Agricultural park data generation method and system based on digital twinning

Abstract

The embodiment of the invention provides an agricultural park data generation method and system based on digital twinning, and the method comprises the steps: obtaining a digital twinning target agricultural virtual park, employing the initial scene simulation data and an agricultural environment analysis model after knowledge learning, carrying out the comprehensive and precise evaluation of the environment condition of the target agricultural virtual park, and achieving the comprehensive and precise evaluation of the environment condition of the target agricultural virtual park. Various environmental factors are comprehensively considered, and the actual growth environment of crops can be reflected more accurately. Through environment condition evaluation, a plurality of target key growth parameters can be determined, and the target key growth parameters directly reflect the growth environment and condition of crops in the target agricultural virtual park. The determination of the target key growth parameters provides a scientific basis for agricultural production, and is helpful for guiding agricultural producers to carry out reasonable planting and management, thereby improving the yield and quality of crops. Therefore, accurate evaluation of the agricultural park environment and scientific determination of crop growth parameters are realized.

Description

Technical Field

[0001] The present application relates to the field of digital twin technology, and more specifically, to a method and system for generating agricultural park data based on digital twins. Background Art

[0002] With the advancement of science and technology and the development of society, modern agriculture is facing a major demand for transformation and upgrading. Traditional agricultural production methods, due to the lack of accurate data support and scientific decision-making basis, often lead to low resource utilization efficiency and difficulty in ensuring crop yield and quality. In order to solve this problem, digital twin technology has been introduced into agricultural production to realize the digitization and intelligence of agricultural production.

[0003] Digital twin technology combines the physical world with the virtual world to achieve digital reproduction of the physical world. In the agricultural field, digital twin technology can build a digital model of an agricultural park, namely an agricultural virtual park. This virtual park can simulate and reflect the various states and changes of the real park, providing strong data support and decision-making basis for agricultural production.

[0004] However, there are still some problems in the use of digital twin technology in the agricultural field. First, although it is possible to build an agricultural virtual park, how to effectively collect scene simulation data from this virtual park and convert this data into information that is instructive for agricultural production is an urgent problem to be solved. Secondly, existing agricultural environmental analysis models often lack sufficient knowledge learning capabilities and cannot accurately evaluate the agricultural environment based on historical data and real-time data, making it difficult to determine key growth parameters. Summary of the invention

[0005] In view of this, the purpose of the embodiments of the present application is to provide an agricultural park data generation method and system based on digital twins.

[0006] In conjunction with one aspect of an embodiment of the present application, a method for generating agricultural park data based on digital twins is provided, the method comprising: Obtain digital twin of the target agricultural virtual park; Collecting scene simulation data for the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park; An environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environment analysis model that has completed knowledge learning in advance, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined. The target key growth parameters reflect the growth environment and conditions of the crops in the target agricultural virtual park.

[0007] In a possible implementation of the first aspect, collecting scene simulation data for the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park includes: Perform multiple rounds of scene simulation data collection on the target agricultural virtual park, and generate initial scene simulation data corresponding to the target agricultural virtual park collected in each round; The environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environmental analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined, including: Determining target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data; An environmental condition assessment is performed based on the target scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined.

[0008] In a possible implementation of the first aspect, determining the target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data includes: Performing scene redundancy optimization on the plurality of initial scene simulation data according to a scene redundancy optimization strategy to generate first scene simulation data corresponding to each of the initial scene simulation data; For the plurality of first scene simulation data, performing deviation correction on each of the first scene simulation data to generate a plurality of second scene simulation data; Averaging is performed on a plurality of the second scene simulation data to generate the target scene simulation data.

[0009] In a possible implementation of the first aspect, the environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning, and a plurality of target key growth parameters corresponding to the target agricultural virtual park are determined, including: The initial scenario simulation data is loaded into the agricultural environment analysis model that has previously completed knowledge learning to conduct environmental condition assessment, and based on the generation result of the agricultural environment analysis model, a plurality of target key growth parameters corresponding to the target agricultural virtual park are generated; or, The initial scene simulation data is sent to the digital twin node, so that the digital twin node loads the initial scene simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct an environmental condition assessment, determine and return multiple target key growth parameters corresponding to the target agricultural virtual park.

[0010] In a possible implementation of the first aspect, the agricultural environment analysis model includes an environmental feature representation network and an environmental status assessment network; The step of loading the initial scenario simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct environmental status assessment includes: Loading the initial scene simulation data into the environmental feature representation network to perform growth environment feature recognition, and generating growth environment feature data corresponding to the target agricultural virtual park; The growth environment characteristic data is loaded into the environmental condition assessment network to generate a plurality of target key growth parameters.

[0011] In combination with another aspect of the embodiment of the present application, a device for generating agricultural park data based on digital twin is provided, the device comprising: An acquisition module is used to acquire the target agricultural virtual park of the digital twin; A collection module, used for collecting scene simulation data of the target agricultural virtual park and generating initial scene simulation data corresponding to the target agricultural virtual park; A determination module is used to evaluate the environmental conditions based on the initial scene simulation data and the agricultural environment analysis model that has completed knowledge learning in advance, and determine multiple target key growth parameters corresponding to the target agricultural virtual park, wherein the target key growth parameters reflect the growth environment and conditions of the crops in the target agricultural virtual park.

[0012] In combination with another aspect of an embodiment of the present application, a digital twin system is provided, which includes a machine-readable storage medium and a processor, wherein the machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the digital twin system implements the steps of the above-mentioned agricultural park data generation method based on digital twins.

[0013] In combination with another aspect of an embodiment of the present application, a readable storage medium is provided, on which a computer program is stored. When the computer program is run by a processor, the steps of the above-mentioned agricultural park data generation method based on digital twins can be executed.

[0014] Compared with the existing technology, by obtaining the target agricultural virtual park of the digital twin, using the initial scene simulation data and the agricultural environment analysis model after knowledge learning, a comprehensive and accurate assessment of the environmental conditions of the target agricultural virtual park is carried out, taking into account a variety of environmental factors, which can more accurately reflect the actual growth environment of crops. Through the environmental condition assessment, multiple target key growth parameters can be determined, which directly reflect the growth environment and conditions of crops in the target agricultural virtual park. The determination of these target key growth parameters provides a scientific basis for agricultural production, helps to guide agricultural producers to carry out reasonable planting and management, thereby improving the yield and quality of crops. Therefore, by combining digital twin technology and agricultural environmental analysis models, accurate assessment of the agricultural park environment and scientific determination of crop growth parameters are achieved, providing strong technical support for agricultural production and helping to improve the efficiency and benefits of agricultural production.

[0015] In order to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the embodiments will be described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained by combining these drawings without creative work.

[0017] Figure 1 A schematic diagram of components of a digital twin system provided in an embodiment of the present application is shown; Figure 2 A flow chart of the agricultural park data generation method based on digital twins provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] In order to enable students in the technical field to better understand the solution of this application, the technical solution in the embodiment of this application will be clearly and completely described below in conjunction with the drawings in the embodiment of this application. Obviously, the described embodiment is only a part of the embodiment of this application, not all of the embodiments. In conjunction with the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] The terms "first", "second", "third", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] Figure 1 An exemplary component diagram of a digital twin system 100 is shown. The digital twin system 100 may include one or more processors 104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The digital twin system 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. Non-limitingly, for example, the storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any storage medium may use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of the digital twin system 100. In one case, when the processor 104 executes an associated instruction stored in any storage medium or combination of storage media, the digital twin system 100 may perform any operation of the associated instruction. The digital twin system 100 also includes one or more drive units 108 for interacting with any storage media, such as a hard disk drive unit, an optical disk drive unit, etc.

[0021] The digital twin system 100 also includes an input / output 110 (I / O) for receiving various inputs (via an input unit 112) and for providing various outputs (via an output unit 114). A specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. The digital twin system 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0022] The communication unit 122 can be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 can include any combination of hardwired links, wireless links, routers, gateway functions, digital twin systems 100, etc., governed by any protocol or combination of protocols.

[0023] Figure 2 The flowchart of the method for generating agricultural park data based on digital twins provided in the embodiment of the present application is shown. The method for generating agricultural park data based on digital twins can be Figure 1 The digital twin system 100 shown in the figure is executed, and the detailed steps of the agricultural park data generation method based on digital twin are introduced as follows.

[0024] Step S110, obtaining the target agricultural virtual park of the digital twin.

[0025] Step S120, collecting scene simulation data for the target agricultural virtual park, and generating initial scene simulation data corresponding to the target agricultural virtual park.

[0026] Step S130, performing environmental condition assessment based on the initial scene simulation data and the agricultural environment analysis model that has previously completed knowledge learning, and determining multiple target key growth parameters corresponding to the target agricultural virtual park, wherein the target key growth parameters reflect the growth environment and conditions of the crops in the target agricultural virtual park.

[0027] In this embodiment, the digital twin system receives a request that specifies a specific agricultural virtual park as the analysis object. This virtual park is an exact replica of a real-world agricultural park under the digital twin technology. The digital twin system locates and obtains all data and information of this specified agricultural virtual park through the internal digital twin platform, including but not limited to soil conditions, climate data, topography, and types of crops planted in the park.

[0028] After acquiring the data of the target agricultural virtual park, the digital twin system began to collect multiple rounds of scene simulation data for the park. In each round of collection, the digital twin system simulates different environmental conditions and time nodes to collect the park's response data under various possible situations. These data include but are not limited to the photosynthesis efficiency of crops when the light intensity changes, the water absorption of crops under different soil moisture, and the impact of temperature changes on the growth cycle of crops. Through multiple rounds of collection, the digital twin system generated a series of initial scene simulation data, which provided a rich information basis for subsequent environmental status assessments.

[0029] After acquiring the initial scenario simulation data, the digital twin system began to use this data and a pre-trained agricultural environmental analysis model to assess environmental conditions. This model is trained with a large amount of historical data and expert knowledge, and can accurately predict the growth environment and conditions of crops based on the input scenario data.

[0030] During the evaluation process, the digital twin system first loads the initial scene simulation data into the model's environmental feature representation network to identify the growth environment characteristics. This process can extract key information from the data, such as soil fertility, moisture content, temperature change trends, etc., and generate corresponding growth environment characteristic data.

[0031] Next, the digital twin system inputs these characteristic data into the model's environmental status assessment network. This network can predict multiple target key growth parameters based on the characteristic data, such as the expected yield of crops, growth cycle, probability of pests and diseases, etc. These parameters directly reflect the growth environment and conditions of crops in the target agricultural virtual park, providing important decision-making basis for agricultural producers.

[0032] Ultimately, the digital twin system compiles these target key growth parameters into reports and sends them to the requesting party, so that agricultural producers can adjust their agricultural management strategies based on these parameters to optimize the growth environment of crops and increase yields.

[0033] Based on the above steps, by obtaining the target agricultural virtual park of the digital twin, using the initial scene simulation data and the agricultural environmental analysis model after knowledge learning, a comprehensive and accurate assessment of the environmental conditions of the target agricultural virtual park is carried out, taking into account a variety of environmental factors, which can more accurately reflect the actual growth environment of crops. Through the environmental status assessment, multiple target key growth parameters can be determined, which directly reflect the growth environment and conditions of crops in the target agricultural virtual park. The determination of these target key growth parameters provides a scientific basis for agricultural production, helps to guide agricultural producers to carry out reasonable planting and management, thereby improving the yield and quality of crops. Therefore, by combining digital twin technology and agricultural environmental analysis models, the accurate assessment of the agricultural park environment and the scientific determination of crop growth parameters are achieved, which provides strong technical support for agricultural production and helps to improve the efficiency and benefits of agricultural production.

[0034] In a possible implementation, collecting scene simulation data for the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park includes: Multiple rounds of scene simulation data collection are performed on the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park collected in each round.

[0035] The environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environmental analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined, including: Based on the multiple initial scene simulation data, the target scene simulation data corresponding to the target agricultural virtual park is determined.

[0036] An environmental condition assessment is performed based on the target scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined.

[0037] In this embodiment, after the target agricultural virtual park is determined, the digital twin system starts to perform multiple rounds of scene simulation data collection. Each round of collection simulates different environmental variables and parameters to capture the park's response under various conditions.

[0038] For example, in the first round of simulation, the digital twin system may simulate a sunny and moderately warm weather condition, and record data such as the photosynthesis efficiency and transpiration rate of crops. In the second round of simulation, the digital twin system may adjust the soil moisture to simulate a drought environment, and observe and record the growth of crops under such conditions, such as the degree of leaf wilting and the water absorption capacity of the roots.

[0039] Through multiple rounds of simulation data collection, the digital twin system obtains a large amount of data on the response of the target agricultural virtual park under different environmental conditions, which constitute the initial scenario simulation data set. Each round of data collection is independent and reflects the state of the park under specific conditions.

[0040] After collecting multiple rounds of initial scenario simulation data, the digital twin system needs to process this data to determine a comprehensive target scenario simulation data. This process includes multiple steps such as data integration, optimization, and correction.

[0041] First, the digital twin system uses the scenario redundancy optimization strategy to process multiple initial scenario simulation data. This scenario redundancy optimization strategy is designed to remove duplicate or similar data to reduce data redundancy and improve the accuracy of subsequent analysis. Through this step, the digital twin system obtains the optimized first scenario simulation data set.

[0042] Next, the digital twin system will perform deviation correction on each data in the first scenario simulation data set. This is because in the actual simulation process, due to the influence of various factors, such as model errors, accuracy limitations of data acquisition equipment, etc., there may be certain deviations in the data. By correcting these deviations, the digital twin system can obtain a more accurate second scenario simulation data set.

[0043] Finally, the digital twin system averages the second scenario simulation data set to obtain a comprehensive target scenario simulation data. This data integrates the information of multiple initial scenario simulation data and can more comprehensively reflect the overall situation of the target agricultural virtual park.

[0044] After determining the target scenario simulation data, the digital twin system will use this target scenario simulation data and the pre-trained agricultural environment analysis model to evaluate the environmental conditions. This agricultural environment analysis model has strong data analysis and prediction capabilities and can accurately predict the growth environment and conditions of crops based on the input scenario data.

[0045] During the evaluation process, the digital twin system will load the target scenario simulation data into the agricultural environmental analysis model. The agricultural environmental analysis model will automatically extract key information from the data and analyze and calculate it in combination with its built-in knowledge base and algorithm. Through this process, the agricultural environmental analysis model can predict multiple target key growth parameters, such as the expected yield of crops, the best irrigation time, the probability of pests and diseases, etc.

[0046] These target key growth parameters are of great guiding significance to agricultural producers. They can not only help producers understand the current growth environment and conditions of crops, but also provide a scientific basis for decision-making for future agricultural production. Ultimately, the digital twin system will output these parameters in the form of a report for reference and use by agricultural producers.

[0047] In a possible implementation, determining the target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data includes: The scene redundancy optimization is performed on the plurality of the initial scene simulation data according to the scene redundancy optimization strategy to generate first scene simulation data corresponding to each of the initial scene simulation data.

[0048] For the plurality of first-scenario simulation data, deviation correction is performed on each of the first-scenario simulation data to generate a plurality of second-scenario simulation data.

[0049] Averaging is performed on a plurality of the second scene simulation data to generate the target scene simulation data.

[0050] In this embodiment, after collecting multiple rounds of initial scene simulation data, the digital twin system begins to implement the scene redundancy optimization strategy. The purpose of this strategy is to remove redundant information in the data and ensure the accuracy and efficiency of subsequent analysis.

[0051] Specifically, the digital twin system first reviews each initial scenario simulation data one by one to identify repeated or highly similar data segments. These data segments may be caused by repeated operations or subtle environmental changes during the simulation process. Through advanced algorithms, the digital twin system can intelligently identify and remove these redundant data while retaining the most representative and informative data segments.

[0052] After this step of processing, the digital twin system generates the first scene simulation data corresponding to each initial scene simulation data. After removing redundant information, these data are more concise and rich in effective information, laying a good foundation for subsequent data processing and analysis.

[0053] After completing the scene redundancy optimization, the digital twin system will then perform deviation correction on each first scene simulation data. This is because during the data collection and simulation process, it may be affected by various factors, resulting in certain deviations or errors in the data.

[0054] In order to correct these deviations, the digital twin system uses advanced mathematical models and algorithms to analyze and adjust each first-scenario simulation data one by one. This process includes identifying outliers in the data, correcting sensor errors, adjusting environmental parameter deviations, etc. Through these correction measures, the digital twin system can ensure the accuracy and reliability of the data.

[0055] After deviation correction, the digital twin system generated multiple second-scenario simulation data, which were significantly improved in accuracy and reliability, providing strong support for subsequent data analysis and decision-making.

[0056] After completing the deviation correction, the digital twin system needs to further process multiple second scene simulation data to generate a comprehensive target scene simulation data. This process is mainly achieved through averaging.

[0057] Specifically, the digital twin system averages the corresponding parameters in all the second scenario simulation data. The purpose of this is to obtain a data set that can represent the overall situation of all simulation scenarios. Through averaging, the digital twin system can eliminate accidental errors and fluctuations in individual data, thereby obtaining a more stable and reliable target scenario simulation data.

[0058] The target scenario simulation data finally generated integrates the information of multiple simulation scenarios and can fully and accurately reflect the overall environment and status of the target agricultural virtual park. This data will provide an important reference for subsequent agricultural production decisions.

[0059] In a possible implementation, the environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning to determine multiple target key growth parameters corresponding to the target agricultural virtual park, including: The initial scenario simulation data is loaded into the agricultural environment analysis model that has completed knowledge learning in advance to evaluate the environmental conditions, and based on the generation results of the agricultural environment analysis model, multiple target key growth parameters corresponding to the target agricultural virtual park are generated. Or, The initial scene simulation data is sent to the digital twin node, so that the digital twin node loads the initial scene simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct an environmental condition assessment, determine and return multiple target key growth parameters corresponding to the target agricultural virtual park.

[0060] In this embodiment, after acquiring the initial scene simulation data, the digital twin system loads the initial scene simulation data into the agricultural environment analysis model that has completed knowledge learning. This agricultural environment analysis model is obtained by training and optimizing a large amount of agricultural environment data and growth parameters in advance, and has the ability to evaluate the agricultural environment status.

[0061] Specifically, the digital twin system will first format the initial scene simulation data to ensure that the data format matches the input requirements of the agricultural environmental analysis model. Then, the digital twin system inputs these processed data into the model, and the model automatically evaluates and analyzes the environmental conditions.

[0062] During the assessment process, the model will comprehensively consider multiple factors such as soil conditions, climate conditions, water resources conditions, and their interactions to produce a comprehensive environmental assessment result. This result not only reflects the current environmental conditions, but also predicts the trend of environmental changes in the future.

[0063] After the agricultural environmental analysis model completes the environmental status assessment, it will generate a series of output results. Based on these results, the digital twin system will further analyze and calculate multiple target key growth parameters corresponding to the target agricultural virtual park.

[0064] These key growth parameters may include the best planting time for crops, appropriate irrigation amount, expected yield, probability of pests and diseases, etc. The digital twin system will use advanced algorithms and data processing technology to accurately calculate and predict these parameters.

[0065] For example, based on the soil fertility and climate conditions assessed by the model, the digital twin system can calculate the optimal amount of fertilizer and irrigation plan for crops. At the same time, combined with historical data and future weather changes predicted by the model, the digital twin system can also predict the risks of pests and diseases that crops may face and give corresponding prevention and control measures.

[0066] In some cases, the digital twin system may send the initial scene simulation data to the digital twin node for processing. The digital twin node is a computing node with high simulation and simulation capabilities, which can perform more sophisticated and complex simulation and analysis of the agricultural virtual park.

[0067] The digital twin system will package the initial scene simulation data and send it to the digital twin node. After receiving the data, the digital twin node will use its own computing resources and agricultural environmental analysis model to perform data analysis and environmental status assessment.

[0068] On the digital twin node, the initial scenario simulation data is loaded into the agricultural environmental analysis model for in-depth environmental status assessment. Since the digital twin node has more powerful computing power and a more sophisticated simulation environment, it can provide more accurate and comprehensive assessment results.

[0069] After the evaluation is completed, the digital twin node will determine the multiple target key growth parameters corresponding to the target agricultural virtual park and return these parameters to the digital twin system. After receiving these parameters, the digital twin system will further process and analyze them, and ultimately provide scientific decision support for agricultural producers.

[0070] In a possible implementation, the agricultural environment analysis model includes an environmental characteristic representation network and an environmental status assessment network.

[0071] The step of loading the initial scenario simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct environmental status assessment includes: The initial scene simulation data is loaded into the environmental feature representation network to perform growth environment feature recognition, and growth environment feature data corresponding to the target agricultural virtual park is generated.

[0072] The growth environment characteristic data is loaded into the environmental condition assessment network to generate a plurality of target key growth parameters.

[0073] In this embodiment, the digital twin system first loads the initial scene simulation data into the environmental feature representation network in the agricultural environment analysis model. This network is specifically used to identify and extract the growth environment characteristics of the agricultural virtual park.

[0074] Specifically, when the digital twin system inputs the initial scene simulation data into the environmental feature representation network, the environmental feature representation network will start working and conduct in-depth analysis of the input data. It will identify key environmental parameters such as soil moisture, temperature, light intensity, and carbon dioxide concentration in the air, and extract these features from complex data.

[0075] For example, if the initial scene simulation data contains information about changes in soil moisture, the environmental feature representation network can identify these changes and convert them into specific moisture feature data. Similarly, for other environmental parameters such as temperature and light, the network can also perform similar feature recognition and extraction.

[0076] After being processed by the environmental characteristic representation network, the digital twin system will obtain the growth environment characteristic data corresponding to the target agricultural virtual park. These data represent the various environmental characteristics of the park in a structured form, providing a basis for subsequent environmental status assessment and growth parameter determination.

[0077] After the environmental feature representation network completes feature recognition and extraction, the digital twin system will obtain a set of growth environment feature data. These data are the refinement and summary of the environmental features in the initial scene simulation data. They represent the characteristics of key environmental parameters such as soil moisture, temperature, and light in the form of numerical values ​​or vectors.

[0078] For example, growth environment characteristic data may include soil moisture values, average temperature values, maximum and minimum light intensity at each time point, etc. These data not only reflect the current state of the environment, but may also contain trends and periodic laws of environmental changes.

[0079] The digital twin system will store these growth environment characteristic data for subsequent use. These data are of great significance for understanding the environmental conditions of the agricultural virtual park and predicting the growth of crops.

[0080] Next, the digital twin system will load the growth environment characteristic data into the environmental status assessment network. The task of this network is to evaluate the environmental status of the target agricultural virtual park based on the input growth environment characteristic data and generate multiple target key growth parameters.

[0081] When the growth environment characteristic data are input into the environmental status assessment network, the network will use its built-in algorithms and models to analyze and calculate the data. The network will comprehensively consider the impact of various environmental characteristics on crop growth, as well as the interactions and dependencies between these characteristics.

[0082] For example, the network may analyze the effects of soil moisture and temperature on crop water absorption and transpiration, as well as the effects of light intensity on photosynthesis and product accumulation. By taking these factors into account, the network can assess the suitability of the current environmental conditions for crop growth and predict the yield and quality that the crops may achieve.

[0083] After completing the environmental assessment, the environmental assessment network will generate a number of target key growth parameters. These parameters are determined based on the input growth environment characteristic data and the network's built-in agricultural knowledge base, and they are of great significance for guiding agricultural production.

[0084] For example, target key growth parameters may include optimal irrigation amount, appropriate fertilizer amount, expected yield, probability of pests and diseases, etc. These parameters not only reflect the growth requirements and potential of crops under current environmental conditions, but may also include predictions of the impact of environmental changes on crop growth in the future.

[0085] The digital twin system will store and output these target key growth parameters for reference and use by agricultural producers. With these parameters, agricultural producers can formulate agricultural production plans such as irrigation and fertilization more scientifically to improve the yield and quality of crops.

[0086] Furthermore, the embodiment of the present application also provides an agricultural park data generation device based on digital twins, the device comprising: An acquisition module is used to acquire the target agricultural virtual park of the digital twin; A collection module, used for collecting scene simulation data of the target agricultural virtual park and generating initial scene simulation data corresponding to the target agricultural virtual park; A determination module is used to evaluate the environmental conditions based on the initial scene simulation data and the agricultural environment analysis model that has completed knowledge learning in advance, and determine multiple target key growth parameters corresponding to the target agricultural virtual park, wherein the target key growth parameters reflect the growth environment and conditions of the crops in the target agricultural virtual park.

[0087] In a possible implementation, collecting scene simulation data for the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park includes: Perform multiple rounds of scene simulation data collection on the target agricultural virtual park, and generate initial scene simulation data corresponding to the target agricultural virtual park collected in each round; The environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environmental analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined, including: Determining target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data; An environmental condition assessment is performed based on the target scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined.

[0088] In a possible implementation, determining the target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data includes: Performing scene redundancy optimization on the plurality of initial scene simulation data according to a scene redundancy optimization strategy to generate first scene simulation data corresponding to each of the initial scene simulation data; For the plurality of first scene simulation data, performing deviation correction on each of the first scene simulation data to generate a plurality of second scene simulation data; Averaging is performed on a plurality of the second scene simulation data to generate the target scene simulation data.

[0089] In a possible implementation, the environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning to determine multiple target key growth parameters corresponding to the target agricultural virtual park, including: The initial scenario simulation data is loaded into the agricultural environment analysis model that has previously completed knowledge learning to conduct environmental condition assessment, and based on the generation result of the agricultural environment analysis model, a plurality of target key growth parameters corresponding to the target agricultural virtual park are generated; or, The initial scene simulation data is sent to the digital twin node, so that the digital twin node loads the initial scene simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct an environmental condition assessment, determine and return multiple target key growth parameters corresponding to the target agricultural virtual park.

[0090] An embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method provided in any embodiment of the present application is implemented.

[0091] The above-mentioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0092] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0093] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the method provided in any embodiment of the present application is implemented.

[0094] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope of the present application is indicated by the claims.

[0095] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for generating agricultural park data based on digital twins, characterized in that: The method comprises: Obtain digital twin of the target agricultural virtual park; Collecting scene simulation data for the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park; An environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environment analysis model that has completed knowledge learning in advance, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined. The target key growth parameters reflect the growth environment and conditions of the crops in the target agricultural virtual park.

2. The method for generating agricultural park data based on digital twin according to claim 1, characterized in that: The collecting of scene simulation data for the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park includes: Perform multiple rounds of scene simulation data collection on the target agricultural virtual park, and generate initial scene simulation data corresponding to the target agricultural virtual park collected in each round; The environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environmental analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined, including: Determining target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data; An environmental condition assessment is performed based on the target scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined.

3. The method for generating agricultural park data based on digital twin according to claim 2, characterized in that: Determining the target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data includes: Performing scene redundancy optimization on the plurality of initial scene simulation data according to a scene redundancy optimization strategy to generate first scene simulation data corresponding to each of the initial scene simulation data; For the plurality of first scene simulation data, performing deviation correction on each of the first scene simulation data to generate a plurality of second scene simulation data; Averaging is performed on a plurality of the second scene simulation data to generate the target scene simulation data.

4. The method for generating agricultural park data based on digital twin according to claim 1, characterized in that: The environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environmental analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined, including: The initial scenario simulation data is loaded into the agricultural environment analysis model that has previously completed knowledge learning to conduct environmental condition assessment, and based on the generation result of the agricultural environment analysis model, a plurality of target key growth parameters corresponding to the target agricultural virtual park are generated; or, The initial scene simulation data is sent to the digital twin node, so that the digital twin node loads the initial scene simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct an environmental condition assessment, determine and return multiple target key growth parameters corresponding to the target agricultural virtual park.

5. The method for generating agricultural park data based on digital twin according to claim 4 is characterized in that: The agricultural environment analysis model includes an environmental characteristic representation network and an environmental status assessment network; The step of loading the initial scenario simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct environmental status assessment includes: Loading the initial scene simulation data into the environmental feature representation network to perform growth environment feature recognition, and generating growth environment feature data corresponding to the target agricultural virtual park; The growth environment characteristic data is loaded into the environmental condition assessment network to generate a plurality of target key growth parameters.

6. An agricultural park data generation device based on digital twins, characterized in that: The device comprises: An acquisition module is used to acquire the target agricultural virtual park of the digital twin; A collection module, used for collecting scene simulation data of the target agricultural virtual park and generating initial scene simulation data corresponding to the target agricultural virtual park; A determination module is used to evaluate the environmental conditions based on the initial scene simulation data and the agricultural environment analysis model that has completed knowledge learning in advance, and determine multiple target key growth parameters corresponding to the target agricultural virtual park, wherein the target key growth parameters reflect the growth environment and conditions of the crops in the target agricultural virtual park.

7. The agricultural park data generation device based on digital twin according to claim 6 is characterized in that: The collecting of scene simulation data for the target agricultural virtual park to generate initial scene simulation data corresponding to the target agricultural virtual park includes: Perform multiple rounds of scene simulation data collection on the target agricultural virtual park, and generate initial scene simulation data corresponding to the target agricultural virtual park collected in each round; The environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environmental analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined, including: Determining target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data; An environmental condition assessment is performed based on the target scenario simulation data and the agricultural environment analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined.

8. The agricultural park data generation device based on digital twin according to claim 7 is characterized in that: Determining the target scene simulation data corresponding to the target agricultural virtual park based on the plurality of initial scene simulation data includes: Performing scene redundancy optimization on the plurality of initial scene simulation data according to a scene redundancy optimization strategy to generate first scene simulation data corresponding to each of the initial scene simulation data; For the plurality of first scene simulation data, performing deviation correction on each of the first scene simulation data to generate a plurality of second scene simulation data; Averaging is performed on a plurality of the second scene simulation data to generate the target scene simulation data.

9. The agricultural park data generation device based on digital twin according to claim 6 is characterized in that: The environmental condition assessment is performed based on the initial scenario simulation data and the agricultural environmental analysis model that has previously completed knowledge learning, and multiple target key growth parameters corresponding to the target agricultural virtual park are determined, including: The initial scenario simulation data is loaded into the agricultural environment analysis model that has previously completed knowledge learning to conduct environmental condition assessment, and based on the generation result of the agricultural environment analysis model, a plurality of target key growth parameters corresponding to the target agricultural virtual park are generated; or, The initial scene simulation data is sent to the digital twin node, so that the digital twin node loads the initial scene simulation data into the agricultural environment analysis model that has previously completed knowledge learning to conduct an environmental condition assessment, determine and return multiple target key growth parameters corresponding to the target agricultural virtual park.

10. A digital twin system, characterized in that: The digital twin system includes a machine-readable storage medium and a processor, wherein the machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the digital twin system implements the agricultural park data generation method based on digital twins as described in any one of claims 1 to 8.

Images