Intelligent modeling method, device and system for unmanned station digital twin model

Abstract

The invention relates to the technical field of unmanned site modeling, and particularly discloses an intelligent modeling method, device and system for an unmanned site digital twin model, and the method comprises the steps: carrying out the construction of the digital twin model of an unmanned site through the data of an unmanned site and the basic environment around the unmanned site; and then optimizing the unmanned station digital twin model based on deployment data of an actual scene corresponding to each grid in the established unmanned station digital twin model, namely, following a mixed mode of combining mechanism modeling and data-driven modeling, and taking a physical model as a framework. And the parameters of the digital twin model of the unmanned station are calibrated by using real-time data, and the precision and generalization ability are balanced, so that the construction accuracy and reliability of the digital twin model of the station are improved, and the real-time monitoring accuracy and reliability of the coverage area of the station in a complex environment are improved. Therefore, the accuracy and timeliness of task dynamic planning, reconstruction and bookbinding are higher, so that when tasks need to be executed, the control accuracy and efficiency of single task and multi-task cooperation in the site can be improved, the possibility of task planning again is reduced, and the task scheduling efficiency and accuracy are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned site modeling, in particular to an intelligent modeling method, device and system for a digital twin model of an unmanned site. BACKGROUND

[0002] With the rapid development of intelligent manufacturing, smart cities and unmanned operations, unmanned systems (such as drones, unmanned vehicles, unmanned ships, robots, and robotic dogs) are increasingly widely used in logistics, inspection, security, agriculture, and other fields. With the rapid development of digital twin technology, digital twin technology has gradually extended from industrial manufacturing, transportation management, and other fields to unmanned systems, i.e., through the construction of a virtual mapping of a physical entity to achieve state monitoring and prediction.

[0003] Currently, through a search, it is found that a comparative document (CN118655808B) “Digital Twin Unmanned Equipment System Combat Situation Fusion and Task Control System” calibrates the simulation data in the model, confirms the accuracy of the data, then evaluates the authenticity of the model, judges the communication interference effect of real-time drills, evaluates the stability of the real-time drill communication state, and comprehensively analyzes it to evaluate the accuracy of the digital twin system reflecting the actual battlefield environment, and divides the accuracy of the digital twin system reflecting the actual battlefield environment, makes decisions when the digital twin system can accurately reflect the actual battlefield environment, and when the digital twin system cannot accurately reflect the actual battlefield environment, evaluates the model prediction state of the digital twin system, adjusts the combat task according to the evaluation result, ensures that the system can continuously reflect the actual battlefield environment and make correct task decision allocation, maximizes combat effectiveness and reduces battle risk.

[0004] However, in practice, it is found that the “model authenticity evaluation module” and “drill effect evaluation module” in the patent document are essentially only a simulation drill system, mainly used for sand table deduction, i.e., it is fundamentally impossible to match the actual situation of the actual scene, i.e., the state, path planning, and equipment health status of the existing unmanned system when performing tasks in a dynamic or unstructured environment are difficult to fully grasp through a single sensor or static model, resulting in insufficient real-time monitoring in complex environments, thus leading to low task deployment efficiency.

[0005] Therefore, it is particularly important to propose a new intelligent modeling method for a digital twin model of an unmanned site to improve the construction accuracy and reliability of the digital twin model, thereby improving the real-time monitoring accuracy in complex environments, and thus improving the task deployment efficiency and accuracy. SUMMARY

[0006] The application provides an intelligent modeling method, device and system for a digital twin model of an unmanned site, which can improve the construction accuracy and reliability of the digital twin model, thereby improving the real-time monitoring accuracy in a complex environment, and further improving the task deployment efficiency and accuracy.

[0007] To solve the above technical problems, the application discloses an intelligent modeling method for a digital twin model of an unmanned site, which comprises the following steps: obtaining first data in a preset range of the unmanned site, wherein the first data in the preset range comprises basic environment data in the preset range, and the preset range is determined based on the location of the unmanned site and / or the sensing range of the unmanned site; performing a digital twin modeling operation on a pre-constructed site digital twin architecture model of the unmanned site based on the first data of the unmanned site, to obtain a basic site digital twin model of the unmanned site; performing a grid division operation on the basic site digital twin model to obtain a basic site digital twin model containing a plurality of grids, and determining deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site; performing an optimization operation on the basic site digital twin model according to the deployment data corresponding to all the grids, to obtain an optimized site digital twin model, wherein the site digital twin model is used as a basis for task execution of the unmanned site.

[0008] As an optional implementation, in the first aspect of the application, the method for obtaining first data in a preset range of the unmanned site comprises the following steps: determining all task instructions required to be dispatched for the preset range of the unmanned site; judging whether a first task data set corresponding to the task instruction is contained in a pre-determined task database for any task instruction; when the result of the judgment is yes, obtaining the first task data set corresponding to the task instruction from the task database, performing a task operation matched with the task instruction in the preset range, and collecting first sensor data in the process of executing the task corresponding to the task instruction, and storing the collected first sensor data to the first task data set in a structured manner, wherein the data stored in the first task data set comprises the first data in the preset range; When the result is determined to be no, according to the task instruction, a target task matched with the task instruction and a corresponding second task data set are set, a task operation matched with the target task is executed in the preset range, second sensor data in the process of executing the target task is collected, and the collected second sensor data is stored in a structured manner to the second task data set, and the data stored in the second task data set includes the first data in the preset range.

[0009] As an optional implementation, in the first aspect of the present application, after the optimization operation is performed on the base site digital twin model according to all the deployment data corresponding to the grids to obtain an optimized site digital twin model, the method further comprises: obtaining attribute parameters of all target component architectures of the target unmanned site, each attribute parameter of the target component architecture including a physical parameter and an identifier; constructing an unmanned site digital twin model of the target unmanned site based on all the attribute parameters of the target component architectures and the optimized site digital twin model; performing a debugging operation from virtual to reality on the unmanned site digital twin model based on a northbound interface of the unmanned site digital twin model to obtain a debugging site digital twin model; after the debugging site digital twin model is installed and deployed, performing a pre-planned task based on the debugging site digital twin model in an actual scene of the target unmanned site to obtain an actual execution result of the pre-planned task, comparing the actual execution result of the pre-planned task with an expected execution result of the pre-planned task to obtain a task execution comparison result of the pre-planned task, and performing an optimization operation on a target object according to the task execution comparison result of the pre-planned task to obtain an optimized target object; wherein, when the target object is the debugging site digital twin model, the optimized target object is an optimized target site digital twin model; and when the target object is the target component architecture of the target unmanned site, the optimized target object is the optimized target component architecture of the target unmanned site.

[0010] As an optional implementation, in the first aspect of the present application, the northbound interface of the unmanned site digital twin model includes northbound interfaces of all the target component architectures on the unmanned site digital twin model. wherein, the debugging operation from virtual to reality is performed on the unmanned site digital twin model based on the northbound interface of the unmanned site digital twin model to obtain a debugging site digital twin model, comprising: For any target component architecture, the target component architecture is executed on the unmanned site digital twin model based on a northbound interface of the target component architecture to perform a control operation to obtain control data of the target component architecture in an actual scene. It is determined whether the control data of the target component architecture matches preset control data of the target component architecture determined in advance. When it is determined that the control data does not match the preset control data, an adjustment operation is performed on a control parameter of the target component architecture on the unmanned site digital twin model based on the control data of the target component architecture and the preset control data of the target component architecture determined in advance. When all the target component architectures in the unmanned site digital twin model that need to be adjusted are adjusted, a debugging site digital twin model is obtained.

[0011] As an optional implementation, in the first aspect of the present application, the execution of the pre-planned task based on the debugging site digital twin model to obtain an actual execution result of the pre-planned task comprises: A corresponding pre-planned task is set for a grid of the debugging site digital twin model based on the preset range. A verification operation is performed on the pre-planned task of each grid by an edge computer of the debugging site digital twin model to obtain a task verification result of each grid. For any grid, when the task verification result of the grid indicates that the pre-planned task of the grid is verified, the pre-planned task of the grid is executed in the actual scene of the target unmanned site based on a northbound interface of the debugging site digital twin model to obtain an actual execution result of the pre-planned task. The method further comprises: A monitoring operation is performed on environmental data in the preset range based on a northbound interface of the debugging site digital twin model to obtain an environmental monitoring result in the preset range. It is determined whether the environmental monitoring result in the preset range indicates that the environment in the preset range has changed. When it is determined that the result is yes, the operation of performing a verification operation on the pre-planned task of each grid by the edge computer of the debugging site digital twin model is re-executed to obtain a task verification result of each grid.

[0012] As an optional implementation, in the first aspect of the present application, the acquisition of the attribute parameters of all target component architectures of the target unmanned site comprises: determining a type of the target unmanned site, the type of the target unmanned site including an existing type or a planning type, wherein the existing type indicates that the target unmanned site has been built or has complete design drawings, and the planning type indicates that the target unmanned site is in planning and does not have complete design drawings; when the type of the target unmanned site is the existing type, obtaining electronic design drawing data of the target unmanned site, and obtaining attribute parameters of all target component architectures of the target unmanned site from the drawing data; when the type of the target unmanned site is the planning type, obtaining design data of the target unmanned site in forward design as the attribute parameters of all target component architectures of the target unmanned site.

[0013] As an optional implementation, in the first aspect of the present application, the determination of the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site includes: determining a corresponding unique identifier for each grid; determining the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site according to the unique identifier corresponding to each grid; wherein the deployment data corresponding to each grid includes environment deployment data and task path deployment data corresponding to the grid; wherein the determination of the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site according to the unique identifier corresponding to each grid includes: for any grid, based on the unique identifier corresponding to the grid and the task planning path previously configured for the grid, performing a virtual task from the virtual position corresponding to the unmanned site to the grid to obtain a virtual task result of the grid, and performing a verification operation on the virtual task result of the grid based on the actual task result of the grid previously determined to obtain a task verification result of the grid as the task path deployment data corresponding to the grid, wherein the starting point of the task planning path of the grid is the virtual position corresponding to the actual position of the unmanned site in the actual scene on the digital twin model of the base site, and the end point of the task planning path of the grid is the virtual position corresponding to the actual position of the grid in the actual scene of the unmanned site on the digital twin model of the base site; for any grid, based on the data collection operation on the actual position corresponding to the grid when the unmanned device arrives at the actual position, obtaining environment deployment data corresponding to the actual position of the grid.

[0014] The second aspect of the present application discloses an intelligent modeling device of an unmanned site digital twin model, the device comprises: An acquisition module is configured to acquire first data within a preset range of an unmanned site, wherein the first data within the preset range comprises basic environment data within the preset range, and the preset range is determined based on a location of the unmanned site and / or a perception range of the unmanned site; A construction module is configured to perform a digital twin modeling operation on a pre-constructed site digital twin architecture model of the unmanned site based on the first data of the unmanned site, to obtain a basic site digital twin model of the unmanned site; A division module is configured to perform a grid division operation on the basic site digital twin model, to obtain a basic site digital twin model comprising a plurality of grids; A determination module is configured to determine deployment data corresponding to an actual location of each grid in an actual scene of the unmanned site; An optimization module is configured to perform an optimization operation on the basic site digital twin model according to the deployment data corresponding to all the grids, to obtain an optimized site digital twin model, wherein the site digital twin model is used as a basis for task execution of the unmanned site.

[0015] The third aspect of the present application discloses another intelligent modeling device of an unmanned site digital twin model, the device comprises: A memory storing executable program codes; A processor coupled with the memory; The processor invokes the executable program codes stored in the memory to perform part or all steps of the intelligent modeling method of the unmanned site digital twin model disclosed in the first aspect of the present application.

[0016] The fourth aspect of the present application discloses an intelligent modeling system of an unmanned site digital twin model, the system comprises a task platform, an edge computer, a target base station and a sensor integrated on the target base station, the target base station comprises a communication base station and a navigation positioning base station, the communication base station is configured to provide communication data for the edge computer and the navigation positioning base station, the navigation positioning base station is configured to position the target base station, the edge computer and an unmanned device, the edge computer is arranged on the task platform and is configured to store data, the data comprises a site digital twin model; wherein the data is obtained by the system by performing part or all steps of the intelligent modeling method of the unmanned site digital twin model disclosed in the first aspect of the present application.

[0017] Compared with the prior art, the embodiments of the present application have the following beneficial effects: In the embodiment of the present application, the first data in the preset range of the unmanned site is obtained, the first data in the preset range includes the basic environment data in the preset range, and the preset range is determined based on the location of the unmanned site and / or the perception range of the unmanned site; based on the first data of the unmanned site, a digital twin modeling operation is performed on the pre-constructed site digital twin architecture model of the unmanned site to obtain a basic site digital twin model of the unmanned site; a grid division operation is performed on the basic site digital twin model to obtain a basic site digital twin model containing a plurality of grids, and deployment data corresponding to the actual location of each grid in the actual scene of the unmanned site is determined; based on the deployment data corresponding to all grids, an optimization operation is performed on the basic site digital twin model to obtain an optimized site digital twin model, wherein the site digital twin model is used as the basis for task execution of the corresponding unmanned site. It can be seen that, by constructing the digital twin model of the unmanned site together with the basic environment data around the unmanned site, and then optimizing the digital twin model of the unmanned site based on the deployment data of the actual scene corresponding to each grid in the digital twin model of the unmanned site, a hybrid mode combining mechanism modeling and data-driven modeling is followed, the physical model is used as a framework, the parameters of the digital twin model of the unmanned site are calibrated with real-time data, the accuracy and generalization ability are balanced, the construction accuracy and reliability of the site digital twin model are improved, the real-time monitoring accuracy and reliability of the site covered range in a complex environment are improved, the accuracy and timeliness of task dynamic planning, reconstruction and binding are higher, so as to improve the control accuracy and efficiency of single task and multi-task cooperation in the site when the task needs to be executed, reduce the possibility of task planning again, and further improve the task deployment efficiency and accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a flowchart of an intelligent modeling method of a digital twin model of an unmanned site disclosed by the embodiment of the present application; Figure 2 is a flowchart of another intelligent modeling method of a digital twin model of an unmanned site disclosed by the embodiment of the present application; Figure 3 is a task deployment scene diagram of a forest and grass fire fighting system of an unmanned hangar disclosed by the embodiment of the present application; Figure 4is a structural schematic view of an intelligent modeling device of a digital twin model of an unmanned site disclosed by an embodiment of the present application. Figure 5 is a structural schematic view of another intelligent modeling device of a digital twin model of an unmanned site disclosed by an embodiment of the present application. Figure 6 is a structural schematic view of still another intelligent modeling device of a digital twin model of an unmanned site disclosed by an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative work fall within the scope of protection of the present application.

[0021] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or end including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or end.

[0022] In this document, the term "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor is it independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] The application discloses an intelligent modeling method, device and system for a digital twin model of an unmanned site. The method comprises the following steps: constructing a digital twin model of an unmanned site by combining the unmanned site and the basic environment data around the unmanned site; and optimizing the digital twin model of the unmanned site based on the deployment data of the actual scene corresponding to each grid in the established digital twin model of the unmanned site, that is, following a hybrid mode combining mechanism modeling and data-driven modeling, taking the physical model as a framework, calibrating the parameters of the digital twin model of the unmanned site with real-time data, balancing the accuracy and generalization ability, and improving the construction accuracy and reliability of the digital twin model of the site, so as to improve the real-time monitoring accuracy and reliability of the coverage range of the site in a complex environment, and to improve the accuracy and timeliness of task dynamic planning, reconstruction and binding, so as to improve the control accuracy and efficiency of single task and multi-task cooperation in the site when a task needs to be executed, reduce the possibility of task planning again, and further improve the task deployment efficiency and accuracy.

[0024] Embodiment one Please refer to Figure 1 , Figure 1 is a flowchart of an intelligent modeling method for a digital twin model of an unmanned site disclosed by the application. Wherein, Figure 1 The method described can be applied to any scene that needs task planning, such as forest fire fighting scene, crop planting scene, power inspection scene, urban traffic monitoring scene, etc. Further, the scene is provided with at least one unmanned site, and all unmanned sites have a topological relationship. As shown in Figure 1 For any unmanned site, the method can include the following operations: 101. Obtain first data within a preset range of the unmanned site, wherein the first data within the preset range includes basic environment data within the preset range, and the preset range is determined based on the location of the unmanned site and / or the perception range of the unmanned site.

[0025] In the embodiments of the present application, optionally, the unmanned site (also referred to as an unmanned system site) can be understood as any site that can exist without personnel, which can be a traffic site or a communication node, as long as it meets the following conditions: it is composed of a take-off and landing platform, an edge computer, a communication base station, a navigation and positioning base station, a monitoring sensor, a meteorological sensor and other basic architectures, and it provides a northbound interface that is independent of the specific device model, operating environment and task type of the unmanned site. Specifically, the unmanned site can be a single-soldier portable unmanned aerial vehicle ground station, a fixedly installed unmanned watch-free hangar / nest, or a take-off and landing site that realizes space-time positioning through CORS (Continuously Operating Reference System) / GNSS (Global Navigation Satellite System) and other technical means, such as an unmanned aerial vehicle site, an unmanned vehicle site, an unmanned ship site, etc. Among them, the communication base station is used to provide communication data for the edge computer and the navigation and positioning base station, the navigation and positioning base station is used to position the communication base station, the edge computer and the unmanned device, the edge computer is arranged on the task platform and is used to store data, and the data includes a site digital twin model. Further, it also includes other related data in the present application, such as structured geographical environment data and structured climate data. Regardless of the type of site, it has the attributes of expressing its space-time position (i.e. three-dimensional space and time dimension), the attributes of the basic environment data within its covered (radiated) range, and further has the attributes of network and topological relationship with at least one other unmanned device or at least one other unmanned site.

[0026] In the embodiments of the present application, the preset range can be understood as a sensing range centered on the location of the unmanned site, or as a geographical range centered on the location of the unmanned site, such as 30 kilometers.

[0027] In the embodiment of the present application, optionally, the basic environment data can include, but is not limited to, ground surface data, ground object elevation data, terrain data and other natural and artificial ground environment data within a preset range. Among them, the basic environment data can be characterized in the form of the above-mentioned multiple data, or can be characterized by the digital surface model (DSM), digital elevation model (DEM) and digital orthophoto map (DOM) based on the above-mentioned multiple data. Further, the geographic environment data can also include electromagnetic environment data and climate data within the preset range. Further, the first data can also include data of components of the unmanned site, such as take-off and landing platform state data. The more data within the coverage range of the unmanned site, the more conducive to improving the construction accuracy and reliability of the basic site digital twin model of the unmanned site.

[0028] 102. Based on the first data of the unmanned site, performing a digital twin modeling operation on the pre-constructed site digital twin architecture model of the unmanned site to obtain a basic site digital twin model of the unmanned site.

[0029] In the embodiment of the present application, the communication base station is used to provide communication data for the edge computer and the navigation positioning base station, the navigation positioning base station is used to position the communication base station, the edge computer and the unmanned equipment, the edge computer is arranged on the task platform and is used to store data, and the data includes the site digital twin model. Further, it also includes other related data in the present application, such as structured geographic environment data and structured climate data.

[0030] In the embodiment of the present application, optionally, the site digital twin architecture model of the unmanned site is constructed based on the basic architecture data of the unmanned site, wherein the basic architecture data of the unmanned site includes basic entity architecture data and basic virtual architecture data. Among them, the basic entity architecture data is used to represent the data of the basic architecture in which the physical entity exists in the basic architecture composed of the unmanned site, such as the data of the task platform, and the basic virtual architecture data is used to represent the data of the basic architecture in which the physical entity does not exist in the basic architecture composed of the unmanned site, such as the data of the sensor. Specifically, for the basic mechanism with physical entity, digital twin modeling is performed based on the physical entity, and for the basic architecture without physical entity, virtual entity is used for digital twin modeling. For example, if there is no physical entity of the navigation positioning base station, a virtual base station based on CORS can be used to realize digital twin modeling of the navigation positioning function equivalent to the physical entity base station, so as to obtain the site digital twin architecture model of the unmanned site. Further, after obtaining the site digital twin architecture model, the data of the model is stored in a structured manner.

[0031] 103. Perform a meshing operation on the base site digital twin model to obtain a base site digital twin model containing a plurality of meshes, and determine deployment data corresponding to the actual position of each mesh in the actual scene of the unmanned site.

[0032] In the embodiment of the present application, after the base site digital twin model of the unmanned site is constructed, the obtained base site digital twin model is expressed as a geographic entity, and the infrastructure in the unmanned site is expressed as a geographic element of the geographic entity, that is, the geographic entity and the geographic element are in a one-to-many relationship. Further, the geographic element conforms to the simple element implementation specification defined by OGC (Open Geospatial Consortium, Open Geospatial Consortium). Further, each geographic element has a geographic geometry attribute, which can express the geometric shape, and the geographic element and the geographic geometry are in a one-to-many relationship, that is, one geographic element can correspond to multiple meshes. The geographic geometry has a coordinate reference system attribute, such as the location of the unmanned site as the reference system, and contains one or more geographic coordinate points. Optionally, the geographic coordinate point can be defined as a four-dimensional space-time coordinate point, that is, three-dimensional space plus time dimension, to further characterize the dynamic base site digital twin model.

[0033] In the embodiment of the present application, optionally, the shape of all meshes can include but is not limited to one or more geometric shapes that can cover the surface of the earth, such as a square, a hexagon, a pentagon, etc.

[0034] 104. Perform an optimization operation on the base site digital twin model according to the deployment data corresponding to all meshes to obtain an optimized site digital twin model.

[0035] In the embodiment of the present application, the site digital twin model is used as the basis for the task execution of the corresponding unmanned site. Specifically, the site digital twin model is constructed as a site digital twin model of the unmanned site with an actual model, and is used for task planning, execution and monitoring within a predetermined range of the unmanned site after construction.

[0036] It can be seen that the implementation Figure 1The described method constructs a digital twin model of the unmanned site by integrating the unmanned site and the basic environment data around the unmanned site, and then optimizes the digital twin model of the unmanned site based on the deployment data of the actual scene corresponding to each grid in the established digital twin model of the unmanned site, that is, follows a hybrid mode combining mechanism modeling and data-driven modeling, uses real-time data to calibrate the parameters of the digital twin model of the unmanned site within the framework of the physical model, balances the accuracy and generalization ability, improves the construction accuracy and reliability of the digital twin model of the site, and improves the real-time monitoring accuracy and reliability of the coverage range of the site in a complex environment, so that the accuracy and timeliness of task dynamic planning, reconstruction and binding are higher, so as to improve the control accuracy and efficiency of single task and multi-task cooperation in the site when the task needs to be executed, reduce the possibility of task planning again, and further improve the task execution efficiency and accuracy.

[0037] In the embodiment of the application, the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site is determined, including: For each grid, a unique identifier is determined; According to the unique identifier corresponding to each grid, the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site is determined; wherein the deployment data corresponding to each grid includes the environment deployment data and the task path deployment data corresponding to the grid; According to the unique identifier corresponding to each grid, the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site is determined, including: For any grid, based on the unique identifier corresponding to the grid and the task planning path configured for the grid in advance, a virtual task is performed from the virtual position corresponding to the actual position of the grid in the digital twin model of the basic site to the grid, to obtain a virtual task result of the grid, and a verification operation is performed on the virtual task result of the grid based on the actual task result of the grid determined in advance, to obtain a task verification result of the grid as the task path deployment data corresponding to the grid, wherein the starting point of the task planning path of the grid is the virtual position corresponding to the actual position of the unmanned site in the actual scene in the digital twin model of the basic site, and the end point of the task planning path of the grid is the virtual position corresponding to the actual position of the grid in the actual scene of the unmanned site in the digital twin model of the basic site; For any grid, based on the data collection operation performed on the actual position corresponding to the grid when the unmanned device reaches the actual position, the environment deployment data corresponding to the actual position of the grid is obtained.

[0038] In the embodiment of the present application, optionally, the geographical entity and each geographical element can also have a corresponding unique identifier. Among them, the unique identifier corresponding to the geographical entity, geographical element and grid can be any identifier that can represent its uniqueness determined by any method, such as generating a corresponding hash code for the grid, geographical element and geographical entity through the recursive GeoHash algorithm.

[0039] In the embodiment of the present application, optionally, the environmental deployment data includes geographical environmental deployment data, and further can include but is not limited to climate data and / or electromagnetic data and all data corresponding to the actual position. Among them, the climate data includes but is not limited to at least one of temperature data, wind speed data, humidity data, visibility data, etc. Further, the actual position in the actual scene of each grid can be deployed based on a predetermined BIM (Building Information Modeling) to obtain corresponding deployment data. Among them, the deployment data corresponding to each grid can be a certain stage, or a whole life cycle, such as for an agricultural peanut planting scene, its deployment data can be the data of the whole life cycle of before ploughing, after ploughing, peanut planting, peanut flowering, peanut fruiting, peanut maturing, etc. It should be noted that the deployment data can be actually collected in the actual scene, or obtained by simulating the actual scene.

[0040] In the embodiment of the present application, optionally, the task planning path corresponding to each grid is pre-stored in the task database. Optionally, the task verification result includes a path verification result and / or a time length verification result, and the actual task result includes an actual path and / or an actual time length. Among them, the path verification result is used to represent the path deviation between the virtual planning path and the actual path, and the time length verification result is used to represent the time length deviation between the virtual time length and the actual time length.

[0041] As can be seen, the embodiment of the present application can also execute a virtual task through the unique identifier allocated to each grid, obtain a corresponding task verification result, and collect the actual position of the grid by the unmanned device, and use the collected environmental deployment data and the aforementioned task verification result as deployment data, which improves the determination comprehensiveness and accuracy of the deployment data of each position covered by the grid, i.e. the unmanned site, thereby facilitating further improving the optimization accuracy and reliability of the digital twin model of the base site.

[0042] In the embodiment of the present application, optionally, the first data in the preset range of the unmanned site is obtained, comprising: determining all task instructions required to be dispatched for the preset range of the unmanned site; For any task instruction, it is judged whether the first task data set corresponding to the task instruction is contained in the predetermined task database; When the result of the judgment is yes, the first task data set corresponding to the task instruction is obtained from the task database, and the task operation matched with the task instruction is executed within the preset range, and the first sensor data in the execution of the task instruction is collected, and the collected first sensor data is stored in the first task data set in a structured manner, the data stored in the first task data set contains the first data within the preset range; When the result of the judgment is no, the target task matched with the task instruction and the corresponding second task data set are set according to the task instruction, and the task operation matched with the target task is executed within the preset range, and the second sensor data in the execution of the target task is collected, and the collected second sensor data is stored in the second task data set in a structured manner, the data stored in the second task data set contains the first data within the preset range.

[0043] In the embodiment of the application, optionally, the specific type of any task instruction is determined by the type of the unmanned site, for example, for the unmanned site of forest fire fighting, the task instruction can be a path planning instruction, etc. Optionally, the task database contains the task data and the basic environment data corresponding to any position / region within the preset range of the unmanned site.

[0044] In the embodiment of the present application, optionally, the services that can be implemented by the edge computer include, but are not limited to, a plurality of services in task management, task planning, task monitoring, spatio-temporal data management and publishing, etc. Specifically, in the edge computer, a task instruction can be dispatched to the task management service through a northbound interface, if there is a first task data set matching the task instruction in the task database of the task management service, the matching first task data set is directly filtered out from the task database, and the task monitoring service is called to control the communication base station / navigation positioning base station / monitoring sensor / meteorological sensor to collect the corresponding first sensor data in real time, and then the spatio-temporal data management service is called to fill the collected first sensor data into the first task data set for structured storage; if there is no first task data set matching it, the task planning service is called to set a corresponding second task data set and a matching target task for the task instruction, to control the communication base station / navigation positioning base station / monitoring sensor / meteorological sensor / unmanned equipment to execute the target task for data collection, obtain second sensor data, and call the spatio-temporal data management service to structure the second sensor data and store it in the second task data set. Further, the corresponding target task can also be stored in the corresponding second task data set. Further, the collected first sensor data / second sensor data can be analyzed to obtain corresponding analysis results such as foreground dynamic images and background static images, and the analysis results can be structured and stored in the first task data set / second task data set.

[0045] It can be seen that the embodiment of the present application can also dispatch corresponding task instructions to the area covered by the unmanned site. For the task instruction with corresponding task data set in the task database, the corresponding task data set is directly filtered from the task database and sensor data is collected for structured filling into the task data set; for the task instruction without task data set, a corresponding task and task data set are newly created, so as to structure the data collected by executing the corresponding task and store it in the corresponding task data set, so as to ensure that all required tasks have corresponding environmental data and other sensor data, improve the acquisition comprehensiveness and accuracy of sensor data in the coverage range of the unmanned site, and thus improve the digital twin construction accuracy and reliability of the digital twin model of the unmanned site.

[0046] In an optional embodiment, the method can further include the following steps: If the current condition of the unmanned site meets the predetermined data reacquisition condition within the preset range, second data within the preset range and an actual position corresponding to the second data are collected, wherein the second data within the preset range includes environmental data within the preset range. Further, the second data within the preset range includes climate data within the preset range; wherein the second data within the preset range is obtained based on the infrastructure of the unmanned site having a physical entity, and / or is obtained based on a third party in communication connection with the unmanned site, and / or is obtained through simulation data simulating the preset range; According to the actual position corresponding to the second data within the preset range, a matching grid matching the actual position is determined in the base site digital twin model of the unmanned site; A unique identifier corresponding to the matching grid is obtained, and an update operation is performed on the matching grid according to the unique identifier corresponding to the matching grid and the environmental data within the preset range, to obtain an updated base site digital twin model of the unmanned site.

[0047] In the optional embodiment, optionally, when the real-time time is within the preset data collection time range, such as periodic collection at intervals of 24 hours, and / or when a data collection request and / or a site digital twin model update request for the unmanned site is received, and / or when it is detected that the climate data and / or the geographical environment data within the preset range of the unmanned site change, all of which indicate that the data reacquisition condition is met. In this way, the data reacquisition condition is determined in multiple ways, and the coverage range of the unmanned site can be reacquired in time, so that the site digital twin model of the unmanned site can be updated in time.

[0048] In the optional embodiment, optionally, the second data in the preset range further includes change data of the device in the preset range, such as adding a base station and a location of the base station. Optionally, the second data in the preset range is acquired based on a physical entity in the infrastructure of the unmanned site, specifically, data of the physical entity is accessed through an Internet of Things protocol, for example, the second data is obtained by publishing and subscribing to a corresponding sensor topic through an MQTT protocol, wherein the data carrier part in the MQTT protocol expresses objects such as geographic entities, geographic elements and geographic geometric bodies in a GeoJSONX specification. In addition, the second data is obtained through simulation data simulating the preset range, specifically, the simulation data is simulated by accessing simulation signals. In addition, the second data is obtained based on a third party in communication connection with the unmanned site, specifically, the second data is integrated based on a third party data service, and only needs to be logically implemented through a virtual entity at a software level, for example, if a hangar of the take-off and landing platform does not install a micro weather station, a data service party authorized by a local meteorological bureau can be selected to push weather data through an online platform to achieve an effect equivalent to installing and using a micro weather station on the hangar. Further optionally, the collection range of the second data can be dynamic, such as periodic collection, or collection of the entire preset range of the unmanned site, for example, if a base station or an environment is added or reduced at a certain position, the corresponding specific position can be collected.

[0049] In the optional embodiment, after obtaining the second data, the second data can be preprocessed, such as cleaning, calibration and quality evaluation, and after updating the base site digital twin model, the second data is stored in a structured manner.

[0050] It can be seen that the optional embodiment monitors the data recollection condition of the unmanned site, and when recollection is needed, the global or targeted local data of the coverage range of the unmanned site is collected, and the corresponding grid of the digital twin model of the unmanned site is adjusted based on the collected data, so that the digital twin model of the unmanned site is updated in time, and corresponds to the actual situation of the actual scene in the coverage range of the unmanned site, further improving the reliability and accuracy of the digital twin model of the unmanned site, and being beneficial to further guarantee the control accuracy and efficiency of single task and multi-task coordination when task planning is needed.

[0051] Embodiment two Please refer to Figure 2 , Figure 2 is another flowchart of the intelligent modeling method of the digital twin model of the unmanned site disclosed in the embodiment of the application. Wherein, Figure 2The described method can be applied to any scenario that needs to be unmanned task planning, such as forest fire fighting scene, crop planting scene, power inspection scene, urban traffic monitoring scene, etc. Further, the scene is provided with at least one unmanned site, and all unmanned sites have a topological relationship. As shown in Figure 2 For any one unmanned site, the method can include the following operations: 201. Obtain first data within a preset range of the unmanned site, the first data within the preset range including basic environment data within the preset range, the preset range being determined based on the location of the unmanned site and / or the perception range of the unmanned site.

[0052] 202. Perform digital twin modeling operation on the pre-constructed site digital twin architecture model of the unmanned site based on the first data of the unmanned site, to obtain a basic site digital twin model of the unmanned site.

[0053] 203. Perform grid division operation on the basic site digital twin model to obtain a basic site digital twin model containing multiple grids, and determine the deployment data corresponding to the actual location of each grid in the actual scene of the unmanned site.

[0054] 204. Perform optimization operation on the basic site digital twin model according to the deployment data corresponding to all grids, to obtain an optimized site digital twin model.

[0055] It should be noted that other descriptions of steps 201-204 are described in other related descriptions of steps 101-104 in Embodiment I, which will not be repeated here.

[0056] 205. Obtain attribute parameters of all target component architectures of the target unmanned site, each target component architecture attribute parameter including physical parameters and identification.

[0057] In the embodiment of the application, optionally, the physical parameters of each target component architecture include but are not limited to one or more of size, shape, position, etc., which are determined by the target component architecture. The identification of each target component architecture is any identification that can represent its uniqueness, such as model number. It should be noted that the types of all target component architectures of the target unmanned site are described in detail in the description of all basic architectures of the unmanned site in Embodiment I, which will not be repeated here.

[0058] 206. Based on the attribute parameters of all target component architectures and the optimized site digital twin model, construct the unmanned site digital twin model of the target unmanned site.

[0059] 207. The northbound interface based on the unmanned site digital twin model performs debugging operations from virtual to reality on the unmanned site digital twin model, and obtains a debugging site digital twin model.

[0060] 208. After installing and deploying the debugging site digital twin model, in the actual scene of the target unmanned site, a pre-planned task is executed based on the debugging site digital twin model, and an actual execution result of the pre-planned task is obtained.

[0061] 209. The actual execution result of the pre-planned task is compared with an expected execution result of the pre-planned task, a task execution comparison result of the pre-planned task is obtained, and an optimization operation is performed on the target object according to the task execution comparison result of the pre-planned task, and an optimized target object is obtained.

[0062] In the embodiment of the application, when the target object is the debugging site digital twin model, the optimized target object is an optimized target site digital twin model, and specifically, model parameters of the target site digital twin model are optimized; when the target object is a target component architecture of the target unmanned site, the optimized target object is an optimized target component architecture of the target unmanned site, and specifically, control parameters of the target component architecture are optimized. It should be noted that the optimization herein can be understood as correction or optimization.

[0063] In the embodiment of the application, optionally, the actual execution result of the pre-planned task includes actual environment data and actual path planning conditions collected by a sensor on the target component architecture of the target unmanned site or a controlled unmanned device.

[0064] In the embodiment of the application, it should be noted that when there are multiple target unmanned sites, all the target unmanned sites form an unmanned system, and each target unmanned site corresponds to the related operations of steps 205-208. After obtaining the corresponding single unmanned site digital twin model, a topological relationship is formed between all the single unmanned site digital twin models, the digital twin environment data is filled between the sites, that is, the sites are no longer isolated, so that the sites can coordinate with each other, so that when a task is dispatched, the control accuracy and efficiency of single task and multi-task cooperation are further improved, and the efficiency and accuracy of task dispatching are further improved.

[0065] It can be seen that the implementation Figure 2The described method constructs a digital twin model of the unmanned site by integrating the unmanned site and the basic environment data around the unmanned site, optimizes the digital twin model of the unmanned site based on the deployment data of the actual scene corresponding to each grid in the established digital twin model of the unmanned site, that is, follows a hybrid mode combining mechanism modeling and data-driven modeling, takes the physical model as a framework, calibrates the parameters of the digital twin model of the unmanned site with real-time data, balances the accuracy and generalization ability, improves the construction accuracy and reliability of the site digital twin model, improves the real-time monitoring accuracy and reliability of the coverage range of the site in a complex environment, and makes the accuracy and timeliness of task dynamic planning, reconstruction and binding higher, so as to improve the control accuracy and efficiency of single task, multi-task cooperation in the site when the task needs to be executed, reduce the possibility of task planning again, and further improve the task execution efficiency and accuracy. In addition, the physical parameters and identifiers corresponding to the single unmanned site are used to construct the general digital twin model obtained in the foregoing, to realize the static site digital twin model construction of the single unmanned site, and to realize one-way digital mapping by performing one-way response from virtual to real objective world on the static digital twin model based on the northbound interface, so as to realize the debugging of the single unmanned site digital twin model, and further to perform actual deployment on the single unmanned site digital twin model after debugging, execute pre-planned tasks, continuously collect data in the actual operation process and feed back to the edge computer to check and correct the accuracy and range of the single unmanned site digital twin model parameters, improve the generalization and reliability of the single site digital twin model, and optimize the control parameters of the composition architecture of the single site through the collected data, realize two-way digital twinning, realize the closed-loop construction of the site digital twin model creation, site data integration in the digital twin model, verification and optimization of the digital twin model to the specific single site digital twin model, improve the individualized construction accuracy and reliability of the single site digital twin model, improve the real-time monitoring accuracy of the single unmanned site in a complex environment, make the accuracy and timeliness of task dynamic planning, reconstruction and binding of the single site higher, so as to improve the control accuracy and efficiency of single task, multi-task cooperation in the single site when the task needs to be executed, reduce the possibility of task planning again, and further improve the task execution efficiency and accuracy of the single site.

[0066] In the embodiment of the application, the northbound interface of the unmanned site digital twin model includes the northbound interfaces of all target component architectures on the unmanned site digital twin model. The debugging operation of the digital twin model of the unmanned site from virtual to real is performed based on the northbound interface of the digital twin model of the unmanned site, and a debugging site digital twin model is obtained, including: For any target component architecture, the northbound interface based on the target component architecture performs a control operation on the target component architecture on the unmanned site digital twin model to obtain control data of the target component architecture in an actual scene. It is judged whether the control data of the target component architecture matches the preset control data of the target component architecture determined in advance, and when it is judged that the control data does not match the preset control data, an adjustment operation is performed on the control parameter of the target component architecture on the unmanned site digital twin model according to the control data of the target component architecture and the preset control data of the target component architecture. Wherein, after all the target component architectures in the unmanned site digital twin model that need to adjust the control parameter are adjusted, the debugging site digital twin model is obtained.

[0067] In the embodiment of the application, optionally, the control data corresponding to the target component architecture includes control parameters for the target component architecture itself, such as acquisition control direction, acquisition control angle, acquisition control speed, acquisition control frequency, etc. Further, it can also include the quality of the data collected based on the control parameters of the target component architecture itself, such as image resolution, image acquisition range, etc.

[0068] In the embodiment of the application, optionally, for the control parameter, the control gap between the control data of the target component architecture and the preset control data of the target component architecture is equal to 0, such as the difference in image acquisition control angle is 0; for the quality of the collected data, the control gap between the two is less than or equal to the preset control gap, such as the difference in image resolution is less than or equal to 1. Further, when the two match, the unmanned site digital twin model is deployed and a pre-planned task is executed.

[0069] As can be seen, after obtaining the monomer unmanned site digital twin model, the embodiment of the application performs joint debugging on each component architecture of the monomer site based on the model through the northbound interface, thereby realizing one-way response of the digital world virtual entity to the objective world physical entity, realizing one-way digital mapping, and further realizing debugging of the control parameter of the component architecture that does not meet the condition to improve the accuracy of the monomer unmanned site digital twin model obtained and its actual scene.

[0070] In the embodiment of the application, optionally, the pre-planned task determined in advance is executed based on the debugging site digital twin model to obtain an actual execution result of the pre-planned task, including: The grid of the debugging site digital twin model is set with a corresponding pre-planned task based on a preset range; Each grid of the debugging site digital twin model performs a verification operation on the pre-planned task based on the edge computer of the debugging site digital twin model to obtain a task verification result of each grid; For any grid, when the task verification result of the grid is used to indicate that the pre-planning task verification of the grid is passed, in the actual scene of the target unmanned site, based on the northbound interface of the debugging site digital twin model, the pre-planning task of the grid is executed to obtain the actual execution result of the pre-planning task.

[0071] In the embodiment of the application, the task verification result is composed of at least one dimension verification result, and specifically, all dimension verification results include but are not limited to task accessibility (such as whether low-altitude obstacles can be avoided, whether low-altitude microclimate meets the unmanned system dispatching condition, etc.), task legality (such as whether airspace resources are applied, whether the flight plan has been approved, whether the flight plan conflicts with the no-fly zone, etc.), task priority (such as whether the tasks in the task management service of the current site edge computer are executed in order according to the task priority, etc.).

[0072] In the embodiment of the application, when the verification is passed, the pre-planning task can be confirmed by the operation and maintenance personnel for execution, or the pre-planning task can be automatically executed.

[0073] As can be seen, in the deployment and operation and maintenance stage, the embodiment of the application performs multi-dimensional task verification operations on the corresponding pre-planning tasks of the single debugging site digital twin model to filter out effective pre-planning tasks, and after the verification is passed, the actual execution is performed in the actual scene, and sensor data is continuously collected and fed back to improve the accuracy and reliability of the actual execution effect of the pre-planning task, thereby facilitating further improvement of the optimization accuracy of the single unmanned site digital twin model and the optimization accuracy of the control parameters of the component architecture of the single unmanned site.

[0074] In the embodiment of the application, optionally, the attribute parameters of all target component architectures of the target unmanned site are obtained, including: determining the type of the target unmanned site, the type of the target unmanned site including an existing type or a planning type, wherein the existing type indicates that the target unmanned site has been built or has complete design drawings, and the planning type is used to indicate that the target unmanned site is in planning and does not have complete design drawings; when the type of the target unmanned site is the existing type, obtaining electronic design drawing data of the target unmanned site, and obtaining the attribute parameters of all target component architectures of the target unmanned site from the drawing data; when the type of the target unmanned site is the planning type, obtaining design data of the target unmanned site in the forward design as the attribute parameters of all target component architectures of the target unmanned site.

[0075] In the embodiment of the present application, optionally, different types of target unmanned sites correspond to different ways of constructing unmanned site digital twin models. For example, for an existing type of target unmanned site, an unmanned site digital twin model can be constructed through a reverse modeling digital twin modeling method. For a planning type of target unmanned site, an unmanned site digital twin model can be constructed through a forward design modeling method.

[0076] It can be seen that, for an existing single unmanned site, the embodiment of the present application directly obtains the attribute parameters of the corresponding component architecture by analyzing the design drawings. For a single unmanned site in planning, the attribute parameters of the corresponding component architecture are determined through the design data in the forward design, that is, the attribute parameters of the component architecture are flexibly obtained according to the actual situation of the single site, thereby improving the accuracy and efficiency of obtaining the attribute parameters of the component architecture of the single unmanned site, and thus facilitating the improvement of the construction efficiency, accuracy and reliability of the single unmanned site digital twin model.

[0077] In an optional embodiment, the method can further include the following steps: Based on the northbound interface of the debugging site digital twin model, performing a monitoring operation on the environmental data in the preset range to obtain an environmental monitoring result in the preset range; When it is judged that the result is yes, the re-executed edge computer based on the debugging site digital twin model performs a verification operation on the pre-planning task of each grid to obtain a task verification result of each grid.

[0078] In the optional embodiment, optionally, when the geographical environment in the preset range of the target unmanned site changes, such as the addition or reduction of houses, the planting of vegetation, etc., or the climate changes, such as the change from sunny to rainy, etc., all of which indicate that the environment in the preset range has changed. Further, the environmental monitoring result can be updated to the entire system based on the spatiotemporal data management and publishing service.

[0079] It can be seen that, by monitoring the environment in the actual scene covered or radiated by the single site and retriggering the verification of the pre-planning task when a change is detected, the optional embodiment can reduce the occurrence of the situation that the task may not match the actual scene due to the change of the environment, thereby ensuring the adaptation of the task to the actual scene, and further facilitating the further guarantee of the task execution accuracy and reliability of the actual scene of the single unmanned site.

[0080] In order for the relevant personnel in the art to more clearly understand the technical solution, an unmanned site is abstractly expressed as an unmanned hangar (or airport, nest), and a specific model of unmanned hangar is taken as an example, and combined with the description of the above-mentioned technical solution. Figure 3The task deployment scene diagram of the described unmanned hangar forest fire fighting system is used to illustrate the technical solution, and the specific embodiments are as follows: After the site digital twin model of the unmanned site is constructed based on the method of the first embodiment, the physical parameters and identifiers of the components included in the unmanned hangar of the forest fire fighting, such as the hangar cabin, the take-off and landing platform, the edge computer, the image and data communication base station, the Beidou navigation base station, the surveillance camera, and the micro weather station, are used to construct the model of the aforementioned site digital twin model, and the forest fire fighting site digital twin model is obtained, and all are digitally expressed in the form of four-dimensional geographic elements. Further, within a 30-kilometer radius under the condition of the image and data transmission link visibility of the unmanned hangar, 1:1000 scale oblique photography modeling is completed, that is, in the circular range with the forest fire fighting site as the center and 30 kilometers as the radius, the digital surface model (DSM), digital elevation model (DEM), digital orthographic map (DOM), and climate data on the forest fire fighting site digital twin model are digitally expressed. Further, the grid of the forest fire fighting site digital twin model is set with corresponding pre-planned flight tasks by using the GeoHash method, and the pre-planned flight tasks are checked in multiple dimensions such as task legality, task accessibility, and task priority, so that the grid of the forest fire fighting site digital twin model is matched with the pre-planned flight tasks. As shown in Figure 3 When a fire occurs at any location within the coverage or radiation range of the unmanned hangar, the corresponding flight path of the corresponding pre-planned flight task can be determined according to the unique identifier of the grid where the destination is located, which eliminates the time-consuming task planning and checking links (task checking links) to control the unmanned aerial vehicle to quickly deploy to the fire site, and after approaching the fire site, switch to a detailed task route for target search, observation, and locking of fire points, fire lines, and other task targets, and finally based on the on-board edge computing power, real-time planning of fire search tasks covering the grid area, autonomous control of task payload observation and locking of fire points and other task targets, and real-time transmission of fire scene pictures.

[0081] Embodiment three Please refer to Figure 4 , Figure 4 is a structural schematic diagram of an intelligent modeling device of an unmanned site digital twin model disclosed in an embodiment of the present application. The device can be applied to any scene that needs task planning, such as forest fire fighting, crop planting, power inspection, urban traffic monitoring, and the like. The scene is provided with at least one unmanned site, and all unmanned sites have a topological relationship, as shown in Figure 4 For any unmanned site, the device includes: The acquisition module 301 is configured to acquire first data within a preset range of the unmanned site, wherein the first data within the preset range comprises basic environment data within the preset range, and the preset range is determined based on a location of the unmanned site and / or a perception range of the unmanned site. The construction module 302 is configured to perform a digital twin modeling operation on a pre-constructed site digital twin architecture model of the unmanned site based on the first data of the unmanned site, to obtain a basic site digital twin model of the unmanned site. The division module 303 is configured to perform a grid division operation on the basic site digital twin model, to obtain the basic site digital twin model containing a plurality of grids. The determination module 304 is configured to determine deployment data corresponding to an actual location of each grid in an actual scene of the unmanned site. The optimization module 305 is configured to perform an optimization operation on the basic site digital twin model according to the deployment data corresponding to all the grids, to obtain an optimized site digital twin model, wherein the site digital twin model is used as a basis for task execution of the unmanned site.

[0082] It can be seen that the intelligent modeling device of the unmanned site digital twin model is implemented Figure 4 The intelligent modeling device of the unmanned site digital twin model described above constructs the digital twin model of the unmanned site by combining the unmanned site and the basic environment data around the unmanned site, and then optimizes the digital twin model of the unmanned site based on the deployment data of the actual scene corresponding to each grid in the established digital twin model of the unmanned site, that is, follows a hybrid mode combining mechanism modeling and data-driven modeling, takes the physical model as a framework, calibrates the parameters of the digital twin model of the unmanned site with real-time data, balances the accuracy and generalization ability, improves the construction accuracy and reliability of the site digital twin model, and thus improves the real-time monitoring accuracy and reliability of the coverage range of the site in a complex environment, so that the accuracy and timeliness of task dynamic planning, reconstruction and binding are higher, so as to improve the control accuracy and efficiency of single task and multi-task cooperation in the site when a task needs to be executed, reduce the possibility of task planning again, and thus improve the task deployment efficiency and accuracy.

[0083] In the embodiment of the application, the specific manner in which the acquisition module 301 acquires the first data within the preset range of the unmanned site comprises: determining all task instructions required to be dispatched for the preset range of the unmanned site; for any task instruction, determining whether the first task data set corresponding to the task instruction is contained in the pre-determined task database; When the result is determined to be yes, a first task data set corresponding to the task instruction is acquired from the task database, and a task operation matched with the task instruction is performed within a preset range, and first sensor data in a task process corresponding to the task instruction is collected, and the collected first sensor data is stored in a structured manner to the first task data set, and the data stored in the first task data set includes first data within the preset range. When the result is determined to be no, a target task matched with the task instruction and a second task data set corresponding to the target task are set according to the task instruction, and a task operation matched with the target task is performed within a preset range, and second sensor data in a task process corresponding to the target task is collected, and the collected second sensor data is stored in a structured manner to the second task data set, and the data stored in the second task data set includes first data within the preset range.

[0084] It can be seen that, by implementing the method Figure 4 The described apparatus can also dispatch corresponding task instructions to the area covered by the unmanned site. For a task instruction with a corresponding task data set in the task database, the corresponding task data set is directly filtered from the task database and sensor data is collected to be structured and filled into the task data set. For a task instruction without a task data set, a corresponding task and task data set are newly created, so that the data collected by executing the corresponding task is stored in a structured manner to the corresponding task data set, so as to ensure that all required tasks have corresponding environmental data and other sensor data, improve the acquisition comprehensiveness and accuracy of sensor data in the coverage range of the unmanned site, and thus improve the digital twin construction accuracy and reliability of the digital twin model of the unmanned site.

[0085] In the embodiment of the application, the specific manner in which the determining module 304 determines the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site includes: For each grid, a unique identifier corresponding to the grid is determined; According to the unique identifier corresponding to each grid, the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site is determined; The deployment data corresponding to each grid includes environmental deployment data and task path deployment data corresponding to the grid; The specific manner in which the determining module determines the deployment data corresponding to the actual position of each grid in the actual scene of the unmanned site according to the unique identifier corresponding to each grid includes: For any given grid, based on the unique identifier corresponding to the grid and the pre-configured task planning path, a virtual task is executed from the virtual location corresponding to the unmanned site to the grid, resulting in the virtual task result of the grid. Based on the pre-determined actual task result of the grid, a verification operation is performed on the virtual task result of the grid, resulting in the task verification result of the grid, which serves as the task path deployment data corresponding to the grid. The starting point of the task planning path of the grid is the virtual location corresponding to the actual location of the unmanned site in the actual scenario on the digital twin model of the base site, and the ending point of the task planning path of the grid is the virtual location corresponding to the actual location of the grid in the actual scenario of the unmanned site on the digital twin model of the base site. For any grid, when the unmanned equipment reaches the actual location corresponding to the grid, it performs data collection operations on that actual location to obtain the environmental deployment data corresponding to the actual location of the grid.

[0086] It is evident that implementation Figure 4 The described device can also perform virtual tasks by assigning a unique identifier to each grid, obtain corresponding task verification results, and collect data on the actual location of the grid based on unmanned equipment. The collected environmental deployment data and the aforementioned task verification results are used as deployment data, which improves the comprehensiveness and accuracy of the determination of deployment data for each location within the grid, i.e., the unmanned site. This is conducive to further improving the optimization accuracy and reliability of the digital twin model of the basic site.

[0087] In an optional embodiment, such as Figure 4 As shown, the acquisition module 301 is also used to perform optimization operations on the basic site digital twin model based on the deployment data corresponding to all grids in the optimization module 305, and obtain the optimized site digital twin model, and then acquire the attribute parameters of all target component architectures of the target unmanned site. The attribute parameters of each target component architecture include physical parameters and identifiers. Module 302 is also used to construct an unmanned site digital twin model of the target unmanned site based on the attribute parameters of all target component architectures and the optimized site digital twin model; like Figure 5 As shown, Figure 5 This is a schematic diagram of the structure of an intelligent modeling device for another unmanned site digital twin model disclosed in an embodiment of the present invention. Figure 5 As shown, the device may further include: The debugging module 306 is used to perform debugging operations from virtual to reality on the unmanned site digital twin model based on the northbound interface of the unmanned site digital twin model, so as to obtain the debugging site digital twin model. The execution module 307 is configured to execute a pre-planned task determined in advance based on the debugging site digital twin model in the actual scene of the target unmanned site after the debugging site digital twin model is installed and deployed, to obtain an actual execution result of the pre-planned task. The comparison module 308 is configured to compare the actual execution result of the pre-planned task with an expected execution result of the pre-planned task, to obtain a task execution comparison result of the pre-planned task. The optimization module 305 is further configured to perform an optimization operation on the target object according to the task execution comparison result of the pre-planned task, to obtain an optimized target object. When the target object is the debugging site digital twin model, the optimized target object is an optimized target site digital twin model; when the target object is a target component architecture of the target unmanned site, the optimized target object is an optimized target component architecture of the target unmanned site.

[0088] It can be seen that the implementation Figure 5 The described device constructs the universal digital twin model obtained in the foregoing by using the physical parameters and the identifier of the monomer unmanned site, to realize the static site digital twin model construction of the monomer unmanned site, and performs a one-way response from the virtual to the real objective world based on the northbound interface of the static digital twin model, to realize one-way digital mapping, thereby realizing the debugging of the monomer unmanned site digital twin model, and further deploying the monomer unmanned site digital twin model after debugging, to execute a pre-planned task, to continuously collect data in the actual running process and feed back to the edge computer to check and correct the precision and range of the monomer unmanned site digital twin model parameters in the reverse direction, to improve the generalization and reliability of the monomer site digital twin model, and to optimize the control parameters of the component architecture of the monomer site by using the collected data, to realize two-way digital twinning, thereby realizing the closed-loop construction of the site digital twin model creation, site data integration in the digital twin model, verification and optimization of the digital twin model, and specific monomer site digital twin model, improving the individualized construction accuracy and reliability of the monomer site digital twin model, to improve the real-time monitoring accuracy of the monomer unmanned site in a complex environment, to make the task dynamic planning, reconstruction and binding accuracy and timeliness of the monomer site higher, to improve the control accuracy and efficiency of a single task and multi-task cooperation in the monomer site, to reduce the possibility of task planning again, and to further improve the task execution efficiency and accuracy of the monomer site.

[0089] In another optional embodiment, the northbound interface of the unmanned site digital twin model includes the northbound interfaces of all target component architectures on the unmanned site digital twin model. The debugging module 306 performs a debugging operation from virtual to reality on the unmanned site digital twin model based on a northbound interface of the unmanned site digital twin model, and the specific manner of obtaining the debugging site digital twin model includes the following steps. For any target component architecture, a control operation is performed on the target component architecture based on a northbound interface of the target component architecture on the unmanned site digital twin model to obtain control data of the target component architecture in an actual scene. It is determined whether the control data of the target component architecture matches the preset control data of the target component architecture determined in advance. When it is determined that the control data of the target component architecture does not match the preset control data of the target component architecture determined in advance, an adjustment operation is performed on a control parameter of the target component architecture based on the control data of the target component architecture and the preset control data of the target component architecture determined in advance on the unmanned site digital twin model. The debugging site digital twin model is obtained after all target component architectures that need to adjust the control parameter in the unmanned site digital twin model are adjusted.

[0090] It can be seen that the optional embodiment can obtain a single unmanned site digital twin model, and then perform joint debugging on each component architecture of the single site based on the model through the northbound interface, so as to realize one-way response of a digital world virtual entity to an objective world physical entity, realize one-way digital mapping, and then realize debugging of a control parameter of a component architecture that does not meet a condition, so as to improve the accuracy of the obtained single unmanned site digital twin model adapting to an actual scene.

[0091] In yet another optional embodiment, the execution module 307 executes a pre-planned task determined in advance based on the debugging site digital twin model, and the specific manner of obtaining an actual execution result of the pre-planned task includes the following steps. A corresponding pre-planned task is set for a grid of the debugging site digital twin model based on a preset range. An edge computer of the debugging site digital twin model performs a verification operation on the pre-planned task of each grid to obtain a task verification result of each grid. For any grid, when the task verification result of the grid indicates that the pre-planned task of the grid is verified, the pre-planned task of the grid is executed in an actual scene of the target unmanned site based on a northbound interface of the debugging site digital twin model to obtain an actual execution result of the pre-planned task. As shown in Figure 5 The apparatus can further include: The monitoring module 309 is configured to perform a monitoring operation on environment data in a preset range based on a northbound interface of the debugging site digital twin model to obtain an environment monitoring result in the preset range. The judgment module 310 is used to determine whether the environmental monitoring results within the preset range are used to indicate that the environment within the preset range has changed. When the judgment result is yes, the execution module 307 is triggered to re-execute the above-mentioned edge computer based on the digital twin model of the debugging site to perform the pre-planned task verification operation on each grid and obtain the task verification result of each grid.

[0092] As can be seen, this optional embodiment performs multi-dimensional task verification operations on the digital twin model of a single debugging site during the deployment and maintenance phase, thereby selecting effective pre-planned tasks. After verification, these tasks are actually executed in real-world scenarios, continuously collecting and feeding back sensor data. This improves the accuracy and reliability of obtaining the actual execution effect of the pre-planned tasks, which in turn helps to further improve the optimization accuracy of the digital twin model of a single unmanned site and the optimization accuracy of the control parameters of the composition architecture of a single unmanned site.

[0093] In yet another optional embodiment, the specific method by which the acquisition module 301 acquires the attribute parameters of all target component architectures of the target unmanned site includes: Determine the type of the target unmanned site. The types of the target unmanned site include existing type and planning type. The existing type means that the target unmanned site has been built or has complete design drawings. The planning type is used to indicate that the target unmanned site is in the planning stage and does not have complete design drawings. When the type of the target unmanned site is an existing type, obtain the electronic design drawing data of the target unmanned site, and obtain the attribute parameters of all target component architectures of the target unmanned site from the drawing data; When the target unmanned site is of the planning type, obtain the design data of the target unmanned site during the forward design and use it as the attribute parameter of all target component architectures of the target unmanned site.

[0094] As can be seen, this optional embodiment obtains the attribute parameters of the corresponding component architecture by directly analyzing the design drawings of existing single unmanned sites. For planned single unmanned sites, the attribute parameters of the corresponding component architecture are determined by the design data during the forward design. That is, the attribute parameters of the component architecture are flexibly obtained according to the actual situation of the single site, which improves the accuracy and efficiency of obtaining the attribute parameters of the component architecture of the single unmanned site. This is conducive to improving the construction efficiency, accuracy and reliability of the digital twin model of the single unmanned site.

[0095] In yet another alternative embodiment, such as Figure 5As shown, the acquisition module 301 is further configured to acquire second data within the preset range and the actual location corresponding to the second data if the current conditions of the unmanned station meet the data re-acquisition conditions within the preset range. The second data within the preset range is acquired based on the infrastructure with physical entities in the infrastructure of the unmanned station, and / or based on a third party communicating with the unmanned station, and / or obtained by simulating simulation data within the preset range. The second data within the preset range includes environmental data within the preset range. The determination module 304 is also used to determine the matching grid that matches the actual location in the base digital twin model of the unmanned site based on the actual location corresponding to the second data within the preset range. The acquisition module 301 is also used to acquire the unique identifier corresponding to the matching grid; And such as Figure 5 As shown, the device may further include: The update module 311 is used to perform an update operation on the matching grid according to the unique identifier corresponding to the matching grid and the second data within a preset range, to obtain the updated digital twin model of the unmanned site, and to trigger the division module 303 to perform a grid division operation on the digital twin model of the site, to obtain a digital twin model of the site containing multiple grids.

[0096] As can be seen, this optional embodiment monitors the data re-collection conditions of unmanned sites and, when re-collection is required, performs global or targeted local data collection on the coverage area of ​​the unmanned site. Based on the collected data, it adjusts the corresponding grid on the digital twin model of the unmanned site, so that the digital twin model of the unmanned site is updated in a timely manner and corresponds to the actual situation of the actual scene within the coverage area of ​​the unmanned site. This further improves the reliability and accuracy of the digital twin model of the unmanned site and helps to further ensure the accuracy and efficiency of single-task and multi-task coordination control when task planning is required.

[0097] Example 4 Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an intelligent modeling device for a digital twin model of an unmanned site, as disclosed in another embodiment of the present invention. This device can be applied to any scenario requiring task planning, such as forest fire fighting, crop planting, power line inspection, urban traffic monitoring, etc. Furthermore, the scenario includes at least one unmanned site, and all unmanned sites have a topological relationship. For example... Figure 6 As shown, for any unmanned site, the device may include: Memory 401 storing executable program code; A processor 402 coupled with the memory 401; Further, an input interface 403 and an output interface 404 coupled with the processor 402 can also be included. The processor 402 invokes the executable program code stored in the memory 401 to execute part or all of the steps of the intelligent modeling method of the unmanned site digital twin model disclosed in the embodiment one or the embodiment two.

[0098] Embodiment five The embodiment of the present application discloses an intelligent modeling system of an unmanned site digital twin model, wherein the system comprises a task platform, an edge computer, a target base station and a sensor integrated on the target base station, the target base station comprises a communication base station and a navigation positioning base station, the communication base station is used to provide communication data for the edge computer and the navigation positioning base station, the navigation positioning base station is used to position the target base station, the edge computer and the unmanned equipment, the edge computer is arranged on the task platform and is used to store data, the data comprises a site digital twin model; wherein the data is obtained by the system by executing part or all of the steps of the intelligent modeling method of the unmanned site digital twin model disclosed in the embodiment one or the embodiment two.

[0099] Embodiment six The embodiment of the present application discloses a computer storage medium, the computer storage medium stores computer instructions, when the computer instructions are invoked, part or all of the steps of the intelligent modeling method of the unmanned site digital twin model disclosed in the embodiment one or the embodiment two are executed.

[0100] The device embodiments described above are only schematic, wherein the modules illustrated as separate components can or can not be physically separated, and the components illustrated as modules can or can not be physical modules, that is, they can be located in one place, or distributed on multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment scheme. Those skilled in the art can understand and implement without creative labor.

[0101] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and the necessary general hardware platform, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product in essence or in the form of a part of the prior art. The computer software product can be stored in a computer readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage, a magnetic tape storage, or any other computer readable medium that can be used to carry or store data.

[0102] Finally, it should be noted that: the intelligent modeling method, device and system of the unmanned site digital twin model disclosed by the embodiments of the present application are only the preferred embodiments of the present application, and are used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that; the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent modeling method for digital twin models of unmanned sites, characterized in that, The method includes: Acquire first data within a preset range of the unmanned station, wherein the first data within the preset range includes basic environmental data within the preset range, and the preset range is determined based on the location of the unmanned station and / or the perception range of the unmanned station; Based on the first data of the unmanned site, a digital twin modeling operation is performed on the pre-constructed digital twin architecture model of the unmanned site to obtain the basic digital twin model of the unmanned site. A grid division operation is performed on the digital twin model of the base site to obtain a digital twin model of the base site containing multiple grids, and the deployment data corresponding to the actual location of each grid in the actual scenario of the unmanned site is determined. Based on the deployment data corresponding to all the grids, an optimization operation is performed on the basic site digital twin model to obtain an optimized site digital twin model, wherein the site digital twin model is used as the basis for task execution corresponding to the unmanned site.

2. The intelligent modeling method for the digital twin model of an unmanned site according to claim 1, characterized in that, The acquisition of first data within a preset range of the unmanned station includes: Determine all task instructions that need to be dispatched within the preset range of the unmanned site; For any of the task instructions, determine whether the pre-determined task database contains the first task dataset corresponding to the task instruction; When the result is determined to be yes, the first task dataset corresponding to the task instruction is obtained from the task database, and within the preset range, the task operation matching the task instruction is executed, and the first sensor data is collected during the execution of the task corresponding to the task instruction. The collected first sensor data is structured and stored in the first task dataset, and the data stored in the first task dataset includes the first data within the preset range. When the result is determined to be negative, according to the task instruction, a target task and a corresponding second task dataset matching the task instruction are set, and within the preset range, a task operation matching the target task is executed, and second sensor data is collected during the execution of the target task. The collected second sensor data is structured and stored in the second task dataset, and the data stored in the second task dataset includes the first data within the preset range.

3. The intelligent modeling method for the digital twin model of an unmanned site according to claim 1 or 2, characterized in that, After performing an optimization operation on the basic site digital twin model based on the deployment data corresponding to all the grids to obtain an optimized site digital twin model, the method further includes: Obtain the attribute parameters of all target component architectures of the target unmanned site, wherein the attribute parameters of each target component architecture include physical parameters and identifiers; Based on the attribute parameters of all the target component architectures and the optimized site digital twin model, construct the unmanned site digital twin model of the target unmanned site; Based on the northbound interface of the unmanned site digital twin model, a debugging operation from virtual to reality is performed on the unmanned site digital twin model to obtain a debugging site digital twin model. After the digital twin model of the debugging site is installed and deployed, in the actual scenario of the target unmanned site, a pre-determined pre-planned task is executed based on the digital twin model of the debugging site to obtain the actual execution result of the pre-planned task. The actual execution result of the pre-planned task is compared with the expected execution result of the pre-planned task to obtain the task execution comparison result of the pre-planned task. Based on the task execution comparison result of the pre-planned task, an optimization operation is performed on the target object to obtain the optimized target object. Wherein, when the target object is the digital twin model of the debugging site, the optimized target object is the optimized target site digital twin model; when the target object is the target component architecture of the target unmanned site, the optimized target object is the optimized target component architecture of the target unmanned site.

4. The intelligent modeling method for the digital twin model of an unmanned site according to claim 3, characterized in that, The northbound interface of the unmanned site digital twin model includes the northbound interface of all the target components built on the unmanned site digital twin model; The process of performing a virtual-to-real debugging operation on the unmanned site digital twin model via the northbound interface to obtain a debugged site digital twin model includes: For any of the target component architectures, on the unmanned site digital twin model, control operations are performed on the target component architecture based on the northbound interface of the target component architecture to obtain control data of the target component architecture in the actual scenario; Determine whether the control data of the target component architecture matches the preset control data of the target component architecture. If a mismatch is found, adjust the control parameters of the target component architecture on the digital twin model of the unmanned site based on the control data of the target component architecture and the preset control data of the target component architecture. Once all the target component architectures that require adjustment of control parameters in the unmanned site digital twin model have been adjusted, the debug site digital twin model is obtained.

5. The intelligent modeling method for the digital twin model of an unmanned site according to claim 3, characterized in that, The execution of pre-determined pre-planned tasks based on the digital twin model of the debugging site, and the obtaining of the actual execution results of the pre-planned tasks, include: Based on the preset range, pre-planned tasks are set for the grid configuration of the digital twin model of the debugging site. The edge computer based on the digital twin model of the debugging site performs verification operations on the pre-planned tasks of each grid to obtain the task verification results of each grid; For any of the grids, when the task verification result of the grid is used to indicate that the pre-planned task of the grid has passed the verification, in the actual scenario of the target unmanned station, the pre-planned task of the grid is executed based on the northbound interface of the digital twin model of the debugging station to obtain the actual execution result of the pre-planned task; The method further includes: Based on the northbound interface of the digital twin model of the debugging site, a monitoring operation is performed on the environmental data within the preset range to obtain the environmental monitoring results within the preset range; Determine whether the environmental monitoring results within the preset range are used to indicate that the environment within the preset range has changed. If the result is yes, re-execute the operation of the edge computer based on the digital twin model of the debugging site to perform the pre-planned task verification operation on each grid and obtain the task verification result of each grid.

6. The intelligent modeling method for the digital twin model of an unmanned site according to any one of claims 3-5, characterized in that, The attribute parameters for obtaining all target component architectures of the target unmanned site include: The type of the target unmanned site is determined. The type of the target unmanned site includes an existing type or a planned type. The existing type means that the target unmanned site has been built or has complete design drawings. The planned type means that the target unmanned site is in the planning stage and does not have complete design drawings. When the type of the target unmanned site is the existing type, obtain the electronic design drawing data of the target unmanned site, and obtain the attribute parameters of all target component architectures of the target unmanned site from the drawing data; When the type of the target unmanned site is the planning type, the design data of the target unmanned site during the forward design is obtained and used as the attribute parameters of all target component architectures of the target unmanned site.

7. The intelligent modeling method for unmanned site digital twin models according to any one of claims 1, 2, 4 and 5, characterized in that, The step of determining the deployment data corresponding to the actual location of each grid in the actual scenario of the unmanned site includes: For each of the grids, a unique identifier is assigned. Based on the unique identifier corresponding to each grid, the deployment data corresponding to the actual location of each grid in the actual scenario of the unmanned site is determined; The deployment data for each grid includes the environment deployment data and task path deployment data for that grid. The step of determining the deployment data corresponding to the actual location of each grid in the actual scenario of the unmanned site based on the unique identifier corresponding to each grid includes: For any of the grids, based on the unique identifier corresponding to the grid and the pre-configured task planning path, a virtual task is executed from the virtual location corresponding to the unmanned station to the grid, and the virtual task result of the grid is obtained. Based on the pre-determined actual task result of the grid, a verification operation is performed on the virtual task result of the grid to obtain the task verification result of the grid, which is used as the task path deployment data corresponding to the grid. The starting point of the task planning path of the grid is the virtual location corresponding to the actual location of the unmanned station in the actual scene on the digital twin model of the base station, and the ending point of the task planning path of the grid is the virtual location corresponding to the actual location of the grid in the actual scene of the unmanned station on the digital twin model of the base station. For any of the grids, when the unmanned equipment arrives at the actual location corresponding to the grid, data collection is performed on that actual location to obtain the environmental deployment data corresponding to the actual location of the grid.

8. The intelligent modeling method for unmanned site digital twin models according to any one of claims 1, 2, 4 and 5, characterized in that, The method further includes: If the current conditions of the unmanned station meet the pre-determined data re-collection conditions within the preset range, the second data within the preset range and the actual location corresponding to the second data are collected. The second data within the preset range is obtained based on the infrastructure with physical entities in the infrastructure of the unmanned station, and / or based on a third party communicating with the unmanned station, and / or obtained by simulating simulation data within the preset range. The second data within the preset range includes environmental data within the preset range. Based on the actual location corresponding to the second data within the preset range, a matching grid matching the actual location is determined in the digital twin model of the unmanned site's base site; Obtain the unique identifier corresponding to the matching grid, and perform an update operation on the matching grid according to the unique identifier corresponding to the matching grid and the second data within the preset range to obtain the updated digital twin model of the unmanned site. Then, perform the grid division operation on the digital twin model of the site to obtain a digital twin model of the site containing multiple grids.

9. An intelligent modeling device for a digital twin model of an unmanned site, characterized in that, The device includes: The acquisition module is used to acquire first data within a preset range of the unmanned station. The first data within the preset range includes basic environmental data within the preset range. The preset range is determined based on the location of the unmanned station and / or the perception range of the unmanned station. The construction module is used to perform digital twin modeling operations on the pre-constructed digital twin architecture model of the unmanned site based on the first data of the unmanned site, so as to obtain the basic site digital twin model of the unmanned site. The partitioning module is used to perform a grid partitioning operation on the basic site digital twin model to obtain a basic site digital twin model containing multiple grids; A determination module is used to determine the deployment data corresponding to the actual location of each grid in the actual scenario of the unmanned site; The optimization module is used to perform optimization operations on the basic site digital twin model based on the deployment data corresponding to all the grids, so as to obtain an optimized site digital twin model, wherein the site digital twin model is used as the basis for task execution corresponding to the unmanned site.

10. An intelligent modeling device for a digital twin model of an unmanned site, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent modeling method of the unmanned site digital twin model as described in any one of claims 1-8.

11. An intelligent modeling system for digital twin models of unmanned sites, characterized in that, The system includes a mission platform, an edge computer, a target base station, and sensors integrated on the target base station. The target base station includes a communication base station and a navigation and positioning base station. The communication base station is used to provide communication data to the edge computer and the navigation and positioning base station. The navigation and positioning base station is used to locate the target base station, the edge computer, and the unmanned equipment. The edge computer is set on the mission platform and is used to store data, including a site digital twin model. The data is obtained by the system through the intelligent modeling method of the unmanned site digital twin model as described in any one of claims 1-8.

Images