Digital twinborn visual application platform

Abstract

The invention discloses a digital twinborn visual application platform, and relates to the technical field of rural digital management, and the platform comprises a data collection module which is used for collecting rural basic data and resource configuration data, and converting the data into three-dimensional point cloud data; the digital twinborn modeling module is used for constructing a rural digital twinborn model; the intelligent analysis module is used for collecting real-time production data and inputting the real-time production data into the digital twin model for simulation production simulation and intelligent analysis; and the visual interaction regulation and control module is used for visually displaying the analysis result and supporting an interaction instruction to carry out resource configuration optimization and dynamic production regulation and control. The technical problems that efficient integration and real-time dynamic analysis of rural scene multi-source data cannot be achieved in the prior art, and accurate resource configuration optimization and intelligent production management are difficult to support are solved, and multi-source data integration and intelligent optimization are achieved through the digital twinborn technology; and the rural resource allocation efficiency and the production management intelligent level are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of rural digital management, and particularly to a digital twin visualization application platform. Background Art

[0002] However, traditional rural management methods usually rely on manual experience and static data, facing problems such as scattered data, lagging updates, and lack of scientific basis for resource allocation. This inefficient management mode not only leads to waste of resources and low production efficiency, but also is difficult to cope with the contradiction between ecological environment protection and agricultural production. Summary of the Invention

[0003] This application provides a digital twin visualization application platform, which is used to solve the technical problems that the prior art cannot achieve the efficient integration and real-time dynamic analysis of multi-source data in rural scenarios, and is difficult to support precise resource allocation optimization and intelligent production management.

[0004] This application provides a digital twin visualization application platform, which includes: a data acquisition module, used to collect rural basic data and resource allocation data, and convert the rural basic data into three-dimensional point cloud data; a digital twin modeling module, used to use the three-dimensional point cloud data to construct a basic rural three-dimensional model, and use the resource allocation data for model empowerment to generate a rural digital twin model; an intelligent analysis module, used to collect rural real-time production data, input it into the rural digital twin model, conduct simulation production simulation, and collect production simulation data for multi-angle intelligent analysis to generate intelligent analysis results; a visualization interaction control module, used to visually interactively display the intelligent analysis results, receive interaction instructions for resource allocation optimization, and perform dynamic production control according to the optimization strategy.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The digital twin visualization application platform provided in this application relates to the technical field of rural digital management. By collecting rural data to generate three-dimensional point clouds, constructing a digital twin model and combining real-time production data for simulation simulation and intelligent analysis, and displaying the analysis results through a visualization interface, it supports interactive resource allocation optimization and dynamic production control, realizes the intelligentization and high efficiency of rural management, solves the technical problems that the prior art cannot achieve the efficient integration and real-time dynamic analysis of multi-source data in rural scenarios, and is difficult to support precise resource allocation optimization and intelligent production management, and realizes the technical effect of realizing multi-source data integration, real-time simulation and intelligent optimization through digital twin technology, and comprehensively improving the efficiency of rural resource allocation and the intelligent level of production management. Description of the Drawings

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0008] Figure 1 Schematic diagram of the digital twin visualization application platform provided by the embodiment of the present application;

[0009] Figure 2 Schematic diagram of the process for the visualization interaction control module in the digital twin visualization application platform provided by the embodiment of the present application to receive interaction instructions for resource configuration optimization.

[0010] Explanation of reference numerals: data acquisition module 11, digital twin modeling module 12, intelligent analysis module 13, visualization interaction control module 14. Detailed implementation manners

[0011] The present application provides a digital twin visualization application platform, which is used to solve the technical problems that the prior art cannot achieve the efficient integration and real-time dynamic analysis of multi-source data in rural scenarios, and it is difficult to support accurate resource configuration optimization and intelligent production management.

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0013] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 shown, the present application provides a digital twin visualization application platform, and the platform includes:

[0015] The data acquisition module 11 is used to collect rural basic data and resource allocation data, and convert the rural basic data into 3D point cloud data.

[0016] Furthermore, the data acquisition module 11 is also used to perform the following steps:

[0017] P11: The rural basic data includes geographical environment information data and hardware infrastructure data, and the resource allocation data includes production capacity area division information and production resource allocation data; P12: After performing noise processing and format conversion on the geographical environment information data and hardware infrastructure data, spatial correction is performed using a geographical coordinate system to generate the 3D point cloud data.

[0018] It should be understood that the data acquisition module of this application is used to achieve the accurate acquisition and processing of rural basic data and resource allocation data, and convert the basic data into 3D point cloud data.

[0019] Specifically, when collecting data, the rural basic data mainly includes geographical environment information data and hardware infrastructure data. Among them, the geographical environment information data covers topographical and geomorphic features (such as slope, elevation, water body distribution) and land use information (such as classification of cultivated land, forest land, roads, etc.); the hardware infrastructure data involves building distribution, road network, and the status of agricultural machinery equipment. The resource allocation data focuses on describing the layout and element distribution of rural production activities, including production capacity area division information (such as division of planting areas and breeding areas) and production resource allocation data (such as irrigation water use, electricity use, etc.). These data lay the foundation for subsequent model construction and analysis.

[0020] The collected data undergoes noise processing and format conversion to ensure its accuracy and consistency. Noise processing uses filtering algorithms (such as mean filtering, Kalman filtering) to remove environmental interference and redundant point data in equipment acquisition. For example, in the terrain data collected by lidar, shadows and vegetation occlusion may generate noise points, and these invalid points can be cleared through filtering techniques. Format conversion unifies multi-source data (such as the LAS format of lidar point cloud and the GeoTIFF format of UAV images) into a standardized format (such as PLY or OBJ) for subsequent processing.

[0021] Furthermore, spatial correction is a crucial step to ensure the geographical accuracy of data. The correction adopts the global geographic coordinate system (such as WGS-84) to perform unified spatial alignment on all collected data, ensuring the coordinate consistency among the data. In this process, high-precision differential GPS (RTK) and ground control points (GCPs) can be used as reference points, and the collected data can be aligned to the standard coordinate system through coordinate mapping algorithms (such as the ICP algorithm). For example, taking the building corner points determined by RTK GPS as the benchmark, the building positions in the point cloud data can be corrected to the actual geographical locations.

[0022] After the above processing, the generated three-dimensional point cloud data is a high-precision digital representation of the rural geographical space and infrastructure. The characteristics of the point cloud data lie in its high density and three-dimensional spatial distribution characteristics, which can completely reflect the geometric shapes and their positional relationships of entities such as rural terrain, buildings, and roads, providing core data support for the subsequent construction of the digital twin model.

[0023] The digital twin modeling module 12 is used to construct a basic rural three-dimensional model using the three-dimensional point cloud data and perform model empowerment using the resource configuration data to generate a rural digital twin model.

[0024] Furthermore, the digital twin modeling module 12 is also used to perform the following steps:

[0025] P21: Extract topographic and geomorphic features, building geometric features, road network features, and infrastructure features based on the three-dimensional point cloud data; P22: Use the topographic and geomorphic features, building geometric features, road network features, and infrastructure features for three-dimensional modeling to generate the basic rural three-dimensional model, where the basic rural three-dimensional model includes a terrain model, a building model, and a road network topology model; P23: Use the resource configuration data to perform model empowerment on the basic rural three-dimensional model to generate a rural digital twin model.

[0026] Optionally, the digital twin modeling module 12 of the present application converts the three-dimensional point cloud data into an accurate basic rural three-dimensional model through multi-step operations, and further combines the resource configuration data to perform model empowerment to generate a rural digital twin model with dynamic semantic information. The specific process is as follows:

[0027] Based on 3D point cloud data, core feature information in rural scenes is first extracted, including topographical and geomorphic features, building geometric features, road network features, and infrastructure features. Among them, topographical and geomorphic features are analyzed through the variation of point cloud elevation values to generate information such as surface height, slope, and water flow paths, which are of great significance for land use and production planning; building geometric features extract the contour, shape, and height information of buildings from the point cloud and accurately model them using shape recognition algorithms (such as RANSAC plane fitting); road network features extract the road positions and topological relationships through sparse areas with linear distribution in the point cloud to generate the rural transportation network; infrastructure features include power poles, irrigation facilities, etc., which are extracted based on specific geometric shapes and position distributions. These feature data provide core support for 3D modeling.

[0028] The extracted feature data is input into 3D modeling tools (such as Open3D or Blender) to construct a basic rural 3D model. The terrain model is generated through a triangulation algorithm for terrain point clouds (such as Delaunay triangulation), visually expressing the undulation and spatial distribution of the rural terrain; the building model uses point cloud segmentation and fitting techniques (such as Bounding Box fitting) to reconstruct the 3D structure of buildings, showing the building shape and layout; the road network topological model constructs the connection relationships and hierarchical topologies of roads through road centerline extraction algorithms (such as the Skeletonization algorithm), clearly showing the rural transportation network. These models together constitute the basic rural 3D model, which is an accurate digital representation of the rural physical environment.

[0029] After completing the basic 3D modeling, the model is empowered using resource configuration data to generate a rural digital twin model with dynamic semantics. First, through a dynamic tagging mechanism, resource configuration data (such as planting area distribution, water resource allocation) is bound to specific objects in the 3D model (such as plots, equipment) to form object association combinations, making the model queryable and interactive; second, through attribute injection technology, the attribute values of resource configuration data (such as land use, irrigation frequency) are injected into the corresponding model elements, enabling the model objects to have rich semantic information; finally, real-time data interfaces are configured to achieve dynamic updates of resource configuration data, enabling the rural digital twin model to reflect production status and resource changes in real time and having dynamic feedback and prediction capabilities.

[0030] Through the above steps, the generated rural digital twin model not only has the 3D spatial characteristics of the physical world but also incorporates the semantic information of resource configuration and production behavior. It is a comprehensive digital mapping and dynamic simulation tool for rural scenes, providing a solid foundation for subsequent intelligent analysis and resource optimization.

[0031] Furthermore, step P23 of the embodiment of the present application further includes:

[0032] P23-1: Set dynamic tags to associate the resource configuration data with the corresponding 3D model for object association, generating an object association combination; P23-2: According to the object association combination, use the resource configuration data to perform attribute injection on the basic rural 3D model, endowing the model with semantic information to generate the rural digital twin model; P23-3: Configure a real-time data interface for the rural digital twin model, and based on an adaptive data update mechanism, receive the resource configuration data for real-time update.

[0033] Specifically, the empowerment and dynamic update of the rural digital twin model can be completed through the following specific steps. First, set dynamic tags to associate the resource configuration data with the corresponding 3D model for object association, generating an object association combination. A dynamic tag refers to a dynamically updatable identifier used to mark specific objects (such as plots, buildings, or facilities) in the 3D model and bind them to the resource configuration data. For example, the dynamic tag of a farmland plot can identify its planted crop type, soil properties, etc. Through object association technology, using information such as plot distribution and irrigation system layout in the resource configuration data, a mapping relationship between the dynamic tag and the model object is constructed to form an object association combination, ensuring that each element of the model has semantic information and can be traced and updated.

[0034] According to the generated object association combination, perform attribute injection operations, endowing the model object with the specific attribute values of the resource configuration data, converting the basic rural 3D model into a rural digital twin model with rich semantics. Attribute injection refers to taking the resource configuration data (such as production factor distribution, equipment status, resource utilization rate) as attribute values and attaching them to the corresponding objects in the 3D model. For example, inject the crop type, yield per mu, and fertilization amount of the planting area into the plot model, and inject the building use (such as warehouse, residence) and equipment operation status (such as the working frequency of the irrigation pump) into the corresponding building or equipment model. Through attribute injection, the rural digital twin model can not only visually present the spatial distribution but also express rich production and resource information.

[0035] Configure a real-time data interface for the rural digital twin model to achieve the dynamic update function. A real-time data interface is a technical means used to interface with Internet of Things devices, sensors, or external systems to receive real-time updated resource configuration data (such as soil humidity, meteorological conditions, water resource usage). Based on an adaptive data update mechanism, the model can dynamically adjust its semantic information according to the changes in the received data. For example, when the irrigation system is turned on, the irrigation area label in the model will display the water resource usage and irrigation coverage in real time; when the meteorological conditions change, the crop growth prediction and water demand will also be updated in real time. This mechanism ensures that the model always remains synchronized with the real world through rule-triggered or time-interval update strategies.

[0036] Through the above three steps, the generated rural digital twin model not only has static three-dimensional spatial characteristics, but also has dynamic semantic association capabilities and real-time feedback capabilities, becoming a comprehensive digital mapping tool for rural scenarios. This dynamic empowerment method ensures the flexibility and practicality of the model, providing strong technical support for rural digital management and intelligent decision-making.

[0037] The intelligent analysis module 13 is used to collect real-time rural production data, input it into the rural digital twin model, conduct simulation production simulations, and collect production simulation data for multi-angle intelligent analysis to generate intelligent analysis results.

[0038] Furthermore, the intelligent analysis module 13 is also used to perform the following steps:

[0039] P31: Based on multiple production capacity areas of the target rural area, deploy edge processing nodes, and the edge processing nodes are configured with data acquisition modules and data processing modules; P32: Through the data acquisition module, obtain diverse production data in real time and transmit it to the data processing module for standardization processing to generate the real-time rural production data; P33: Input the real-time rural production data into the rural digital twin model, conduct simulation production simulations for each production capacity area, and collect and obtain multiple simulated production data sets.

[0040] It should be understood that the intelligent analysis module 13 of the present application is used to collect real-time rural production data, input it into the rural digital twin model, conduct simulation production simulations, complete the collection, processing, simulation and data analysis of real-time rural production data, and generate intelligent analysis results.

[0041] First, based on multiple production capacity areas of the target rural area, deploy edge processing nodes in each area to achieve distributed data collection and processing. Edge processing nodes are hardware facilities deployed close to the data source, configured with data acquisition modules and data processing modules. The data acquisition module collects diverse production data in real time through a sensor network, including soil humidity, air temperature and humidity, crop growth status, and equipment operation status, etc.; the data processing module then conducts preliminary processing of the data locally, such as denoising, filtering, and format conversion. The distributed deployment of edge processing nodes significantly reduces data transmission latency, while reducing the load on cloud computing and improving the real-time performance and stability of the system. For example, the edge processing node in a planting area can collect soil humidity data in real time and immediately process and determine whether irrigation is required.

[0042] The diverse production data obtained by the data acquisition module is transmitted to the data processing module for standardization processing to generate rural real-time production data that meets the requirements of the rural digital twin model. Standardization processing is the process of converting multi-source acquired data into a unified format, unit, and range to ensure data consistency and availability. For example, soil moisture may come from sensors of different brands, using different measurement units and resolutions, and it needs to be unified to a standard range (such as 0~100%) through normalization or linear conversion. At the same time, noise processing and outlier detection are also completed in the data processing module to eliminate invalid or incorrect data and improve data quality.

[0043] The standardized rural real-time production data is input into the rural digital twin model to start the simulation production simulation, and multiple simulated production data sets are collected and obtained. The simulation production simulation is the process of virtually reproducing rural production activities based on the digital twin model. Through built-in dynamic rules and algorithms (such as crop growth models, resource consumption models), it predicts production behaviors and evaluates the effects of resource allocation. For example, in the simulation of the planting area, the model simulates the crop growth process according to real-time weather conditions and soil data, and at the same time predicts yields, resource consumption (such as water and fertilizer amounts), and environmental impacts (such as carbon emissions). The simulation results of each production capacity area are stored in the form of simulated production data sets, covering multi-dimensional data, such as crop health status, equipment operation efficiency, and resource utilization rate.

[0044] Through the above steps, the intelligent analysis module 13 can achieve a complete closed-loop from data acquisition to simulation, providing accurate basic data support for subsequent multi-angle intelligent analysis and optimization decisions. The introduction of the edge processing node and the implementation of standardized data processing significantly improve the data real-time and the efficiency of model calculation. The simulation production simulation provides an efficient virtual experimental environment for complex rural scenarios, facilitating rural digital management and scientific decision-making.

[0045] Furthermore, the intelligent analysis module 13 is also used to perform the following steps:

[0046] P34: The production simulation data at least includes diverse production data, resource utilization data, and environmental impact data; P35: The production simulation data is input into the multi-angle integrated analysis model for intelligent analysis and evaluation respectively to generate the intelligent analysis results. Among them, the multi-angle integrated analysis model includes multiple intelligent analysis units of different types, and each intelligent analysis unit is configured with a corresponding model weight, and can match corresponding algorithm rules and training data volumes according to the model weight and type.

[0047] Optionally, the multi-angle analysis and evaluation of the production simulation data are further achieved through the following steps to generate intelligent analysis results, providing scientific support for rural digital management.

[0048] In simulation production, the collected production simulation data includes at least multivariate production data, resource utilization data, and environmental impact data. Multivariate production data reflects the dynamics of production activities in the production capacity area, such as crop growth status, harvest prediction, equipment operation efficiency, etc.; resource utilization data indicates the usage of production factors such as water resources, electricity, fertilizers, etc., revealing the resource allocation efficiency; environmental impact data quantifies the impact of production activities on the ecological environment, such as carbon emissions, soil erosion degree, and pollutant emissions. These data categories comprehensively cover the key dimensions of rural production activities, providing a rich input basis for multi-angle analysis.

[0049] Step P35: Input the production simulation data into a multi-angle integrated analysis model for intelligent analysis and evaluation, and generate intelligent analysis results for different requirements. The multi-angle integrated analysis model is a framework that integrates multiple analysis methods and contains different types of intelligent analysis units, each of which conducts in-depth analysis for a specific dimension. For example: The production capacity analysis unit evaluates the production capacity change trend through time series analysis and predicts the yields of different crops. The resource efficiency unit calculates the resource utilization efficiency based on a linear regression model and discovers high-energy-consuming areas. The environmental impact unit evaluates the comprehensive impact of production activities on the ecosystem by combining a carbon footprint model and a clustering algorithm.

[0050] The model weight refers to the relative importance assigned to each intelligent analysis unit, which is used to adjust the comprehensiveness and pertinence of the analysis results according to user needs. For example, in a scenario that emphasizes environmental protection, the weight of the environmental impact unit can be set higher, while in a scenario that pursues yield, the weight of the production capacity analysis unit will be dominant. The matching of the algorithm rules and the volume of training data determines the accuracy and applicability of each intelligent analysis unit. Based on the type (such as time series data, spatial distribution data) and scale (such as the number of data points, feature dimensions) of the production simulation data, the model automatically selects the optimal analysis algorithm (such as support vector machine, random forest) and the size of the training data set to ensure the accuracy and efficiency of the analysis results.

[0051] Through this multi-angle integrated analysis model, the generated intelligent analysis results cover the key indicators of different dimensions. For example, users can obtain the health score of crops, the heat map of resource utilization efficiency, and the prediction of the potential impact of production on the environment. The results not only support the optimization of rural resources and production regulation but also provide a scientific basis for formulating long-term sustainable development strategies. The dynamic adjustment of the model weight and the adaptive matching of the algorithm significantly improve the flexibility and intelligence level of the analysis, meeting the actual needs of multiple scenarios.

[0052] The visual interactive regulation module 14 is used to visually interactively display the intelligent analysis results, receive interactive instructions for resource configuration optimization, and perform dynamic production regulation according to the optimization strategy.

[0053] Further, as Figure 2 shown, the visual interaction control module 14 is further configured to perform the following steps:

[0054] P41: The interaction instruction includes multi-objective optimization indicators, and the user can set the weights of different optimization objectives according to actual needs; P42: Integrate the production-related data of each production capacity area, construct an optimization decision matrix, and perform dimensionless processing on the index data in the optimization decision matrix; P43: According to the weights set by the user in the multi-objective optimization indicators, assign weights to each index of the optimization decision matrix to generate a weighted decision matrix; P44: Optimize the resource allocation according to the weighted decision matrix to generate an optimal resource allocation plan.

[0055] It should be understood that the visual interaction control module 14 of the present application is used to intuitively display the intelligent analysis results to the user, and supports multi-objective optimization and dynamic production control to ensure the maximization of resource allocation efficiency and production benefits.

[0056] First, the user inputs an interaction instruction through the visual interaction interface to set multi-objective optimization indicators and their weights. The multi-objective optimization indicators cover target requirements in different dimensions, such as improving production capacity efficiency, reducing resource consumption, and reducing environmental impact. The user assigns weights to each target according to actual needs. For example, 50% of the weight is assigned to production capacity efficiency, 30% to resource utilization rate, and 20% to environmental protection. The setting of weights is achieved through sliders or input boxes provided by the interface, which is intuitive and simple. This weight allocation mechanism gives the user flexible decision-making control ability to ensure that the optimization strategy meets the requirements of a specific scenario.

[0057] Next, integrate the production-related data from each production capacity area (such as resource usage, production capacity level, environmental impact data) to construct an optimization decision matrix. The optimization decision matrix is a tool for quantifying the performance of different production capacity areas in various optimization indicators. Its rows represent production capacity areas, and its columns represent optimization indicators. For example, a decision matrix may include index data such as water resource utilization rate, unit output, and carbon emission intensity of each area. To ensure the comparability of data, perform dimensionless processing on the index data in the matrix, such as normalization processing (scaling the data value to the range of 0 to 1) or standardization processing (removing the mean and scaling by the standard deviation). By dimensionless processing, the influence of data scale is eliminated, enabling comparison and optimization between different indicators under the same weight system.

[0058] Furthermore, according to the optimization target weights set by the user, weights are assigned to the indicators in the optimization decision matrix to generate a weighted decision matrix. The indicator weighting is completed by multiplying the weight values specified by the user with the dimensionless indicator data. For example, for the water resource utilization rate in a certain region, its weight is 30%, and the original dimensionless value is 0.8, so the weighted value is 0.24 (0.8×0.3). The weighted decision matrix comprehensively considers the relative performance of each region under multiple optimization targets and is an important basis for calculating the optimal resource allocation. Finally, based on the weighted decision matrix, resource allocation optimization is performed to generate the optimal resource allocation plan. The optimization process can adopt a multi-objective decision-making algorithm to improve the scenario adaptability of the allocation plan.

[0059] Through these steps, users can intuitively view the resource allocation before and after optimization on the visualization interface. For example, the implementation effect of the optimal plan is displayed through heat maps, trend charts, etc. At the same time, the system supports automatic execution of the regulation operations of the optimal plan (such as controlling the irrigation system through the Internet of Things) to ensure that the optimization strategy can be efficiently implemented. The entire process combines user decision-making and system intelligent optimization, fully reflecting the advantages of human-machine collaboration in rural digital management.

[0060] Furthermore, step P44 in the embodiment of the present application further includes:

[0061] P44-1: Determine the positive ideal solution and negative ideal solution of each indicator; P44-2: According to the weighted decision matrix, calculate the relative distances between the actual values of each production capacity region and the positive ideal solution and the negative ideal solution; P44-3: Evaluate the ratio of the relative distances and calculate the comprehensive priority scores of each production capacity region; P44-4: Recommend the optimal resource allocation plan according to the comprehensive priority scores.

[0062] In a possible embodiment of the present application, the recommendation of the optimal resource allocation plan can be achieved through a clear multi-objective decision-making process.

[0063] First, determine the positive ideal solution and negative ideal solution of each optimization indicator. The positive ideal solution refers to the optimal value of a certain indicator in the ideal state (such as maximizing production and minimizing carbon emissions), while the negative ideal solution is the worst value of the indicator (such as the lowest efficiency or the highest resource waste). The basis for determining these values is historical data, industry benchmarks, or model calculations. For example, for the unit water resource utilization rate, the positive ideal solution is 1 (fully efficient utilization), and the negative ideal solution is 0 (ineffective utilization). This process provides a clear evaluation criterion for subsequent priority calculations.

[0064] Then, according to the weighted decision matrix, calculate the relative distances between the actual values of each production capacity region and the positive ideal solution and the negative ideal solution. The calculation of the relative distance can adopt the Euclidean distance formula, which is used to quantify the deviation degree of the performance of each production capacity region from the ideal state or the worst state. The specific calculation formula can be:

[0065] ; where, is the distance from the positive ideal solution, is the distance from the negative ideal solution, is the index weight, is the actual index value, and are the positive ideal solution and the negative ideal solution respectively. By calculating the above distances region by region, the performance of the resource allocation in each region on different objectives can be quantified.

[0066] Next, evaluate the ratio of the above relative distances and calculate the comprehensive priority score for each production capacity region. The priority score formula is:

[0067] ; where, represents the priority score of the i-th production capacity region, ranging from 0 to 1. The closer the score value is to 1, the closer the resource allocation in this region is to the positive ideal solution, and the better the optimization effect; the closer the value is to 0, the greater the deviation of the resource allocation in this region, and it needs to be adjusted preferentially. The comprehensive score balances the weights of various optimization objectives and the actual performance of each region, and is the core basis for generating the optimal resource allocation plan.

[0068] Finally, based on the comprehensive priority score, recommend the optimal resource allocation plan. Sort the score results of all production capacity regions and recommend specific resource allocation strategies according to the priority level. For example, for the irrigation system, allocate water resources preferentially to high-priority regions; for the fertilization plan, adjust the application amount and frequency of fertilizers to improve the production efficiency of low-priority regions. The recommended plan can also be presented through visual methods such as heat maps, intuitively showing the optimized resource distribution and the change in production efficiency.

[0069] Through the above steps, module 14 not only realizes the in-depth optimization of the intelligent analysis results, but also provides an intelligent and flexible solution for rural resource management through a scientific multi-objective decision-making algorithm, significantly improving the resource utilization efficiency and management effectiveness.

[0070] In summary, the embodiments of the present application at least have the following technical effects:

[0071] The present application realizes rural digital management through multi-module collaboration: collects rural basic data and resource allocation data, converts them into three-dimensional point cloud data, constructs a basic three-dimensional model and generates a rural digital twin model in combination with resource data; collects real-time production data and inputs it into the model for simulation, and generates optimization decision-making basis through multi-angle intelligent analysis; uses a visual interaction interface to display the analysis results and supports users to dynamically adjust resource allocation and production control through interaction instructions.

[0072] It has achieved the technical effect of realizing multi-source data integration, real-time simulation and intelligent optimization through digital twin technology, comprehensively improving the efficiency of rural resource allocation and the intelligent level of production management.

[0073] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0075] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. Digital twin visualization application platform, characterized by: The platform includes: A data acquisition module, used to collect basic rural data and resource allocation data, and convert the basic rural data into three-dimensional point cloud data; A digital twin modeling module, used to use the three-dimensional point cloud data to construct a basic rural three-dimensional model, and use the resource configuration data to empower the model to generate a rural digital twin model; An intelligent analysis module is used to collect real-time rural production data, input it into the rural digital twin model, perform simulated production simulation, collect production simulation data for multi-angle intelligent analysis, and generate intelligent analysis results; The visual interactive control module is used to visually and interactively display the intelligent analysis results, receive interactive instructions to optimize resource allocation, and perform dynamic production control according to the optimization strategy.

2. The digital twin visualization application platform according to claim 1, characterized in that: The data acquisition module is also used for: The rural basic data includes geographical environment information data and hardware infrastructure data, and the resource allocation data includes production capacity area division information and production resource allocation data; After the geographic environment information data and the hardware infrastructure data are subjected to noise processing and format conversion, a geographic coordinate system is used for spatial correction to generate the three-dimensional point cloud data.

3. The digital twin visualization application platform according to claim 1, characterized in that: The digital twin modeling module is also used to: Extracting topographic features, building geometry features, road network features, and infrastructure features based on the three-dimensional point cloud data; Performing three-dimensional modeling using the terrain features, building geometry features, road network features, and infrastructure features to generate the basic rural three-dimensional model, wherein the basic rural three-dimensional model includes a terrain model, a building model, and a road network topology model; The resource configuration data is used to empower the basic rural three-dimensional model to generate a rural digital twin model.

4. The digital twin visualization application platform according to claim 3, characterized in that: The digital twin modeling module is also used to: Setting dynamic tags, associating the resource configuration data with the corresponding three-dimensional model, and generating an object association combination; According to the object association combination, the resource configuration data is used to inject attributes into the basic village three-dimensional model, and semantic information is given to the model to generate the village digital twin model; A real-time data interface is configured for the rural digital twin model, and based on an adaptive data update mechanism, the resource configuration data is received for real-time updating.

5. The digital twin visualization application platform according to claim 1, characterized in that: The intelligent analysis module is also used for: Based on multiple production capacity areas of the target village, edge processing nodes are deployed, and the edge processing nodes are configured with a data collection module and a data processing module; Through the data acquisition module, multivariate production data is acquired in real time, and transmitted to the data processing module for standardized processing to generate the real-time production data of the village; The real-time production data of the village is input into the digital twin model of the village, simulation production of each production capacity area is carried out, and multiple simulated production data sets are collected and acquired.

6. The digital twin visualization application platform according to claim 4, characterized in that: The intelligent analysis module is also used for: The production simulation data at least includes multivariate production data, resource utilization data and environmental impact data; The production simulation data is input into a multi-angle integrated analysis model, and intelligent analysis and evaluation are performed respectively to generate the intelligent analysis results, wherein the multi-angle integrated analysis model includes multiple intelligent analysis units of different types, each intelligent analysis unit is configured with a corresponding model weight, and the corresponding algorithm rules and training data volume can be matched according to the model weight and type.

7. The digital twin visualization application platform according to claim 1, characterized in that: The visual interaction control module is also used for: The interactive instructions include multi-objective optimization indicators, and users can set the weights of different optimization objectives according to actual needs; Integrate the production-related data of each production capacity area, construct an optimization decision matrix, and perform dimensionless processing on the indicator data in the optimization decision matrix; According to the weights set by the user in the multi-objective optimization indicators, weighting each indicator of the optimization decision matrix is ​​assigned to generate a weighted decision matrix; The resource allocation is optimized according to the weighted decision matrix to generate an optimal resource allocation plan.

8. The digital twin visualization application platform according to claim 7, characterized in that: The visual interaction control module is also used for: Determine the positive ideal solution and negative ideal solution of each indicator; According to the weighted decision matrix, the relative distance between the actual value of each production capacity area and the positive ideal solution and the negative ideal solution is calculated; evaluating the ratio of the relative distances and calculating a comprehensive priority score for each capacity area; An optimal resource allocation solution is recommended based on the comprehensive priority score.

Images