document generation parameters; Determine the photosynthetic status of germplasm resources or systems in advance to obtain photosynthetic status cultivation parameters, evaluate the time of normal evolution of germplasm resources or systems, and evaluate the calibration efficiency of germplasm resources or systems for future digital monitoring work; according to the photosynthetic status of germplasm resources or systems, combined with the calibration efficiency of germplasm resources or systems for future digital monitoring work, optimize genetic stress tolerance modeling.

Images