WO2023151566A1 - 数字孪生体系的构建方法、终端设备及存储介质 - Google Patents

数字孪生体系的构建方法、终端设备及存储介质 Download PDF

Info

Publication number
WO2023151566A1
WO2023151566A1 PCT/CN2023/074865 CN2023074865W WO2023151566A1 WO 2023151566 A1 WO2023151566 A1 WO 2023151566A1 CN 2023074865 W CN2023074865 W CN 2023074865W WO 2023151566 A1 WO2023151566 A1 WO 2023151566A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
target object
models
physical
digital twin
Prior art date
Application number
PCT/CN2023/074865
Other languages
English (en)
French (fr)
Inventor
滕云露
晏雁
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2023151566A1 publication Critical patent/WO2023151566A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/006—Mixed reality

Definitions

  • the present disclosure relates to the field of computer technology, and in particular to a method for constructing a digital twin system, a terminal device, and a storage medium.
  • Digital twin is a simulation process that makes full use of physical models, sensor updates, operation history, etc., integrates multi-disciplinary, multi-physical quantities, multi-scale, and multi-probability simulation processes, and completes the mapping in the virtual space to reflect the entire life cycle of the corresponding physical equipment. process.
  • an embodiment of the present disclosure provides a method for constructing a digital twin system, the construction method comprising: obtaining spatial data of the physical space where the target object is located, analyzing the spatial data, and obtaining plane graphic information of the physical entity and appearance feature description tag language; according to the plane graphic information and the appearance feature description tag language, match a first number of first models and target rendering materials corresponding to each of the first models in a preset model library Obtain a second model of the physical entity in the virtual space according to the first number of first models and the target rendering material corresponding to each of the first models; and acquire physical information data of the target object and mapping the physical information data into the second model to generate a digital twin system corresponding to the target object.
  • an embodiment of the present disclosure further provides a terminal device, the terminal device includes a processor, a memory, a computer program stored on the memory and executable by the processor, and a computer program for implementing the processor A data bus connecting and communicating with the memory, wherein when the computer program is executed by the processor, the steps of the method for constructing a digital twin system according to any one of the disclosures provided are realized.
  • an embodiment of the present disclosure further provides a storage medium for computer-readable storage, the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors , so as to realize the steps of the method for constructing a digital twin system as described in any one of the disclosure specifications.
  • FIG. 1 is a schematic flowchart of a method for constructing a digital twin system provided by an embodiment of the present disclosure
  • FIG. 2 is an application scenario diagram of a construction method of a digital twin system provided by an embodiment of the present disclosure.
  • Fig. 3 is a schematic structural block diagram of a terminal device provided by an embodiment of the present disclosure.
  • the digital twin system established in the virtual space requires the use of 3D modeling technology, and the current mainstream methods are mostly 3D modeling through manual modeling. This method requires the purchase of professional modeling software and a certain degree of expertise. Skilled personnel perform 3D modeling, and for different scenarios, the model is generally not reusable and needs to be remodeled, resulting in a long modeling cycle and high cost for 3D modeling.
  • the digital twin system established in the virtual space requires 3D modeling technology.
  • common modeling methods include: manual tool modeling, image synthesis modeling, and 3D scanner modeling.
  • 3D modeling through manual modeling requires the purchase of professional modeling software, and at the same time requires personnel with certain professional skills to perform 3D modeling, and if it is for different scenarios, the model is generally not reusable and needs to be re-used.
  • Modeling which leads to a long modeling cycle and high cost of 3D modeling;
  • 3D modeling through image synthesis modeling requires a specific algorithm to extract data from multiple 2D images and synthesize 3D data.
  • Embodiments of the present disclosure provide a method for constructing a digital twin system, a terminal device, and a storage medium.
  • the construction method can be applied to the server, thereby reducing the modeling cycle and modeling cost of 3D modeling, improving the modeling accuracy of 3D modeling, and thus constructing an accurate digital twin system.
  • FIG. 1 is a schematic flowchart of a method for constructing a digital twin system provided by an embodiment of the present disclosure.
  • the construction method of the digital twin system is used to automatically construct the digital twin system corresponding to the target object, so as to monitor the target object, and the construction method of the digital twin system can be specifically applied to a server.
  • the construction method of the digital twin system includes steps S101 to S104.
  • Step S101 Obtain the spatial data of the physical space where the target object is located, analyze the spatial data, and obtain the plane graphic information and appearance feature description tag language of the physical entity.
  • the embodiments of the present disclosure may be applied in a digital twin scenario.
  • the physical space can be the space corresponding to the need to build a digital twin system, for example, it can be a space such as a data center computer room.
  • the target object can be the equipment that needs to be monitored, such as servers, micro modules, power supply equipment, air conditioners, and generators in the data center computer room. All electronic equipment can be monitored.
  • Spatial data can include basic data for modeling such as spatial plans, spatial pictures, and spatial configuration data.
  • the physical entity may be an entity in physical space such as a building.
  • Plane graphic information can include a set of plane figures and a set of information descriptions corresponding to each figure, for example, it can include information such as the position of the figure, the size of the figure, the attributes of the figure; Pass parameters and parse internally. It should be noted that any language used to represent appearance features can also be used.
  • the line outline of the spatial plan is analyzed to obtain the plane graphic information of the physical entity; the spatial image is analyzed to obtain the appearance attributes of the physical entity; according to the spatial configuration data, the appearance attributes are configured to generate appearance features Describes the markup language. Therefore, by analyzing the space plan, space picture, and space configuration data, etc., the plane graphic information and appearance feature description label language can be obtained, so that the corresponding first model and target rendering material can be accurately matched in the model library, and It can make the analysis results more accurate and the matching degree higher.
  • the space plan can be a plan such as a construction drawing of a physical entity
  • the space picture can be a picture such as an appearance picture of the physical entity
  • the space configuration data can include the material type file of the physical entity and the information file of the target object, etc.
  • the appearance attribute can be the Material properties, color properties, lighting properties, horticultural properties, etc. of physical entities.
  • the plane graphic information of the physical entity is generated; and the spatial picture is analyzed to obtain the material attributes, color attributes, light source attributes, and gardening attributes of the physical entity, and then read the spatial configuration data to determine
  • the extended configuration parameter object corresponding to each attribute of the physical entity is used to perform attribute extension configuration binding on each attribute through the extended configuration parameter object, and generate the appearance feature description tag language.
  • the extended parameter object is generally Including angles, proportions, building classes, decorations, etc.
  • analyzing the line outline of the construction drawing to generate the planar graphic information of the physical entity may include a collection of various graphics such as squares and circles, and information such as the graphic position, graphic size, and graphic attributes of each graphic. And analyze the space picture, get the material of the physical entity is glass, the color attribute is green, blue and other attributes, and then read the space configuration data to determine the extended configuration parameter object corresponding to the material attribute and color attribute of the physical entity, Through the extended configuration parameter object, the properties such as material properties and color properties are bound to property expansion configuration, and the appearance feature description label language is generated.
  • Step S102 Match the first number of first models and target rendering materials corresponding to each first model in the preset model library according to the plane graphic information and the appearance feature description tag language.
  • the preset model library is used to store various first models and various rendering materials.
  • the first model can be a basic model for modeling. For example, when modeling a building, the corresponding models can be found in the model library for the exterior walls, interior walls, floors, doors, and windows of the building in the physical space. Both models can be considered as the first model.
  • the target rendering material is the rendering material corresponding to the matched first model.
  • the first quantity may be any quantity, which is not specifically limited here.
  • the first model in the model library is traversed according to the plane graphics information, and a first number of first models are matched; the rendering material of the model library is traversed according to the appearance feature description tag language, and the corresponding first models are matched.
  • the target render material for . Therefore, the first model corresponding to each planar figure in the planar figure information can be quickly matched, and the target rendering material corresponding to each first model can be quickly matched.
  • the first quantity may be the same as the number of components composed of the plane graphics in the plane graphics information.
  • the first A quantity is 4, which are the first models corresponding to the interior walls, floors, doors and windows respectively.
  • Step S103 Obtain a second model of the physical entity in the virtual space according to the first number of first models and the target rendering material corresponding to each first model.
  • the virtual space uses special software and hardware technology to divide a computer host into "virtual" hosts.
  • Each virtual host has an independent domain name and IP address (or shared IP address), with complete Internet server function.
  • It uses special software and hardware technology to divide a real physical computer host into multiple logical storage units. Since each unit has no physical entity, each physical unit can be on the network like a real physical host Work.
  • the second model is a model corresponding to the physical entity mapping in the virtual space.
  • the physical entity is modeled according to the first model to obtain a primitive model of the physical entity in the virtual space; based on a preset rendering algorithm, the pixel is modeled according to the target rendering material Momo The model is rendered to obtain the second model of the physical entity in the virtual space.
  • the 3D modeling of the physical entity and the rendering processing of the plain model can be intelligently performed, so that a second model with a high degree of restoration can be obtained.
  • the modeling algorithm is used to construct the model of the physical entity, so as to obtain the raw model model
  • the rendering algorithm is used to perform rendering processing on the raw model model, so as to obtain the second model.
  • various types of processing such as permutation, combination, fusion, deduplication, and optimization can be performed on various first models through preset modeling algorithms, so as to intelligently obtain the prime model of the physical entity in the virtual space, and then through The rendering algorithm performs rendering processing on each first model in the plain model, so as to intelligently obtain the second model of the physical entity in the virtual space.
  • the first number of first models are arranged and combined according to a preset modeling level to construct a second number of third models; the third model is deduplicated to obtain a third number of third models.
  • the physical entity can be accurately constructed, so as to obtain a plain model with a high degree of reduction.
  • it is easy to maintain and has a high degree of reusability, and there is no need to analyze and sample a large amount of training data and extract features through machine learning.
  • the modeling level may include levels such as base, building, floor, and room, and physical entities may be constructed sequentially according to the modeling level.
  • the third model is generated by permuting and combining the first model
  • the fourth model is obtained by deduplicating the third model
  • the initial plain model is obtained by fusing the fourth model. Used to generate prime models.
  • first quantity is greater than the second quantity
  • second quantity is greater than the third quantity
  • the first models can be sorted and constructed in sequence according to the modeling levels, and then the models constructed at these levels can be combined to generate the second number of third models, and these Where the third models overlap with each other, compare the attributes of the overlapped places. If the attribute comparison results show that they are the same third model, then perform deduplication processing on these third models, and remove the repeated third models. , to get the fourth model of the third quantity, and then render the fourth model as a whole to fuse them to generate the initial plain model model, and finally perform optimization processes such as aligning and elevating the initial plain model model as a whole to obtain the plain model model .
  • the mapping relationship between the target rendering material and the first model is determined; based on the mapping relationship, rendering processing is performed on the first model in the sketch model to obtain a second model of the physical entity in the virtual space. In this way, the rendering process can be performed on the plain model to obtain a second model with a high degree of restoration.
  • mapping relationship is used to reflect the relationship between the target rendering material and the first model.
  • mapping relationship between the target rendering material and the first model can be determined first; based on the mapping relationship, veneering, lighting, perspective, and texture processing are performed on the materials of each first model in the plain model model to obtain the physical entity in the virtual space.
  • the second model in .
  • the first model includes the models corresponding to the floor and the door, and the two models are obtained by matching in the preset model library.
  • the target rendering material corresponding to the first model for example, match the material corresponding to the floor with wood, and the material corresponding to the door is stainless steel, respectively determine and establish the mapping relationship between the target rendering material and the first model, and then according to the mapping relationship, the basic model
  • the first model in the model is rendered, and the first model corresponding to the floor and the door is rendered respectively, and so on, all the first models in the plain model are rendered to obtain the physical entity in the virtual space of the second model.
  • target rendering material includes not only material material, but also color material, texture material, etc., which are not specifically limited here.
  • Step S104 acquiring the physical information data of the target object, mapping the physical information data into the second model, and generating a digital twin system corresponding to the target object.
  • the physical information data is the associated information data of the target object in the physical space, which can specifically include sensor configuration data, object configuration information, and historical operation data, etc.
  • These physical information data can be stored in a preset information database, and the information database also includes It is used to store the constructed digital twin system.
  • the target object model is determined in the second model according to the physical information data; the physical information data and the target object model are bound to generate a digital twin system corresponding to the target object. In this way, a digital twin system corresponding to the target object can be constructed to monitor the target object in real time.
  • the target object model is the model corresponding to the target object in the virtual space.
  • the target object model can be considered as a type in the first model, and the corresponding target object model can be matched in the model library, and then compared with each first model Build together to get the second model.
  • the corresponding target object model can be determined in the second model in the virtual space through the associated information data of the target object in the physical space, so as to bind the physical information data with the target object model and generate the corresponding number of the target object twin system.
  • the second model is traversed to match the target object model.
  • the target object model can be accurately matched to the second model.
  • the sensor configuration data can include data such as the position of the sensor, the distance between the sensor and the target object, etc., which can be used to determine the position of the target object;
  • the object configuration information can include information such as unique identification code, object type, function description, and function data collection interface .
  • one or more ranging sensors may be set to measure the distances between multiple sensors and the target object, and then traverse the second model according to the positional relationship, so as to match the target object model in the second model.
  • the target object model can be quickly matched in the second model.
  • the unique identification code on the target object can be recognized by the recognition device, so as to determine the location and attributes of the target object, and then quickly match the target object model in the second model.
  • the sensor configuration data and object configuration information in the physical information data are bound with the target object model to obtain the monitoring information of the target object; according to the historical operation data and monitoring information, the state of the target object is evaluated, Get the state information of the target object. In this way, all states of each target object can be reflected, thereby reflecting the real life characteristics of each target object.
  • the monitoring information may be the information data of the target object, for example, may include online time, physical location, running time, working time, maintenance information, and alarm information.
  • the historical operation data is used to represent data such as the historical working hours of the target object, and the status information may specifically include working status and health status.
  • the sensor configuration data and object configuration information can be bound to the target object model, so that the monitoring information of the target object can be obtained through the second model, and the target object can be monitored according to the monitoring information, and then according to the historical operation data and Monitor information, evaluate the working status and health status of the target object, obtain the status information of the target object, realize the monitoring of the target object, analyze and evaluate in time whether it needs maintenance, whether it can withstand the next task load, etc.
  • the state information of the target object is acquired through the digital twin system, and it is determined whether the state information exceeds the corresponding alarm threshold; if the state information exceeds the corresponding alarm threshold, control Target object stops working. In this way, the target object can be monitored and alarmed in real time through the digital twin system, so as to solve the problem in time before it occurs and prevent downtime.
  • the alarm threshold may be any threshold, different target object types have different alarm thresholds, and each type of target device may have multiple alarm thresholds.
  • the alarm threshold can be any value, which is not specifically limited here.
  • the control target object stops working; if the state information does not exceed the corresponding warning threshold, the control target object continues to work.
  • the status information may be the battery level and health status of the battery; if the alarm threshold corresponding to the battery level is 30%, and the corresponding alarm threshold value is 70%, when the battery level is When the health status is 30%, it will control the target object to stop working, and send the corresponding alarm information to the corresponding terminal device to notify the user; when the health status is lower than 70%, it will also control the target object to stop working, and send the corresponding alarm information to the The corresponding terminal equipment to notify the user.
  • the application environment includes a terminal device 110 and a server 120, wherein the terminal device 110 can communicate with the server 120 through a network.
  • the server 120 obtains the access request sent by the terminal device 110, and the server 120 parses the access request, then reads the relevant information in the information database, encapsulates and packs it, obtains the information data set, and sends the information data set to the terminal Device 110 is used.
  • users can input various data in the model library and information database on the terminal device, specifically Various first models, various target object models and various rendering materials can be entered in the model library first. Then enter the physical information data of the target object in the information database, and finally import the spatial plan, spatial picture and spatial configuration data in the spatial data, so as to complete the information entry work.
  • the spatial plan, spatial picture, and spatial configuration data in the spatial data are analyzed in sequence, and the analysis result set corresponding to each spatial data will be obtained after analysis. If there is an error code in the analysis result set, the analysis is considered unsuccessful. , send the prompt message "spatial data cannot be parsed, please re-import" to the user, so that the user can re-import the corresponding spatial data; if there is no error code in the parsing result set, it is considered that the parsing is successful, and the plane graphic information of the physical entity is obtained and appearance feature description labeling language.
  • the parsing is successful, traverse the first model in the preset model library according to the plane graphic information. If the matching is successful, the first number of first models will be matched. If the matching is unsuccessful, it will send "Missing the first model, please Re-import" prompt information is given to the user, so that the user can re-import the corresponding first model.
  • processing such as permutation, combination, fusion, deduplication and optimization is performed according to the first number of first models, so as to generate a prime model of the physical entity in the virtual space.
  • processing such as permutation, combination, fusion, deduplication and optimization is performed according to the first number of first models, so as to generate a prime model of the physical entity in the virtual space.
  • traverse the rendering materials of the model library if the matching is successful, match the target rendering materials corresponding to each first model, if the matching is unsuccessful, send the prompt message "Missing rendering materials, please re-import" to the user, so that the user can re-import the corresponding rendered material.
  • the first model in the plain model is rendered, and the second model of the physical entity in the virtual space is obtained.
  • the physical information data of the target object is obtained from the information database, and the physical information data is mapped to the second model to generate a digital twin system corresponding to the target object, and the generated digital twin system is stored in the information database.
  • the user can send an access request on the terminal device and access the information database through the platform integration interface, so as to read the relevant information in the information database for packaging and packaging, and finally return the information data set to the terminal device for use.
  • the embodiments of the present disclosure can effectively reduce the labor cost, time cost, and capital investment cost of 3D modeling, and make up for the deficiencies in related modeling technologies; improve the accuracy of 3D modeling, and can automatically generate 3D models and intelligently build The digital twin system removes unnecessary attributes, has smaller capacity and better performance.
  • FIG. 3 is a schematic structural block diagram of a terminal device provided by an embodiment of the present disclosure.
  • the terminal device 200 includes a processor 201 and a memory 202, and the processor 201 and the memory 202 are connected through a bus 203, such as an I2C (Inter-integrated Circuit) bus.
  • a bus 203 such as an I2C (Inter-integrated Circuit) bus.
  • the processor 201 is used to provide computing and control capabilities to support the operation of the entire terminal device.
  • the processor 301 can be a central processing unit (Central Processing Unit, CPU), and the processor 301 can also be other general-purpose processors, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC ), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the memory 202 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) disk, an optical disk, a U disk, or a mobile hard disk.
  • FIG. 3 is only a block diagram of a part of the structure related to the embodiment of the present disclosure, and does not constitute a limitation on the terminal device to which the embodiment of the present disclosure is applied.
  • the terminal device may include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.
  • the processor is configured to run a computer program stored in the memory, and implement any one of the construction methods of the digital twin system provided by the embodiments of the present disclosure when executing the computer program.
  • the processor is configured to run a computer program stored in a memory, and implement the following steps when executing the computer program.
  • the processor parses the spatial data to obtain the plane graphic information and appearance feature description tag language of the physical entity, it is used to implement: parse the line outline of the spatial plane diagram to obtain the physical entity's Plane graphic information; analyzing the space picture to obtain the appearance attribute of the physical entity; configuring the appearance attribute according to the space configuration data to generate an appearance feature description tag language.
  • the processor realizes matching the first number of first models and the target rendering materials corresponding to each first model in the preset model library according to the plane graphic information and appearance feature description tag language , used to implement: Traverse the first model of the model library according to the plane graphics information, and match the first number of first models; according to the appearance feature description label language, traverse the rendering materials of the model library, and match each first model corresponding Target rendering material.
  • the processor when the processor obtains the second model of the physical entity in the virtual space according to the first number of first models and the target rendering material corresponding to each first model, it is used to realize: based on the preset The established modeling algorithm constructs the model of the physical entity according to the first model, and obtains the raw model of the physical entity in the virtual space; based on the preset rendering algorithm, renders the raw model according to the target rendering material, and obtains the physical model A second model of the entity in virtual space.
  • the processor when the processor implements a preset-based modeling algorithm, constructs a model of the physical entity according to the first model, and obtains a prime model of the physical entity in the virtual space, it is used to realize: according to the preset modeling level Arranging and combining the first models of the first quantity to construct the third model of the second quantity; performing deduplication processing on the third model to obtain the fourth model of the third quantity; performing model fusion processing on the fourth model to generate The initial raw model of the physical entity in the virtual space; the initial raw model is optimized to obtain the raw model of the physical entity in the virtual space.
  • the processor when the processor implements a rendering algorithm based on a preset, renders the model model according to the target rendering material, and obtains the second model of the physical entity in the virtual space, it is used to: determine the target Render the mapping relationship between the material and the first model; based on the mapping relationship, perform rendering processing on the first model in the plain model to obtain a second model of the physical entity in the virtual space.
  • the processor when the processor realizes mapping the physical information data into the second model to generate a digital twin system corresponding to the target object, it is used to realize: determining the target object model in the second model according to the physical information data ; Bind the physical information data with the target object model to generate a digital twin system corresponding to the target object.
  • the processor determines the target object model in the second model according to the physical information data, and is used to realize: traversing the second model according to the sensor configuration data and/or object configuration information to match the target object Model.
  • the processor when the processor implements the binding of the physical information data and the target object model, it is configured to: bind the sensor configuration data and object configuration information in the physical information data with the target object model, Obtain the monitoring information of the target object; evaluate the state of the target object according to the historical operation data and monitoring information, and obtain the state information of the target object.
  • the processor After the processor realizes generating the digital twin system corresponding to the target object, it is used to: obtain the state information of the target object through the digital twin system, and determine whether the state information exceeds the corresponding alarm threshold; if the state If the information exceeds the corresponding alarm threshold, the control target object will stop working.
  • An embodiment of the present disclosure also provides a storage medium for computer-readable storage, the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the following: The steps of any digital twin system construction method provided in the description of the embodiments of the present disclosure.
  • the storage medium may be an internal storage unit of the terminal device described in the foregoing embodiments, such as a hard disk or a memory of the terminal device.
  • the storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk equipped on the terminal device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, Flash card (Flash Card), etc.
  • the functional modules/units in the system, and the device can be implemented as software, firmware, hardware, and an appropriate combination thereof.
  • the The division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be cooperatively performed by several physical components.
  • Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit .
  • Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media).
  • computer storage media includes both volatile and nonvolatile media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. permanent, removable and non-removable media.
  • Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, tape, magnetic disk storage or other magnetic storage devices, or can Any other medium used to store desired information and which can be accessed by a computer.
  • communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Graphics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本公开实施例提供一种数字孪生体系的构建方法、终端设备及存储介质，属于计算机技术领域。该方法包括：获取目标对象所处物理空间的空间数据，对空间数据进行解析，得到物理实体的平面图形信息和外观特征描述标签语言；根据平面图形信息和外观特征描述标签语言，在预设的模型库中匹配出第一数量的第一模型和各个第一模型对应的目标渲染素材；根据第一数量的第一模型和各个第一模型对应的目标渲染素材，得到物理实体在虚拟空间中的第二模型；以及获取目标对象的物理信息数据，将物理信息数据映射到第二模型中，生成目标对象对应的数字孪生体系。

Description

数字孪生体系的构建方法、终端设备及存储介质
相关申请的交叉引用
本申请要求享有2022年02月08日提交的名称为“数字孪生体系的构建方法、终端设备及存储介质”的中国专利申请202210119344.9的优先权，其全部内容通过引用并入本申请中。
技术领域
本公开涉及计算机技术领域，尤其涉及一种数字孪生体系的构建方法、终端设备及存储介质。
背景技术
数字孪生是充分利用物理模型、传感器更新、运行历史等数据，集成多学科、多物理量、多尺度、多概率的仿真过程，在虚拟空间中完成映射，从而反映相对应的实体装备的全生命周期过程。
发明内容
第一方面，本公开实施例提供一种数字孪生体系的构建方法，所述构建方法包括：获取目标对象所处物理空间的空间数据，对所述空间数据进行解析，得到物理实体的平面图形信息和外观特征描述标签语言；根据所述平面图形信息和所述外观特征描述标签语言，在预设的模型库中匹配出第一数量的第一模型和各个所述第一模型对应的目标渲染素材；根据所述第一数量的第一模型和各个所述第一模型对应的所述目标渲染素材，得到所述物理实体在虚拟空间中的第二模型；以及获取所述目标对象的物理信息数据，将所述物理信息数据映射到所述第二模型中，生成所述目标对象对应的数字孪生体系。
第二方面，本公开实施例还提供一种终端设备，所述终端设备包括处理器、存储器、存储在所述存储器上并可被所述处理器执行的计算机程序以及用于实现所述处理器和所述存储器之间的连接通信的数据总线，其中所述计算机程序被所述处理器执行时，实现如本公开说明书提供的任一项所述的数字孪生体系的构建方法的步骤。
第三方面，本公开实施例还提供一种存储介质，用于计算机可读存储，所述存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现如本公开说明书提供的任一项所述的数字孪生体系的构建方法的步骤。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的一种数字孪生体系的构建方法的流程示意图；
图2为本公开实施例提供的一种数字孪生体系的构建方法的应用场景图；以及
图3为本公开实施例提供的一种终端设备的结构示意性框图。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开的一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
附图中所示的流程图仅是示例说明，不是必须包括所有的内容和操作/步骤，也不是必须按所描述的顺序执行。例如，有的操作/步骤还可以分解、组合或部分合并，因此实际执行的顺序有可能根据实际情况改变。
应当理解，在此本公开说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本公开。如在本公开说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
在虚拟空间中建立的数字孪生体系需要利用3D建模技术，而目前主流方法大多是通过手工建模的方式进行3D建模，这种方式需要购买专业的建模软件，同时还需要具有一定专业技能的人员进行3D建模，而且若针对不同的场景时，该模型一般都不可复用，需要重新进行建模，从而导致3D建模的建模周期长，成本也较高。
首先，先对相关技术中常见的3D建模方法进行介绍。
在虚拟空间中建立的数字孪生体系需要3D建模技术，目前常见的建模方法有：手工工具建模、图片合成建模、三维扫描仪建模。通过手工建模的方式进行3D建模需要购买专业的建模软件，同时还需要具有一定专业技能的人员进行3D建模，而且若针对不同的场景时，该模型一般都不可复用，需要重新进行建模，从而导致3D建模的建模周期长，成本也较高；而通过图片合成建模的方式进行3D建模需要通过特定算法将多张二维图片提取数据合成三维数据，这种方式还原度低、精度低，且凹凸面无法建模；而通过三维扫描仪建模的方式进行3D建模需要通过三维扫描仪设备对物体进行扫描，得到三维数据， 但是扫描仪价格较高，且扫描模型需要人工后期调整修复，才能达到效果与质量的平衡。综上所述，目前常见的建模方法均会导致3D建模的建模周期长，成本也相对比较高。
本公开实施例提供一种数字孪生体系的构建方法、终端设备及存储介质。其中，该构建方法可应用于服务器中，由此可以降低3D建模的建模周期以及建模成本，提高3D建模的建模精度，从而构建精准的数字孪生体系。
请参照图1，图1为本公开实施例提供的一种数字孪生体系的构建方法的流程示意图。该数字孪生体系的构建方法用于自动构建目标对象对应的数字孪生体系，从而对目标对象进行监控，该数字孪生体系的构建方法具体可以应用于服务器中。
如图1所示，该数字孪生体系的构建方法包括步骤S101至步骤S104。
步骤S101、获取目标对象所处物理空间的空间数据，对空间数据进行解析，得到物理实体的平面图形信息和外观特征描述标签语言。
其中，本公开实施例可以应用在数字孪生的场景中。物理空间可以为需要构建数字孪生体系对应的空间，比如可以是数据中心机房等空间。目标对象可以为需要被监控的设备，比如可以为数据中心机房中的服务器、微模块、电源设备、空调和发电机等设备，所有的电子设备都是可以被监控的。空间数据可以包括空间平面图、空间图片和空间配置数据等用于建模的基础数据。物理实体可以为建筑物等在物理空间的实体。平面图形信息可以包括平面图形集合和各个图形对应的信息描述集合，比如可以包括图形位置、图形大小、图形属性等信息；外观特征描述标签语言(Meta description Language，MDL)为一个脚本语言，供程序内部进行传参以及解析。需要说明的是，也可以使用任何用于表征外观特征的语言。
在一些实施例中，对空间平面图的线条轮廓进行解析，得到物理实体的平面图形信息；对空间图片进行解析，得到物理实体的外观属性；根据空间配置数据，对外观属性进行配置，生成外观特征描述标签语言。由此可以通过对空间平面图、空间图片和空间配置数据等进行解析，得到平面图形信息和外观特征描述标签语言，从而能够准确地在模型库中匹配出对应的第一模型和目标渲染素材，且能够使分析结果更为精准，匹配度更高。
其中，空间平面图可以为物理实体的施工图纸等平面图，空间图片可以为物理实体的外观图片等图片，空间配置数据可以包括物理实体的材质类型文件和目标对象的信息文件等，外观属性可以为该物理实体的材料属性、颜色属性、光源属性、园艺属性等等。
具体地，通过解析空间平面图的线条轮廓，生成物理实体的平面图形信息；并对空间图片进行解析，得到物理实体的材料属性、颜色属性、光源属性、园艺属性，再读取空间配置数据，确定物理实体的各个属性对应的扩展配置参数对象，通过扩展配置参数对象对各个属性进行属性扩展配置绑定，生成外观特征描述标签语言。其中，扩展参数对象一般 包括角度、比例、建筑物等级、装饰等。
示例性的，解析施工图纸的线条轮廓，生成物理实体的平面图形信息可以包括正方形、圆形等各种图形集合，以及每个图形的图形位置、图形大小、图形属性等信息。并对空间图片进行解析，得到物理实体的材料为玻璃，颜色属性为绿色、蓝色等属性，再读取空间配置数据，确定物理实体的材料属性和颜色属性等属性对应的扩展配置参数对象，通过扩展配置参数对象对材料属性和颜色属性等属性进行属性扩展配置绑定，生成外观特征描述标签语言。
步骤S102、根据平面图形信息和外观特征描述标签语言，在预设的模型库中匹配出第一数量的第一模型和各个第一模型对应的目标渲染素材。
其中，预设的模型库用于存储各种第一模型和各种渲染素材。第一模型可以为建模的基础模型，比如在对建筑物进行建模时，物理空间的楼房的外墙、内墙、地板、门、窗等均可以在模型库中找到对应的模型，这些模型均可以认为是第一模型。目标渲染素材为匹配出的第一模型所对应的渲染素材。第一数量可以为任意数量，在此不做具体限定。
在一些实施例中，根据平面图形信息，遍历模型库的第一模型，匹配出第一数量的第一模型；根据外观特征描述标签语言，遍历模型库的渲染素材，匹配出各个第一模型对应的目标渲染素材。由此可以快速匹配出与平面图形信息中各个平面图形相对应的第一模型，并快速匹配出与各个第一模型相对应的目标渲染素材。
其中，第一数量可以与平面图形信息的平面图形所组成的部件数量相同，比如平面图形信息中平面图形所组成的部件有4种，分别为内墙、地板、门和窗，则此时第一数量为4个，分别为内墙、地板、门和窗对应的第一模型。
具体地，可以先根据平面图形信息，遍历模型库中存储的各种第一模型，匹配出与平面图形信息相适配的第一模型，再根据外观特征描述标签语言，遍历模型库的各种渲染素材，再匹配出与各个第一模型相对应的目标渲染素材。
步骤S103、根据第一数量的第一模型和各个第一模型对应的目标渲染素材，得到物理实体在虚拟空间中的第二模型。
其中，虚拟空间是使用特殊的软硬件技术，把一台计算机主机分成一台台“虚拟”的主机，每一台虚拟主机都具有独立的域名和IP地址(或共享的IP地址)，具有完整的Internet服务器功能。是使用特别的软件和硬件技术，把一台真实的物理电脑主机分割成多个的逻辑存储单元，每个单元由于没有物理实体，但是每一个物理单元都能像真实的物理主机一样在网络上工作。第二模型为物理实体映射在虚拟空间中对应的模型。
在一些实施例中，基于预设的建模算法，根据第一模型对物理实体进行模型构建，得到物理实体在虚拟空间中的素模模型；基于预设的渲染算法，根据目标渲染素材对素模模 型进行渲染处理，得到物理实体在虚拟空间中的第二模型。由此可以智能对物理实体进行3D建模以及智能对素模模型进行渲染处理，从而能够得到还原度高的第二模型。
其中，建模算法用于对物理实体进行模型构建，从而得到素模模型，渲染算法用于对素模模型进行渲染处理，从而得到第二模型。
具体地，可以通过预设的建模算法对各种第一模型进行排列组合、融合、去重和优化等各种类型的处理，从而智能得到物理实体在虚拟空间中的素模模型，再通过渲染算法对素模模型中各个第一模型进行渲染处理，从而智能得到物理实体在虚拟空间中的第二模型。
在一些实施例中，根据预设的建模层级对第一数量的第一模型进行排列组合，构建得到第二数量的第三模型；对第三模型进行去重处理，得到第三数量的第四模型；对第四模型进行模型融合处理，生成物理实体在虚拟空间中的初始素模模型；对初始素模模型进行模型优化处理，得到物理实体在虚拟空间中的素模模型。由此可以准确地对物理实体进行构建，从而得到还原度高的素模模型。同时通过采用对第一模型进行排列组合的理念，易维护，复用度高，无需通过机器学习对大量训练数据进行分析采样、特征提取。
其中，建模层级可以包括基层、楼房、楼层和房间等层级，可以根据建模层级依次对物理实体进行构建。第三模型为通过对第一模型进行排列组合后生成的，第四模型为通过对第三模型进行去重处理后得到的，初始素模模型为通过对第四模型进行融合处理后得到的，用于生成素模模型。
需要说明的是，第一数量大于第二数量，第二数量大于第三数量。
具体地，可以根据预设的建模算法，根据建模层级依次对第一模型进行排序以及构建，再将这几个层级构建的模型组合起来，生成第二数量的第三模型，分别确定这些第三模型的相互重叠的地方，通过对相互重叠的地方进行属性对比，若属性对比结果显示为相同的第三模型，则对这些第三模型进行去重处理，将重复的第三模型去除掉，得到第三数量的第四模型，再将对第四模型进行整体渲染，使之融合生成初始素模模型，最后再对初始素模模型整体进行对齐、拉高等优化处理，从而得到素模模型。
在一些实施例中，确定目标渲染素材与第一模型的映射关系；基于映射关系，对素模模型中的第一模型进行渲染处理，得到物理实体在虚拟空间中的第二模型。由此可以对素模模型进行渲染处理，得到还原度高的第二模型。
其中，映射关系用于反映目标渲染素材与第一模型的关系。
具体地，可以先确定目标渲染素材与第一模型的映射关系；基于映射关系，对素模模型中各个第一模型的材质进行贴面、打光、透视、纹理处理，得到物理实体在虚拟空间中的第二模型。
示例性的，第一模型包括地板和门对应的模型，通过在预设的模型库中匹配得到这两 个第一模型所对应的目标渲染素材，比如匹配出地板对应的材质木质，门对应的材质为不锈钢，分别确定并建立目标渲染素材与第一模型的映射关系，再根据映射关系，对素模模型中的第一模型进行渲染处理，分别对地板和门对应的第一模型进行渲染处理，以此类推，对素模模型中的所有的第一模型进行渲染处理，得到物理实体在虚拟空间中的第二模型。
需要说明的是，目标渲染素材不仅仅包括材质素材，还可以包括颜色素材、纹路素材等等，在此不做具体限定。
步骤S104、获取目标对象的物理信息数据，将物理信息数据映射到第二模型中，生成目标对象对应的数字孪生体系。
其中，物理信息数据为目标对象在物理空间中的关联信息数据，具体可以包括传感器配置数据、对象配置信息和历史运行数据等，这些物理信息数据可以存储在预设的信息数据库中，信息数据库还用于存储构建好的数字孪生体系。
在一些实施例中，根据物理信息数据在第二模型中确定目标对象模型；将物理信息数据与目标对象模型进行绑定，生成目标对象对应的数字孪生体系。由此可以构建目标对象对应的数字孪生体系，从而对目标对象进行实时监控。
其中，目标对象模型为目标对象在虚拟空间对应的模型，目标对象模型可以被认为是第一模型中的一种类型，可以通过模型库中匹配出对应的目标对象模型，再与各个第一模型一起构建得到第二模型。
具体地，可以通过目标对象在物理空间中的关联信息数据在虚拟空间中的第二模型中确定对应的目标对象模型，从而将物理信息数据与目标对象模型进行绑定，生成目标对象对应的数字孪生体系。
在一些实施例中，根据传感器配置数据和/或对象配置信息，遍历第二模型，匹配出目标对象模型。由此可以准确地在第二模型中匹配出目标对象模型。
其中，传感器配置数据可以包括传感器的位置，传感器与目标对象的距离等数据，可以用于确定目标对象的位置；对象配置信息可以包括唯一标识码、对象类型、功能描述和功能数据采集接口等信息。
示例性的，可以通过设置一个或多个测距传感器，从而测得多个传感器与目标对象的距离，再根据位置关系遍历第二模型，从而在第二模型中匹配出目标对象模型。
示例性的，可以通过确定目标对象的对象类型比如为空调，根据对象类型遍历第二模型中各个第一模型的属性信息，从而快速在第二模型中匹配出目标对象模型。
示例性的，假如传感器为识别装置，可以通过识别装置对目标对象上的唯一标识码进行识别，从而确定目标对象的位置以及属性等信息，进而快速在第二模型中匹配出目标对象模型。
在一些实施例中，将物理信息数据中的传感器配置数据和对象配置信息与目标对象模型进行绑定，得到目标对象的监控信息；根据历史运行数据和监控信息，对目标对象的状态进行评估，得到目标对象的状态信息。由此可以反映每个目标对象的所有状态，从而反映每个目标对象真实的生命特征。
其中，监控信息可以为目标对象的信息数据，比如可以包括上线时间，物理位置，运行时长，工作时长，维修信息以及告警信息等。历史运行数据用于表征目标对象的历史工作时长等数据，状态信息具体可以包括工作状态、健康状态等。
具体地，可以将传感器配置数据和对象配置信息与目标对象模型进行绑定，从而能够通过第二模型得到目标对象的监控信息，并根据该监控信息对目标对象进行监控，再根据历史运行数据和监控信息，对目标对象的工作状态、健康状态等进行评估，得到目标对象的状态信息，实现对目标对象的监控，及时分析评估是否需要维修，能否承受下次的任务载荷等。
在一些实施例中，在生成目标对象对应的数字孪生体系之后，通过数字孪生体系获取目标对象的状态信息，并确定状态信息是否超过对应的告警阈值；若状态信息超过对应的告警阈值，则控制目标对象停止工作。由此可以通过数字孪生体系对目标对象进行监控并实时告警，以在问题发生之前就及时解决，防止停机。
其中，告警阈值可以为任意阈值，不同的目标对象类型有不同的告警阈值，且每一种类型的目标设备可以有多种告警阈值。告警阈值可以为任意数值，在此不做具体限定。
具体地，确定状态信息是否超过对应的告警阈值；若状态信息超过对应的告警阈值，则控制目标对象停止工作；若状态信息未超过对应的告警阈值，则控制目标对象继续工作。
示例性的，比如当目标对象为电池时，状态信息可以为电池的电池电量和健康状态；若电池电量对应的告警阈值为30％，健康状态对应的告警阈值为70％，当电池电量低于30％时，会控制目标对象停止工作，并发送对应的告警信息给对应的终端设备以通知用户；当健康状态低于70％时，也会控制目标对象停止工作，并发送对应的告警信息给对应的终端设备以通知用户。
如图2所示，本申请实施例提供的数字孪生体系的构建方法，可以应用于如图2所示的应用环境中。该应用环境中包含有终端设备110和服务器120，其中，终端设备110可以通过网络与服务器120进行通信。具体地，服务器120获取终端设备110发送的访问请求，服务器120对该访问请求进行解析，然后读取信息数据库中的相关信息进行封装以及打包，得到信息数据集，并将信息数据集发送给终端设备110进行使用。
以下说明一下本申请实施例的整体流程。
首先，用户可以在终端设备上对模型库以及信息数据库中的各类数据进行录入，具体 可以先在模型库中录入各类第一模型、各种目标对象模型和各类渲染素材。再在信息数据库中录入目标对象的物理信息数据，最后再导入空间数据中的空间平面图、空间图片和空间配置数据等，从而完成信息录入工作。
信息录入后，分别对空间数据中的空间平面图、空间图片和空间配置数据等依次进行解析，解析后会得到各个空间数据对应的解析结果集，若解析结果集存在错误码，则认为解析不成功，发送“空间数据无法解析，请重新导入”的提示信息给用户，以使用户重新导入对应的空间数据；若解析结果集不存在错误码，则认为解析成功，则得到物理实体的平面图形信息和外观特征描述标签语言。
若解析成功后，根据平面图形信息，遍历预设模型库中的第一模型，若匹配成功，则匹配出第一数量的第一模型，若匹配不成功，则发送“缺失第一模型，请重新导入”的提示信息给用户，以使用户重新导入对应的第一模型。
若第一模型匹配成功后，根据第一数量的第一模型进行排列组合、融合、去重和优化等处理，从而生成物理实体在虚拟空间中的素模模型。根据外观特征描述标签语言，遍历模型库的渲染素材，若匹配成功，则匹配出各个第一模型对应的目标渲染素材，若匹配不成功，则发送“缺失渲染素材，请重新导入”的提示信息给用户，以使用户重新导入对应的渲染素材。
若目标渲染素材匹配成功后，对素模模型中的第一模型进行渲染处理，得到物理实体在虚拟空间中的第二模型。最后从信息数据库中获取目标对象的物理信息数据，并将物理信息数据映射到第二模型中，从而生成目标对象对应的数字孪生体系，并将生成的数字孪生体系存储在信息数据库中。用户可以在终端设备上发送访问请求，并通过平台集成接口来访问信息数据库，从而读取信息数据库中的相关信息进行封装、打包，最后将信息数据集返回给终端设备使用。本公开实施例能够有效地降低3D建模的人力成本、时间成本、资金投入成本，弥补了相关建模技术中的不足；提高3D建模的精准度，且能够自动生成的3D模型以及智能构建的数字孪生体系，去掉了不必要的属性，容量更小，性能更优。
请参阅图3，图3为本公开实施例提供的一种终端设备的结构示意性框图。
如图3所示，终端设备200包括处理器201和存储器202，处理器201和存储器202通过总线203连接，该总线比如为I2C(Inter-integrated Circuit)总线。
具体地，处理器201用于提供计算和控制能力，支撑整个终端设备的运行。处理器301可以是中央处理单元(Central Processing Unit，CPU)，该处理器301还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。其中，通用处理 器可以是微处理器或者该处理器也可以是任何常规的处理器等。
具体地，存储器202可以是Flash芯片、只读存储器(ROM，Read-Only Memory)磁盘、光盘、U盘或移动硬盘等。
本领域技术人员可以理解，图3中示出的结构，仅仅是与本公开实施例方案相关的部分结构的框图，并不构成对本公开实施例方案所应用于其上的终端设备的限定，具体的终端设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
其中，所述处理器用于运行存储在存储器中的计算机程序，并在执行所述计算机程序时实现本公开实施例提供的任意一种所述的数字孪生体系的构建方法。
在一实施例中，所述处理器用于运行存储在存储器中的计算机程序，并在执行所述计算机程序时实现如下步骤。
获取目标对象所处物理空间的空间数据，对空间数据进行解析，得到物理实体的平面图形信息和外观特征描述标签语言；根据平面图形信息和外观特征描述标签语言，在预设的模型库中匹配出第一数量的第一模型和各个第一模型对应的目标渲染素材；根据第一数量的第一模型和各个第一模型对应的目标渲染素材，得到物理实体在虚拟空间中的第二模型；获取目标对象的物理信息数据，将物理信息数据映射到第二模型中，生成目标对象对应的数字孪生体系。
在一实施例中，所述处理器在实现对空间数据进行解析，得到物理实体的平面图形信息和外观特征描述标签语言时，用于实现：对空间平面图的线条轮廓进行解析，得到物理实体的平面图形信息；对所述空间图片进行解析，得到所述物理实体的外观属性；根据所述空间配置数据，对所述外观属性进行配置，生成外观特征描述标签语言。
在一实施例中，所述处理器在实现根据平面图形信息和外观特征描述标签语言，在预设的模型库中匹配出第一数量的第一模型和各个第一模型对应的目标渲染素材时，用于实现：根据平面图形信息，遍历模型库的第一模型，匹配出第一数量的第一模型；根据外观特征描述标签语言，遍历模型库的渲染素材，匹配出各个第一模型对应的目标渲染素材。
在一实施例中，所述处理器在实现根据第一数量的第一模型和各个第一模型对应的目标渲染素材，得到物理实体在虚拟空间中的第二模型时，用于实现：基于预设的建模算法，根据第一模型对物理实体进行模型构建，得到物理实体在虚拟空间中的素模模型；基于预设的渲染算法，根据目标渲染素材对素模模型进行渲染处理，得到物理实体在虚拟空间中的第二模型。
在一实施例中，所述处理器在实现基于预设的建模算法，根据第一模型对物理实体进行模型构建，得到物理实体在虚拟空间中的素模模型时，用于实现：根据预设的建模层级 对第一数量的第一模型进行排列组合，构建得到第二数量的第三模型；对第三模型进行去重处理，得到第三数量的第四模型；对第四模型进行模型融合处理，生成物理实体在虚拟空间中的初始素模模型；对初始素模模型进行模型优化处理，得到物理实体在虚拟空间中的素模模型。
在一实施例中，所述处理器在实现基于预设的渲染算法，根据目标渲染素材对素模模型进行渲染处理，得到物理实体在虚拟空间中的第二模型时，用于实现：确定目标渲染素材与第一模型的映射关系；基于映射关系，对素模模型中的第一模型进行渲染处理，得到物理实体在虚拟空间中的第二模型。
在一实施例中，所述处理器在实现将物理信息数据映射到第二模型中，生成目标对象对应的数字孪生体系时，用于实现：根据物理信息数据在第二模型中确定目标对象模型；将物理信息数据与目标对象模型进行绑定，生成目标对象对应的数字孪生体系。
在一实施例中，所述处理器在实现根据物理信息数据在第二模型中确定目标对象模型，用于实现：根据传感器配置数据和/或对象配置信息，遍历第二模型，匹配出目标对象模型。
在一实施例中，所述处理器在实现将物理信息数据与目标对象模型进行绑定时，用于实现：将物理信息数据中的传感器配置数据和对象配置信息与目标对象模型进行绑定，得到目标对象的监控信息；根据历史运行数据和监控信息，对目标对象的状态进行评估，得到目标对象的状态信息。
在一实施例中，所述处理器在实现生成目标对象对应的数字孪生体系之后，用于实现：通过数字孪生体系获取目标对象的状态信息，并确定状态信息是否超过对应的告警阈值；若状态信息超过对应的告警阈值，则控制目标对象停止工作。
需要说明的是，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的终端设备的具体工作过程，可以参考前述数字孪生体系的构建方法实施例中的对应过程，在此不再赘述。
本公开实施例还提供一种存储介质，用于计算机可读存储，所述存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现如本公开实施例说明书提供的任一项数字孪生体系的构建方法的步骤。
其中，所述存储介质可以是前述实施例所述的终端设备的内部存储单元，例如所述终端设备的硬盘或内存。所述存储介质也可以是所述终端设备的外部存储设备，例如所述终端设备上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。
本领域普通技术人员可以理解，上文中所公开方法中的全部或某些步骤、系统、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。在硬件实施例中，在 以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分；例如，一个物理组件可以具有多个功能，或者一个功能或步骤可以由若干物理组件合作执行。某些物理组件或所有物理组件可以被实施为由处理器，如中央处理器、数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外，本领域普通技术人员公知的是，通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据，并且可包括任何信息递送介质。
应当理解，在本公开说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本公开实施例序号仅仅为了描述，不代表实施例的优劣。以上所述，仅为本公开的具体实施例，但本公开的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应以权利要求的保护范围为准。

Claims (12)

  1. 一种数字孪生体系的构建方法，包括：
    获取目标对象所处物理空间的空间数据，对所述空间数据进行解析，得到物理实体的平面图形信息和外观特征描述标签语言；
    根据所述平面图形信息和所述外观特征描述标签语言，在预设的模型库中匹配出第一数量的第一模型和各个所述第一模型对应的目标渲染素材；
    根据所述第一数量的第一模型和各个所述第一模型对应的所述目标渲染素材，得到所述物理实体在虚拟空间中的第二模型；以及
    获取所述目标对象的物理信息数据，将所述物理信息数据映射到所述第二模型中，生成所述目标对象对应的数字孪生体系。
  2. 根据权利要求1所述的数字孪生体系的构建方法，其中，所述空间数据包括空间平面图、空间图片和空间配置数据，所述对所述空间数据进行解析，得到物理实体的平面图形信息和外观特征描述标签语言，包括：
    对所述空间平面图的线条轮廓进行解析，得到所述物理实体的平面图形信息；
    对所述空间图片进行解析，得到所述物理实体的外观属性；以及
    根据所述空间配置数据，对所述外观属性进行配置，生成外观特征描述标签语言。
  3. 根据权利要求1所述的数字孪生体系的构建方法，其中，所述根据所述平面图形信息和所述外观特征描述标签语言，在预设的模型库中匹配出第一数量的第一模型和各个所述第一模型对应的目标渲染素材，包括：
    根据所述平面图形信息，遍历所述模型库的第一模型，匹配出第一数量的第一模型；以及
    根据所述外观特征描述标签语言，遍历所述模型库的渲染素材，匹配出各个所述第一模型对应的目标渲染素材。
  4. 根据权利要求1所述的数字孪生体系的构建方法，其中，所述根据所述第一数量的第一模型和各个所述第一模型对应的所述目标渲染素材，得到所述物理实体在虚拟空间中的第二模型，包括：
    基于预设的建模算法，根据所述第一模型对所述物理实体进行模型构建，得到所述物理实体在虚拟空间中的素模模型；以及
    基于预设的渲染算法，根据所述目标渲染素材对所述素模模型进行渲染处理，得 到所述物理实体在虚拟空间中的第二模型。
  5. 根据权利要求4所述的数字孪生体系的构建方法，其中，所述基于预设的建模算法，根据所述第一模型对所述物理实体进行模型构建，得到所述物理实体在虚拟空间中的素模模型，包括：
    根据预设的建模层级对所述第一数量的第一模型进行排列组合，构建得到第二数量的第三模型；
    对所述第三模型进行去重处理，得到第三数量的第四模型；
    对所述第四模型进行模型融合处理，生成所述物理实体在虚拟空间中的初始素模模型；以及
    对所述初始素模模型进行模型优化处理，得到所述物理实体在虚拟空间中的素模模型。
  6. 根据权利要求4所述的数字孪生体系的构建方法，其中，所述基于预设的渲染算法，根据所述目标渲染素材对所述素模模型进行渲染处理，得到所述物理实体在虚拟空间中的第二模型，包括：
    确定所述目标渲染素材与所述第一模型的映射关系；以及
    基于所述映射关系，对所述素模模型中的所述第一模型进行渲染处理，得到所述物理实体在虚拟空间中的第二模型。
  7. 根据权利要求1所述的数字孪生体系的构建方法，其中，所述将所述物理信息数据映射到所述第二模型中，生成所述目标对象对应的数字孪生体系，包括：
    根据所述物理信息数据在所述第二模型中确定目标对象模型；以及
    将所述物理信息数据与所述目标对象模型进行绑定，生成所述目标对象对应的数字孪生体系。
  8. 根据权利要求7所述的数字孪生体系的构建方法，其中，所述物理信息数据包括传感器配置数据和对象配置信息，所述根据所述物理信息数据在所述第二模型中确定目标对象模型，包括：
    根据所述传感器配置数据和/或所述对象配置信息，遍历所述第二模型，匹配出目标对象模型。
  9. 根据权利要求7所述的数字孪生体系的构建方法，其中，所述物理信息数据还包括历史运行数据，所述将所述物理信息数据与所述目标对象模型进行绑定，包括：
    将所述物理信息数据中的传感器配置数据和对象配置信息与所述目标对象模型进行绑定，得到所述目标对象的监控信息；以及
    根据所述历史运行数据和所述监控信息，对所述目标对象的状态进行评估，得到所述目标对象的状态信息。
  10. 根据权利要求1所述的数字孪生体系的构建方法，其中，在所述生成所述目标对象对应的数字孪生体系之后，所述方法还包括：
    通过所述数字孪生体系获取所述目标对象的状态信息，并确定所述状态信息是否超过对应的告警阈值；以及
    若所述状态信息超过对应的告警阈值，则控制所述目标对象停止工作。
  11. 一种终端设备，包括：
    处理器、存储器、存储在所述存储器上并可被所述处理器执行的计算机程序以及用于实现所述处理器和所述存储器之间的连接通信的数据总线，其中所述计算机程序被所述处理器执行时，实现如权利要求1至10中任一项所述的数字孪生体系的构建方法的步骤。
  12. 一种存储介质，用于计算机可读存储，其中，所述存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现如权利要求1至10中任一项所述的数字孪生体系的构建方法的步骤。
PCT/CN2023/074865 2022-02-08 2023-02-08 数字孪生体系的构建方法、终端设备及存储介质 WO2023151566A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210119344.9A CN116612232A (zh) 2022-02-08 2022-02-08 数字孪生体系的构建方法、终端设备及存储介质
CN202210119344.9 2022-02-08

Publications (1)

Publication Number Publication Date
WO2023151566A1 true WO2023151566A1 (zh) 2023-08-17

Family

ID=87563612

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/074865 WO2023151566A1 (zh) 2022-02-08 2023-02-08 数字孪生体系的构建方法、终端设备及存储介质

Country Status (2)

Country Link
CN (1) CN116612232A (zh)
WO (1) WO2023151566A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117112117A (zh) * 2023-10-18 2023-11-24 北京和欣运达科技有限公司 基于图形处理的智能控制显示交互方法及系统
CN117274464A (zh) * 2023-11-15 2023-12-22 成都市灵奇空间软件有限公司 基于元宇宙的数据渲染方法、装置及设备
CN117292079A (zh) * 2023-11-27 2023-12-26 浙江城市数字技术有限公司 应用于数字孪生的多维度场景坐标点位转换及映射方法
CN117574691A (zh) * 2024-01-17 2024-02-20 湘江实验室 虚拟实体数据系统构建方法及相关设备
CN117632970A (zh) * 2023-12-18 2024-03-01 智人开源(北京)科技有限公司 多模融合数据库、数据库的数字孪生实体数据存储方法
CN117635846A (zh) * 2023-12-12 2024-03-01 北京达美盛软件股份有限公司 一种工程对象的数字孪生方法、系统及存储介质
CN117830511A (zh) * 2023-12-12 2024-04-05 中国交通信息科技集团有限公司 一种数字孪生体生成方法、系统、电子设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117171849B (zh) * 2023-09-04 2024-07-16 广联达科技股份有限公司 基于建筑模块在业务工作单元中自动创建业务模块的方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112733461A (zh) * 2021-01-21 2021-04-30 广东工业大学 数字孪生驱动的实时渲染方法、系统和计算机可读介质
CN113239442A (zh) * 2021-06-03 2021-08-10 中移智行网络科技有限公司 一种三维模型构建方法、装置、设备和计算机可读存储介质
WO2021222384A1 (en) * 2020-04-28 2021-11-04 Strong Force Intellectual Capital, Llc Digital twin systems and methods for transportation systems

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021222384A1 (en) * 2020-04-28 2021-11-04 Strong Force Intellectual Capital, Llc Digital twin systems and methods for transportation systems
CN112733461A (zh) * 2021-01-21 2021-04-30 广东工业大学 数字孪生驱动的实时渲染方法、系统和计算机可读介质
CN113239442A (zh) * 2021-06-03 2021-08-10 中移智行网络科技有限公司 一种三维模型构建方法、装置、设备和计算机可读存储介质

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117112117A (zh) * 2023-10-18 2023-11-24 北京和欣运达科技有限公司 基于图形处理的智能控制显示交互方法及系统
CN117112117B (zh) * 2023-10-18 2023-12-29 北京和欣运达科技有限公司 基于图形处理的智能控制显示交互方法及系统
CN117274464A (zh) * 2023-11-15 2023-12-22 成都市灵奇空间软件有限公司 基于元宇宙的数据渲染方法、装置及设备
CN117274464B (zh) * 2023-11-15 2024-04-16 成都市灵奇空间软件有限公司 基于元宇宙的数据渲染方法、装置及设备
CN117292079A (zh) * 2023-11-27 2023-12-26 浙江城市数字技术有限公司 应用于数字孪生的多维度场景坐标点位转换及映射方法
CN117292079B (zh) * 2023-11-27 2024-03-05 浙江城市数字技术有限公司 应用于数字孪生的多维度场景坐标点位转换及映射方法
CN117635846A (zh) * 2023-12-12 2024-03-01 北京达美盛软件股份有限公司 一种工程对象的数字孪生方法、系统及存储介质
CN117830511A (zh) * 2023-12-12 2024-04-05 中国交通信息科技集团有限公司 一种数字孪生体生成方法、系统、电子设备及存储介质
CN117632970A (zh) * 2023-12-18 2024-03-01 智人开源(北京)科技有限公司 多模融合数据库、数据库的数字孪生实体数据存储方法
CN117574691A (zh) * 2024-01-17 2024-02-20 湘江实验室 虚拟实体数据系统构建方法及相关设备
CN117574691B (zh) * 2024-01-17 2024-05-14 湘江实验室 虚拟实体数据系统构建方法及相关设备

Also Published As

Publication number Publication date
CN116612232A (zh) 2023-08-18

Similar Documents

Publication Publication Date Title
WO2023151566A1 (zh) 数字孪生体系的构建方法、终端设备及存储介质
US11663375B2 (en) Configuration of a digital twin for a building or other facility via BIM data extraction and asset register mapping
CN109559069B (zh) 基于装配式建筑平台的生产管理方法、装置及终端设备
JP6227278B2 (ja) 買い物経験における仮想イメージと現実イメージとの比較
US11557088B2 (en) Generating space models from map files
CN107944187B (zh) 一种基于Revit的钢筋计算方法、装置、终端设备及介质
CN112929602B (zh) 基于图像处理的数据监控方法、装置及相关设备
US20230015599A1 (en) Data management system, management method, and storage medium
CN109543209B (zh) 一种构件数据库的管理方法及装置
Weinmann et al. Efficient 3d mapping and modelling of indoor scenes with the microsoft hololens: A survey
CN110516628A (zh) 货架空缺位置商品信息获取方法、系统、设备及存储介质
CN117951920B (zh) 一种基于bim模型仿真的数字孪生平台构建方法
CN113297652B (zh) 施工图的生成方法、装置及设备
US10824976B2 (en) Infeasibility management in e-sourcing systems
CN116503538A (zh) 基于倾斜摄影的单体建模方法、系统、终端及存储介质
CN112489191B (zh) 楼宇三维模型的显示方法、设备及介质
CN115816831A (zh) 基于云端控制3d打印机功耗缩减方法、装置、设备及介质
US11651116B2 (en) Method and system for identifying external conflicts with a wall panel assembly
CN113313809A (zh) 一种渲染方法和装置
CN105184379A (zh) 一种利用机器人实现实时自动订房的方法
CN111210524B (zh) 一种ar量房自动拼接方法
CN114139248B (zh) 模型材质升级方法、装置、电子设备及存储介质
US11610029B2 (en) Method and system for identifying conflicts within roof truss of a structure
US11657191B2 (en) Method and system for identifying external conflicts with a roof truss assembly
US12086949B2 (en) Digital positioning handles for a design platform

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23752346

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE