Digital twin object processing method and system

Abstract

The embodiment of the present specification provides a digital twin object processing method and system, wherein the digital twin object processing method comprises: determining object configuration data of a target physical object and a digital twin object template corresponding to the target physical object; determining an initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template; and determining a target digital twin object corresponding to the target physical object based on current state data of the target physical object and the initial digital twin object. The generation efficiency of the target digital twin object is improved, thereby avoiding the problem of low efficiency of constructing the digital twin object due to spending a large amount of time on data processing, and thereby quickly constructing the digital twin object for the target physical object.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of computer technology, and in particular to a method and system for processing digital twin objects. Background Technology

[0002] With the continuous development of computer technology, the operation of building digital twin objects for physical entities is involved in many fields. For example, in the smart city scenario, due to the characteristic that data twin technology can build digital twin objects for physical entities in the city, it is also widely used to build city digital twins.

[0003] However, in practical applications, the process of building digital twin objects for physical entities is very time-consuming due to the large amount and complexity of the physical entity's data. This results in low efficiency in building digital twin objects. Therefore, how to quickly build digital twin objects for physical entities has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, embodiments of this specification provide a method for processing digital twin objects. One or more embodiments of this specification also relate to a digital twin object processing apparatus, a digital twin object processing system, a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.

[0005] According to a first aspect of the embodiments of this specification, a method for processing digital twin objects is provided, comprising:

[0006] Determine the object configuration data of the target physical object and the digital twin object template corresponding to the target physical object;

[0007] Based on the object configuration data and the digital twin object template, the initial digital twin object corresponding to the target physical object is determined;

[0008] Based on the current state data of the target physical object and the initial digital twin object, the target digital twin object corresponding to the target physical object is determined.

[0009] According to a second aspect of the embodiments of this specification, a digital twin object processing apparatus is provided, comprising:

[0010] The determination module is configured to determine the object configuration data of the target physical object and the digital twin object template corresponding to the target physical object;

[0011] The initial object determination module is configured to determine the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template.

[0012] The target object determination module is configured to determine the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object.

[0013] According to a third aspect of the embodiments of this specification, a digital twin object processing system is provided, including an object determination node, a data acquisition node, a data fusion node, and an object display node, wherein...

[0014] The object determination node is configured to determine the object configuration data of the target physical object and the digital twin object template corresponding to the target physical object, and to determine the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template.

[0015] The data acquisition node is configured to acquire the current state data of the target physical object;

[0016] The data fusion node is configured to determine the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object;

[0017] The object display node is configured to render the target digital twin object to the object display page of the user terminal, and display the target digital twin object to the user through the object display page of the user terminal.

[0018] According to a fourth aspect of the embodiments of this specification, a computing device is provided, comprising:

[0019] Memory and processor;

[0020] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the above-described digital twin object processing method.

[0021] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the digital twin object processing method described above.

[0022] According to a sixth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the digital twin object processing method described above.

[0023] This specification provides an embodiment of a digital twin object processing method, comprising: determining object configuration data of a target physical object and a digital twin object template corresponding to the target physical object; determining an initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template; and determining a target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object.

[0024] Specifically, this method uses a digital twin object template corresponding to the target physical object to quickly generate an initial digital twin object based on the object configuration data of the target physical object. Then, by using the current state data of the target physical object and the initial digital twin object, the generation efficiency of the target digital twin object is further improved, thereby avoiding the problem of low efficiency in building digital twin objects due to spending a lot of time on data processing, thus quickly building a digital twin object for the target physical object. Attached Figure Description

[0025] Figure 1 This is a schematic diagram illustrating an application scenario of a digital twin object processing method provided in one embodiment of this specification;

[0026] Figure 2 This is a flowchart illustrating the processing procedure of a digital twin object processing method provided in one embodiment of this specification.

[0027] Figure 3 This is a schematic diagram illustrating the entire process of constructing a city digital twin scenario in a digital twin object processing method provided in one embodiment of this specification;

[0028] Figure 4 This is a flowchart illustrating the global digital construction process in a digital twin object processing method provided in one embodiment of this specification.

[0029] Figure 5 This is a flowchart illustrating the multi-source data fusion process in a digital twin object processing method provided in one embodiment of this specification.

[0030] Figure 6 This is a schematic diagram illustrating the application of a digital twin system in a digital twin object processing method provided in one embodiment of this specification.

[0031] Figure 7 This is a schematic diagram of the digital twin system architecture in a digital twin object processing method provided in one embodiment of this specification;

[0032] Figure 8 This is a schematic diagram of the data structure of a digital twin system architecture in a digital twin object processing method provided in one embodiment of this specification;

[0033] Figure 9 This is a schematic diagram of the data flow in a digital twin system architecture provided in one embodiment of the digital twin object processing method in this specification;

[0034] Figure 10 This is a flowchart illustrating the processing procedure of a digital twin object processing method provided in one embodiment of this specification.

[0035] Figure 11 This is a schematic diagram of the structure of a digital twin object processing system provided in one embodiment of this specification;

[0036] Figure 12 This is a structural block diagram of a computing device provided in one embodiment of this specification. Detailed Implementation

[0037] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0038] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of this specification. The singular forms “a,” “described,” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0039] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this specification, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0040] First, the terms and concepts used in one or more embodiments of this specification will be explained.

[0041] First, the terms and concepts used in one or more embodiments of this specification will be explained.

[0042] Digital twin: also known as a digital twin, is a digital mapping of the physical world.

[0043] City digital twin: A digital mapping of the entire city and its entire lifecycle.

[0044] Digital twin objects: digital mappings of every physical entity in a city.

[0045] Digital twin object modeling: a digital descriptive information model of every physical entity in a city.

[0046] Digital twin object encoding: A unique digital identifier (ID) for a digital twin object.

[0047] Digital twin space construction: digitally reconstructing objects in every cubic meter of space in a city.

[0048] The Internet of Things (IoT) is a network that connects all ordinary objects capable of independent functions, using the internet, traditional telecommunications networks, and other information carriers.

[0049] PaaS is an abbreviation for Platform as a Service. It refers to a business model that provides a server platform as a service. Additionally, services provided via the network are called SaaS (Software-as-a-Service).

[0050] SaaS: an abbreviation for Software-as-a-Service, meaning software as a service, which is the provision of software services over the network.

[0051] BIM stands for Building Information Modeling, a new tool for architecture, engineering, and civil engineering.

[0052] OSS: Object Storage Service (OSS) is a cloud storage service that provides massive, secure, low-cost, and highly reliable storage services.

[0053] DAG: Short for Database Availability Group.

[0054] OneID, also known as ID-Mapping, combines device IDs, phone numbers, ID card numbers, email addresses, usernames, and other information with tag systems, knowledge graphs, machine learning, and other technologies and algorithms to map various IDs to a unified ID.

[0055] RTK: refers to Real-time Kinematic carrier phase differential technology. RTK is a method for processing the carrier phase observations of two measurement stations in real time. The carrier phase collected by the reference station is sent to the user receiver to calculate the coordinates by difference.

[0056] POS: Position and orientation system (POS).

[0057] DOM: refers to the Document Object Model.

[0058] DEM: refers to Digital Elevation Model.

[0059] DLG: Digital Line Graphic, is a vector dataset that stores basic geographic features in layers on existing topographic maps.

[0060] LOD stands for Levels of Detail. LOD technology refers to allocating rendering resources based on the position and importance of an object's nodes in the display environment, reducing the face count and detail of less important objects to achieve more efficient rendering computation.

[0061] OGC: Open Geospatial Consortium.

[0062] UE: It is an abbreviation for User Experience, which refers to the entire experience a user has when visiting a website or using a product.

[0063] Web: The full name is World Wide Web, also known as the World Wide Web.

[0064] CAD: refers to software that uses computers and their graphics equipment to help designers perform design work.

[0065] CIM platform: It is a basic platform for creating three-dimensional digital models of buildings, infrastructure and other structures based on the city's basic geographic information, and for expressing and managing the city's three-dimensional space.

[0066] RTK (Real-time kinematic) generally refers to real-time dynamic carrier phase differential technology.

[0067] AOI: Automated Optical Inspection, abbreviated as AOI, generally refers to automated optical inspection.

[0068] GIS: Geographic Information System, abbreviated as GIS, generally refers to a geographic information system.

[0069] The concept of digital twins was initially named "information mirror model," later evolving into the term "digital twin." The earliest application of Digital Twin technology was in the health maintenance and support of aerospace vehicles. First, a model of the real aircraft is created in digital space, and sensors are used to achieve complete synchronization with the aircraft's actual condition. After each flight, based on the current structural condition and past loads, timely analysis and assessment can be conducted to determine if maintenance is needed and whether the aircraft can withstand the loads of the next mission.

[0070] Digital twin technology was listed as one of the top ten emerging technologies for three consecutive years from 2017 to 2019. Some important strategic technology trend reports also mentioned that new technologies such as behavioral internet and super automation all require the support of digital twin systems to be realized.

[0071] In order to promote the healthy development of the digital economy, "exploring the construction of digital twin cities" has also been included in some social development plans, and the construction of digital twin cities has become an important development direction for smart cities. For example, in the field of water conservancy projects, in order to improve defense capabilities and raise defense standards, it is necessary to accelerate the construction of digital twin river basins and digital twin projects, realize the functions of forecasting, early warning, and emergency response plans, improve the river basin flood control dispatch and command system, strengthen unified planning, unified governance, unified dispatch and unified management, and firmly safeguard the bottom line of flood and drought disaster prevention and control.

[0072] However, the construction of urban digital twins has suffered from a lack of unified standards and planning, resulting in a fragmented landscape characterized by isolated systems, inefficient infrastructure development, weak vertical integration, and isolated perception systems. A unified approach to digital twin construction and management standards has not been established. Several problems are reflected in this situation:

[0073] I. Low Data Value: The explosive growth in data types and scale means that spatial data is no longer singular and static, urgently requiring an upgrade to high-performance, massive spatiotemporal data processing capabilities. Heterogeneous data makes data parsing and sharing difficult in smart cities, and the lack of project correlation between massive amounts of data leads to low data utilization efficiency and the inability to fully realize data value. Especially when conducting cross-system information fusion modeling and analysis for digital twin cities, the different data format standards significantly increase the time and cost of data processing.

[0074] Second, the replication cost between different projects is high: different devices have different standards, the development cost of device access is high and time is long, there is a lack of integrated online governance of structured and unstructured data, the link is automated, the standards are continuous and the quality is traceable. As the number of smart city applications and devices increases, new applications also need to be customized and developed multiple times for different standards, which increases the replication cost between different projects.

[0075] Third, difficulties in industry chain cooperation: The smart city industry chain is extensive, with numerous access protocols and data models from different manufacturers, each operating in its own closed system. This makes collaboration between the various entities in the industry chain difficult, resulting in challenges in equipment linkage and maintenance, poor service compatibility, and a serious impact on user experience.

[0076] Fourth, there are conceptual misconceptions: Most "digital twins" on the market have data collection, calculation and visualization that are separated. A common misconception is that "digital twins" are equivalent to large screens and 3D visualizations, which can only be displayed and cannot participate in calculations.

[0077] Based on the above issues, this document provides several digital twin solutions. The first is for building small-scale digital twin scenarios in the industrial manufacturing sector, such as physical factories, buildings, or industrial plants. However, this solution only supports small-scale scenarios and cannot achieve city-wide digital twins. The second solution is to provide an industrial twin platform. This platform has a broader scope, covering supply chain, manufacturing, construction, and cities, with more cases and solutions in the construction field, and these are also small-scale. It only supports the capability of twin object modeling. This product is a PaaS layer service under IoT, so its overall positioning is still biased towards industrial twins.

[0078] The third solution is to provide a digital twin platform for visualization rendering. This platform has strong BIM modeling and visualization rendering capabilities, but its core capability lies only in visualization rendering; it lacks the ability to construct digital twin objects. The fourth solution is to provide a cloud-based facility digitization platform. This platform can quickly combine a map with a virtual engine and the GPU pooling capabilities of cloud computing. However, the core advantage of this solution is still on the rendering side; its ability to construct the entire digital twin chain is insufficient.

[0079] Based on this, this specification provides a digital twin object processing method, a digital twin object processing apparatus, a digital twin object processing system, a computing device, and a computer-readable storage medium, which will be described in detail in the following embodiments.

[0080] See Figure 1 , Figure 1The illustration shows an application scenario diagram of a digital twin object processing method provided according to an embodiment of this specification, wherein the target building can be understood as the target physical object, the building configuration data can be understood as the object configuration data, the personnel entry and exit data can be understood as the current status data, the initial digital twin object of the target building can be understood as the initial digital twin object of the target physical object, and the target digital twin object of the target building can be understood as the target digital twin object of the target physical object.

[0081] Based on this, the digital twin object processing method provided in this specification, when used to construct a digital twin object for a target building, firstly, the server obtains the building configuration data of the target building collected by the data acquisition device. Then, using the digital twin object template corresponding to the target building and the building configuration information, an initial digital twin object of the target building is generated. Next, the data acquisition device monitors the personnel entry and exit data of the target building. By fusing the personnel entry and exit data with the initial digital twin object of the target building, a target digital twin object corresponding to the target building is obtained. Finally, the target digital twin object of the target building can be rendered onto the user terminal for display to the user.

[0082] The digital twin object processing method provided in this manual forms a method for rapidly constructing urban digital twin scenarios during the construction of a systematic digital twin system. This solution can quickly construct urban digital twins through a full-link process for building urban digital twin scenarios.

[0083] See Figure 2 , Figure 2 A flowchart of a digital twin object processing method according to an embodiment of this specification is shown, which specifically includes the following steps:

[0084] Step 202: Determine the object configuration data of the target physical object and the digital twin object template corresponding to the target physical object.

[0085] The target physical object can be understood as the physical entity object that needs to be used to construct a digital twin object, such as buildings in a city, water networks and road networks (transportation facilities) in a city, or physical entities such as woodlands and rivers.

[0086] The configuration data of this object can be understood as data that characterizes the composition of the target physical object, such as satellite images of urban traffic facilities or point cloud data of urban road networks collected by radar.

[0087] A digital twin object template can be understood as the digital twin data structure corresponding to the target physical object. In practical applications, physical entities in a city can be abstracted to form a set of standard entity model definitions, with a unified spatial unit as the basic unit for urban data exchange, sharing and integration. This entity model definition can be a digital twin object template.

[0088] In one embodiment provided in this specification, the object configuration data for determining the target physical object includes:

[0089] Determine the type of the target physical object;

[0090] Based on the type of the target physical object, the object configuration data of the target physical object is determined from the object configuration data of at least two types of initial physical objects obtained in advance, and the digital twin object template corresponding to the target physical object is determined from the digital twin object templates of at least two types of initial physical objects that are pre-configured.

[0091] The digital twin object processing method provided in this specification can be applied to create a digital twin of a city in a city digital twin scenario. Based on this, the at least two types of initial physical objects can be understood as constructing various physical entities for the entire city, such as buildings, woodlands, road networks, water networks, and power grids. Furthermore, the target physical object can be any one of the at least two types of initial physical objects. Based on this, by constructing digital twin objects from the target physical object, digital twins of at least two types of initial physical objects are created, thereby obtaining target digital twin objects corresponding to at least two types of initial physical objects. Then, by merging at least two target digital twin objects, a digital twin object of the entire city can be obtained, thus realizing a city digital twin.

[0092] Based on this, the digital twin object processing method provided in this specification can determine the object configuration data of at least two types of initial physical objects, determine the type of the target physical object to be digitally twinned, and then determine the physical configuration parameters corresponding to the target physical object from the object configuration parameters based on the type of the target physical object.

[0093] For example, if the target physical object is a road network, the digital twin object processing method provided in this specification can select the physical entities that need to be digitally twinned (where digital twinning can be understood as performing the operation of constructing digital twin objects) from the physical entities such as buildings, woodlands, road networks, water networks, and power grids in the entire city as the road network, and determine the corresponding data of the road network from the urban data of the entire city (high-definition urban map, urban point cloud data, etc.) based on the physical entity type of the road network (road network type).

[0094] In one embodiment provided in this specification, before determining the object configuration data of the target physical object, the method further includes:

[0095] Obtain the configuration data to be processed for the at least two types of initial physical objects, wherein the configuration data to be processed is obtained by configuring the data acquisition device to perform data acquisition and processing on the at least two types of initial physical objects;

[0096] The configuration data to be processed is preprocessed to obtain object configuration data for the at least two types of initial physical objects.

[0097] The configuration data to be processed can be understood as data that needs to be preprocessed, and the configuration data acquisition device can be a satellite, vehicle radar, sensor, etc.

[0098] Data preprocessing includes, but is limited to, image mosaicking (error correction and stitching), integrity detection, encryption, coordinate error correction and fusion of the configuration data to be processed. This manual does not impose specific restrictions on this, and the settings can be made according to the actual application scenario.

[0099] Specifically, the digital twin object processing method provided in this specification can perform data acquisition and processing on at least two types of initial physical objects through the configuration data acquisition device, thereby obtaining the configuration data to be processed for the at least two types of initial physical objects. Then, the configuration data to be processed is sent to the server on which the digital twin object processing method is applied. The server performs data preprocessing on the configuration data to be processed through a predefined data preprocessing method to obtain the object configuration data of the at least two types of initial physical objects.

[0100] For example, the digital twin object processing method provided in this specification can connect all the perceived data to the server. This all the perceived data includes static spatial data such as high-precision maps, satellite imagery, and urban white film, as well as dynamic data such as video, radar, coils, and Gaode Maps. After the data is connected, the server performs standardized processing, storage, and quality monitoring to ensure that the instructions for configuring the object's data have high-quality data available later.

[0101] In one embodiment provided in this specification, determining the digital twin object template corresponding to the target physical object from pre-configured digital twin object templates of at least two types of initial physical objects specifically involves:

[0102] First, determine the digital twin object templates corresponding to at least two types of pre-configured initial physical objects, and after determining the type of the target physical object; based on the type of the target physical object, determine the digital twin object template corresponding to the target physical object from the digital twin object templates of the at least two types of pre-configured initial physical objects.

[0103] In the digital twin object processing method provided in this specification, the operation of determining the initial digital twin object corresponding to the target physical object based on the digital twin object template can be understood as the process of performing entity modeling on the target physical object. In the process of performing entity modeling on a physical entity, the model can include multiple types.

[0104] Following the previous example, the digital twin object processing method provided in this specification can select the physical entity to be digitally twinned from the physical entities such as buildings, woodlands, road networks, water networks, and power grids in the entire city as the road network, and determine the corresponding entity model definition of the road network from the entity model definition corresponding to the city data (high-definition city map, city point cloud data, etc.) of the entire city, thereby realizing the rapid construction of digital twin objects based on the digital twin object template.

[0105] Step 204: Based on the object configuration data and the digital twin object template, determine the initial digital twin object corresponding to the target physical object.

[0106] In practical applications, the object configuration data can be understood as the static data of the target physical object, which is used to represent the structure, location, etc. of the target physical object. The initial digital twin object obtained by digital twinning through the object configuration data can be understood as the static digital twin model of the target physical object.

[0107] Furthermore, in one embodiment provided in this specification, determining the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template includes:

[0108] Determine the object generation algorithm corresponding to the digital twin object template, and use the object generation algorithm to process the object configuration data to obtain the digital twin data corresponding to the object configuration data;

[0109] The digital twin data is filled into the digital twin object template to obtain the initial digital twin object corresponding to the target physical object.

[0110] The object generation algorithm can be understood as an algorithm that models the target physical object based on the object configuration algorithm. In practical applications, the object processing method provided in this specification offers a low-code programmable platform during the generation of twin objects. For different physical entities, due to the diverse types of their source data, different types of data need to be abstracted into operators. Through the DAG orchestration capability, the algorithm development is flexible and open. Through the platform's capabilities, the algorithm can be bound to the entity model definition and published as an entity generation algorithm.

[0111] The digital twin data can be understood as the model obtained by entity modeling based on the configuration data of the object. For example, the digital twin data can be road surface, vegetation surface, building surface, road markings, urban components, etc.

[0112] Specifically, the digital twin object processing method provided in this specification requires determining the object generation algorithm corresponding to the digital twin object template during the process of determining the initial digital twin object, and inputting the object configuration data into the object generation algorithm for modeling processing, thereby obtaining the digital twin data corresponding to the object configuration data.

[0113] Then, based on the data storage rules corresponding to the digital twin object template, the digital twin data is filled into the digital twin object template to obtain the initial digital twin object corresponding to the target physical object.

[0114] Furthermore, in practical applications, after object generation is complete, the quality inspection module checks the accuracy, completeness, and uniqueness of the data for each object, and provides corresponding topology checks such as spatial intersection and coverage. Objects that pass the quality inspection can be published. Throughout the object's lifecycle, changes to the object need to be managed. An entity can run the object generation algorithm multiple times, and the results of each calculation are first entered into a temporary table. Only after meeting service and quality requirements can the final object be made public and provide services to other service systems.

[0115] In one embodiment provided in this specification, the object generation algorithm is at least two, and the object configuration data is of at least two types;

[0116] Accordingly, the step of processing the object configuration data using the object generation algorithm to obtain the digital twin data corresponding to the object configuration data includes:

[0117] Determine the data types of at least two types of object configuration data, and based on the data types, determine the object generation algorithm associated with the at least two types of object configuration data from at least two object generation algorithms;

[0118] The configuration data of the at least two types of objects are input into an associated object generation algorithm to obtain digital twin data corresponding to the configuration data of the at least two types of objects.

[0119] In practical applications, the digital twin object processing method provided in this manual utilizes a large amount of structured and unstructured data during the twin construction process, including but not limited to: 1. Raster data: including but not limited to tif, grib2, png, and other raster data. 2. Vector data: including but not limited to shp, gdb, dwg, fly, and other vector data. 3. 3D data: including but not limited to rvt, 3ds, osgb, and other 3D data. 4. Other data includes static CSV data, such as facility and equipment ledger data, and real-time IoT data. Furthermore, unstructured data can be stored through OSS, and the data engine can unify the representation of structured and unstructured data. Through unified data access, three major data types are formed: Raster, Geometry, and Mesh, thereby achieving data unification in storage format. The biggest advantage of unified storage format is that various operators can be implemented on these storage types, achieving the goal of unified data fusion and computation.

[0120] Furthermore, entity modeling includes project modeling, geometric modeling, mechanism modeling, and spatial semantic modeling. The entity model constructed through this entity modeling constitutes the initial digital twin object corresponding to the target physical object.

[0121] 1. Project modeling describes the attributes of entities, and generally uses conventional data types such as strings, integers, floating-point numbers, timestamps, etc.

[0122] 2. Geometric modeling is a two- or three-dimensional representation of entities, typically using points, lines, surfaces, volumes (Geometry), as well as raster and mesh. An entity can have multiple geometric representations, depending on how we observe the entity. For example, at an altitude of several thousand meters, we see a road as a line; at a altitude of several hundred meters, we see a road as a surface; and when the slope of the road needs to be considered, it transforms from a two-dimensional surface into a three-dimensional volume. The level of abstraction and the method of representation depend on which information we need to extract for computation.

[0123] 3. Mechanism modeling expresses the physical properties of an entity, such as the dynamics model of a car or the friction coefficient of a road. It is usually a mathematical expression.

[0124] 4. Spatial semantic modeling: Spatial semantics expresses the relationships between objects, especially spatial relationships. Spatial relationships are divided into distance relationships and topological relationships. Distance relationships are one of the most common spatial relationships, generally using Euclidean distance. Topological relationships do not change with distance or angle. Examples include the relationship between adjacent polygons and common arcs, and the edge-to-edge connection relationship in a geometric network. Real-world meaningful topological relationships include nine types: intersection, connection, equality, separation, containment, contained in, covering, covered, and overlapping.

[0125] It should be noted that this digital twin object processing method provides a way to rapidly construct urban digital twin scenarios, mainly including a full-chain process such as full-domain digital construction, intelligent fusion perception, multi-source data fusion, unified twin services, and spatiotemporal data visualization. (See [link to relevant documentation]). Figure 3 , Figure 3 This is a schematic diagram illustrating the end-to-end construction of a city digital twin scenario in a digital twin object processing method provided in one embodiment of this specification. See also... Figure 3 It can be seen that, Figure 3This document illustrates the specific process of urban digital twin technology, the basic platform types supporting its implementation, the scenarios and corresponding industry products, and the services achievable based on this technology. The specific process includes steps such as full-domain digital construction, intelligent fusion perception, multi-source data fusion, unified twin services, and spatiotemporal data visualization. Full-domain digital construction includes twin object modeling, unified identification coding, twin object generation (including road networks, buildings, water networks, and land parcels), and 2D / 3D spatial construction, thereby constructing static digital twin objects. Intelligent fusion perception refers to abstracting physical entities in the city to form a standard entity model definition, using unified spatial units as the basic unit for urban data exchange, sharing, and fusion, and simultaneously constructing a unified code as the unique identity of each spatial unit. This system maps the correspondence between every cubic meter of digital space and physical space in the city. It integrates data from different levels, dimensions, and granularities using a "unit-code-attribute" approach, providing a comprehensive and full-cycle digital description of the city from a spatiotemporal perspective. Ultimately, it enables simultaneous editing in one location across four scenarios (perception, computation, display, and simulation), ensuring data consistency across project domains and improving data accuracy. Intelligent fusion perception includes functions such as basic infrastructure monitoring, basic visual perception, millimeter-wave radar perception, point cloud data processing, and perception fusion technology to acquire dynamic data on physical entities in the city (including road networks, buildings, water networks, and land parcels). This multi-source data fusion uses a dynamic-static fusion approach, combining dynamic data with static twin objects to obtain twin data models (including water conservancy, transportation, government affairs, and planning). During dynamic fusion, specific twin intelligent algorithms are required, including but not limited to traffic prediction, trajectory reconstruction, diffusion warning, and source tracing algorithms. The unified digital twin service refers to the services adopted to realize the city's digital twin, including but not limited to structured RESTful (an internet software architecture) services, real-time WebSocket (a full-duplex communication protocol) services, spatial OGC services, 3D S3M (a spatial 3D model data format) services, and 3D DTiles (a 3D spatial data standard) services. After the digital twin object is built, it can be rendered through spatiotemporal data visualization steps, specifically including 3D model generation, 3D data mounting, low-code construction, and WEB / UE rendering. The project scenarios for this city's digital twin technology include traffic analysis, intelligent traffic control, vehicle-road cooperation, intelligent navigation, unified network management, and unified online government services. Industry products provided based on the city's digital twin technology include a traffic cloud control platform, a water conservancy governance platform, a transportation supervision platform, a spatial governance CIM platform, intelligent government services, and intelligent urban operation.The basic platform types supporting the implementation of urban digital twin technology include data acquisition platforms, scheduling platforms, R&D platforms, monitoring platforms, alarm platforms, computing and storage platforms, and information publishing platforms. Furthermore, the services achievable based on urban digital twin technology include, but are not limited to, simulation analysis and cloud-edge collaborative computing. The simulation analysis includes functions such as traffic simulation, natural resource simulation, and autonomous driving simulation, while the cloud-edge collaborative computing includes functions such as multi-layer interconnection, data compilation, and node scheduling.

[0126] See Figure 4 , Figure 4 This is a schematic diagram of the process of global digital construction in a digital twin object processing method provided in one embodiment of this specification; the process includes data acquisition, raw data processing, standard result data, and object generation.

[0127] The data acquisition process for the comprehensive digital construction includes: firstly, configuring hyperspectral and infrared sensors on spaceborne and airborne vehicles; secondly, configuring hyperspectral, panchromatic, and infrared sensors on airborne, vehicle-mounted, and manned vehicles as well as at fixed points; and thirdly, equipping monocular / multi-spectral optical sensors and lidar on airborne, vehicle-mounted, and manned vehicles; and finally, configuring RTK and total station equipment at fixed points. Then, using these devices, the city's imagery (satellite), imagery (aerial), imagery (ground acquisition), imagery (oblique photography), POS data, ground control points, and laser point clouds are collected. The aforementioned devices can be understood as configuring data acquisition equipment, and the aforementioned data can be understood as object configuration data.

[0128] The data acquired by the aforementioned data acquisition equipment undergoes a raw data processing flow, including image mosaicking (correction and stitching), aerial triangulation, 3D reconstruction, coordinate correction, and fusion. This yields standard output data: DOM, DEM, real-world 3D data, point cloud (imagery), point cloud (LiDAR), DLG, planning CAD (referring to the physically corresponding planning CAD drawing, created using CAD software), and BIM data.

[0129] In the process of selecting different physical entities for digital twins based on different application scenarios, it is necessary to abstract the physical entities in the city to form a standard entity model definition (schema). For example, physical entities such as urban transportation, natural resources, and watershed networks can be selected to construct twins (i.e., digital twin objects). Further, for example, in the process of constructing an urban transportation twin, it is necessary to determine the entities included in the urban transportation system and abstract these entities to obtain the corresponding entity model definition (digital twin object template). Since each digital twin object requires multiple data models to support it, each entity model definition will correspond to multiple model data. For example, urban transportation entities correspond to road network type model data, including roads, information points, lanes, stations, intersections, and traffic areas; facility type model data, including traffic markings, traffic signs, and roadside facilities; and equipment type model data, including traffic lights, monitoring systems, and lighting systems.

[0130] Based on this, during the object generation process, an object generation algorithm corresponding to each entity is determined, and the standard result data is processed using this algorithm to obtain the data required to generate digital twin objects. Specifically, this solution can perform target recognition and extraction, as well as terrain classification, on remote sensing images. Finally, object extraction is performed on the extracted targets and terrain classifications to obtain the data required to generate digital twin objects such as vegetation surfaces and building surfaces. Alternatively, target recognition and extraction, real-scene 3D individualization, and other processing can be performed on point cloud data, and urban road markings can be extracted and vectorized from the processing results to obtain the data required to generate digital twin objects such as road surfaces, building surfaces, road markings, and urban components.

[0131] Finally, to facilitate querying the constructed digital twin objects, a corresponding code is generated for each digital twin object. The management of entity codes integrates multiple industry standards, forming a system covering macro and micro levels, indoor and outdoor environments, and above-ground and underground infrastructure. This weakens the easily changing and inconsistent industry classifications, incorporating them into attributes rather than codes or classifications. Industry standards establish mapping relationships through the digital identification of all objects, enabling accurate identification and rapid construction of urban elements, thereby providing standardized management of codes.

[0132] This unified coding system uses a management code + spatial code + time code model to lock in the rules for spatial unit changes and the start and end of the entire life cycle. The coding system needs to adhere to the principles of uniqueness, hierarchy, scalability, applicability, and ease of use. Specifically, the management code: refers to the classification standards stipulated by national standards, and classifies and records spatial entities or conceptual entities according to their characteristics. The spatial code: based on the spatial characteristics of spatial entities, it performs two-dimensional grid coding + three-dimensional elevation coding. The time code: based on the life cycle characteristics of spatial entities or conceptual entities, it performs time coding. Specifically, in one embodiment provided in this specification, after determining the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template, it further includes:

[0133] The corresponding digital twin object code is determined for the initial digital twin object based on the encoding generation rules;

[0134] Accordingly, after determining the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object, the process further includes:

[0135] The receiving end sends an object acquisition request, wherein the object acquisition request carries the digital twin object code of the digital twin object to be acquired, and the initial digital twin object has the same digital twin object code as the corresponding target digital twin object;

[0136] Based on the digital twin object encoding, the digital twin object to be acquired is determined from the target digital twin object, and the digital twin object to be acquired is returned to the object acquisition end.

[0137] The encoding of the digital twin object can be understood as a unified encoding determined for the initial digital twin object.

[0138] In this context, the object acquisition end can be the user's corresponding user terminal. Based on this, the object acquisition request can be understood as a request sent by the user to obtain a specific target digital twin object. Alternatively, the object acquisition end can be another server. Based on this, the object acquisition request can be understood as a request from another server to invoke a specific target digital twin object.

[0139] Furthermore, determining the corresponding digital twin object code for the initial digital twin object based on a preset encoding rule includes:

[0140] The spatial parameters of the initial digital twin object are determined, and the spatial parameters are encoded to obtain the spatial code of the initial digital twin object;

[0141] Determine the time parameters of the initial digital twin object, and encode the time parameters to obtain the time code of the initial digital twin object;

[0142] The object type parameter of the initial digital twin object is determined, and the object type parameter is encoded to obtain the object management code of the initial digital twin object;

[0143] The spatial encoding, temporal encoding, and / or object management encoding are determined as the digital twin object encoding of the initial digital twin object.

[0144] The spatial parameter can be understood as the spatial information of the target physical object corresponding to the initial digital twin object, such as the spatial semantic model mentioned above; the temporal parameter can be understood as the creation time of the target physical object corresponding to the initial digital twin object; and the object type parameter can be understood as a parameter characterizing the type of the target physical object corresponding to the initial digital twin object.

[0145] Specifically, the digital twin object processing method provided in this specification involves determining the spatial parameters of an initial digital twin object and encoding these parameters to obtain its spatial code; determining the temporal parameters of the initial digital twin object and encoding them to obtain its temporal code; determining the object type parameters of the initial digital twin object and encoding them to obtain its object management code; and then using the spatial code, temporal code, and / or object management code as the digital twin object code for the initial digital twin object, and storing the digital twin object uniformly to facilitate subsequent queries of the target digital twin object based on this digital twin object code.

[0146] Step 206: Based on the current state data of the target physical object and the initial digital twin object, determine the target digital twin object corresponding to the target physical object.

[0147] Specifically, after determining the initial digital twin object, the server can determine the current state data of the target physical object, and generate the target digital twin object corresponding to the target physical object based on the current state data and the initial digital twin object.

[0148] Specifically, the method described in this specification for determining the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object includes:

[0149] The current state of the target physical object is monitored by the state data acquisition device to obtain the current state data of the target physical object;

[0150] Based on the current state data, the digital twin data corresponding to the initial digital twin object is updated and / or added to obtain the target digital twin object corresponding to the target physical object.

[0151] The current state data is acquired by collecting the current state of the target physical object through a state data acquisition device. This process can be understood as intelligent joint perception in the end-to-end process of building a city's digital twin scenario. This intelligent joint perception refers to all-weather, full-coverage, all-element, low-latency multimodal fusion perception and reconstruction, requiring high-performance sensing equipment and high-performance algorithms. Through model compression and pruning techniques and clever fusion strategies, the algorithm latency is less than 100ms, achieving decimeter-level perception error and a target fusion reconstruction rate of approximately 97%. Achieving this intelligent joint perception requires four conditions: higher resolution, longer distance, greater computing power, and more complex algorithms. Higher resolution is achieved through cameras, millimeter-wave radar, and lidar, using hardware, software, or a combination of both, to improve their respective resolutions, even leading to new forms like 4D millimeter-wave radar. Greater Distance: For cameras, multi-camera setups can be used, with low-resolution cameras focusing on nearby objects and high-resolution cameras focusing on distant objects. For millimeter-wave radar, since its resolution depends on the number of channels, a cascaded antenna design can be employed, with fewer channels for near-field objects and more for distant objects. Similarly, for lidar, a smaller number of channels (lines) for near-field objects and more for distant objects can be used to achieve approximately consistent resolution across the entire road segment. Greater Computing Power: Greater distances inevitably bring new challenges, such as the identification of small objects, occlusion issues, and stability problems caused by device vibration. These require more powerful computing power and algorithms to solve. Single-task devices (such as speed measurement devices) cannot meet the requirements for all-weather, full-coverage, and all-element perception. Therefore, detection devices are often installed at intersections and road sections to achieve (but not limited to) traffic violation capture, traffic parameter monitoring, traffic event detection, perception of traffic environment and road elements, as well as the location / trajectory reconstruction of traffic objects and perception of traffic environment and road elements, which are of interest to digital twins and vehicle-road cooperative systems. More complex algorithms: On the one hand, as mentioned above, the perception tasks are becoming more diverse; on the other hand, even for the same perception task, the algorithms used to achieve more stable and accurate perception will be more complex. For example, the algorithm needs to be able to adapt to straight roads, curves, flat roads, undulating roads, large objects, small objects, good weather, bad weather, slow or stationary objects, and fast-moving objects, etc.

[0152] Based on the above, it can be seen that the digital twin object processing method provided in this specification requires greater computing power and more complex algorithms to process image data when problems such as unclear identification of small target objects, occlusion, and stability issues caused by device shake occur in the image, thereby ensuring data quality. Specifically, the state data acquisition device monitors the current state of the target physical object to obtain the current state data of the target physical object, including:

[0153] The current state of the target physical object is monitored by the state data acquisition device to obtain the initial current state data of the target physical object;

[0154] Determine whether the initial current state data meets the preset data conditions.

[0155] If so, then the initial current state data shall be used as the current state data of the target physical object.

[0156] If not, the initial current state data is adjusted using a data processing algorithm, and the adjusted initial current state data is used as the current state data of the target physical object.

[0157] Continuing with the previous example, the status data acquisition device can be a camera, radar, etc. Based on this, during the process of collecting current vehicle data in urban traffic through cameras and radar, problems such as weather and equipment tilt can lead to unclear data. Therefore, it is necessary to analyze the current vehicle data collected by the device. If it is determined that the current vehicle data does not have the above-mentioned problems, the current vehicle data can be directly entered into the database. If it is determined that the current vehicle data has the above-mentioned problems, algorithms are needed to correct, adjust, and accurately identify the collected data to obtain high-quality current vehicle data.

[0158] In the digital twin object processing method provided in this specification, after determining the current state data of the target physical object, the object simulation data corresponding to the initial digital twin object is updated and / or added based on the current state data to obtain the target digital twin object corresponding to the target physical object. This operation can be understood as multi-source data fusion in the end-to-end process of building a city digital twin scenario. (See also...) Figure 5 , Figure 5 This is a flowchart illustrating the multi-source data fusion process in a digital twin object processing method provided in one embodiment of this specification. Here, multi-source data refers to the digital twin objects corresponding to city entities during the process of creating a city digital twin; for example, see [link to relevant documentation]. Figure 5 The objects in the image include high-rise buildings, houses, road networks, vegetation, water sources, and terrain. Multi-source data fusion refers to the need to solve the consistency and reusability problems of dynamic and static data in the process of creating a city digital twin. It changes the traditional way of organizing spatiotemporal data in layers and establishes a digital volume mapping of twin entities, thereby enabling the connection of data across the entire life cycle and all elements. This allows dynamic and static data to flow freely and be fused in the indicator calculation domain, simulation domain (i.e., simulation domain), display domain (e.g., 3D rendering domain), and perception domain (e.g., autonomous driving domain), achieving visual and computational integration of twin data and fusion of the four domains. This constructs the spatiotemporal data fabric of the city, which is the city digital twin.

[0159] The data sources for urban digital twins can be categorized into project data, spatial two-dimensional data, and spatial three-dimensional data. The detailed layer and thematic data layer are designed using paradigm modeling, dimensional modeling, and KV (Key-value) modeling concepts, respectively.

[0160] Based on a project-driven data model architecture design concept, and built upon a unified platform, a loosely coupled, flexible, and open industry data model system is constructed with a project-oriented approach. This allows for "build once, use multiple times," enabling the accumulation and reuse of capabilities across different service scenarios, and providing standardized, componentized, and professional data services for upper-layer applications. Industry data modeling mainly covers information such as the subject domain, hierarchy, application area, environment, publication scope, and storage type of physical tables. Taking the transportation industry data model as an example: the detailed layer is divided into entity basic information, object relationships, traffic control, traffic events, location information, traffic operation, financial information, maintenance, and spatial information; the summary layer includes themes such as situation center, travel center, control center, vehicle center, user center, equipment center, network center, event center, toll collection center, urban experience, ecological environment, spatial profile, and enterprise profile; application layer data is processed according to the application corresponding to the product line and can be classified according to application themes.

[0161] The city's digital twin system constructs a standardized, scalable, and widely applicable multi-source data fusion data model perception system and automated data processing workflow. Taking traffic scenarios as an example, it integrates and analyzes basic road network topology channelization information, equipment and facility data (gantry / checkpoint / video, coil, microwave, etc.), toll record data, vehicle satellite positioning data, alarm data, meteorological data, and internet data. This data fusion addresses both the deficiencies and incompleteness of data from single data sources, maximizing data resource expansion. Furthermore, it processes data features to obtain a revised and more robust representation of traffic characteristics. Ultimately, it provides applications with integrated, unified, and high-quality traffic parameter services. All platform indicators are provided externally via data interfaces, facilitating the accelerated construction of a digital ecosystem.

[0162] Indicator fusion needs to be carried out on the basis of a unified twin object construction data standard, building an indicator system needed for service development analysis, and then carrying out spatiotemporal data indicator fusion. It can supplement basic traffic parameters of the road network based on various data, including speed, flow, trajectory, and some indicator parameters. The basic indicator algorithm has certain requirements for the input data; when the input data does not meet the requirements, the algorithm will automatically degrade, and in extreme cases, it will stop producing indicators.

[0163] During the data collection (production), processing, and use processes, standardized definitions are implemented for data timeliness, data accuracy, and other quality aspects, including pre-emptive problem prevention, in-process problem resolution, and post-event in-depth optimization. This ensures the management of the monitorability, verifiability, and verifiability of data quality, builds a long-term, stable, and secure data quality management system, controls data quality, and enhances the value of data operations.

[0164] In the embodiments provided in this specification, after obtaining the target digital twin object, the target digital twin object can be displayed to the user through spatiotemporal data visualization. Specifically, after determining the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object, the method further includes:

[0165] In response to an object rendering request sent by a user, the target digital twin object is rendered onto the object display page of the user's terminal, and the target digital twin object is displayed to the user through the object display page of the user's terminal.

[0166] For example, the target digital twin object is a digital twin object of urban transportation. Based on this, after generating the digital twin object of urban transportation, upon receiving an object rendering request sent by the user, the digital twin object of urban transportation can be determined and rendered onto the object display page of the user terminal. The digital twin object of urban transportation is then displayed to the user through the digital twin object of urban transportation on the user terminal.

[0167] It's important to note that users can send object rendering requests to the server through the object display page on their user terminals; the server will then render the digital twin object of the city's traffic onto the user's terminal's object display page. However, in some scenarios, the terminal device sending the object rendering request may differ from the user's terminal. For example, in urban traffic monitoring scenarios, the user can send the object rendering request to the server through their terminal device; but to allow people in the city to perceive traffic conditions in real time, the server will render the digital twin object of the city's traffic onto devices such as subway displays and shopping mall displays. In this case, the device sending the object rendering request and the device rendering the digital twin object of the city's traffic are inconsistent.

[0168] The aforementioned rendering process of the target digital twin object can be understood as the spatiotemporal data visualization in the end-to-end process of building a city's digital twin scene. This spatiotemporal data visualization uses a real-time rendering engine to perform dynamic and static real-time 3D rendering of the digital twin model, and combines various 3D model data (including but not limited to GLTF, OBJ, FBX, BIM, oblique photogrammetry, satellite imagery, and DEM) to recreate the environment and natural environment. The 3D scene supports LOD display capabilities, performing 3D model simulation of rivers, mountains, buildings, streets, cars, ground infrastructure, underground pipe networks, etc., realistically recreating the city's real-world environment, realizing multi-scene and multi-view 3D applications, solving the problem of 3D scene applications from different angles for customers, and managing different scenes through creation. For example, a full-element twin of a city of more than 8,000 square kilometers can be generated within one minute, with overall stability and CPU (Central Processing Unit) / GPU (Graphics Processing Unit) utilization reduced by 10X times. In the process of achieving visualization, a large-scale urban twin visualization engine is adopted: integrating the features of GIS and game engines, it has the ability to simulate real environments and perform spatial analysis; it loads quickly and supports real-time rendering of ultra-large urban scenes to components; it can achieve seamless switching between multiple terminals and multiple engines with only one setup; in addition, this manual provides a graphical application building method, which allows users to develop applications through graphical drag and drop, reducing the threshold for users to develop twin applications and improving application maintenance efficiency; the spatial simulation algorithm provides real-time dynamic and accurate mapping, restoring the details of algorithm deduction.

[0169] Furthermore, the entire process of building a city's digital twin scenario also includes a unified digital twin service. This service, in addition to supporting conventional structured offline and real-time data services, provides two-dimensional and three-dimensional spatial data services and a core map engine module. It enables the on-demand, low-latency, and accurate delivery of source data or processed spatial data to users according to the principles of "comprehensive, efficient, and coordinated" sharing, facilitating data consumption by more applications and realizing the value of data. It also supports the collaborative management of various organizations, providing intelligent operation support and enabling real-time information sharing across levels, departments, industries, and regions, achieving high reliability and low latency, and completing the closed loop of data from production to use to evaluation. Specifically, the spatial data service provides the following data service capabilities: 1. Support for the registration and management of vector data. 2. Support for the registration and management of Raster file data. 3. Support for the registration and management of three-dimensional data. 4. Support for the publication of OGC standard map services. 5. Support for unified proxying of mainstream commercial software GIS services.

[0170] Spatial data services provide users with data service capabilities during the construction of a spatial data platform. For data developers, it offers convenient data query, service conversion, service management, and service operation and maintenance capabilities with a unified experience covering all processing stages. For data asset managers, it provides statistical analysis, service usage statistical analysis, and popular data statistical analysis capabilities, enabling the effective implementation of "data application" in the second half of data platform construction and supporting the efficient development of data intelligent applications.

[0171] The above embodiments have explained the digital twin object processing method provided in this specification. In practical applications, a complete digital twin system consists of general infrastructure, a twin data foundation, intelligent application support, and best practices. Figure 6 This is a schematic diagram illustrating the application of a digital twin system in a digital twin object processing method provided in one embodiment of this specification. See also... Figure 6 Among them, the digital twin system is Figure 6 The twin construction steps in the process include data access, entity modeling, object generation, spatial construction, indicator fusion, and quality monitoring.

[0172] in, Figure 6The fundamental capabilities required for realizing urban data twins are the basic capabilities upon which they depend. Specifically, these capabilities mainly include PaaS (General Platform) and IaaS infrastructure. Infrastructure provides the environmental support, offering capabilities such as intelligent sensing, spatiotemporal storage, and massive computing to support the construction of the digital twin system. This includes, but is not limited to, facilities such as public transportation clouds, dedicated transportation clouds, and integrated transportation systems, as well as roadside sensing devices, communication infrastructure, intelligent edge terminals, control infrastructure, and mobile intelligent sensing terminals. PaaS (General Platform) includes facilities supporting digital twins such as the Flying Platform, Agile Platform, and Lightweight Platform. The core capability layer of this PaaS, relying on a digital twin foundation and the general capabilities of a data platform, performs integrated 2D and 3D encoding of dynamic and static urban elements. It accurately and efficiently integrates multi-source heterogeneous data, generates knowledge graphs among various elements, and enables rapid retrieval of various urban information, events, subjects, and relationships. This constructs a computable digital city, providing a stable spatial foundation for traffic indicator calculation, simulation analysis, and twin rendering. It offers capabilities such as spatiotemporal data source aggregation, entity modeling, spatial construction, object generation, indicator fusion, service publishing, and quality monitoring, achieving integrated access, governance, fusion, and analysis of basic traffic data. The PaaS layer organically combines machine learning algorithms and urban system models; it fully utilizes data resources to reconstruct the city's full-volume, all-time, and all-location information, constructing an industry knowledge engineering and graph technology foundation. Through the standardization of industry data models and the accumulation of industry knowledge, it assists in the digital transformation of industries.

[0173] Furthermore, it should be noted that the intelligent sensing layer, including roadside sensing devices, communication infrastructure, intelligent edge terminals, control infrastructure, and mobile intelligent sensing terminals, significantly reduces the operation and maintenance costs of digital city systems through a hardware-software integrated approach using terminal intelligent devices and edge acquisition and computing units, effectively lowering the threshold for digital transformation. Based on unified data standards and specifications, it aggregates geographic entity data (covering basic geospatial data, two-dimensional basic road network data, high-precision data, and environmental element-related data), and collects real-time IoT sensing data (covering IoT device data, video AI (artificial intelligence) analysis data, road defect inspection data, and vehicle-road cooperative related data), as well as data from internal and external related systems (covering internal enterprise data, external relevant department traffic data, meteorological and environmental data, and internet-based travel-related data, etc.).

[0174] Furthermore, the infrastructure platform adopts a cloud-native architecture, based on self-developed distributed technologies and products. It supports all cloud products and services with a single system, provides complete cloud platform open capabilities, has comprehensive enterprise-level service features, comprehensive disaster recovery and backup capabilities, and complete independent controllability. At the same time, it provides full-stack security support to ensure the reliability and continuity of the cloud platform.

[0175] Among its core capabilities is the SSS intelligent engine, which extracts and consolidates common service functions from various scenarios. Leveraging a digital reconstruction foundation and intelligent algorithm capabilities, it provides a standardized intelligent engine for services. This digital intelligent engine includes simulation analysis, intelligent optimization, green travel, security service, twin rendering, intelligent scheduling, planning and decision-making, and temperature-sensing video analysis engines. The application of intelligent algorithms connects industry needs with twin data, enabling rapid application and project incubation. The final result, the practical implementation, embodies the value of building digital-informatization-intelligentization-twin capabilities, providing rich services for urban governance, economic development, and public services. It should be noted that the SaaS industry engine layer utilizes technologies such as cloud computing, big data, and artificial intelligence to uniformly construct a secure, efficient, command-line, and service platform cloud foundation. By integrating the ecosystem and leveraging a cloud platform, we achieve core practical values ​​in traffic management, including secure control, efficient command, refined governance, and convenient services. This enables precise perception, accurate analysis, refined control, and attentive service for highway management, significantly improving highway management efficiency and travel safety. Similarly, it enables precise perception, accurate analysis, refined control, and attentive service for comprehensive urban traffic supervision, significantly improving the efficiency and quality of urban traffic supervision. In collaboration with upstream and downstream partners, we build a rich and diverse solution system around the three layers of digital needs in urban infrastructure, governance, and services, supporting government and enterprise users in achieving comprehensive digital management and upgrades of their cities.

[0176] In addition, this core capability also includes the data infrastructure DaaS, namely... Figure 6 The digital twin foundation provides the capability to build scenario-based digital twin data platforms, helping ISVs (Independent Software Vendors) quickly achieve data access, management, scenario construction, data fusion, and service deployment. Specifically, this digital twin foundation is a core production resource, achieving cross-domain data fusion by establishing a closed loop of big data processing encompassing unified expression, twin construction, project modeling, and unified services. It includes an asset center with twin asset assessment, unified service management, and twin asset management capabilities, as well as the aforementioned functions for building a city's digital twin. Figure 6 The construction of digital twins within the smart city concept involves a complex and comprehensive technological platform. This platform supports the construction of new smart cities, is a key pillar for continuous innovation in intelligent urban operations, represents the evolution and upgrading of smart cities, and forms the foundational basis for the future of cities where the virtual and physical worlds coexist and blend seamlessly. Based on a cloud-native spatiotemporal data technology stack, the digital twin platform constructs an integrated online governance system for structured and unstructured data, forming a full-stack capability for a new era of digital twin data foundation encompassing data, tools, models, and algorithms.

[0177] Best practice creation refers to providing end-to-end complete product solutions based on industry standard product capabilities, integrating / relying on ISV capabilities, including but not limited to applications in smart transportation and natural resources. Products provided in smart transportation scenarios include, but are not limited to, traffic control, highway operation management, and public transportation supervision. Traffic control products include traffic analysis and judgment, control optimization, situational awareness, unified traffic control, congestion analysis, timing optimization, organizational optimization, integrated command, intelligence and supervision, intelligent guidance, and special operations support. Highway operation management products include smart highways, traffic situation monitoring, collaborative control, analysis and judgment, facility maintenance, vehicle-road cooperation, digital parallel world, travel services, emergency safety, and operation management. Public transportation products include smart hubs, traffic planning, hub passenger flow monitoring, comprehensive passenger flow analysis, hub evacuation scheduling, public transport network analysis, green travel, public transport-railway connection analysis, integrated travel, and green travel supervision. Transportation supervision products include hazardous chemical transportation supervision, TOCC (Transportation Operations Coordination Center), highway maintenance, commercial vehicle supervision, and regional traffic management; other products include digital terminals, digital aprons, urban parking, highway auditing, smart waterways, and smart ports.

[0178] Based on the above Figure 6 This specification describes the application of the digital twin object processing method in real-world scenarios and the infrastructure supporting its implementation. For the structure of the digital twin object processing system, please refer to [link to relevant documentation]. Figure 7 , Figure 7 This is a schematic diagram of the digital twin system architecture in a digital twin object processing method provided in one embodiment of this specification; according to Figure 7 As can be seen, the digital twin object processing system provided in this specification relies on cloud-based implementation. This system includes basic modules such as a computing engine, a unified data platform, source data, and a data space engine. Through this basic model, it processes the data collected from the device and provides these other modules to construct a digital twin of the city.

[0179] In constructing a city's digital twin, this system acquires data from the basic modules via a data access module. Through modules such as data processing, data modeling, a data execution engine, system operation and maintenance, twin object construction, and a spatial construction platform, it completes the construction of the city's digital twin and performs simulations based on it using a city simulation platform. Furthermore, the system includes modules for managing the city's digital twin, such as a metadata center, data asset management, unified services, and packaging / instantiation. Finally, during the usage phase, the system provides services to users through client-side applications based on various types of industry applications and city simulation platform applications. These industry applications include, but are not limited to, applications in transportation, housing, water pollution source tracing, stormwater and sewage pipe network health analysis, and urban flooding traffic impact analysis. The city simulation platform applications include, but are not limited to, applications in transportation, water systems, and multiple simulation scenarios. It should be noted that the system also manages edge devices and equipment through a cloud control terminal.

[0180] Based on the architecture diagram of the digital twin object processing system described above, this specification... Figure 8 The diagram shows the data architecture of this digital twin object processing system. (See attached image.) Figure 8 , Figure 8 This is a schematic diagram of the data structure of a digital twin system architecture in a digital twin object processing method provided in one embodiment of this specification. Specifically, the data architecture of this digital twin object processing system includes two parts: global digital construction and project application.

[0181] The comprehensive digital construction comprises three parts: data access, industry models, and comprehensive digital assets. Data access refers to acquiring the data needed to build a city data twin from the device end, including project data, 2D data, and 3D data. Project data includes, but is not limited to, traffic facility data, engineering construction data, environmental monitoring data, traffic flow data, meteorological data, economic data, population data, enterprise data, and land use data. 2D data includes, but is not limited to, road networks, waterways, public transport networks, industrial enterprises, sewage treatment plants, 2D pipelines, remote sensing imagery, resource surveys, and planning management data. 3D data includes, but is not limited to, digital elevation data, BIM models, pipeline and utility tunnel data, laser point clouds, detailed model data, white model data, oblique photogrammetry, and CAD data.

[0182] Subsequently, the aforementioned data is processed through standardization procedures to build a model. This standardization process includes data standardization transformation, spatial calibration, twin object management, and unified data coding. Data standardization transformation includes, but is not limited to, format conversion, coordinate system conversion, quality inspection, and repair processing; spatial calibration includes, but is not limited to, image pixel geographic coordinate calibration, tilted spatial geometry adjustment, 3D model spatial location calibration, and BIM spatial coordinate conversion; twin object management includes, but is not limited to, spatial object definition, object relationship construction, logical model design, and data standard definition; and unified data coding includes, but is not limited to, road network coding, water network coding, land parcel coding, pipeline coding, building coding, and public transport route coding.

[0183] The industry model section refers to the application of urban data twin models constructed based on different scenarios, including traffic and natural resource scenarios. Taking the traffic scenario as an example, the data structure in the traffic scenario application includes a detailed layer, a thematic layer, and an application layer. The detailed layer includes basic information, object relationships, traffic control, traffic events, location information, and traffic operation data of the urban data twin model. The basic information includes, but is not limited to, a unified road network, vehicles, traffic participants, and traffic facilities. The object relationships include, but are not limited to, intersection relationships, road segment relationships, equipment-intersection relationships, and vehicle-road relationships. The traffic control includes, but is not limited to, signal control, traffic restriction control, and flow control. The traffic events include, but are not limited to, police incidents, construction incidents, internet incidents, and weather incidents. The location information includes, but is not limited to, personnel location, vehicle location, ship location, and equipment location. The traffic operation data includes, but is not limited to, road condition information, equipment speed, vehicle passing data, and trajectory data.

[0184] The detailed layer data, processed by restoration algorithms, yields the thematic data sets included in the thematic layer. These restoration algorithms include diffusion algorithms (for traffic flow and pollutants), trajectory path restoration algorithms (for vehicles, people, and pollutants), source tracing algorithms (for traffic flow and pollutants), high-precision traffic flow restoration and prediction algorithms, and high-precision road condition restoration and prediction algorithms. The thematic layer includes thematic data sets from the situation center, travel center, control center, vehicle center, event center, and equipment center. The situation center includes, but is not limited to, data on traffic efficiency, delay index, queue length, and congestion duration; the travel center includes, but is not limited to, data on traffic statistics, traffic prediction, OD (Original Distance) travel, and passenger flow analysis; the control center includes, but is not limited to, data on signal optimization, green wave recommendation, tidal lanes, and reversible lanes; the vehicle center includes, but is not limited to, data on vehicle profiles, travel purposes, and vehicle trajectories; the event center includes, but is not limited to, data on congestion point detection, congestion events, safety incidents, and illegal events; and the equipment center includes, but is not limited to, data on equipment statistics, equipment status, equipment blind spot filling, and equipment monitoring. The application layer refers to the application services provided during the application of the urban data twin model, including but not limited to traffic guidance, signal optimization, situational awareness, public transport optimization, event awareness, transportation supervision, digital apron, security and control, fare evasion investigation, and key vehicles.

[0185] Taking the natural resource scenario as an example, in the application of the natural resource scenario, the data structure includes a detailed layer, a thematic layer, and an application layer. The detailed layer includes basic information, project information, spatial information, object relationships, events, and other data of the natural resource digital twin model. Among them, the basic information includes, but is not limited to, participants, natural resources, buildings (structures), and management units; project information includes, but is not limited to, development, construction, protection, management, and transactions; object relationships include, but are not limited to, river segment relationships, spatial relationships, component relationships, and land parcel relationships; events include, but are not limited to, disaster events, regulatory events, and violation events; spatial information includes, but is not limited to, vectors, coordinate systems, and grids.

[0186] This thematic layer includes thematic data sets such as management approvals, ecological environment, urban health check, enterprise profiling, natural resources, and spatial profiling. Management approvals include, but are not limited to, data on status, quantity, temporality, and evaluation; ecological environment includes, but is not limited to, data on climate, AOI, weather, and quality; urban health check includes, but is not limited to, data on ecological livability, convenient transportation, distinctive landscape, and safety resilience; enterprise profiling includes, but is not limited to, data on emissions, land, credit, and finance; natural resources includes, but is not limited to, data on temporality, density, quantity, and ownership; and spatial profiling includes, but is not limited to, development intensity, density, connectivity, and topography. This application layer includes application services such as urban health check, job-housing analysis, unified land management, intelligent site selection, spatial governance, benefit evaluation, land use identification, asset appraisal, spatial planning, and BIM review.

[0187] The full-domain digital assets include three aspects: data assets, unified services, and twin object construction. Data assets include, but are not limited to, asset cataloging, asset retrieval, asset permissions, asset access, security policies, and end-to-end lineage. Unified services include, but are not limited to, data reporting services, spatial service publishing, data service publishing, service flow control, service monitoring, and service authentication. Twin object construction includes, but is not limited to, twin object construction, spatial semantic retrieval, spatial object retrieval, spatial object management, spatial association analysis, object relationship management, and object attribute management.

[0188] Furthermore, the "Building a Digital China in the Whole Domain" initiative also provides 2D and 3D rendering engines, as well as data governance tools. The 2D and 3D rendering engines include 2D map rendering, 3D scene rendering, physical entity rendering, and index indicator rendering. The data governance tools include solution tools for product packaging, version management, and solution instantiation; data quality tools for quality rule design, quality plan management, quality reporting, and quality monitoring alarms; data modeling tools for data standard management, physical table design, and model relationship management; data exploration tools for physical table exploration and spatial data exploration; and data synchronization tools for unstructured data access, vector and structured data access, databases, and raster message middleware.

[0189] The project's application component can be understood as the applications provided to users based on the constructed urban digital twin. These applications mainly include transportation, main construction, water pollution source tracing, stormwater and sewage pipe network health analysis, and urban flooding traffic impact analysis. Among these, the housing and construction applications include comprehensive treatment of idle and inefficient land, urban health check, CIM digital construction assessment, and the entire life cycle of buildings. The transportation applications include signal optimization and control, traffic situation analysis, traffic simulation pre-research, and holographic intersection reconstruction. The water pollution source tracing applications include analysis of the spatiotemporal distribution of pollutant propagation, calculation of propagation paths, and inversion of water quality parameters. The stormwater and sewage pipe network health analysis applications include analysis of overall liquid level, flow rate, and water quality, identification of urban flooding points, and spatiotemporal analysis of urban flooding. The urban flooding traffic impact analysis applications include meteorological impact analysis, urban flooding traffic simulation, and pipe network water flow simulation.

[0190] Based on the above Figure 8 This specification describes the application of the digital twin object processing method in real-world scenarios and the data structure of the digital twin object processing system. For details on the data flow of this digital twin object processing system, please refer to [link to relevant documentation]. Figure 9 , Figure 9 This is a schematic diagram of the data flow in a digital twin system architecture provided in one embodiment of a digital twin object processing method according to this specification; based on Figure 9As can be seen, this data stream comprises three parts: file storage, database, and front-end rendering. The file storage data stream includes spatial data and project data. The spatial data includes raster data, vector data, 2D data, and 3D data. The project data includes offline data and real-time data. After storing the data received from the file storage into the database, a digital twin object construction process is performed based on the data in the database. Through steps such as data access and object management involved in digital twin object construction, a city digital twin object is constructed, and indicators are fused with the digital twin object and project data. Simultaneously, the constructed digital twin object can be sent to the front-end (client) for rendering via a rendering service.

[0191] The twin object processing method provided in this specification enables the rapid generation of an initial digital twin object based on the object configuration data of the target physical object using a digital twin object template corresponding to the target physical object. Then, by using the current state data of the target physical object and the initial digital twin object, the generation efficiency of the target digital twin object is further improved, thereby avoiding the problem of low efficiency in building digital twin objects due to spending a lot of time on data processing, thus quickly building a digital twin object for the target physical object.

[0192] The following is in conjunction with the appendix Figure 10 Taking the application of the digital twin object processing method provided in this specification in the construction of an urban traffic twin scenario as an example, the digital twin object processing method will be further explained. Figure 10 The present specification illustrates a flowchart of a digital twin object processing method according to an embodiment, which includes the following steps.

[0193] Step 1002: Based on the physical entities such as roads, traffic lights, and ground in various cities, the server defines a set of standard entity data templates (i.e., entity model definitions); and generates one or more object generation algorithms for each entity data template.

[0194] Each physical entity corresponds to a digital twin object.

[0195] Step 1004: Receive a request to build a digital twin of the city's transportation system for city A. Based on the request, select the entity data template corresponding to the city's transportation system from the pre-defined entity data templates.

[0196] The city's transportation system has multiple corresponding entity data templates, and each entity data template corresponds to a type of transportation facility (such as roads, traffic lights, bus stops, etc.). The digital twin construction request is a request sent by the user through a terminal device.

[0197] Step 1006: Obtain data on traffic infrastructure such as roads, traffic lights, and bus stops in City A.

[0198] Specifically, this solution uses sensors, radars, or cameras mounted on spaceborne or airborne vehicles to collect data on traffic infrastructure in City A, such as roads, traffic lights, and bus stops. This data includes static spatial data such as high-precision maps, satellite imagery, and urban white-film maps, as well as dynamic data such as video, radar, loop detectors, and Gaode Maps data. After the data is integrated, it undergoes standardized processing, storage, and quality monitoring to ensure its availability.

[0199] Step 1008: Perform data preprocessing on the traffic facility data, such as format unification and integrity checks, to obtain standardized traffic facility data.

[0200] Step 1010: Based on the facility type of the transportation facility data, determine the corresponding entity data template.

[0201] Step 1012: Input the traffic facility data into the object generation algorithm corresponding to each entity to perform entity modeling and obtain the digital twin object corresponding to the entity.

[0202] The entity modeling includes project modeling, geometric modeling, mechanism modeling, and spatial semantic modeling; through entity modeling, multiple data models corresponding to the transportation facility can be obtained.

[0203] For example, image data of a road entity is input into an algorithm model for modeling, thereby obtaining the road surface data module corresponding to that road entity. A physical entity has multiple types of entity data (e.g., imagery, point cloud data), therefore, after entity modeling, the physical entity will correspond to multiple data models; a digital twin of a physical entity is achieved through these multiple data models.

[0204] Based on the above operations, the entire road network model can be constructed, enriching the spatial attributes of the road network; including editing of high-precision road networks, mounting of intersection equipment, and 3D modeling.

[0205] Step 1014: Using predefined unified encoding rules, encode each object uniformly to obtain the management code, spatial code, and time code of each digital twin object, which are used for querying digital twin objects.

[0206] Step 1016: Based on the digital twin object corresponding to the entity, construct the urban transportation twin of City A.

[0207] Step 1018: Collect dynamic traffic data of city A in real time using devices such as cameras and sensors.

[0208] This dynamic traffic data can include vehicle flow, number of pedestrians, etc.

[0209] Step 1020: Determine the dynamic traffic data and the corresponding digital twin object, and use intelligent algorithms to fuse and calculate the dynamic traffic data and the digital twin object to obtain the digital twin object of the city's traffic.

[0210] Specifically, based on a road network model with spatial attributes, multi-source index fusion analysis is performed. On the basis of the road segment entity ONEID, various dynamic data are integrated to realize the analysis of various traffic indicators, such as congestion rate.

[0211] Furthermore, based on the collected data, road network analysis and simulation can be performed, including vehicle trajectory reconstruction, vehicle-road cooperation, and variable lane analysis and optimization. Users, through service publishing and command issuance, bridge the gap between roadside and terminal control, achieving true signal optimization and vehicle-road cooperation, forming a closed loop from data perception to fusion computing to analysis and simulation to control optimization.

[0212] Step 1022: Visualize the urban traffic twin and simulation results, and display them to the user through the terminal.

[0213] This urban traffic twin can be understood as a digital twin object of urban traffic.

[0214] Step 1024: Monitor the dynamic traffic data of traffic infrastructure in real time and update the urban traffic twin based on the data.

[0215] This manual provides a method for constructing a city's digital twin scene across the entire chain. Compared to solutions that focus on visualization and rendering, and solutions that concentrate on building digital twin object knowledge graphs in the industrial manufacturing field, the method provided in this manual can quickly establish a digital volume mapping of twin entities, realize the integration of their entire lifecycle and all elements of data, and allow dynamic and static data to flow freely and be fused in the indicator calculation domain, simulation and deduction domain, 3D rendering domain, and autonomous driving domain, achieving the integration of visual and computational aspects of twin data and the fusion of the four domains.

[0216] It should be noted that the solution provides a method for constructing urban digital twin scenarios across the entire chain. This method is a data intelligent generation pipeline that integrates data collection, urban digital twin object generation, twin scenario construction, multi-source data fusion calculation, unified twin services, and finally, 2D and 3D spatiotemporal data rendering. It enables rapid construction of urban digital twin scenarios and supports the construction of digital twin scenarios for ultra-large-scale cities. It integrates urban digital twin data collection, twin object generation, spatial scenario construction, multi-source fusion index calculation, and 2D and 3D rendering across the entire chain.

[0217] Based on the aforementioned core capabilities, a smart production line for rapidly constructing urban spatiotemporal digital twins has been established, achieving unified entity definition, unified spatiotemporal coding, unified twin construction, and unified service support. It realizes a closed-loop output of urban twin object digitization, spatial editing, 3D modeling, and visualization secondary development, providing partners with a one-stop platform for the entire process of data access, editing, indicator retrieval, 3D model generation, and visualization development. Ecosystem partners building urban digital twin applications based on this platform have significantly improved the richness and expressive accuracy of twin elements, increasing application development efficiency by 50%.

[0218] Corresponding to the above method embodiments, this specification also provides embodiments of a digital twin object processing system. Figure 11 A schematic diagram of the structure of a digital twin object processing system provided in one embodiment of this specification is shown. Figure 11 As shown, the system includes an object determination node 1102, a data acquisition node 1104, a data fusion node 1106, and an object display node 1108.

[0219] The object determination node 1102 is configured to determine the object configuration data of the target physical object and the digital twin object template corresponding to the target physical object, and to determine the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template.

[0220] The data acquisition node 1104 is configured to acquire the current state data of the target physical object;

[0221] The data fusion node 1106 is configured to determine the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object;

[0222] The object display node 1108 is configured to render the target digital twin object to the object display page of the user terminal, and display the target digital twin object to the user through the object display page of the user terminal.

[0223] The multiple nodes in this digital twin object processing system can be understood as multiple servers, which can be cloud servers or physical servers.

[0224] Among them, the object determination node 1102 can realize the above-mentioned steps of global digital construction, the data acquisition node 1104 can realize the above-mentioned steps of intelligent fusion perception, the data fusion node 1106 can realize the above-mentioned steps of multi-source data fusion, and the object display node 1108 can realize the above-mentioned steps of spatiotemporal data visualization.

[0225] It should be noted that the explanation of this digital twin object processing system can be found in the corresponding or relevant content of the above-mentioned digital twin object processing method, and will not be elaborated further here.

[0226] The digital twin object processing system provided in this specification enables the rapid generation of an initial digital twin object based on the object configuration data of the target physical object using a digital twin object template corresponding to the target physical object. Then, by using the current state data of the target physical object and this initial digital twin object, the generation efficiency of the target digital twin object is further improved. This avoids the problem of low efficiency in constructing digital twin objects due to spending a lot of time on data processing, thus enabling the rapid construction of digital twin objects for the target physical object.

[0227] The above is an illustrative scheme of a digital twin object processing system according to this embodiment. It should be noted that the technical solution of this digital twin object processing system and the technical solution of the digital twin object processing method described above belong to the same concept. For details not described in detail in the technical solution of the digital twin object processing system, please refer to the description of the technical solution of the digital twin object processing method described above.

[0228] Corresponding to the above method embodiments, this specification also provides embodiments of a digital twin object processing apparatus, which includes:

[0229] The determination module is configured to determine the object configuration data of the target physical object and the digital twin object template corresponding to the target physical object;

[0230] The initial object determination module is configured to determine the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template.

[0231] The target object determination module is configured to determine the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object.

[0232] Optionally, the determining module is further configured to:

[0233] Determine the type of the target physical object;

[0234] Based on the type of the target physical object, the object configuration data of the target physical object is determined from the object configuration data of at least two types of initial physical objects obtained in advance, and the digital twin object template corresponding to the target physical object is determined from the digital twin object templates of at least two types of initial physical objects that are pre-configured.

[0235] Optionally, the digital twin object processing device further includes a data acquisition module, configured to:

[0236] Obtain the configuration data to be processed for the at least two types of initial physical objects, wherein the configuration data to be processed is obtained by configuring the data acquisition device to perform data acquisition and processing on the at least two types of initial physical objects;

[0237] The configuration data to be processed is preprocessed to obtain object configuration data for the at least two types of initial physical objects.

[0238] Optionally, the initial object determination module is further configured to:

[0239] Determine the object generation algorithm corresponding to the digital twin object template, and use the object generation algorithm to process the object configuration data to obtain the digital twin data corresponding to the object configuration data;

[0240] The digital twin data is filled into the digital twin object template to obtain the initial digital twin object corresponding to the target physical object.

[0241] Optionally, the object generation algorithm is at least two, and the object configuration data is of at least two types;

[0242] Accordingly, the initial object determination module is further configured to:

[0243] Determine the data types of at least two types of object configuration data, and based on the data types, determine the object generation algorithm associated with the at least two types of object configuration data from at least two object generation algorithms;

[0244] The configuration data of the at least two types of objects are input into an associated object generation algorithm to obtain digital twin data corresponding to the configuration data of the at least two types of objects.

[0245] Optionally, the digital twin object processing device further includes an encoding module configured to:

[0246] The corresponding digital twin object code is determined for the initial digital twin object based on the encoding generation rules;

[0247] Accordingly, after determining the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object, the process further includes:

[0248] The receiving end sends an object acquisition request, wherein the object acquisition request carries the digital twin object code of the digital twin object to be acquired, and the initial digital twin object has the same digital twin object code as the corresponding target digital twin object;

[0249] Based on the digital twin object encoding, the digital twin object to be acquired is determined from the target digital twin object, and the digital twin object to be acquired is returned to the object acquisition end.

[0250] Optionally, the encoding module is further configured to:

[0251] The spatial parameters of the initial digital twin object are determined, and the spatial parameters are encoded to obtain the spatial code of the initial digital twin object;

[0252] Determine the time parameters of the initial digital twin object, and encode the time parameters to obtain the time code of the initial digital twin object;

[0253] The object type parameter of the initial digital twin object is determined, and the object type parameter is encoded to obtain the object management code of the initial digital twin object;

[0254] The spatial encoding, temporal encoding, and / or object management encoding are determined as the digital twin object encoding of the initial digital twin object.

[0255] Optionally, the target object determination module is further configured to:

[0256] The current state of the target physical object is monitored by the state data acquisition device to obtain the current state data of the target physical object;

[0257] Based on the current state data, the digital twin data corresponding to the initial digital twin object is updated and / or added to obtain the target digital twin object corresponding to the target physical object.

[0258] Optionally, the target object determination module is further configured to:

[0259] The current state of the target physical object is monitored by the state data acquisition device to obtain the initial current state data of the target physical object;

[0260] Determine whether the initial current state data meets the preset data conditions.

[0261] If so, then the initial current state data shall be used as the current state data of the target physical object.

[0262] If not, the initial current state data is adjusted using a data processing algorithm, and the adjusted initial current state data is used as the current state data of the target physical object.

[0263] Optionally, the digital twin object processing apparatus further includes a rendering module, configured to:

[0264] In response to an object rendering request sent by a user, the target digital twin object is rendered onto the object display page of the user's terminal, and the target digital twin object is displayed to the user through the object display page of the user's terminal.

[0265] The digital twin object processing device provided in this specification enables the rapid generation of an initial digital twin object based on the object configuration data of the target physical object using a digital twin object template corresponding to the target physical object. Then, by using the current state data of the target physical object and the initial digital twin object, the generation efficiency of the target digital twin object is further improved, thereby avoiding the problem of low efficiency in building digital twin objects due to spending a lot of time on data processing, thus quickly building a digital twin object for the target physical object.

[0266] The above is a schematic scheme of a digital twin object processing device according to this embodiment. It should be noted that the technical solution of this digital twin object processing device and the technical solution of the digital twin object processing method described above belong to the same concept. For details not described in detail in the technical solution of the digital twin object processing device, please refer to the description of the technical solution of the digital twin object processing method described above.

[0267] Figure 12 A structural block diagram of a computing device 1200 according to an embodiment of this specification is shown. The components of the computing device 1200 include, but are not limited to, a memory 1210 and a processor 1220. The processor 1220 is connected to the memory 1210 via a bus 1230, and a database 1250 is used to store data.

[0268] The computing device 1200 also includes an access device 1240, which enables the computing device 1200 to communicate via one or more networks 1260. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 1240 may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) interface, a Wi-MAX interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0269] In one embodiment of this specification, the aforementioned components of the computing device 1200 and Figure 12 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 12 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0270] The computing device 1200 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device 1200 can also be a mobile or stationary server.

[0271] The processor 1220 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-described digital twin object processing method.

[0272] The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the digital twin object processing method described above belong to the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the digital twin object processing method described above.

[0273] An embodiment of this specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the digital twin object processing method described above.

[0274] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the digital twin object processing method described above belong to the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the digital twin object processing method described above.

[0275] An embodiment of this specification also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described digital twin object processing method.

[0276] The above is an illustrative scheme of a computer program according to this embodiment. It should be noted that the technical solution of this computer program and the technical solution of the digital twin object processing method described above belong to the same concept. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the digital twin object processing method described above.

[0277] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0278] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0279] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0280] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0281] The preferred embodiments disclosed above are merely illustrative of this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for processing digital twin objects, comprising: The method involves determining the object configuration data of a target physical object and the corresponding digital twin object template. This determination includes: determining the type of the target physical object; based on the type of the target physical object, determining the object configuration data of the target physical object from object configuration data of at least two types of initial physical objects obtained in advance; and determining the corresponding digital twin object template of the target physical object from digital twin object templates of at least two types of initial physical objects that have been pre-configured, wherein the target physical object includes at least two types. Based on the object configuration data and the digital twin object template, entity modeling is performed on the target physical object to determine the initial digital twin object corresponding to the target physical object; wherein, the entity modeling includes project modeling, geometric modeling, mechanism modeling and spatial semantic modeling; the spatial semantics in the spatial semantic modeling is used to express the spatial relationships between objects; Based on the current state data of the target physical object and the initial digital twin object, the target digital twin object corresponding to the target physical object is determined, and the target digital twin object is merged to obtain a digital twin object.

2. The digital twin object processing method according to claim 1, before determining the object configuration data of the target physical object and the digital twin object template corresponding to the target physical object, further includes: Obtain the configuration data to be processed for the at least two types of initial physical objects, wherein the configuration data to be processed is obtained by configuring the data acquisition device to perform data acquisition and processing on the at least two types of initial physical objects; The configuration data to be processed is preprocessed to obtain object configuration data for the at least two types of initial physical objects.

3. The digital twin object processing method according to claim 1, wherein determining the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template includes: Determine the object generation algorithm corresponding to the digital twin object template, and use the object generation algorithm to process the object configuration data to obtain the digital twin data corresponding to the object configuration data; The digital twin data is filled into the digital twin object template to obtain the initial digital twin object corresponding to the target physical object.

4. The digital twin object processing method according to claim 3, wherein the object generation algorithm is at least two, and the object configuration data is of at least two types; Accordingly, the step of processing the object configuration data using the object generation algorithm to obtain the digital twin data corresponding to the object configuration data includes: Determine the data types of at least two types of object configuration data, and based on the data types, determine the object generation algorithm associated with the at least two types of object configuration data from at least two object generation algorithms; The configuration data of the at least two types of objects are input into an associated object generation algorithm to obtain digital twin data corresponding to the configuration data of the at least two types of objects.

5. The digital twin object processing method according to any one of claims 1 to 4, after determining the initial digital twin object corresponding to the target physical object based on the object configuration data and the digital twin object template, further comprising: The corresponding digital twin object code is determined for the initial digital twin object based on the encoding generation rules; Accordingly, after determining the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object, the process further includes: The receiving end sends an object acquisition request, wherein the object acquisition request carries the digital twin object code of the digital twin object to be acquired, and the initial digital twin object has the same digital twin object code as the corresponding target digital twin object; Based on the digital twin object encoding, the digital twin object to be acquired is determined from the target digital twin object, and the digital twin object to be acquired is returned to the object acquisition end.

6. The digital twin object processing method according to claim 5, wherein determining the corresponding digital twin object code for the initial digital twin object based on the encoding generation rule includes: The spatial parameters of the initial digital twin object are determined, and the spatial parameters are encoded to obtain the spatial code of the initial digital twin object; Determine the time parameters of the initial digital twin object, and encode the time parameters to obtain the time code of the initial digital twin object; The object type parameter of the initial digital twin object is determined, and the object type parameter is encoded to obtain the object management code of the initial digital twin object; The spatial encoding, temporal encoding, and / or object management encoding are determined as the digital twin object encoding of the initial digital twin object.

7. The digital twin object processing method according to any one of claims 1 to 4, wherein determining the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object comprises: The current state of the target physical object is monitored by the state data acquisition device to obtain the current state data of the target physical object; Based on the current state data, the digital twin data corresponding to the initial digital twin object is updated and / or added to obtain the target digital twin object corresponding to the target physical object.

8. The digital twin object processing method according to claim 7, wherein the state data acquisition device monitors the current state of the target physical object to obtain the current state data of the target physical object, comprising: The current state of the target physical object is monitored by the state data acquisition device to obtain the initial current state data of the target physical object; Determine whether the initial current state data meets the preset data conditions; If so, the initial current state data shall be used as the current state data of the target physical object; If not, the initial current state data is adjusted using a data processing algorithm, and the adjusted initial current state data is used as the current state data of the target physical object.

9. The digital twin object processing method according to claim 7, after determining the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object, further includes: In response to a user's object rendering request, the target digital twin object is rendered onto the object display page of the user's terminal, and the target digital twin object is displayed to the user through the object display page of the user's terminal.

10. A digital twin object processing system, comprising an object identification node, a data acquisition node, a data fusion node, and an object display node, wherein, The object determination node is configured to determine the object configuration data of a target physical object and the digital twin object template corresponding to the target physical object. Based on the object configuration data and the digital twin object template, entity modeling is performed on the target physical object to determine the initial digital twin object corresponding to the target physical object. The determination of the object configuration data and the digital twin object template includes: determining the type of the target physical object; determining the object configuration data of the target physical object from object configuration data of at least two types of pre-acquired initial physical objects based on the type of the target physical object; and determining the digital twin object template corresponding to the target physical object from digital twin object templates of at least two types of pre-configured initial physical objects, wherein the target physical object includes at least two types; the entity modeling includes project modeling, geometric modeling, mechanistic modeling, and spatial semantic modeling; the spatial semantics in the spatial semantic modeling is used to express the spatial relationships between objects. The data acquisition node is configured to acquire the current state data of the target physical object; The data fusion node is configured to determine the target digital twin object corresponding to the target physical object based on the current state data of the target physical object and the initial digital twin object, and to fuse the target digital twin object to obtain a digital twin object. The object display node is configured to render the target digital twin object to the object display page of the user terminal, and display the target digital twin object to the user through the object display page of the user terminal.

11. A computing device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the digital twin object processing method according to any one of claims 1 to 9.

12. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the digital twin object processing method according to any one of claims 1 to 9.

Images