Optimized scheduling method based on physical ID drive and digital twinborn model

Abstract

The invention relates to the technical field of optimal scheduling, in particular to an optimal scheduling method based on physical ID drive and a digital twinborn model. The method comprises the following steps: carrying out landform modeling on a target fruit farm to obtain a three-dimensional landform model of the fruit farm; carrying out planting area data acquisition on the target fruit farm to obtain detailed data of a planting area of the fruit farm; performing intelligent semantic annotation on the three-dimensional terrain model of the fruit farm according to detailed data of a planting area of the fruit farm to obtain a digital twin model of the fruit farm; performing passable path intelligent identification on the fruit farm digital twinborn model, and performing identifier endowing to obtain a fruit farm path network diagram and a fruit farm path ID list; performing picking operation area division on a target fruit farm based on the fruit farm digital twinborn model, and performing identifier endowing to obtain a fruit farm picking area division map and a fruit farm acquisition area ID list; according to the method, the resource scheduling efficiency is remarkably improved, including reasonable distribution of personnel, effective use of tools and optimal scheduling of transport vehicles.

Description

Technical Field

[0001] The present invention relates to the field of optimization scheduling technology, and in particular to an optimization scheduling method based on physical ID drive and digital twin model. Background Art

[0002] In modern agricultural production, fruit farms are important agricultural product production bases, and their production efficiency and resource utilization directly affect economic benefits and market competitiveness. Especially in fruit farms with diversified planting, how to reasonably allocate collection personnel and transportation vehicles to achieve optimal resource scheduling is the key to improving production efficiency. However, existing technologies mostly rely on manual experience and intuition for decision-making, which has many limitations. First, manual experience is often limited by individual cognitive biases and incomplete information, and it is difficult to adapt to the variability of the fruit farm environment. For example, in mountainous fruit farms with complex terrain, there are significant differences in fruit maturity and collection difficulty in different areas, and it is difficult to make accurate resource allocation decisions based solely on experience. Secondly, the existing resource scheduling methods lack in-depth analysis of the characteristics of each area in the fruit farm and support from real-time data. In fruit farms with a combination of plains and mountains, the diversity of terrain puts higher requirements on collection and transportation, but existing technologies often ignore this point, resulting in unreasonable resource allocation and low efficiency. Finally, the existing resource scheduling methods show obvious deficiencies in responding to emergencies and dynamic changes. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an optimization scheduling method based on physical ID drive and digital twin model to solve at least one of the above technical problems.

[0004] To achieve the above purpose, an optimization scheduling method based on physical ID drive and digital twin model includes the following steps:

[0005] Step S1: Modeling the topography of the target orchard to obtain a three-dimensional terrain model of the orchard; collecting planting area data of the target orchard to obtain detailed data of the planting area of ​​the orchard; and intelligently semantically annotating the three-dimensional terrain model of the orchard according to the detailed data of the planting area of ​​the orchard to obtain a digital twin model of the orchard;

[0006] Step S2: Intelligently identify the traversable paths of the orchard digital twin model and assign identifiers to obtain a orchard path network diagram and an orchard path ID list; divide the target orchard into picking operation areas based on the orchard digital twin model and assign identifiers to obtain a orchard picking area division diagram and an orchard collection area ID list;

[0007] Step S3: count the types of fruits planted in the detailed data of the orchard planting area to obtain a list of the types of fruits planted; collect the types of fruits to be picked in the target orchard to obtain a list of the types of fruits to be picked;

[0008] Step S4: Collecting data of pickers in the target orchard to obtain a data set of identity data of pickers; intelligently allocating picking tasks to the target orchard based on the digital twin model of the orchard and the list of fruit types to be picked and the data set of identity data of pickers to obtain an intelligent allocation plan for pickers;

[0009] Step S5: Collect the transport vehicle data of the target orchard to obtain an intelligent database of the orchard transport vehicles; plan the transport task of the target orchard according to the orchard path network diagram, the orchard path ID list and the intelligent database of the orchard transport vehicles to obtain an intelligent transport vehicle dispatching plan;

[0010] Step S6: Based on the orchard path network diagram and the orchard path ID list and in accordance with the intelligent allocation plan for pickers and the intelligent transport vehicle scheduling plan, the pickers' passage plan is planned for the target orchard to obtain the pickers' passage plan; collaborative picking and transportation operations are performed according to the intelligent allocation plan for pickers, the intelligent transport vehicle scheduling plan and the pickers' passage plan.

[0011] The present invention significantly improves the decision-making accuracy of orchard resource allocation through three-dimensional terrain modeling and intelligent semantic annotation, and effectively overcomes the shortcomings of traditional reliance on manual experience. By using the digital twin model, the regional characteristics of the orchard are deeply analyzed, resource allocation is optimized, and resource utilization is improved. By intelligently dividing the picking operation area and optimizing the path network, repetitive labor and time waste are further reduced, and the operation efficiency is significantly improved. This solution also particularly strengthens the ability to cope with complex terrain, whether it is mountainous or plain, a reasonable picking and transportation strategy can be formulated. By collecting real-time data support, it is ensured that this solution can quickly respond to various changes in the orchard and enhance the ability to respond to emergencies. Intelligent task allocation promotes the coordination of picking and transportation operations, reduces waiting and idle time, and improves the fluency of operations. At the same time, the optimized scheduling of this solution reduces interference with the environment. In addition, the scalable design of this solution enables it to be adjusted according to the specific needs of different orchards, showing good versatility and adaptability. Finally, the use of the interactive decision interface improves the user experience, allowing users to operate more intuitively and conveniently, thereby achieving efficient, intelligent, and user-friendly orchard resource optimization scheduling as a whole. In summary, the present invention significantly improves the efficiency of resource scheduling, including the rational allocation of personnel, the effective use of tools and the optimal scheduling of transport vehicles, thereby improving the efficiency of the overall operation.

[0012] Preferably, the present invention also provides an optimization scheduling system based on physical ID drive and digital twin model, which is used to execute the optimization scheduling method based on physical ID drive and digital twin model as described above, and the optimization scheduling system based on physical ID drive and digital twin model includes:

[0013] The terrain modeling and annotation module is used to model the terrain of the target orchard to obtain a three-dimensional terrain model of the orchard; collect planting area data of the target orchard to obtain detailed data of the planting area of ​​the orchard; perform intelligent semantic annotation on the three-dimensional terrain model of the orchard based on the detailed data of the planting area of ​​the orchard to obtain a digital twin model of the orchard;

[0014] The path and area identification module is used to intelligently identify the traversable paths of the fruit farm digital twin model and assign identifiers to obtain a fruit farm path network diagram and a fruit farm path ID list; based on the fruit farm digital twin model, the target fruit farm is divided into picking operation areas and identifiers are assigned to obtain a fruit farm picking area division diagram and a fruit farm collection area ID list;

[0015] The fruit species statistics module is used to count the species of planted fruits based on the detailed data of the planting area of ​​the orchard to obtain a list of planted fruit species; collect the species of fruits to be picked in the target orchard to obtain a list of the species of fruits to be picked;

[0016] The picking task allocation module is used to collect the information of the pickers in the target orchard and obtain the identity information data set of the pickers; based on the digital twin model of the orchard and the list of fruit types to be picked and the identity information data set of the pickers, the picking tasks are intelligently allocated to the target orchard to obtain the intelligent allocation plan for the pickers;

[0017] The transport vehicle dispatching module is used to collect transport vehicle data for the target orchard to obtain an intelligent database of transport vehicles for the orchard; according to the orchard path network diagram, the orchard path ID list and the intelligent database of transport vehicles for the orchard, the transport vehicle transportation task of the target orchard is planned to obtain an intelligent transport vehicle dispatching plan;

[0018] The personnel passage planning module is used to plan the passage mode of pickers for the target orchard based on the orchard path network diagram and the orchard path ID list and in accordance with the intelligent allocation plan for pickers and the intelligent transport vehicle scheduling plan, and obtain the pickers passage plan; and to perform collaborative picking and transportation operations according to the intelligent allocation plan for pickers, the intelligent transport vehicle scheduling plan and the pickers passage plan.

[0019] In the present invention, the terrain modeling and annotation module is used to accurately capture the three-dimensional terrain and planting area data of the fruit field, providing a solid foundation for optimizing decision-making. The intelligent path and area recognition module further improves the efficiency of the operation process, and identifies the passable path and effective area division through intelligent technology. In terms of fruit variety management, the system greatly improves management efficiency by quickly counting and updating the list to be picked in real time. The intelligent picking task allocation module ensures the optimal match between personnel and resources, while the transport vehicle scheduling module reduces transportation costs and improves transportation efficiency through intelligent management. The personnel passage planning module comprehensively considers various factors, intelligently plans the passage mode, and reduces the operation time. The system's collaborative operation capability reduces waiting and idle time and improves overall operation efficiency. The flexible and adaptable design enables the system to be adjusted and expanded according to the needs of different fruit fields, and the user-friendly operation interface further improves the user experience. The system improves operation efficiency and resource utilization. In addition, the system has the ability to cope with dynamic changes, and can respond in real time and quickly adjust the scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0021] Figure 1 A schematic diagram of the steps of an optimization scheduling method based on physical ID drive and digital twin model in one embodiment is shown.

[0022] Figure 2 A detailed flow chart of step S3 of an embodiment is shown.

[0023] Figure 3 A detailed flow chart of step S4 of an embodiment is shown. DETAILED DESCRIPTION

[0024] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0026] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0027] To achieve this, please refer to Figures 1 to 3 The present invention provides an optimization scheduling method based on physical ID drive and digital twin model, comprising the following steps:

[0028] Step S1: Modeling the topography of the target orchard to obtain a three-dimensional terrain model of the orchard; collecting planting area data of the target orchard to obtain detailed data of the planting area of ​​the orchard; and intelligently semantically annotating the three-dimensional terrain model of the orchard according to the detailed data of the planting area of ​​the orchard to obtain a digital twin model of the orchard;

[0029] Step S2: Intelligently identify the traversable paths of the orchard digital twin model and assign identifiers to obtain a orchard path network diagram and an orchard path ID list; divide the target orchard into picking operation areas based on the orchard digital twin model and assign identifiers to obtain a orchard picking area division diagram and an orchard collection area ID list;

[0030] Step S3: count the types of fruits planted in the detailed data of the orchard planting area to obtain a list of the types of fruits planted; collect the types of fruits to be picked in the target orchard to obtain a list of the types of fruits to be picked;

[0031] Step S4: Collecting data of pickers in the target orchard to obtain a data set of identity data of pickers; intelligently allocating picking tasks to the target orchard based on the digital twin model of the orchard and the list of fruit types to be picked and the data set of identity data of pickers to obtain an intelligent allocation plan for pickers;

[0032] Step S5: Collect the transport vehicle data of the target orchard to obtain an intelligent database of the orchard transport vehicles; plan the transport task of the target orchard according to the orchard path network diagram, the orchard path ID list and the intelligent database of the orchard transport vehicles to obtain an intelligent transport vehicle dispatching plan;

[0033] Step S6: Based on the orchard path network diagram and the orchard path ID list and in accordance with the intelligent allocation plan for pickers and the intelligent transport vehicle scheduling plan, the pickers' passage plan is planned for the target orchard to obtain the pickers' passage plan; collaborative picking and transportation operations are performed according to the intelligent allocation plan for pickers, the intelligent transport vehicle scheduling plan and the pickers' passage plan.

[0034] In this embodiment, the laser radar (LiDAR) scanning equipment carried by the drone is first deployed to perform a detailed topographic scan of the target orchard. The acquired point cloud data is converted into an accurate three-dimensional terrain model of the orchard through professional processing software such as Pix4Dmapper. Subsequently, a field survey team is organized to use a handheld data collector to record various types of information in the planting area, such as fruit types, planting areas, and maturity, and upload this information to the central database through data synchronization software to form detailed data of the orchard planting area. Further, an intelligent semantic analysis tool, such as Semantic Mapper, is used to semantically annotate the received three-dimensional terrain model, combine the detailed data of the orchard planting area with the three-dimensional terrain model of the orchard, and generate a digital twin model of the orchard with rich attribute information. Next, the Network Analyst tool in the ArcGIS software is used to intelligently identify the traversable paths of the digital twin model, automatically extract and assign identifiers, and construct a network diagram of the orchard path and a list of orchard path IDs. In terms of the division of picking operation areas, based on the digital twin model of the fruit farm, the regional analysis tool of GIS software is used to intelligently divide the picking areas according to the distribution and maturity information of fruit species, and identifiers are assigned to obtain the picking area division map and the ID list of the fruit farm collection area. At the same time, agricultural data management software such as AgriData Pro is used to conduct in-depth analysis of the detailed data of the planting area, and to count and generate a list of planted fruit species. Through field surveys, combined with maturity assessment and historical picking data, a list of fruit species to be picked is compiled. In addition, the human resources information system is used to collect the personal information, skills and work experience of the pickers in detail to form a data set of the identity information of the pickers. Combining the digital twin model, the list of fruit species to be picked and the data set of the identity information of the pickers, the optimization solver in Excel or other intelligent algorithms are used to perform multi-dimensional analysis and task allocation to form an intelligent allocation plan for the pickers. In terms of the collection of transport vehicle information, a vehicle management system such as Fleet Management Pro is used to collect and manage the basic information of the vehicle, such as load, size and performance, and to build an intelligent database of transport vehicles in the fruit farm. Then, combined with the orchard path network diagram, path ID list and vehicle intelligent database, transportation optimization software such as Oracle Transportation Management is used to intelligently plan the transportation tasks of transport vehicles and generate intelligent transport vehicle scheduling plans. Finally, in the GIS software, the intelligent allocation plan for pickers, the intelligent transportation vehicle scheduling plan, as well as the path network diagram and path ID list are comprehensively considered, and the network analysis tool is used to intelligently plan the passage mode of pickers to form a picker passage plan. After integrating all the plans, they are visualized and updated in real time in the GIS software to ensure efficient coordination of picking and transportation operations.

[0035] Preferably, step S1 comprises the following steps:

[0036] Step S11: Modeling the topography of the target orchard to obtain a three-dimensional terrain model of the orchard;

[0037] Step S12: Collecting data on the types of fruits planted in the target orchard to obtain data on the types of fruits planted in the orchard;

[0038] Step S13: collecting geographical data of the planting areas of various types of fruits according to the fruit type data of the orchard to obtain the spatial distribution data of fruit planting;

[0039] Step S14: spatially associate the fruit type data of the orchard with the fruit planting spatial distribution data to obtain detailed data of the orchard planting area;

[0040] Step S15: Intelligently semantically annotate the three-dimensional terrain model of the orchard according to the detailed data of the orchard planting area to obtain a digital twin model of the orchard.

[0041] The present invention provides a highly realistic three-dimensional terrain model for orchard management through precise terrain modeling, greatly enhancing the accuracy of geographic information. By comprehensively collecting data on planted fruit species, the planting structure of the orchard is revealed in detail. Further spatial distribution data collection enables refined management of different fruit planting areas and optimizes the spatial allocation of resources. By deeply integrating the planting species with spatial distribution, detailed planting area data is formed. Through the application of intelligent semantic annotation technology, not only the readability and ease of use of the data are improved, but also a digital twin model of the orchard is created.

[0042] In this embodiment, a three-dimensional laser scanner is first used to collect comprehensive topographic data of the target fruit farm. The device can accurately capture every subtle topographic change of the fruit farm and convert this information into a digital format to construct a detailed three-dimensional terrain model of the fruit farm. Next, the geographic information system (GIS) software is used to collect data on the types of fruit planted, and the planting location, area and quantity of each type of fruit are recorded in detail, thereby forming the data of the types of fruit planted in the fruit farm. Subsequently, an unmanned aerial vehicle equipped with a multispectral sensor is operated to perform aerial photogrammetry on the fruit farm to obtain the spatial distribution information of fruit planting, and then obtain the spatial distribution data of fruit planting. These data are then imported into the GIS software, spatially associated with the data of the types of fruit planted, and accurate superposition and correspondence of the data are achieved, generating detailed data of the fruit farm planting area. Finally, the intelligent semantic analysis tool is used in combination with the artificial intelligence algorithm to deeply process and analyze these detailed data, perform intelligent semantic annotation on the three-dimensional terrain model, identify and classify the key information of different fruit planting areas, such as boundaries and maturity, and mark and annotate the model, and successfully construct a digital twin model of the fruit farm that reflects the physical characteristics of the fruit farm and detailed information of the planting area.

[0043] Preferably, step S2 comprises the following steps:

[0044] Step S21: performing a global path topology analysis on the fruit farm digital twin model to obtain a fruit farm initial path set, wherein the fruit farm initial path set includes a plurality of fruit farm initial paths;

[0045] Step S22: Based on the fruit farm digital twin model, the maximum slope of the initial path of the fruit farm is identified to obtain a maximum slope set of the fruit farm path, wherein the maximum slope set of the fruit farm path includes a plurality of maximum slopes of the fruit farm path;

[0046] Step S23: measuring the minimum width of the initial path of the orchard based on the digital twin model of the orchard to obtain a minimum width set of the orchard path;

[0047] Step S24: Eliminate the initial fruit field paths corresponding to the fruit field paths with maximum slopes greater than a preset safe passage slope threshold in the fruit field path maximum slope set, and obtain a set of safe and passable fruit field paths;

[0048] Step S25: integrating and numbering the safe and passable orchard path set based on the orchard path maximum slope set and the orchard path minimum width set, to obtain an orchard path network diagram and an orchard path ID list;

[0049] Step S26: performing conformal mapping and distance-preserving expansion on the digital twin model of the fruit farm to obtain a fruit planting layout diagram of the fruit farm;

[0050] Step S27: identifying and depicting the boundaries of the fruit planting area on the fruit farm fruit planting layout map to obtain a contour map of the fruit farm planting area;

[0051] Step S28: Based on the digital twin model of the orchard and the outline map of the orchard planting area, the target orchard is divided into picking operation areas, and identifiers are assigned to obtain a orchard picking area division map and a orchard collection area ID list.

[0052] The present invention realizes comprehensive identification of the passage paths within the orchard through global path topology analysis, providing a solid foundation for path optimization and safety management. At the same time, by identifying and eliminating unsafe paths through the maximum slope, it significantly improves the safety of operations and reduces the risk of accidents. The minimum width measurement further enhances the traffic efficiency and ensures the smooth passage of vehicles and personnel. By integrating and numbering safe and passable paths, a clear path network diagram and ID list are created, the path network is rationalized, and resource allocation and navigation are optimized. Through the application of conformal mapping and distance-preserving expansion technology, an accurate planting layout diagram is provided, which helps to facilitate more sophisticated regional management and picking operation planning. Intelligent path and regional management not only improves the automation level of resource scheduling, but also reduces the reliance on manual monitoring. At the same time, the rapid and accurate recognition capability improves the system's response speed to changes in operational requirements.

[0053] In this embodiment, the topology analysis software GraphTheory Pro is first started, and the three-dimensional data of the digital twin model of the fruit farm is imported. The software uses its inherent algorithm to automatically identify and record all the passage paths, including trails and lanes, to construct the initial path set of the fruit farm and digitally store it in the database. Subsequently, the Terrain Analyst tool is used to process the three-dimensional terrain model, calculate the maximum slope of each path, and form the maximum slope set of the fruit farm path; AutoCAD Civil 3D measures the path width and creates the minimum width set of the fruit farm path. After setting the safe passage slope threshold, the slope filtering function of the script or QGIS is used to eliminate the path with too large a slope, and obtain a safe and passable fruit farm path set. ArcGIS software is used to combine the maximum slope set and the minimum width set data, perform path integration and numbering, optimize the path network, and form a fruit farm path network diagram and a fruit farm path ID list. Next, the GDAL library of MATLAB or Python is used to apply conformal mapping technology and distance-preserving expansion algorithm to convert the fruit farm digital twin model into a two-dimensional fruit farm fruit planting layout map, clearly showing the planting layout. Image processing software such as Adobe Photoshop or ImageJ further enhances the image, intelligently identifies the boundaries of the planting area through edge detection algorithms, and depicts the contour map of the orchard planting area. Finally, MapInfo or a customized GIS application is used to divide the picking operation area based on the orchard digital twin model and the planting area contour map. The area can be automatically or semi-automatically divided according to the size, shape and maturity factors of the area, and a unique identifier is assigned to generate a field picking area division map and a list of orchard collection area IDs.

[0054] Preferably, step S28 comprises the following steps:

[0055] Step S281: performing independent planting area segmentation on the fruit farm planting area outline map to obtain a fruit farm planting area segmentation set, and performing independent planting area area calculation on the fruit farm planting area segmentation set based on the fruit farm planting area outline map to obtain a fruit farm planting area area set, wherein the fruit farm planting area area set includes a plurality of fruit farm planting area areas;

[0056] Step S282: marking the planting areas in the fruit farm planting area area set whose planting areas are less than or equal to the preset standard picking area areas as independent picking area data, and marking the planting areas in the fruit farm planting area area set whose planting areas are greater than the preset standard picking area areas as to-be-divided picking areas, to obtain to-be-divided picking area data;

[0057] Step S283: dividing the corresponding planting area according to the data of the picking areas to be divided according to the preset standard picking area area to obtain a first divided picking area set;

[0058] Step S284: Counting the planting areas corresponding to the independent picking area data and the first divided picking area set to obtain an initial picking area set, wherein the initial picking area set includes a plurality of initial picking areas;

[0059] Step S285: performing three-dimensional spatial mapping and fusion on the digital twin model of the fruit field according to the initial picking area set to obtain a fused digital twin model of the picking area;

[0060] Step S286: Calculate the maximum drop distance for each initial picking area in the initial picking area set based on the fused picking area digital twin model to obtain a maximum drop distance data set in the picking area, wherein the maximum drop distance data set in the picking area includes maximum drop distance data in several picking areas;

[0061] Step S287: the initial picking area corresponding to the maximum drop distance data in the picking area being greater than the preset maximum allowable height drop value in the maximum drop distance data set in the picking area is recorded as the picking area to be divided twice, and the initial picking area corresponding to the maximum drop distance data in the picking area being less than the preset maximum allowable height drop value in the maximum drop distance data set in the picking area is recorded as the final picking area, to obtain a final picking area set;

[0062] Step S288: re-dividing the picking area that needs to be divided twice based on contour line analysis based on the fused picking area digital twin model to obtain a set of twice-divided picking areas;

[0063] Step S289: Intelligently fuse the boundaries and assign identifiers to the orchard planting area outline map based on the final picking area set and the secondary division picking area set to obtain the orchard picking area division map and the orchard collection area ID list.

[0064] The present invention provides detailed basic data for the orchard through precise regional segmentation and management, ensuring the fine identification and efficient management of the planting area. By intelligently dividing the suitable picking area according to the preset standards, not only the efficiency and balance of the picking work are improved, but also the plots that need further operation can be quickly identified through efficient data processing. Through the application of three-dimensional space mapping technology, the two-dimensional data is converted into a three-dimensional model, which enhances the ability to analyze complex terrain. At the same time, the drop distance of each picking area is accurately calculated, which provides an important guarantee for the safety of the operation. In addition, the present invention can adapt to the changeable terrain, and by distinguishing areas with different drops, it avoids picking operations in high-risk areas and reduces the risk of operations. For those that need to be re-divided, secondary division and optimization based on contour lines can be performed to ensure the rationality and feasibility of the picking area. Through intelligent boundary fusion and identifier allocation, a picking area division map and ID list that are easy to identify and navigate are formed, which improves the planning of the operation.

[0065] In this embodiment, the polygon segmentation tool of ArcGIS software is first used to accurately segment the fruit field planting area contour map, create a fruit field planting area segmentation set, and calculate the area of ​​each independent area through the spatial analysis function to generate a fruit field planting area area set containing the area data of each area. After setting the standard picking area area threshold, Microsoft Access or SQL Server database management software is used to store and query area data, automatically identify and mark the area of ​​suitable area as independent picking area data, and mark the planting area corresponding to the area of ​​the fruit field planting area greater than the preset standard picking area as the picking area data to be divided. Then, the area division tool of GIS software is used to divide these areas to be divided into equal areas according to the preset standard picking area area, forming a first divided picking area set, and merging it with the independent picking area data to construct an initial picking area set. Subsequently, SketchUp or 3ds Max three-dimensional modeling software is used to perform three-dimensional spatial mapping and fusion on the fruit field digital twin model according to the initial picking area set, and a fused picking area digital twin model is developed. Using this model and GIS software, the maximum drop distance of each initial picking area is calculated to form a maximum drop distance data set in the picking area, and the area is classified into a picking area that needs to be divided twice or a final picking area according to the preset maximum allowable height drop value, and the corresponding area set is obtained. For the area that needs to be divided twice, the contour line analysis tool of the GIS software is used to re-divided to form a secondary division picking area set. Finally, the final picking area set is combined with the secondary division picking area set through the intelligent boundary fusion tool of the GIS software, and the intelligent boundary fusion and identifier allocation are performed on the contour map of the orchard planting area to generate a clear orchard picking area division map and an orchard collection area ID list.

[0066] Preferably, step S3 comprises the following steps:

[0067] Step S31: Count the types of fruits planted in the detailed data of the fruit farm planting area to obtain data on the types of fruits planted in the fruit farm;

[0068] Step S32: Automatically encode the data of fruit species planted in the orchard to obtain an ID list of fruits planted in the orchard;

[0069] Step S33: collecting the maturity period data of the fruit species planted in the orchard to obtain a distribution table of the maturity periods of the fruit species;

[0070] Step S34: Intelligently integrate and index the fruit species data, the fruit ID list and the fruit species maturity period distribution table to obtain a fruit species list;

[0071] Step S35: displaying the ID list of fruits grown in the orchard to the user through a preset interactive picking decision interface for picking type selection, and recording the user's selection in real time to obtain the ID list of fruits to be picked;

[0072] Step S36: Based on the list of planted fruit species, intelligent retrieval and list generation are performed according to the list of to-be-picked fruit IDs to obtain a list of to-be-picked fruit species.

[0073] The present invention creates an easy-to-manage fruit ID list by accurately counting and automatically coding the types of planted fruits, greatly improving the efficiency and accuracy of data management. By scientifically collecting and managing the fruit maturity cycle, it is possible to reasonably arrange the picking plan and human resources, and optimize the scientific management of the maturity cycle. A comprehensive index of planted fruit types is constructed through intelligent data fusion technology, providing data support for accurate scheduling. Through the interactive interface combined with the real-time recording and feedback mechanism, not only the flexibility and response speed of decision-making are improved, but also the accuracy of the ID list of fruits to be picked is ensured, providing reliable guidance for picking operations. The intelligent retrieval and list generation functions simplify the preparation workflow and improve the efficiency before picking.

[0074] In this embodiment, the agricultural information management system is first used to perform detailed statistics on the detailed data of the fruit farm planting area, determine and record the various types of fruits planted, and create data on the types of fruits planted in the fruit farm. Through the built-in automated coding tool of the system, a specific identification code is assigned to each fruit to form an ID list of fruits planted in the fruit farm. Subsequently, a handheld data collector, such as a smart phone or tablet computer equipped with a customized application, is used to directly collect fruit ripening cycle information on the orchard site, and these information are summarized to form a distribution table of fruit types and ripening cycles. Next, the data of fruit types planted in the fruit farm, the ID list of fruits planted in the fruit farm, and the distribution table of ripening cycles are comprehensively processed through the data fusion function of the system, and an index is intelligently constructed to generate a structured list of fruit types planted. Further, a user-friendly interactive picking decision interface is developed, which can be a Web application or a mobile App, so that users can intuitively view and select the types of fruits to be picked, and the system records the user's selection in real time to generate a list of fruit IDs to be picked. Finally, the system automatically screens and generates a detailed list of fruit types to be picked based on the list of planted fruit types and the list of fruit IDs to be picked, using an intelligent retrieval algorithm.

[0075] Preferably, step S4 comprises the following steps:

[0076] Step S41: Collecting information about the pickers in the target orchard to obtain a data set of identity information about the pickers;

[0077] Step S42: color-coding and labeling the fruit field picking area division map according to the list of fruit types to be picked, to obtain a labeled fruit field picking area map, wherein the labeled fruit field picking area map includes a plurality of picking areas, and extracting the picking area IDs from the fruit field collection area ID list according to the labeled fruit field picking area map to obtain a picking area ID list;

[0078] Step S43: determining the demand for picking personnel in the area to be picked based on the marked area map of the fruit field to be picked, and obtaining the personnel demand data of the area to be picked;

[0079] Step S44: extracting three-dimensional features of the to-be-picked area from the digital twin model of the fruit field according to the labeled to-be-picked area map of the fruit field, obtaining a terrain feature model of the to-be-picked area, and performing terrain complexity analysis on the to-be-picked area based on the terrain feature model of the to-be-picked area to obtain a regional terrain complexity assessment result;

[0080] Step S45: If the regional terrain complexity assessment result shows that the area to be picked is a high-complexity terrain, the age range of high-difficulty pickers in the area to be picked is determined to obtain the age range of pickers;

[0081] Step S46: If the regional terrain complexity assessment result shows that the area to be picked is of low-complexity terrain, it is not necessary to determine the age range of pickers in the area to be picked;

[0082] Step S47: Based on the pickers' identity data set and the ID list of the area to be picked, pickers are allocated to the area to be picked according to the personnel demand data of the area to be picked and the age range of the pickers, or according to the personnel demand data of the area to be picked, to obtain an intelligent allocation plan for pickers.

[0083] The present invention provides a detailed data basis for the personalized management and optimal configuration of picking personnel through personalized personnel data management, greatly improving the efficiency of human resource management. By using color coding technology to visually mark the picking area, it not only enhances the intuitiveness of regional identification, but also simplifies the information communication process and reduces the communication cost. Through efficient and intelligent matching of regions and personnel, it is ensured that each picking area can obtain suitable human resources, thereby significantly improving the picking efficiency. By extracting three-dimensional features and evaluating the complexity of terrain in the picking area, a scientific basis is provided for personnel allocation, especially in areas with high terrain complexity, by determining the appropriate age range of picking personnel, the safety of the operation is ensured. In areas with low terrain complexity, the personnel allocation process is simplified, and the flexibility and response speed of scheduling are improved. By comprehensively considering personnel data, regional characteristics and personnel needs, an optimized picking personnel allocation plan is intelligently generated to achieve the optimal configuration of resources. This not only improves the operating efficiency and reduces the waiting and idle time in the operation, but also enhances the planning of the picking operation and reduces the risk of operation delays through advance analysis and planning.

[0084] In this embodiment, first, by starting a customized human resources information collection system, the identity information, work experience and skill level of the pickers are collected in detail through online forms and mobile applications, and these data are automatically sorted and stored in the pickers' identity data set. Then, ArcGIS Desktop software is used to color-code the fruit field picking area division map, color each area according to different fruit types and maturity, and the software's attribute table and query builder tool are used to extract the area ID to create a list of area IDs to be picked. Based on the labeled map, the spatial analysis tool of GIS software is used to evaluate the personnel needs of each picking area to form personnel demand data for the area to be picked. Blender software is used to extract three-dimensional terrain features of the fruit field digital twin model, construct a terrain feature model, and evaluate the terrain complexity in ArcGIS Desktop to set a suitable age range for the pickers in the high-complexity area. Finally, the intelligent optimization algorithm in the information system, such as a genetic algorithm or a simulated annealing algorithm, is used to comprehensively consider all data to generate an intelligent allocation plan for pickers.

[0085] Preferably, step S5 comprises the following steps:

[0086] Step S51: Collecting the transport vehicle data of the target fruit farm to obtain a transport vehicle original data set;

[0087] Step S52: generating a unique identification code for the transport vehicle based on the original data set of the transport vehicle, and constructing an intelligent database to obtain an intelligent database of the transport vehicle in the fruit farm;

[0088] Step S53: obtaining a map of the fruit field's to-be-picked areas and a list of to-be-picked area IDs;

[0089] Step S54: estimating the fruit yield of the to-be-picked area based on the marked to-be-picked area map of the fruit field, and obtaining estimated yield data of the to-be-picked area;

[0090] Step S55: Based on the orchard transport vehicle intelligent database and according to the marked orchard area map, the area to be picked ID list, the estimated yield data of the area to be picked, the orchard path network map and the orchard path ID list, the transport task of the transport vehicle is planned for the target orchard to obtain an intelligent transport vehicle scheduling plan.

[0091] The present invention provides detailed data support for efficient management and scheduling of transport vehicles through accurate vehicle data management, ensuring the accuracy and rationality of vehicle use. By generating a unique identification code and building an intelligent database, the vehicle identification and tracking process is simplified, and management efficiency is improved. By accurately estimating the yield of the picking area, key decision-making information is provided for the planning of transportation tasks. Intelligent transportation task planning combines multiple factors such as vehicle data, picking area, estimated yield and path network to generate an optimized scheduling plan, which significantly improves the scientific nature and transportation efficiency of transportation scheduling. In addition, the present invention enhances the coordination of operations, reduces the phenomenon of uncoordinated operations, and improves the smoothness of operations. At the same time, by optimizing the use of vehicles, it helps to reduce operating costs and improve the rationality of resource allocation. It also improves the response speed to changes in picking demand and enhances the ability to respond to emergencies. Reasonable vehicle scheduling also reduces the risk of driving in complex terrain, thereby enhancing operational safety.

[0092] In this embodiment, a data collection team is first deployed, carrying a handheld data terminal (such as an RFID scanner and a mobile computer) to collect detailed information on each transport vehicle in the target fruit field. These data include but are not limited to the size, load capacity, and energy type of the vehicle, and these information are entered to form a data set of raw data of the transport vehicle. Subsequently, a unique identification code is generated for each vehicle using vehicle management software, and an intelligent database is constructed in a database management system (such as SQL Server) to create an intelligent database of fruit field transport vehicles. Next, a GIS software such as ArcGIS is used to obtain and analyze the map of the area to be picked in the marked fruit field, and a list of IDs of the area to be picked is extracted at the same time. By combining with a preset agricultural yield prediction model, the fruit yield of each area to be picked is estimated to form estimated yield data of the area to be picked. Finally, in combination with the intelligent database of the fruit field transport vehicle, the map of the area to be picked in the marked fruit field, the list of IDs of the area to be picked, the estimated yield data, the fruit field path network diagram, and the fruit field path ID list, the transportation optimization software (such as Oracle Transportation Management) is used to plan the transportation task of the transport vehicle. The software will automatically generate an intelligent transportation vehicle scheduling plan by considering the vehicle's load limit, the path's traffic conditions, and the yield distribution factors in the picking area. The plan specifies in detail the picking area, expected load, transportation route and schedule for each vehicle, ensuring efficient coordination and optimal configuration of transportation tasks.

[0093] Preferably, step S55 includes the following steps:

[0094] Step S551: extracting the minimum passage width of the transport vehicles based on the intelligent database of the transport vehicles in the fruit farm to obtain the minimum passage width of the transport vehicles;

[0095] Step S552: Path screening is performed on the fruit field path network diagram according to the minimum pass width of the transport vehicle to obtain a vehicle passable path network diagram, and spatial superposition is performed on the marked fruit field to-be-picked area diagram and the vehicle passable path network diagram to obtain a first fused to-be-picked area path diagram;

[0096] Step S553: ​​Collect the geographic coordinates of the target orchard camp to obtain geographic coordinate data of the orchard camp, and search for the shortest path of the to-be-picked area based on the first fused path map of the to-be-picked area and the orchard path ID list according to the geographic coordinate data of the orchard camp to obtain the first shortest path ID data;

[0097] Step S554: performing a road bearing capacity analysis on the path corresponding to the first shortest path ID data to obtain the shortest transport path bearing capacity data;

[0098] Step S555: Calculate the maximum transport load of the corresponding path according to the shortest transport path carrying capacity data to obtain the maximum transport load data of the path;

[0099] Step S556: Based on the fruit farm transport vehicle intelligent database and the fruit farm path ID list, the vehicle selection for the to-be-picked area is performed based on multi-objective optimization according to the path maximum transport load data and the estimated yield data of the to-be-picked area, and the optimal transport vehicle ID data is obtained;

[0100] Step S557: extracting the vehicle load-bearing range based on the optimal transport vehicle ID data based on the fruit field transport vehicle intelligent database to obtain the transport vehicle load-bearing range interval;

[0101] Step S558: Estimating the number of transports according to the load-bearing range of the transport vehicle and the estimated yield data of the area to be picked, and calculating the one-way transport time, to obtain the estimated number of transports and one-way transport time data of the transport vehicle;

[0102] Step S559: Generate an intelligent dispatching plan for the picking area ID list, the first shortest path ID data, the optimal transport vehicle ID data, the estimated transport times and one-way transport duration data of the transport vehicle to obtain an intelligent transport vehicle dispatching plan.

[0103] The present invention ensures that the screening of the orchard path network is both safe and feasible by accurately evaluating the vehicle's traffic capacity. By optimizing the path network, a path map integrating the area to be picked is generated, providing a scientific basis for efficient transportation planning. By quickly searching for the shortest path and performing road bearing capacity analysis, not only the transportation efficiency is improved, but also the stability and safety of transportation are ensured. By accurately calculating the transport load, selecting the most suitable vehicle through multi-objective optimization, and reasonably allocating transportation tasks, waste of resources is avoided. At the same time, this solution rationally utilizes the vehicle's load-bearing capacity, accurately estimates the number and duration of transportation, and automatically and intelligently generates a scheduling plan, which improves the coordination and response speed of operations. The present invention enhances operational safety and reduces energy consumption and environmental impact.

[0104] In this embodiment, the intelligent database of the fruit field transport vehicle is first accessed, and the minimum pass width of each transport vehicle is extracted using a database query tool (such as an SQL query analyzer) and recorded in the minimum pass width data set of the transport vehicle. Then, the path network diagram of the fruit field is screened using ArcGIS software, and the inappropriate paths are eliminated according to the minimum pass width of the vehicle, and a vehicle passable path network diagram is generated. Through the map overlay function of the GIS software, the marked fruit field to-be-picked area map and the vehicle passable path network diagram are spatially superimposed to create a first fused to-be-picked area path map. Subsequently, the GPS device is used to collect the geographic coordinates of the campsite of the target fruit field, and the geographic coordinate data of the fruit field campsite is accurately recorded. In ArcGIS, based on the first fused to-be-picked area path map, the fruit field path ID list and the fruit field campsite geographic coordinate data, the network analysis tool is used to search the shortest path for the to-be-picked area, and the first shortest path ID data is determined. Further, the road bearing capacity analysis is performed on the path corresponding to the first shortest path ID data, which involves on-site investigation and material strength testing to obtain the shortest transportation path bearing capacity data. Based on these data, the maximum transport load of the corresponding path is calculated to obtain the maximum transport load data of the path. Next, combined with the intelligent database of fruit field transport vehicles and the path ID list, the multi-objective optimization algorithm in operations research is used to consider the maximum transport load of the path and the estimated yield of the area to be picked, and the vehicle selection is optimized to determine the optimal transport vehicle ID data. In the vehicle intelligent database, according to the optimal transport vehicle ID data, the load-bearing range of the vehicle is queried and extracted to obtain the load-bearing range interval of the transport vehicle. Then, according to the vehicle load-bearing range interval and the estimated yield data of the area to be picked, the statistical and mathematical modeling methods are used to estimate the number of transports and the one-way transport time, and the estimated number of transports and one-way transport time data of the transport vehicle are formed. Finally, the ID list of the area to be picked, the first shortest path ID data, the optimal transport vehicle ID data, and the transport number and time data are integrated, and the algorithm is used in the intelligent scheduling system to generate a comprehensive scheduling plan to obtain the intelligent transport vehicle scheduling plan.

[0105] Preferably, step S6 comprises the following steps:

[0106] Step S61: Obtaining a map of the fruit field to be picked and geographic coordinate data of the fruit field campsite;

[0107] Step S62: spatially superimposing the fruit farm path network diagram, the annotated fruit farm area to be picked map and the fruit farm camp geographic coordinate data to obtain a second fused area to be picked path map;

[0108] Step S63: searching for the shortest accessible path between the campsite and the area to be picked based on the second fused path map of the area to be picked and the orchard path ID list to obtain second shortest path ID data;

[0109] Step S64: If the second shortest path ID data is consistent with the first shortest path ID data in the intelligent transport vehicle scheduling plan, taking the intelligent transport vehicle is used as the pickers' passage mode, and a pickers' passage plan is obtained;

[0110] Step S65: If the second shortest path ID data is inconsistent with the first shortest path ID data in the intelligent transport vehicle scheduling solution, the walking time of the pickers is estimated based on the second fused path map of the area to be picked and the second shortest path ID data to obtain the walking time estimation data of the pickers;

[0111] Step S66: If the estimated walking time of the pickers is less than the one-way transportation time in the intelligent transport vehicle scheduling plan, the path corresponding to the second shortest path ID data is used as the walking path for the pickers, and walking is used as the pickers' travel mode to obtain the pickers' travel plan; otherwise, taking the intelligent transport vehicle is used as the pickers' travel mode to obtain the pickers' travel plan;

[0112] Step S67: performing collaborative picking and transportation operations according to the intelligent allocation plan for pickers, the intelligent transportation vehicle scheduling plan, and the pickers' passage plan.

[0113] The present invention provides the orchard with a detailed second fusion path map of the area to be picked through precise geographic data integration, greatly improving the accuracy of path planning. By performing efficient path search, the shortest accessible path between the camp and the picking area is quickly determined, significantly optimizing the traffic efficiency. Intelligently choosing to walk or take a car based on real-time data ensures efficient traffic. Accurate estimation of walking time provides an important basis for decision-making, and intelligent selection of traffic mode further reduces time waste. The optimization of collaborative operations ensures efficient coordination of picking and transportation operations, reduces waiting time during operations, and improves operation continuity. The present invention improves resource utilization efficiency and avoids waste by rationally allocating vehicles and human resources. Enhanced adaptability and flexibility enable the system to flexibly adjust traffic plans according to different situations. At the same time, a reasonable traffic plan improves operational safety and reduces safety risks under adverse conditions.

[0114] In this embodiment, first, GIS software, such as ArcGIS Desktop, is used to obtain and load the geographic coordinate data of the fruit field to be picked area map and the fruit field camp. Through the map overlay function of the GIS software, the fruit field path network map, the marked fruit field to be picked area map and the fruit field camp geographic coordinate data are spatially superimposed, and these layers are integrated to generate a second fused path map of the area to be picked. Next, the network analysis tool of ArcGIS Desktop is used to analyze the path between the picking area and the camp based on the second fused path map of the area to be picked and the fruit field path ID list, and the shortest path search algorithm is executed to obtain the second shortest path ID data. In this step, it is ensured that the network analysis takes into account the access restrictions and priorities of the path. After obtaining the second shortest path ID data, it is compared with the first shortest path ID data previously determined by the intelligent transport vehicle scheduling plan. If the two are consistent, it is decided that the pickers will take the intelligent transport vehicle as a means of passage, and a corresponding picker passage plan is formulated. If there is any inconsistency, use time estimation tools such as Walking Time Calculator to estimate the time it takes for pickers to walk to the area to be picked based on the second fused path map of the area to be picked and the second shortest path ID data, and obtain the estimated walking time data for pickers. Then, compare the walking time estimation data with the one-way transportation time data in the intelligent transport vehicle scheduling plan. If the walking time is shorter, formulate a walking plan for pickers; if the transportation time is shorter or considering the convenience and efficiency of transportation, choose to take the intelligent transport vehicle, and update the pickers' travel plan accordingly. Finally, combine the intelligent allocation plan for pickers, the intelligent transport vehicle scheduling plan and the newly formulated pickers' travel plan, and conduct comprehensive analysis and scheduling in the GIS software to ensure the coordinated progress of picking and transportation operations.

[0115] Preferably, the present invention also provides an optimization scheduling system based on physical ID drive and digital twin model, which is used to execute the optimization scheduling method based on physical ID drive and digital twin model as described above, and the optimization scheduling system based on physical ID drive and digital twin model includes:

[0116] The terrain modeling and annotation module is used to model the terrain of the target orchard to obtain a three-dimensional terrain model of the orchard; collect planting area data of the target orchard to obtain detailed data of the planting area of ​​the orchard; perform intelligent semantic annotation on the three-dimensional terrain model of the orchard based on the detailed data of the planting area of ​​the orchard to obtain a digital twin model of the orchard;

[0117] The path and area identification module is used to intelligently identify the traversable paths of the fruit farm digital twin model and assign identifiers to obtain a fruit farm path network diagram and a fruit farm path ID list; based on the fruit farm digital twin model, the target fruit farm is divided into picking operation areas and identifiers are assigned to obtain a fruit farm picking area division diagram and a fruit farm collection area ID list;

[0118] The fruit species statistics module is used to count the species of planted fruits based on the detailed data of the planting area of ​​the orchard to obtain a list of planted fruit species; collect the species of fruits to be picked in the target orchard to obtain a list of the species of fruits to be picked;

[0119] The picking task allocation module is used to collect the information of the pickers in the target orchard and obtain the identity information data set of the pickers; based on the digital twin model of the orchard and the list of fruit types to be picked and the identity information data set of the pickers, the picking tasks are intelligently allocated to the target orchard to obtain the intelligent allocation plan for the pickers;

[0120] The transport vehicle dispatching module is used to collect transport vehicle data for the target orchard to obtain an intelligent database of transport vehicles for the orchard; according to the orchard path network diagram, the orchard path ID list and the intelligent database of transport vehicles for the orchard, the transport vehicle transportation task of the target orchard is planned to obtain an intelligent transport vehicle dispatching plan;

[0121] The personnel passage planning module is used to plan the passage mode of pickers for the target orchard based on the orchard path network diagram and the orchard path ID list and in accordance with the intelligent allocation plan for pickers and the intelligent transport vehicle scheduling plan, and obtain the pickers passage plan; and to perform collaborative picking and transportation operations according to the intelligent allocation plan for pickers, the intelligent transport vehicle scheduling plan and the pickers passage plan.

[0122] In the present invention, the terrain modeling and annotation module is used to accurately capture the three-dimensional terrain and planting area data of the fruit field, providing a solid foundation for optimizing decision-making. The intelligent path and area recognition module further improves the efficiency of the operation process, and identifies the passable path and effective area division through intelligent technology. In terms of fruit variety management, the system greatly improves management efficiency by quickly counting and updating the list to be picked in real time. The intelligent picking task allocation module ensures the optimal match between personnel and resources, while the transport vehicle scheduling module reduces transportation costs and improves transportation efficiency through intelligent management. The personnel passage planning module comprehensively considers various factors, intelligently plans the passage mode, and reduces the operation time. The system's collaborative operation capability reduces waiting and idle time and improves overall operation efficiency. The flexible and adaptable design enables the system to be adjusted and expanded according to the needs of different fruit fields, and the user-friendly operation interface further improves the user experience. The system improves operation efficiency and resource utilization. In addition, the system has the ability to cope with dynamic changes, and can respond in real time and quickly adjust the scheduling plan.

[0123] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0124] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An optimization scheduling method based on physical ID drive and digital twin model, characterized in that: The following steps are involved: Step S1: Modeling the topography of the target orchard to obtain a three-dimensional terrain model of the orchard; collecting planting area data of the target orchard to obtain detailed data of the planting area of ​​the orchard; and intelligently semantically annotating the three-dimensional terrain model of the orchard according to the detailed data of the planting area of ​​the orchard to obtain a digital twin model of the orchard; Step S2: Intelligently identify the traversable paths of the fruit farm digital twin model and assign identifiers to obtain a fruit farm path network diagram and a fruit farm path ID list; Based on the digital twin model of the orchard, the target orchard is divided into picking operation areas and identifiers are assigned to obtain a picking area division map and an ID list of the orchard collection areas. Step S3: Count the types of fruit planted according to the detailed data of the fruit farm planting area to obtain a list of the types of fruit planted; Collect the types of fruits to be picked in the target orchard and obtain a list of the types of fruits to be picked; Step S4: Collecting data of pickers in the target orchard to obtain a data set of identity data of pickers; intelligently allocating picking tasks to the target orchard based on the digital twin model of the orchard and the list of fruit types to be picked and the data set of identity data of pickers to obtain an intelligent allocation plan for pickers; Step S5: Collect the transport vehicle data of the target orchard to obtain an intelligent database of the orchard transport vehicles; plan the transport task of the target orchard according to the orchard path network diagram, the orchard path ID list and the intelligent database of the orchard transport vehicles to obtain an intelligent transport vehicle dispatching plan; Step S6: Based on the orchard path network diagram and the orchard path ID list and in accordance with the intelligent allocation plan for pickers and the intelligent transport vehicle scheduling plan, the pickers' passage plan is planned for the target orchard to obtain the pickers' passage plan; collaborative picking and transportation operations are performed according to the intelligent allocation plan for pickers, the intelligent transport vehicle scheduling plan and the pickers' passage plan.

2. The optimization scheduling method based on physical ID drive and digital twin model according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Modeling the topography of the target orchard to obtain a three-dimensional terrain model of the orchard; Step S12: Collecting data on the types of fruits planted in the target orchard to obtain data on the types of fruits planted in the orchard; Step S13: collecting geographical data of the planting areas of various types of fruits according to the fruit type data of the orchard to obtain the spatial distribution data of fruit planting; Step S14: spatially associate the fruit type data of the orchard with the fruit planting spatial distribution data to obtain detailed data of the orchard planting area; Step S15: Intelligently semantically annotate the three-dimensional terrain model of the orchard according to the detailed data of the orchard planting area to obtain a digital twin model of the orchard.

3. The optimization scheduling method based on physical ID drive and digital twin model according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing a global path topology analysis on the fruit farm digital twin model to obtain a fruit farm initial path set, wherein the fruit farm initial path set includes a plurality of fruit farm initial paths; Step S22: Based on the fruit farm digital twin model, the maximum slope of the initial path of the fruit farm is identified to obtain a maximum slope set of the fruit farm path, wherein the maximum slope set of the fruit farm path includes a plurality of maximum slopes of the fruit farm path; Step S23: measuring the minimum width of the initial path of the orchard based on the digital twin model of the orchard to obtain a minimum width set of the orchard path; Step S24: Eliminate the initial fruit field paths corresponding to the fruit field paths with maximum slopes greater than a preset safe passage slope threshold in the fruit field path maximum slope set, and obtain a set of safe and passable fruit field paths; Step S25: integrating and numbering the safe and passable orchard path set based on the orchard path maximum slope set and the orchard path minimum width set, to obtain an orchard path network diagram and an orchard path ID list; Step S26: performing conformal mapping and distance-preserving expansion on the digital twin model of the fruit farm to obtain a fruit planting layout diagram of the fruit farm; Step S27: identifying and depicting the boundaries of the fruit planting area on the fruit farm fruit planting layout map to obtain a contour map of the fruit farm planting area; Step S28: Based on the digital twin model of the orchard and the outline map of the orchard planting area, the target orchard is divided into picking operation areas, and identifiers are assigned to obtain a orchard picking area division map and a orchard collection area ID list.

4. The optimization scheduling method based on physical ID drive and digital twin model according to claim 3 is characterized in that: Step S28 includes the following steps: Step S281: performing independent planting area segmentation on the fruit farm planting area outline map to obtain a fruit farm planting area segmentation set, and performing independent planting area area calculation on the fruit farm planting area segmentation set based on the fruit farm planting area outline map to obtain a fruit farm planting area area set, wherein the fruit farm planting area area set includes a plurality of fruit farm planting area areas; Step S282: marking the planting areas in the fruit farm planting area area set whose planting areas are less than or equal to the preset standard picking area areas as independent picking area data, and marking the planting areas in the fruit farm planting area area set whose planting areas are greater than the preset standard picking area areas as to-be-divided picking areas, to obtain to-be-divided picking area data; Step S283: dividing the corresponding planting area according to the data of the picking areas to be divided according to the preset standard picking area area to obtain a first divided picking area set; Step S284: Counting the planting areas corresponding to the independent picking area data and the first divided picking area set to obtain an initial picking area set, wherein the initial picking area set includes a plurality of initial picking areas; Step S285: performing three-dimensional spatial mapping and fusion on the digital twin model of the fruit field according to the initial picking area set to obtain a fused digital twin model of the picking area; Step S286: Calculate the maximum drop distance for each initial picking area in the initial picking area set based on the fused picking area digital twin model to obtain a maximum drop distance data set in the picking area, wherein the maximum drop distance data set in the picking area includes maximum drop distance data in several picking areas; Step S287: the initial picking area corresponding to the maximum drop distance data in the picking area being greater than the preset maximum allowable height drop value in the maximum drop distance data set in the picking area is recorded as the picking area to be divided twice, and the initial picking area corresponding to the maximum drop distance data in the picking area being less than the preset maximum allowable height drop value in the maximum drop distance data set in the picking area is recorded as the final picking area, to obtain a final picking area set; Step S288: re-dividing the picking area that needs to be divided twice based on contour line analysis based on the fused picking area digital twin model to obtain a set of twice-divided picking areas; Step S289: Intelligently fuse the boundaries and assign identifiers to the orchard planting area outline map based on the final picking area set and the secondary division picking area set to obtain the orchard picking area division map and the orchard collection area ID list.

5. The optimization scheduling method based on physical ID drive and digital twin model according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Count the types of fruits planted in the detailed data of the fruit farm planting area to obtain data on the types of fruits planted in the fruit farm; Step S32: Automatically encode the data of fruit species planted in the orchard to obtain an ID list of fruits planted in the orchard; Step S33: collecting the maturity period data of the fruit species planted in the orchard to obtain a distribution table of the maturity periods of the fruit species; Step S34: Intelligently integrate and index the fruit species data, the fruit ID list and the fruit species maturity period distribution table to obtain a fruit species list; Step S35: displaying the ID list of fruits grown in the orchard to the user through a preset interactive picking decision interface for picking type selection, and recording the user's selection in real time to obtain the ID list of fruits to be picked; Step S36: Based on the list of planted fruit species, intelligent retrieval and list generation are performed according to the list of to-be-picked fruit IDs to obtain a list of to-be-picked fruit species.

6. The optimization scheduling method based on physical ID drive and digital twin model according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: Collecting information about the pickers in the target orchard to obtain a data set of identity information about the pickers; Step S42: color-coding and labeling the fruit field picking area division map according to the list of fruit types to be picked, to obtain a labeled fruit field picking area map, wherein the labeled fruit field picking area map includes a plurality of picking areas, and extracting the picking area IDs from the fruit field collection area ID list according to the labeled fruit field picking area map to obtain a picking area ID list; Step S43: determining the demand for picking personnel in the area to be picked based on the marked area map of the fruit field to be picked, and obtaining the personnel demand data of the area to be picked; Step S44: extracting three-dimensional features of the to-be-picked area from the digital twin model of the fruit field according to the labeled to-be-picked area map of the fruit field, obtaining a terrain feature model of the to-be-picked area, and performing terrain complexity analysis on the to-be-picked area based on the terrain feature model of the to-be-picked area to obtain a regional terrain complexity assessment result; Step S45: If the regional terrain complexity assessment result shows that the area to be picked is a high-complexity terrain, the age range of high-difficulty pickers in the area to be picked is determined to obtain the age range of pickers; Step S46: If the regional terrain complexity assessment result shows that the area to be picked is of low-complexity terrain, it is not necessary to determine the age range of pickers in the area to be picked; Step S47: Based on the pickers' identity data set and the ID list of the area to be picked, pickers are allocated to the area to be picked according to the personnel demand data of the area to be picked and the age range of the pickers, or according to the personnel demand data of the area to be picked, to obtain an intelligent allocation plan for pickers.

7. The optimization scheduling method based on physical ID drive and digital twin model according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: Collecting the transport vehicle data of the target fruit farm to obtain a transport vehicle original data set; Step S52: generating a unique identification code for the transport vehicle based on the original data set of the transport vehicle, and constructing an intelligent database to obtain an intelligent database of the transport vehicle in the fruit farm; Step S53: obtaining a map of the fruit field's to-be-picked areas and a list of to-be-picked area IDs; Step S54: estimating the fruit yield of the to-be-picked area based on the marked to-be-picked area map of the fruit field, and obtaining estimated yield data of the to-be-picked area; Step S55: Based on the orchard transport vehicle intelligent database and according to the marked orchard area map, the area to be picked ID list, the estimated yield data of the area to be picked, the orchard path network map and the orchard path ID list, the transport task of the transport vehicle is planned for the target orchard to obtain an intelligent transport vehicle scheduling plan.

8. The optimization scheduling method based on physical ID drive and digital twin model according to claim 7 is characterized in that: Step S55 The following steps are involved: Step S551: extracting the minimum passage width of the transport vehicles based on the intelligent database of the transport vehicles in the fruit farm to obtain the minimum passage width of the transport vehicles; Step S552: Path screening is performed on the fruit field path network diagram according to the minimum pass width of the transport vehicle to obtain a vehicle passable path network diagram, and spatial superposition is performed on the marked fruit field to-be-picked area diagram and the vehicle passable path network diagram to obtain a first fused to-be-picked area path diagram; Step S553: ​​Collect the geographic coordinates of the target orchard camp to obtain geographic coordinate data of the orchard camp, and search for the shortest path of the to-be-picked area based on the first fused path map of the to-be-picked area and the orchard path ID list according to the geographic coordinate data of the orchard camp to obtain the first shortest path ID data; Step S554: performing a road bearing capacity analysis on the path corresponding to the first shortest path ID data to obtain the shortest transport path bearing capacity data; Step S555: Calculate the maximum transport load of the corresponding path according to the shortest transport path carrying capacity data to obtain the maximum transport load data of the path; Step S556: Based on the fruit farm transport vehicle intelligent database and the fruit farm path ID list, the vehicle selection for the to-be-picked area is performed based on multi-objective optimization according to the path maximum transport load data and the estimated yield data of the to-be-picked area, and the optimal transport vehicle ID data is obtained; Step S557: extracting the vehicle load-bearing range based on the optimal transport vehicle ID data based on the intelligent database of the transport vehicle of the fruit farm, and obtaining the load-bearing range interval of the transport vehicle; Step S558: Estimating the number of transports according to the load-bearing range of the transport vehicle and the estimated yield data of the area to be picked, and calculating the one-way transport time, to obtain the estimated number of transports and one-way transport time data of the transport vehicle; Step S559: Generate an intelligent dispatching plan for the picking area ID list, the first shortest path ID data, the optimal transport vehicle ID data, the estimated transport times and one-way transport duration data of the transport vehicle to obtain an intelligent transport vehicle dispatching plan.

9. The optimization scheduling method based on physical ID drive and digital twin model according to claim 1 is characterized in that: Step S6 includes the following steps: Step S61: Obtaining a map of the fruit field to be picked and geographic coordinate data of the fruit field campsite; Step S62: spatially superimposing the fruit farm path network diagram, the annotated fruit farm area to be picked map and the fruit farm camp geographic coordinate data to obtain a second fused area to be picked path map; Step S63: searching for the shortest accessible path between the campsite and the area to be picked based on the second fused path map of the area to be picked and the orchard path ID list to obtain second shortest path ID data; Step S64: If the second shortest path ID data is consistent with the first shortest path ID data in the intelligent transport vehicle scheduling plan, taking the intelligent transport vehicle is used as the pickers' passage mode, and a pickers' passage plan is obtained; Step S65: If the second shortest path ID data is inconsistent with the first shortest path ID data in the intelligent transport vehicle scheduling solution, the walking time of the pickers is estimated based on the second fused path map of the area to be picked and the second shortest path ID data to obtain the walking time estimation data of the pickers; Step S66: If the estimated walking time of the pickers is less than the one-way transportation time in the intelligent transport vehicle scheduling plan, the path corresponding to the second shortest path ID data is used as the walking path for the pickers, and walking is used as the pickers' travel mode to obtain the pickers' travel plan; otherwise, taking the intelligent transport vehicle is used as the pickers' travel mode to obtain the pickers' travel plan; Step S67: performing collaborative picking and transportation operations according to the intelligent allocation plan for pickers, the intelligent transportation vehicle scheduling plan, and the pickers' passage plan.

Images