A visual management system and method for logistics parks based on digital twins

Abstract

The present application provides a logistics park visualization management system and method based on digital twins, which relates to the field of visualization management technology, and obtains a real-time operation data mapping set in the logistics park; performs relative variation measurement on the real-time operation data mapping set to obtain physical relative variation and virtual relative variation, and converts the real-time operation data mapping set into a twin driving domain during the operation of the logistics park based on the physical relative variation and the virtual relative variation; obtains a digital twin model of the logistics park, and performs logistics behavior prediction based on the digital twin model and the twin driving domain to obtain dynamic characteristics of logistics behavior prediction during the operation of the logistics park; and dynamically displays the operation process of the logistics park in the visualization display layer based on the dynamic characteristics of logistics behavior prediction. The present application can improve the accuracy of the prediction of logistics behavior during the operation of the logistics park, so as to improve the accuracy of the visualization of the logistics park.

Description

Technical Field

[0001] The present application relates to the field of visual management technology. More specifically, the present application relates to a digital twin-based logistics park visual management system and method. Background Art

[0002] Digital twin-based logistics park visualization management refers to a new intelligent management model that achieves real-time monitoring, predictive analysis, and visualization of the operational status of people, vehicles, cargo, and equipment within the park by building a virtual model that is highly consistent with the actual logistics park, integrating physical layer perception data, business layer operational information, and intelligent decision-making logic. This improves the park's operational efficiency, safety, and scientific decision-making. Its core lies in the construction of a digital twin. That is, through three-dimensional modeling, data-driven, behavioral modeling, and feedback mechanisms, elements such as the structural layout, transportation routes, operational processes, and resource allocation of the real park are mapped into the virtual space. The model is continuously driven by real-time IoT data, enabling the coordinated operation and mutual mapping of virtual and real systems, thereby achieving comprehensive, dynamic, and precise control of the logistics process.

[0003] However, existing technologies often face frequent changes in logistics operations, placing extremely high demands on system response speed and synchronization accuracy. Furthermore, factors such as sensor errors, data latency, and network congestion can cause the twin scenarios to deviate from the real-world scenarios, impacting decision reliability. Furthermore, behavior prediction algorithms rely on large amounts of high-quality historical data and prior knowledge. However, in real-world scenarios, especially in new, rapidly changing industrial parks, there may be a lack of sufficient samples or frequent rule changes, resulting in low prediction accuracy and insufficient generalization capabilities. Therefore, improving the accuracy of logistics behavior predictions during logistics park operations, and thereby enhancing the accuracy of logistics park visualization, is a challenge facing the industry. Summary of the Invention

[0004] This application provides a logistics park visualization management system and method based on digital twins, which can improve the accuracy of predicting logistics behavior during the operation of the logistics park, thereby improving the accuracy of logistics park visualization.

[0005] In a first aspect, the present application provides a logistics park visualization management method based on digital twins, the management method comprising the following steps:

[0006] Monitor the operation process of the logistics park in real time, and dynamically simulate the real-time operation data in the virtual model to obtain the real-time operation data mapping set in the logistics park;

[0007] Relative variation measurement is performed on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set respectively, thereby obtaining a physical relative variation degree and a virtual relative variation degree, and the real-time operation data mapping set is converted into a twin driving domain in the operation process of the logistics park according to the physical relative variation degree and the virtual relative variation degree;

[0008] Obtaining a digital twin model of the logistics park, performing logistics behavior prediction based on the digital twin model and the twin driving domain, and obtaining dynamic characteristics of logistics behavior prediction during the operation of the logistics park;

[0009] The working process of the logistics park is dynamically displayed on the visual display layer according to the dynamic characteristics of the logistics behavior prediction.

[0010] In this embodiment, the operation process of the logistics park is monitored in real time through the sensor equipment and monitoring equipment deployed in the logistics park.

[0011] In this embodiment, the real-time monitored physical real-time operation data is dynamically simulated in the virtual model, thereby obtaining a real-time operation data mapping set in the logistics park, specifically including:

[0012] The real-time monitored physical operation data is transmitted to the virtual model based on the data transmission protocol;

[0013] The virtual model uses a simulation engine to dynamically simulate the physical real-time operation data to obtain virtual real-time operation data corresponding to the physical real-time operation data;

[0014] A real-time operation data mapping set in the logistics park is constructed according to the physical real-time operation data and the virtual real-time operation data.

[0015] In this embodiment, the physical real-time operating data and the virtual real-time operating data in the real-time operating data mapping set are standardized respectively.

[0016] In this embodiment, relative variation measurement is performed on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set, thereby obtaining the physical relative variation and the virtual relative variation, which specifically include:

[0017] Get the relative control coefficient;

[0018] For the physical real-time operation data in the real-time operation data mapping set, determining a physical data contribution value of each physical operation point in the physical real-time operation data;

[0019] Performing variation measurement on the physical real-time operation data according to all physical data contribution values ​​and the relative control coefficient, thereby obtaining a physical relative variation;

[0020] For the virtual real-time operating data in the real-time operating data mapping set, determining a virtual data contribution value of each virtual operating point in the virtual real-time operating data;

[0021] The virtual real-time operation data is subjected to variation measurement according to all virtual data contribution values ​​and the relative control coefficient, thereby obtaining a virtual relative variation.

[0022] In this embodiment, converting the real-time operation data mapping set into a twin driving domain in the operation process of the logistics park according to the physical relative variability and the virtual relative variability specifically includes:

[0023] determining a physical twin coefficient and a virtual twin coefficient based on the physical relative variability and the virtual relative variability;

[0024] For each operating point in the real-time operating data mapping set, obtaining a physical real-time operating data value and a virtual real-time operating data value corresponding to the operating point;

[0025] Determining the twin drive data corresponding to the operating point according to the physical twin coefficient, the virtual twin coefficient, the physical real-time operating data value, and the virtual real-time operating data value, thereby obtaining the twin drive data corresponding to each operating point in the real-time operating data mapping set;

[0026] The twin drive domain during the operation of the logistics park is constructed through the twin drive data corresponding to all operating points.

[0027] In this embodiment, obtaining the digital twin model of the logistics park specifically includes:

[0028] Obtain BIM model and GIS data of the logistics park;

[0029] A digital twin model of the logistics park is constructed using a three-dimensional modeling tool based on the BIM model and the GIS data.

[0030] In this embodiment, logistics behavior prediction based on the digital twin model and the twin drive domain is to input the twin drive domain as input data into the digital twin model to perform logistics behavior prediction, and then obtain the dynamic characteristics of logistics behavior prediction during the operation of the logistics park.

[0031] In this embodiment, dynamically displaying the operation process of the logistics park on the visualization display layer according to the dynamic characteristics of the logistics behavior prediction specifically includes:

[0032] Generate a spatiotemporal behavior event flow during the operation of the logistics park based on the dynamic characteristics of the logistics behavior prediction;

[0033] The spatiotemporal behavior event stream is mapped to the digital twin model in the digital twin platform, and then the spatiotemporal behavior event stream is dynamically presented in the visualization display layer through the visualization engine of the digital twin model.

[0034] In a second aspect, the present application provides a logistics park visualization management system based on digital twins, which is used to implement a logistics park visualization management method based on digital twins. The management system includes:

[0035] The dynamic simulation module is used to monitor the operation process of the logistics park in real time and dynamically simulate the real-time monitored physical operation data in the virtual model to obtain the real-time operation data mapping set in the logistics park;

[0036] A twin drive module is used to measure the relative variation of the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set, thereby obtaining a physical relative variation and a virtual relative variation, and convert the real-time operation data mapping set into a twin drive domain in the operation process of the logistics park based on the physical relative variation and the virtual relative variation;

[0037] A dynamic prediction module is used to obtain a digital twin model of the logistics park, perform logistics behavior prediction based on the digital twin model and the twin driving domain, and obtain dynamic characteristics of logistics behavior prediction during the operation of the logistics park;

[0038] The dynamic display module is used to dynamically display the working process of the logistics park in the visual display layer according to the dynamic characteristics of the logistics behavior prediction.

[0039] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0040] By monitoring the working operation process of the logistics park in real time and dynamically simulating the real-time monitored physical real-time operation data in a virtual model, a real-time operation data mapping set in the logistics park is obtained; relative variation measurement is performed on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set respectively, and physical relative variation and virtual relative variation are obtained, and the real-time operation data mapping set is converted into a twin driving domain in the working operation process of the logistics park according to the physical relative variation and the virtual relative variation; a digital twin model of the logistics park is obtained, and logistics behavior prediction is performed based on the digital twin model and the twin driving domain to obtain the dynamic characteristics of logistics behavior prediction in the working operation process of the logistics park; the working operation process of the logistics park is dynamically displayed in the visualization display layer according to the dynamic characteristics of logistics behavior prediction.

[0041] It can be seen that in this application, first, the working operation process of the logistics park is monitored in real time, and the physical real-time operation data is dynamically mapped to the virtual model, which not only realizes the synchronous interaction between the physical and digital spaces, but also accurately reflects the actual situation on site through real-time simulation, forming a high-precision real-time operation data mapping set; then, the physical real-time operation data and the virtual real-time operation data in the logistics park are measured for relative variation, and then the physical relative variation and the virtual relative variation are obtained, and a twin driving domain is constructed based on this, which can effectively integrate the operating status of the real physical system and the predictive ability of the virtual simulation model. The physical relative variation and the virtual relative variation can dynamically identify the logistics park. The fluctuation intensity and sensitivity of various operating data in the zone can be determined, so as to determine the weighted contribution of the physical system and the virtual system to the current state, and realize the construction of driving data that is closer to reality and more predictive. Secondly, the digital twin model of the logistics park is combined with the twin driving domain to predict logistics behavior, which can significantly improve the accuracy of the perception and prediction of the operating status of the logistics park, so that the visualization display is not limited to static presentation, but also more forward-looking and intelligent. Finally, according to the dynamic characteristics of logistics behavior prediction, the working operation process of the logistics park is dynamically displayed in the visualization layer, which can realize the intuitive and real-time presentation of the future logistics status, thereby improving the timeliness and accuracy of visualization.

[0042] In summary, the technical solution adopted in this application can improve the accuracy of prediction of logistics behavior during the operation of the logistics park, so as to improve the accuracy of logistics park visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 This is a flowchart of a digital twin-based logistics park visualization management method provided in this application;

[0045] Figure 2 It is a schematic diagram of the process of determining the twin driving domain in the operation process of the logistics park provided by this application;

[0046] Figure 3 This is a module structure diagram of a logistics park visualization management system based on digital twins provided in this application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] The embodiment of the present application provides a logistics park visualization management system and method based on digital twins, the core of which is to monitor the working operation process of the logistics park in real time, and dynamically simulate the physical real-time operation data monitored in real time in a virtual model, thereby obtaining a real-time operation data mapping set in the logistics park; respectively perform relative variation measurement on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set, thereby obtaining a physical relative variation degree and a virtual relative variation degree, and convert the real-time operation data mapping set into a twin driving domain in the working operation process of the logistics park based on the physical relative variation degree and the virtual relative variation degree; obtain a digital twin model of the logistics park, and predict logistics behavior based on the digital twin model and the twin driving domain to obtain dynamic characteristics of logistics behavior prediction in the working operation process of the logistics park; dynamically display the working operation process of the logistics park in the visualization display layer based on the dynamic characteristics of logistics behavior prediction. The above scheme can improve the accuracy of the prediction of logistics behavior in the working process of the logistics park, so as to improve the accuracy of the visualization of the logistics park.

[0049] Example 1: In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG, this figure is an exemplary flow chart of a logistics park visualization management method based on digital twin according to this embodiment of the present application, and the management method includes the following steps:

[0050] In step S1, the operation process of the logistics park is monitored in real time, and the real-time monitored physical real-time operation data is dynamically simulated in the virtual model to obtain a real-time operation data mapping set in the logistics park.

[0051] In specific implementation, the working process of the logistics park is monitored in real time through the sensor equipment and monitoring equipment deployed in the logistics park. It should be noted that through the sensor equipment and monitoring equipment deployed in the logistics park, real-time and all-round monitoring of the working process of the park can be achieved, providing basic support for subsequent digital twin drive, visual management and intelligent scheduling; the sensor equipment and monitoring equipment used in this application mainly include positioning and motion tracking equipment, operation behavior recognition equipment, video monitoring and image recognition equipment, environmental and safety monitoring sensors, etc., which will not be repeated here.

[0052] In this embodiment, the real-time monitored physical real-time operation data is dynamically simulated in the virtual model to obtain the real-time operation data mapping set in the logistics park. Specifically, the following methods can be used, namely:

[0053] The real-time monitored physical operation data is transmitted to the virtual model based on the data transmission protocol;

[0054] The virtual model uses a simulation engine to dynamically simulate the physical real-time operation data to obtain virtual real-time operation data corresponding to the physical real-time operation data;

[0055] A real-time operation data mapping set in the logistics park is constructed according to the physical real-time operation data and the virtual real-time operation data.

[0056] In specific implementation, first, the real-time monitored physical real-time operation data can be transmitted to the virtual model based on the data transmission protocol. It should be noted that the data transmission protocol selected in this application is the MQTT protocol. Other data transmission protocols can also be selected in actual implementation, which is not limited here; then, the virtual model can use a simulation engine to dynamically simulate the physical real-time operation data, that is, after receiving the physical real-time operation data, it will use the simulation engine embedded in the virtual model to perform dynamic simulation, so as to generate virtual real-time operation data corresponding to the physical real-time operation data; finally, a real-time operation data mapping set in the logistics park can be constructed based on the physical real-time operation data and the virtual real-time operation data, that is, the data set composed of the physical real-time operation data and the virtual real-time operation data is combined as the real-time operation data mapping set in the logistics park.

[0057] In addition, in this embodiment, the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set may be standardized respectively. It should be noted that the standardization process can eliminate heterogeneous differences and enhance comparability and consistency.

[0058] It's important to note that real-time monitoring of the logistics park's operational processes and the dynamic mapping of real-time physical operational data into the virtual model not only achieves the simultaneous interaction between physical and digital spaces, but also accurately reflects actual on-site conditions through real-time simulation, forming a highly accurate real-time operational data mapping set. This tightly coupled data feedback mechanism significantly improves the data quality and timeliness of the logistics behavior prediction model, making the predictions more closely aligned with actual operational trends, thereby enhancing the dynamic responsiveness and accuracy of the logistics park's visualization.

[0059] In step S2, relative variation measurement is performed on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set respectively, thereby obtaining the physical relative variation and the virtual relative variation. Based on the physical relative variation and the virtual relative variation, the real-time operation data mapping set is converted into a twin driving domain in the operation process of the logistics park.

[0060] In this embodiment, relative variation measurement is performed on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set, and the physical relative variation and the virtual relative variation are obtained in the following manner, namely:

[0061] Get the relative control coefficient;

[0062] For the physical real-time operation data in the real-time operation data mapping set, determining a physical data contribution value of each physical operation point in the physical real-time operation data;

[0063] Performing variation measurement on the physical real-time operation data according to all physical data contribution values ​​and the relative control coefficient, thereby obtaining a physical relative variation;

[0064] For the virtual real-time operating data in the real-time operating data mapping set, determining a virtual data contribution value of each virtual operating point in the virtual real-time operating data;

[0065] The virtual real-time operation data is subjected to variation measurement according to all virtual data contribution values ​​and the relative control coefficient, thereby obtaining a virtual relative variation.

[0066] In specific implementation, first, it should be noted that the relative control coefficient in this application is a coefficient used to control the value and accuracy of the relative variability. The total number of operating points in the real-time operation data mapping set can be determined, and the reciprocal of the natural logarithm of the total number of operating points can be used as the relative control coefficient. Then, for the physical real-time operation data in the real-time operation data mapping set, the physical data contribution value of each physical operation point in the physical real-time operation data can be determined, wherein the data collection point in the physical real-time operation data can be used as the physical operation point. The physical data contribution value represents the degree of information contribution of the physical operation point in the overall data. The ratio of the physical real-time operation data value of the physical operation point to the sum of all physical real-time operation data values ​​in the physical real-time operation data can be used as the physical data contribution value of the physical operation point. The physical data contribution value of each physical operation point in the physical real-time operation data can be obtained in the above manner. Secondly, the variation of the physical real-time operation data can be measured according to all physical data contribution values ​​and the relative control coefficient to obtain the physical relative variability, wherein the physical relative variability represents the relative abnormality of the overall fluctuation of the physical real-time operation data. In actual implementation, the physical relative variability can be determined by the following formula:

[0067]

[0068] in, Represents the physical relative variability, represents the relative control coefficient, m represents the total number of physical operating points in the physical real-time operation data, Represents the physical data contribution value of the i-th physical operating point in the physical real-time operating data.

[0069] In addition, in a specific implementation, for the virtual real-time operation data in the real-time operation data mapping set, a virtual data contribution value of each virtual operation point in the virtual real-time operation data can be determined, wherein the data collection point in the virtual real-time operation data can be used as the virtual operation point, and the virtual data contribution value represents the degree of information contribution of the virtual operation point in the overall data. The ratio of the virtual real-time operation data value of the virtual operation point to the sum of all virtual real-time operation data values ​​in the virtual real-time operation data can be used as the virtual data contribution value of the virtual operation point. The virtual data contribution value of each virtual operation point in the virtual real-time operation data can be obtained through the above method; then, the variation of the virtual real-time operation data can be measured based on all virtual data contribution values ​​and the relative control coefficient to obtain a virtual relative variation degree, wherein the virtual relative variation degree represents the relative abnormality degree of the overall fluctuation of the virtual real-time operation data. In actual implementation, the virtual relative variation degree can be determined by the following formula:

[0070]

[0071] in, represents the virtual relative variability, represents the relative control coefficient, n represents the total number of virtual operating points in the virtual real-time operating data, It represents the virtual data contribution value of the jth virtual operating point in the virtual real-time operating data.

[0072] It should be noted that in this application, the physical real-time operation data and the virtual real-time operation data have a corresponding relationship, so the amount of data contained in the physical real-time operation data and the virtual real-time operation data is the same, and in the real-time operation data mapping set, each operation point corresponds to a physical real-time operation data value and a virtual real-time operation data value.

[0073] Preferably, in this embodiment, the real-time operation data mapping set is converted into a twin drive domain in the operation process of the logistics park according to the physical relative variability and the virtual relative variability, and the reference Figure 2 As shown in FIG, this figure is a schematic diagram of the process of determining the twin drive domain during the operation of the logistics park in some embodiments of the present application. In this embodiment, determining the twin drive domain during the operation of the logistics park can be achieved by using the following steps:

[0074] In step S21, a physical twin coefficient and a virtual twin coefficient are determined based on the physical relative variability and the virtual relative variability;

[0075] In step S22, for each operating point in the real-time operating data mapping set, a physical real-time operating data value and a virtual real-time operating data value corresponding to the operating point are obtained;

[0076] In step S23, the twin drive data corresponding to the operating point is determined according to the physical twin coefficient, the virtual twin coefficient, the physical real-time operating data value, and the virtual real-time operating data value, thereby obtaining the twin drive data corresponding to each operating point in the real-time operating data mapping set;

[0077] In step S24, the twin drive domain during the operation of the logistics park is constructed through the twin drive data corresponding to all operating points.

[0078] In specific implementation, first, the physical twin coefficient and the virtual twin coefficient can be determined based on the physical relative variability and the virtual relative variability, wherein the physical twin coefficient represents the driving proportion of the physical real-time operation data in the data twin, and the virtual twin coefficient represents the driving proportion of the virtual real-time operation data in the data twin. The sum of the physical relative variability and the virtual relative variability can be calculated, and the ratio of the physical relative variability to the calculation result can be used as the physical twin coefficient, and the ratio of the virtual relative variability to the calculation result can be used as the virtual twin coefficient; then, for each operation point in the real-time operation data mapping set, the physical real-time operation data value and the virtual real-time operation data value corresponding to the operation point can be obtained; secondly, the operation point can be determined based on the physical twin coefficient, the virtual twin coefficient, the physical real-time operation data value and the virtual real-time operation data value. The twin drive data corresponding to the point, that is, the product of the physical twin coefficient and the physical real-time operation data value can be calculated, and the product of the virtual twin coefficient and the virtual real-time operation data value can be calculated, and the sum of the two calculation results is used as the twin drive data corresponding to the operation point. The above method can be used to obtain the twin drive data corresponding to each operation point in the real-time operation data mapping set; finally, the twin drive domain during the operation of the logistics park can be constructed through the twin drive data corresponding to all operation points, that is, the data set composed of the twin drive data corresponding to all operation points is collected as the twin drive domain during the operation of the logistics park. Among them, the twin drive domain can directly guide the site on the one hand, and on the other hand, it can be imported into the digital twin model for feasibility simulation analysis of decision-making, and finally provide data support for the visual management of the logistics park.

[0079] It should be noted that by measuring the relative variation of the physical real-time operation data and the virtual real-time operation data in the logistics park respectively, and then obtaining the physical relative variation and the virtual relative variation, and constructing the twin driving domain based on this, it can effectively integrate the operating status of the real physical system and the predictive ability of the virtual simulation model. The physical relative variation and the virtual relative variation can dynamically identify the fluctuation intensity and sensitivity of various operating data in the logistics park, thereby determining the weight contribution of the physical system and the virtual system to the current state, and realizing a driving data construction that is closer to reality and more predictive.

[0080] In step S3, a digital twin model of the logistics park is obtained, and logistics behavior prediction is performed based on the digital twin model and the twin driving domain to obtain dynamic characteristics of logistics behavior prediction during the operation of the logistics park.

[0081] In this embodiment, the digital twin model of the logistics park can be obtained in the following ways:

[0082] Obtain BIM model and GIS data of the logistics park;

[0083] A digital twin model of the logistics park is constructed using a three-dimensional modeling tool based on the BIM model and the GIS data.

[0084] In specific implementation, first, the BIM model and GIS data of the logistics park can be obtained. The BIM (Building Information Modeling) model is mainly used to describe the three-dimensional structural information of the logistics park, such as the internal building structure, facility layout, equipment installation location, and pipeline routing. The BIM model is usually derived from architectural design data during the park construction planning phase or reverse-generated from existing facilities through laser scanning and modeling tools (such as Revit and Navisworks). GIS (Geographic Information System) data is used to describe the park's geographical environment, including topography, road network, surrounding transportation resources, regional climate, land use, and other information. GIS data can be obtained from the National Geographic Information Platform, urban planning systems, or commercial map APIs. Then, based on the BIM model and GIS data, a digital twin model of the logistics park can be constructed using 3D modeling tools. That is, using 3D modeling tools (such as Unity3D, Unreal Engine, Bentley OpenCities Planner, Cesium, etc.), the GIS data and BIM model are spatially aligned and integrated, and the digital environment of the logistics park is reconstructed in a unified 3D coordinate system, thereby generating a digital twin model of the logistics park.

[0085] In this embodiment, logistics behavior prediction based on the digital twin model and the twin drive domain is to input the twin drive domain as input data into the digital twin model to perform logistics behavior prediction, and then obtain the dynamic characteristics of logistics behavior prediction during the operation of the logistics park.

[0086] In specific implementation, first, the twin driving domain can be input as input data into the pre-built digital twin model. The digital twin model integrates the park space topology, equipment rules, operation logic and scheduling constraints. With the help of the simulation engine in the digital twin model (such as discrete event simulation, multi-agent simulation, etc.), the logistics behavior evolution process in the future period can be predicted based on the current twin driving domain, including task flow, equipment scheduling path, personnel distribution, resource occupancy changes, etc.; then, during the simulation process, the dynamic changes of various key indicators over time can be recorded in real time, such as material circulation speed, operation efficiency changes, potential congestion nodes, abnormal task warning probability, etc. These features can be used as dynamic features for logistics behavior prediction, which can be used for subsequent prediction optimization, risk assessment or dynamic visualization.

[0087] It should be noted that combining the digital twin model of a logistics park with the twin drive domain to predict logistics behavior can significantly improve the accuracy of the perception and prediction of the logistics park's operating status. The digital twin model creates a highly realistic model of the park's spatial structure, resource allocation, and operational processes. The twin drive domain is then used as input to drive the model, enabling accurate reproduction of the park's current state and dynamic evolutionary prediction of future behavioral trends. During this process, the system can capture subtle data variations and potential behavioral patterns, extracting key dynamic features for predicting logistics behavior, such as task load fluctuations, resource bottlenecks, and congestion risk areas, providing timely and high-precision predictive support for park operations. This not only improves the accuracy of logistics behavior predictions but also provides real, updateable, and interactive dynamic data support for the visualization system, making visualizations more forward-looking and intelligent rather than limited to static presentations.

[0088] In step S4, the operation process of the logistics park is dynamically displayed on the visualization display layer according to the dynamic characteristics of the logistics behavior prediction.

[0089] In this embodiment, the following methods can be used to dynamically display the operation process of the logistics park in the visualization display layer based on the dynamic characteristics of the logistics behavior prediction, namely:

[0090] Generate a spatiotemporal behavior event flow during the operation of the logistics park based on the dynamic characteristics of the logistics behavior prediction;

[0091] The spatiotemporal behavior event stream is mapped to the digital twin model in the digital twin platform, and then the spatiotemporal behavior event stream is dynamically presented in the visualization display layer through the visualization engine of the digital twin model.

[0092] In the specific implementation, first, the spatiotemporal behavior event stream of the logistics park can be generated based on the dynamic characteristics of logistics behavior prediction. It should be noted that the dynamic characteristics of logistics behavior prediction include such contents as material movement trajectory, equipment operation status changes, personnel operation distribution evolution, resource occupation trend, potential risk warning, etc. Therefore, through time series modeling and spatial labeling technology, the dynamic characteristics of logistics behavior prediction are organized into a series of behavior event streams with timestamps and spatial location labels. It is possible to construct a digital behavior trajectory that reflects the changes in the operation status of the park in the future, that is, the spatiotemporal behavior event stream during the operation of the logistics park; then, the spatiotemporal behavior event can be The document flow is mapped to the digital twin model in the digital twin platform. Each event in the spatiotemporal behavior event flow will be bound one-to-one with the corresponding entity in the digital twin model (such as trucks, warehouses, yards, forklifts, personnel, etc.), and these virtual objects will be driven to respond dynamically according to the predicted path and behavior state evolution logic; finally, through the visualization engine integrated in the digital twin model, such as using a three-dimensional graphics rendering engine (such as Unity3D, CesiumJS, etc.), the mapped spatiotemporal behavior event flow will be presented in real time in the visualization display layer in various forms such as dynamic graphics, color coding, heat maps, streamline animation, status panels, etc.

[0093] It's important to note that the dynamic display of logistics park operations at the visualization layer, based on the dynamic characteristics of logistics behavior prediction, provides an intuitive, real-time overview of future logistics status. This allows managers to not only see the current operational status but also foresee potential trends and risk points. This dynamic display visualizes complex spatiotemporal behavioral events, enhancing data comprehensibility and interactivity, helping to quickly identify anomalies, optimize resource scheduling, and adjust operational processes. By closely integrating the dynamic characteristics of prediction, the visualization improves both timeliness and accuracy.

[0094] It can be seen that in this application, first, the working operation process of the logistics park is monitored in real time, and the physical real-time operation data is dynamically mapped to the virtual model, which not only realizes the synchronous interaction between the physical and digital spaces, but also accurately reflects the actual situation on site through real-time simulation, forming a high-precision real-time operation data mapping set; then, the physical real-time operation data and the virtual real-time operation data in the logistics park are measured for relative variation, and then the physical relative variation and the virtual relative variation are obtained, and a twin driving domain is constructed based on this, which can effectively integrate the operating status of the real physical system and the predictive ability of the virtual simulation model. The physical relative variation and the virtual relative variation can dynamically identify the logistics park. The fluctuation intensity and sensitivity of various operating data in the zone can be determined, so as to determine the weighted contribution of the physical system and the virtual system to the current state, and realize the construction of driving data that is closer to reality and more predictive. Secondly, the digital twin model of the logistics park is combined with the twin driving domain to predict logistics behavior, which can significantly improve the accuracy of the perception and prediction of the operating status of the logistics park, so that the visualization display is not limited to static presentation, but also more forward-looking and intelligent. Finally, according to the dynamic characteristics of logistics behavior prediction, the working operation process of the logistics park is dynamically displayed in the visualization layer, which can realize the intuitive and real-time presentation of the future logistics status, thereby improving the timeliness and accuracy of visualization.

[0095] In summary, the technical solution adopted in this application can improve the accuracy of prediction of logistics behavior during the operation of the logistics park, so as to improve the accuracy of logistics park visualization.

[0096] In the second embodiment, this application provides a digital twin-based logistics park visualization management system. Figure 3 As shown in FIG, this figure is a schematic diagram of a logistics park visualization management system based on digital twin according to this embodiment of the present application, and the management system includes:

[0097] The dynamic simulation module 100 is used to monitor the operation process of the logistics park in real time and dynamically simulate the real-time monitored physical operation data in the virtual model to obtain a real-time operation data mapping set in the logistics park;

[0098] The twin drive module 200 is used to measure the relative variation of the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set, thereby obtaining the physical relative variation and the virtual relative variation, and convert the real-time operation data mapping set into a twin drive domain during the operation of the logistics park based on the physical relative variation and the virtual relative variation;

[0099] A dynamic prediction module 300 is used to obtain a digital twin model of the logistics park, perform logistics behavior prediction based on the digital twin model and the twin driving domain, and obtain dynamic characteristics of logistics behavior prediction during the operation of the logistics park;

[0100] The dynamic display module 400 is used to dynamically display the working process of the logistics park in the visual display layer according to the dynamic characteristics of the logistics behavior prediction.

[0101] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, including 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 electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, or magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0103] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. A visual management method for logistics parks based on digital twins, characterized in that: The management method comprises the following steps: Monitor the operation process of the logistics park in real time, and dynamically simulate the real-time operation data in the virtual model to obtain the real-time operation data mapping set in the logistics park; Relative variation measurement is performed on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set respectively, thereby obtaining a physical relative variation degree and a virtual relative variation degree, and the real-time operation data mapping set is converted into a twin driving domain in the operation process of the logistics park according to the physical relative variation degree and the virtual relative variation degree; Obtaining a digital twin model of the logistics park, performing logistics behavior prediction based on the digital twin model and the twin driving domain, and obtaining dynamic characteristics of logistics behavior prediction during the operation of the logistics park; Dynamically display the operation process of the logistics park in the visual display layer according to the dynamic characteristics of the logistics behavior prediction; The relative variation measurement is performed on the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set respectively, and the physical relative variation and the virtual relative variation are obtained. Specifically, the measurement includes: Get the relative control coefficient; For the physical real-time operation data in the real-time operation data mapping set, determining a physical data contribution value of each physical operation point in the physical real-time operation data; Performing variation measurement on the physical real-time operation data according to all physical data contribution values ​​and the relative control coefficient, thereby obtaining a physical relative variation; For the virtual real-time operating data in the real-time operating data mapping set, determining a virtual data contribution value of each virtual operating point in the virtual real-time operating data; The virtual real-time operation data is subjected to variation measurement according to all virtual data contribution values ​​and the relative control coefficient, thereby obtaining a virtual relative variation.

2. A digital twin-based logistics park visualization management method according to claim 1, characterized in that: The operation process of the logistics park is monitored in real time through the sensor equipment and monitoring equipment deployed in the logistics park.

3. A digital twin-based logistics park visualization management method according to claim 1, characterized in that: The real-time monitored physical real-time operation data is dynamically simulated in the virtual model, and the real-time operation data mapping set in the logistics park is obtained, which specifically includes: The real-time monitored physical operation data is transmitted to the virtual model based on the data transmission protocol; The virtual model uses a simulation engine to dynamically simulate the physical real-time operation data to obtain virtual real-time operation data corresponding to the physical real-time operation data; A real-time operation data mapping set in the logistics park is constructed according to the physical real-time operation data and the virtual real-time operation data.

4. A method for visual management of a logistics park based on digital twins according to claim 1, characterized in that: The physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set are respectively standardized.

5. A digital twin-based logistics park visualization management method according to claim 1, characterized in that: Converting the real-time operation data mapping set into a twin driving domain in the operation process of the logistics park according to the physical relative variability and the virtual relative variability specifically includes: determining a physical twin coefficient and a virtual twin coefficient based on the physical relative variability and the virtual relative variability; For each operating point in the real-time operating data mapping set, obtaining a physical real-time operating data value and a virtual real-time operating data value corresponding to the operating point; Determining the twin drive data corresponding to the operating point according to the physical twin coefficient, the virtual twin coefficient, the physical real-time operating data value, and the virtual real-time operating data value, thereby obtaining the twin drive data corresponding to each operating point in the real-time operating data mapping set; The twin drive domain during the operation of the logistics park is constructed through the twin drive data corresponding to all operating points.

6. A method for visual management of a logistics park based on digital twins according to claim 1, characterized in that: Obtaining a digital twin model of a logistics park specifically includes: Obtain BIM model and GIS data of the logistics park; A digital twin model of the logistics park is constructed using a three-dimensional modeling tool based on the BIM model and the GIS data.

7. A method for visual management of a logistics park based on digital twins according to claim 1, characterized in that: The logistics behavior prediction based on the digital twin model and the twin drive domain is to input the twin drive domain as input data into the digital twin model to predict the logistics behavior, and then obtain the dynamic characteristics of the logistics behavior prediction during the operation of the logistics park.

8. The method for visual management of a logistics park based on digital twins according to claim 1, characterized in that: The dynamic display of the operation process of the logistics park in the visual display layer based on the dynamic characteristics of the logistics behavior prediction specifically includes: Generate a spatiotemporal behavior event flow during the operation of the logistics park based on the dynamic characteristics of the logistics behavior prediction; The spatiotemporal behavior event stream is mapped to the digital twin model in the digital twin platform, and then the spatiotemporal behavior event stream is dynamically presented in the visualization display layer through the visualization engine of the digital twin model.

9. A digital twin-based logistics park visualization management system, used to implement a digital twin-based logistics park visualization management method according to any one of claims 1 to 8, characterized in that: The management system includes: The dynamic simulation module is used to monitor the operation process of the logistics park in real time and dynamically simulate the real-time monitored physical operation data in the virtual model to obtain the real-time operation data mapping set in the logistics park; A twin drive module is used to measure the relative variation of the physical real-time operation data and the virtual real-time operation data in the real-time operation data mapping set, thereby obtaining a physical relative variation and a virtual relative variation, and convert the real-time operation data mapping set into a twin drive domain in the operation process of the logistics park based on the physical relative variation and the virtual relative variation; A dynamic prediction module is used to obtain a digital twin model of the logistics park, perform logistics behavior prediction based on the digital twin model and the twin driving domain, and obtain dynamic characteristics of logistics behavior prediction during the operation of the logistics park; The dynamic display module is used to dynamically display the working process of the logistics park in the visual display layer according to the dynamic characteristics of the logistics behavior prediction.

Images