Metacosm logistics digital space construction method, device and equipment

Abstract

The invention discloses a meta-universe logistics digital space construction method, device and equipment, and relates to the technical field of logistics management, and the method comprises the steps: obtaining a logistics data construction demand; obtaining multiple pieces of dimension data according to the logistics data construction demand, and establishing a three-dimensional demand matrix model based on the multiple pieces of dimension data; determining a target and an application scene of the digital twin pedestal based on the logistics data construction demand, and constructing the digital twin pedestal according to the target and the application scene; constructing a dynamic data governance process based on the logistics data construction demand; and generating a meta-universe interaction space based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process. By constructing a three-dimensional demand matrix model, a digital twin base and an intelligent data preprocessing assembly line, efficient integration of multi-source heterogeneous data is achieved, information transmission time delay is eliminated, and real-time decision making is supported.

Description

Technical Field

[0001] The present application relates to the field of logistics management technology, and in particular to methods, devices and equipment for constructing a digital space for metaverse logistics. Background Art

[0002] With the rapid development of the logistics industry, modern logistics systems are facing challenges such as data silos, inefficient collaboration, and low resource utilization. Traditional logistics management systems struggle to efficiently integrate heterogeneous data from multiple sources, resulting in information transmission delays and an inability to support real-time decision-making. Furthermore, the logistics system lacks data connectivity with upstream and downstream supply chain nodes, hindering global collaboration and impacting overall operational efficiency. Furthermore, existing systems are unable to fully utilize emerging technologies such as virtual reality to provide users with an immersive interactive experience, limiting their application value. Summary of the Invention

[0003] The main purpose of this application is to provide a method, device and equipment for constructing a metaverse logistics digital space, aiming to solve the technical problems that existing logistics management systems are difficult to achieve efficient integration of multi-source heterogeneous data, resulting in delays in information transmission, inability to support real-time decision-making and inability to provide users with an immersive interactive experience.

[0004] To achieve the above objectives, this application proposes a method for constructing a digital space for metaverse logistics, which includes:

[0005] Obtain logistics data construction requirements;

[0006] Acquire multiple dimensional data based on the logistics data to build demand, and establish a three-dimensional demand matrix model based on the multiple dimensional data;

[0007] Determining the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and constructing the digital twin base according to the goals and the application scenarios;

[0008] Building a dynamic data governance process based on the logistics data construction requirements, the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection and logistics equipment knowledge graph construction;

[0009] A metaverse interaction space is generated based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process.

[0010] In one embodiment, the step of acquiring multiple dimensional data based on the logistics data and establishing a three-dimensional demand matrix model based on the multiple dimensional data includes:

[0011] Determining a plurality of dimensional data according to the logistics data construction requirements, wherein the plurality of dimensional data includes a spatial dimension, a modal dimension, and an efficiency dimension;

[0012] A three-dimensional demand matrix model is established according to the spatial dimension, the modal dimension, and the effectiveness dimension.

[0013] In one embodiment, the step of establishing a three-dimensional demand matrix model according to the spatial dimension, the modal dimension, and the performance dimension includes:

[0014] Dividing the physical unit into a storage physical unit, a packaging physical unit, and a transportation physical unit according to the spatial dimension to obtain a spatial dimension division result;

[0015] Defining multi-source data acquisition requirements according to the modal dimension, wherein the multi-source data acquisition requirements include video stream data acquisition requirements, mechanical data acquisition requirements, and temperature and humidity data acquisition requirements;

[0016] Setting performance indicators according to the performance dimensions, the performance indicators including a real-time response threshold indicator, a data cleaning accuracy indicator, and a system availability performance indicator;

[0017] A three-dimensional demand matrix model is constructed according to the spatial dimension division result, the multi-source data collection requirements and the performance index.

[0018] In one embodiment, the steps of determining the goals and application scenarios of the digital twin base based on the logistics data construction requirements and constructing the digital twin base according to the goals and the application scenarios include:

[0019] Analyze the requirements for building logistics data to obtain the goals and application scenarios of the digital twin base;

[0020] Determine a target edge computing platform based on the target and the application scenario, and deploy edge computing nodes on the target edge computing platform;

[0021] Constructing a spatiotemporal reference framework to synchronize the time of the edge computing nodes and obtain a synchronization result;

[0022] Build a multimodal encoder based on the Transformer architecture based on data of different modalities;

[0023] A digital twin base is generated according to the synchronization result and the multimodal encoder.

[0024] In one embodiment, the step of constructing a multimodal encoder based on a Transformer architecture based on data of different modalities includes:

[0025] Preprocess and extract features of data of different modalities to obtain feature data;

[0026] Mapping the feature data to an embedding space through an initial multimodal encoder so that a Transformer model processes the feature data and learns the correlation between different modalities;

[0027] Assigning different weights to the feature data of different modalities through a self-attention mechanism to obtain weighted data;

[0028] An embedded representation of the feature data is obtained based on the embedding space, and the Transformer model is optimized through a joint training method based on the weight data to generate a multimodal encoder based on the Transformer architecture.

[0029] In one embodiment, the step of building a dynamic data governance process based on the logistics data building requirements includes:

[0030] Establishing an intelligent data pre-processing architecture based on the logistics data construction requirements;

[0031] Deploy a frequency domain feature extraction algorithm of wavelet packet transform, an anomaly detection module for multi-dimensional sensor data joint anomaly diagnosis, and a logistics equipment knowledge graph for logistics equipment data storage on the intelligent data preprocessing architecture to obtain deployment results;

[0032] Generate a dynamic data governance process based on the deployment results.

[0033] In one embodiment, the construction of the logistics equipment knowledge graph includes:

[0034] According to the preset screening rules, the quantity of old equipment with the same equipment demand and the same equipment on hand is processed to obtain the logistics equipment metadata;

[0035] Get operation manuals and troubleshooting cases;

[0036] The logistics equipment metadata, the operation manual and the fault case are converted into RDF triples for storage to generate a logistics equipment knowledge graph.

[0037] In one embodiment, the step of generating a metaverse interaction space based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process includes:

[0038] Creating a virtual physical image layer based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process;

[0039] Build event-driven data pipelines based on distributed stream processing platforms to generate digital threads;

[0040] Developing mixed reality interfaces through mixed reality headsets and force feedback gloves;

[0041] A metaverse interaction space is generated according to the virtual physical mirror layer, the digital main line, and the mixed reality interface.

[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes a metaverse logistics digital space construction device, which includes:

[0043] Acquisition module, used to obtain logistics data construction requirements;

[0044] A construction module, configured to acquire a plurality of dimensional data according to the logistics data construction demand, and establish a three-dimensional demand matrix model based on the plurality of dimensional data;

[0045] A determination module, configured to determine the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and to construct the digital twin base according to the goals and the application scenarios;

[0046] The construction module is further used to construct a dynamic data governance process based on the logistics data construction requirements, and the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection, and logistics equipment knowledge graph construction;

[0047] A generation module is used to generate a metaverse interaction space based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a metaverse logistics digital space construction device, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the metaverse logistics digital space construction method as described above.

[0049] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the method for constructing the metaverse logistics digital space as described above are implemented.

[0050] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for constructing the metaverse logistics digital space as described above.

[0051] One or more technical solutions proposed in this application are to build demand by acquiring logistics data; acquire multiple dimensional data based on the logistics data construction demand, and establish a three-dimensional demand matrix model based on the multiple dimensional data; determine the goals and application scenarios of the digital twin base based on the logistics data construction demand, and build the digital twin base according to the goals and the application scenarios; build a dynamic data governance process based on the logistics data construction demand, and the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection and logistics equipment knowledge graph construction; generate a metaverse interactive space based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process. By constructing a three-dimensional demand matrix model, a digital twin base and an intelligent data preprocessing pipeline, efficient integration of multi-source heterogeneous data is achieved, information transmission delay is eliminated, real-time decision-making is supported, and virtual reality technology is fully utilized to provide users with an immersive interactive experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0054] Figure 1 A flow chart illustrating the first embodiment of the method for constructing a digital space for Metaverse Logistics in this application;

[0055] Figure 2 A flow chart illustrating the second embodiment of the method for constructing a digital space for Metaverse Logistics in this application;

[0056] Figure 3 A flow chart illustrating the third embodiment of the method for constructing a digital space for Metaverse Logistics in this application;

[0057] Figure 4 A flowchart of the fourth embodiment of the method for constructing a digital space for Metaverse Logistics provided in this application;

[0058] Figure 5 This is a schematic diagram of the module structure of the device for constructing the digital space of Metaverse Logistics in an embodiment of the present application;

[0059] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the method for constructing the digital space of metaverse logistics in the embodiment of this application.

[0060] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0062] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0063] The main solutions of the embodiments of the present application are: obtaining logistics data construction requirements; obtaining multiple dimensional data according to the logistics data construction requirements, and establishing a three-dimensional demand matrix model based on the multiple dimensional data; determining the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and constructing the digital twin base according to the goals and the application scenarios; constructing a dynamic data governance process based on the logistics data construction requirements, and the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection and logistics equipment knowledge graph construction; generating a metaverse interaction space based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process.

[0064] Since existing technologies mainly focus on formulating digital transformation plans, installing highly compatible equipment and sensors, realizing real-time collection and processing of multimodal information, and utilizing standardized data formats and communication protocols to seamlessly integrate data from different devices and sensors into a unified platform, there are still problems with data cleaning and integration algorithms that need to be further optimized to improve data accuracy and consistency.

[0065] This application provides a solution to build a new type of logistics digital space. By constructing a three-dimensional demand matrix model, a digital twin base and an intelligent data preprocessing pipeline, it achieves efficient integration of multi-source heterogeneous data, eliminates information transmission delays, supports real-time decision-making, generates a metaverse interactive space, and makes full use of emerging technologies such as virtual reality to provide users with an immersive interactive experience and expand the application value of the system.

[0066] It should be noted that the execution entity of this embodiment can be a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the aforementioned functions, such as a Metaverse Logistics Digital Space Construction Device. This embodiment and the following embodiments will be described below using the Metaverse Logistics Digital Space Construction Device as an example.

[0067] Based on this, the embodiment of the present application provides a method for constructing a digital space of metaverse logistics, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for constructing the digital space of metaverse logistics of this application.

[0068] In this embodiment, the method for constructing the Metaverse Logistics Digital Space includes steps S10 to S50:

[0069] Step S10: Obtain logistics data construction requirements.

[0070] It should be noted that before constructing the digital logistics metaverse space, the specific construction requirements can be clarified first, so the logistics data construction requirements can be obtained. The logistics data construction requirements may include data such as the construction architecture, construction content, processing rules, etc., and may also include other requirements, which are not limited in this embodiment.

[0071] Step S20: constructing demand according to the logistics data to obtain multiple dimensional data, and establishing a three-dimensional demand matrix model based on the multiple dimensional data.

[0072] It should be noted that the demand for logistics data construction can be analyzed to determine multiple dimensional data, such as multiple dimensional data including spatial dimension, modal dimension, efficiency dimension, and other dimensions, such as time dimension.

[0073] In practice, a 3D demand matrix model can be constructed based on data from different dimensions. The 3D demand matrix model is a tool for analyzing and describing multidimensional demand relationships, and is commonly used in fields such as product design, project management, and market demand analysis. It maps different demand factors into a three-dimensional space to better understand the interactions between these dimensions and help decision makers make optimal decisions in complex environments. The 3D demand matrix clearly illustrates the relationships between different spatial units, different data collection modalities, and performance requirements.

[0074] By establishing a three-dimensional requirements matrix model, we can clearly define the relationships between various functions, interactive elements, and experience requirements within the Metaverse's interactive space. This model helps us understand the priorities, interdependencies, and complementarities between different requirements when building the Metaverse, ensuring that the constructed virtual space accurately meets user needs.

[0075] Step S30: Determine the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and build the digital twin base according to the goals and the application scenarios.

[0076] In practice, the requirements for building physical flow data can be analyzed to determine the goals and application scenarios for establishing the digital twin foundation. Before construction begins, the goals and application scenarios for the digital twin foundation must be clearly defined. For example, could the purpose be equipment monitoring, fault prediction, production optimization, or energy management? Therefore, specific requirements can be determined based on the physical data requirements to ensure the design meets business objectives.

[0077] After determining specific goals and application scenarios, a Digital Twin Foundation can be constructed based on these goals and application scenarios. In practice, the Digital Twin Foundation is the core foundational platform for building a digital twin system, providing a complete set of technical architectures, tools, and frameworks to support the creation, management, and operation of digital twins. A digital twin is essentially a virtual replica of a physical entity or system, enabling real-time monitoring, simulation, and optimization of the physical object's state, behavior, and performance.

[0078] The purpose of building a digital twin foundation is to establish a connection between the virtual and real worlds. By digitally replicating real-world physical objects and environments, it provides accurate, real-time data support for the metaverse's interactive space. Digital twin technology provides dynamic feedback and simulated data from the real world to the metaverse's interactive space, ensuring the real-time and accuracy of the virtual environment. In the metaverse, digital twins can facilitate interaction between the virtual and real worlds. For example, by driving changes in the virtual world through sensor data, physical models, and environmental changes, the digital twins enhance the immersiveness and interactivity of the virtual space.

[0079] Step S40: Construct a dynamic data governance process based on the logistics data construction requirements, and the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection and logistics equipment knowledge graph construction.

[0080] It should be noted that the dynamic data governance process is a management process for logistics data, which can be constructed according to the data rules in the Wulilu data construction requirements. Specifically, the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection, and logistics equipment knowledge graph construction. Through this series of processes, the accuracy of the data can be improved.

[0081] A data governance system ensures that all data flows within the metaverse (e.g., user behavior data, environmental data, interaction data, etc.) are valid, accurate, and dynamically adaptable to changes in the virtual space. Data governance encompasses not only data collection and storage but also real-time data analysis, user privacy and data security, and large-scale data flow processing.

[0082] Step S50: Generate a metaverse interaction space based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process.

[0083] It should be noted that after constructing the three-dimensional demand matrix model, digital twin base and dynamic data governance process, a planning and design framework, links with the real world and effective data management are provided for the construction of the metaverse interactive space. Therefore, a metaverse interactive space about physical data can be generated based on the constructed three-dimensional demand matrix model, digital twin base and dynamic data governance process, providing users with an immersive interactive experience.

[0084] In a feasible implementation, step S50 may include steps S51 to S54:

[0085] Step S51: creating a virtual physical image layer based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process;

[0086] It should be noted that a virtual physical mirror layer can be created based on the three-dimensional demand matrix model, digital twin base and dynamic data governance process. Specifically, NVIDIA Omniverse can be used to achieve real-time collaborative rendering of multiple CAD / BIM models. Multiple CAD (computer-aided design) and BIM (building information model) models can be loaded in a virtual environment and rendered and collaboratively operated in real time. Using the NVIDIA Omniverse platform, a unified virtual environment is created to support simultaneous collaboration among multiple parties, real-time viewing and modification of three-dimensional models, and improved collaborative efficiency in the design, construction and operation stages, thereby obtaining a virtual physical mirror layer, improving the authenticity of the simulation, and making the analysis results more accurate.

[0087] In addition, the virtual physical image layer also supports mainstream 3D file formats such as FBX, OBJ, and STEP. The virtual physical image mechanism enables dynamic optimization of warehouse layout and improves space utilization.

[0088] Step S52: Building an event-driven data pipeline based on a distributed stream processing platform to generate a digital thread;

[0089] In practice, by creating a virtual physical image layer, rich 3D models can be generated and presented. These models will become the data source in the event-driven data pipeline, providing real-time data and status information to downstream processing and monitoring systems. Therefore, an event-driven data pipeline can be built based on the distributed stream processing platform Apache Kafka, supporting tens of millions of concurrent transactions per second (TPS), thereby generating a digital thread.

[0090] Apache Kafka builds efficient and scalable event-driven data pipelines to process and transmit various sensor data, status information, user operation events, etc. in real time.

[0091] During this process, Kafka will carry the virtual physical image layer data created in step S51, sensor data (such as CAD / BIM model status changes, user operation events, etc.), and other information flows involving the interaction between virtual reality and physical devices. Through the Kafka event-driven pipeline, the data and status of the virtual physical image layer are transmitted and updated in real time, ensuring real-time rendering and data collaboration of different CAD / BIM models. By utilizing digital mainline technology, the data silos of the logistics system and upstream and downstream supply chain nodes are connected, a global collaborative network of virtual-to-real mapping is established, and overall operational efficiency is improved.

[0092] Step S53: developing a mixed reality interface through a mixed reality head display and force feedback gloves;

[0093] It should be understood that the mixed reality headset is the Hololens 2. By integrating the Hololens 2 with force feedback gloves, a mixed reality interface is developed to enable interaction between the virtual and real worlds. Through these devices, users can not only view multiple CAD / BIM models in a virtual environment, but also manipulate and interact with the models, and even remotely control devices. Specifically, a mixed reality interface can be developed that integrates the Hololens 2 with HaptX VR gloves, enabling remote device control that integrates the virtual and real worlds. The gloves have a refresh rate of 4kHz.

[0094] Step S54: Generate a metaverse interaction space based on the virtual physical mirror layer, the digital main line, and the mixed reality interface.

[0095] In specific implementations, a metaverse interaction space can be generated based on the established virtual physical mirror layer, digital main line, and mixed reality interface. This metaverse interaction space is the metaverse interaction space of physical data.

[0096] The mixed reality interface maps the 3D model in the virtual physical image layer to devices such as Hololens2, allowing users to perceive and interact with the real-time rendering data of multiple CAD / BIM models through the virtual environment.

[0097] Data in the virtual-physical image layer, user interaction events, and state changes are all transmitted through the Kafka pipeline, ensuring that the Hololens 2 and force feedback gloves can receive and respond to data in real time. The Kafka data pipeline plays a role in transmitting and processing real-time data streams, supporting virtual-reality linkage.

[0098] This embodiment provides a method for constructing a digital space for metaverse logistics, which includes obtaining logistics data to construct requirements; obtaining multiple dimensional data based on the logistics data construction requirements, and establishing a three-dimensional demand matrix model based on the multiple dimensional data; determining the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and constructing the digital twin base based on the goals and application scenarios; constructing a dynamic data governance process based on the logistics data construction requirements, the dynamic data governance process including intelligent data preprocessing, frequency domain feature extraction, anomaly detection, and logistics equipment knowledge graph construction; and generating a metaverse interactive space based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process. By constructing a three-dimensional demand matrix model, a digital twin base, and an intelligent data preprocessing pipeline, efficient integration of multi-source heterogeneous data is achieved, eliminating information transmission delays, supporting real-time decision-making, and fully utilizing virtual reality technology to provide users with an immersive interactive experience.

[0099] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 , step S20 includes steps S201 to S202:

[0100] Step S201: Determine a plurality of dimensional data according to the logistics data construction requirements, wherein the plurality of dimensional data include a spatial dimension, a modal dimension, and an efficiency dimension.

[0101] It should be noted that the multiple dimensional data that need to be constructed can be determined based on the physical data construction requirements, specifically including spatial dimension, modal dimension and efficiency dimension. The spatial dimension is the physical unit used by logistics data, the modal dimension is the form of collecting logistics data, and the efficiency dimension is the requirements and specifications for logistics data processing.

[0102] Step S202: establishing a three-dimensional demand matrix model according to the spatial dimension, the modal dimension, and the performance dimension.

[0103] In a specific implementation, after determining the spatial dimension, modal dimension and performance dimension, a three-dimensional demand matrix model can be jointly constructed based on the spatial dimension, modal dimension and performance dimension.

[0104] In a feasible implementation, step S202 may include steps A11 to A14:

[0105] Step A11: Divide the physical unit into a storage physical unit, a packaging physical unit, and a transportation physical unit according to the spatial dimension, and obtain a spatial dimension division result;

[0106] In a specific implementation, in terms of the spatial dimension, the physical units can be divided into storage physical units, packaging physical units and transportation physical units. For example, the physical units can be divided into storage areas, packaging production lines and transportation channels to obtain spatial dimension division results.

[0107] Step A12: defining multi-source data acquisition requirements according to the modal dimension, wherein the multi-source data acquisition requirements include video stream data acquisition requirements, mechanical data acquisition requirements, and temperature and humidity data acquisition requirements;

[0108] It can be understood that in the modal dimension, multi-source data acquisition requirements can be defined, specifically including video stream data acquisition requirements, mechanical data acquisition requirements, and temperature and humidity data acquisition requirements.

[0109] Specifically, the video stream acquisition requirement can be defined as using AR devices to collect video streams with a resolution of 1080P and a frame rate of 30 frames per second; the mechanical sensing acquisition requirement can be defined as using a six-axis torque sensor to collect mechanical data with a sampling rate of 10KHz; and the temperature and humidity acquisition requirement can be defined as using industrial-grade IoT sensors to collect environmental data with a sampling rate of 0.1Hz.

[0110] Step A13: Setting performance indicators according to the performance dimensions, the performance indicators including a real-time response threshold indicator, a data cleaning accuracy indicator, and a system availability performance indicator;

[0111] It should be noted that in terms of performance, performance indicators can be set, including real-time response threshold indicators. For example, the real-time response threshold can be set to less than 50 milliseconds of delay or less than 30 milliseconds of delay. The threshold can be adjusted according to needs. Performance indicators also include data cleaning accuracy indicators. To improve data accuracy, the data cleaning accuracy indicator can be set to 99%, 99.8%, 99.9%, etc. Performance indicators also include system availability indicators. The system availability indicator can be set to reach an SLA level of 90%, an SLA level of 99.99%, or an SLA level of 99.999%.

[0112] In a feasible implementation, in terms of performance, the real-time response threshold is set to be less than 50 milliseconds of delay, the data cleaning accuracy is greater than 99.8%, and the system availability reaches an SLA level of 99.99%.

[0113] In another feasible implementation, in terms of performance, the real-time response threshold is set to be less than 30 milliseconds of delay, the data cleaning accuracy is greater than 99.9%, and the system availability reaches an SLA level of 99.999%.

[0114] Step A14: constructing a three-dimensional demand matrix model according to the spatial dimension division result, the multi-source data collection requirements and the performance index.

[0115] It should be noted that a three-dimensional demand matrix model can be constructed based on the spatial dimension division results, multi-source data collection requirements, and performance indicators, as shown in Tables 1 and 2 below. Table 1 is a mapping table between spatial dimension and modal dimension, and Table 2 is a mapping table between spatial dimension and performance dimension.

[0116] Table 1

[0117]

[0118]

[0119] Table 2

[0120] Spatial dimension\Effective dimension Respond to needs in real time Data cleaning accuracy requirements System availability requirements Warehousing Delay <ams Data accuracy>b% System availability > c% Package Packaging process response <ams Packaging data accuracy>b% Packaging system availability > c% transportation Transportation Response <ams Shipping data accuracy > b% Transport system availability > c%

[0121] In Table 1 and Table 2, the values of a, b, and c can be set as required.

[0122] This embodiment determines multiple dimensional data based on the demand construction of the logistics data, and the multiple dimensional data include spatial dimension, modal dimension and efficiency dimension; a three-dimensional demand matrix model is established based on the spatial dimension, the modal dimension and the efficiency dimension. By refining the logistics demand in the spatial dimension, modal dimension and efficiency dimension, the different factors in the logistics system can be analyzed more comprehensively. For example, the spatial dimension can cover different geographical areas or distribution routes, the modal dimension can consider different modes of transportation, and the efficiency dimension focuses on time, cost, resource utilization efficiency and other aspects. The combination of the three can accurately describe the diversity and complexity of logistics demand, and provide a more detailed analysis basis for subsequent logistics planning and decision-making.

[0123] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 3 , step S30 includes steps S301 to S305:

[0124] Step S301: Analyze the logistics data construction requirements to obtain the goals and application scenarios of the digital twin base.

[0125] During implementation, the logistics data requirements within the logistics system are analyzed to clarify the system's goals, requirements, and application scenarios. The purpose of this analysis is to understand the elements of logistics operations that require monitoring and optimization, such as shipping timeliness, cargo tracking, and warehouse management. This provides the goals and context for creating the digital twin foundation. For example, the goal is to improve warehouse efficiency, and the application scenario involves real-time tracking of inventory flows to reduce wasted warehouse space and lost goods. By analyzing these requirements, we can set goals for building the digital twin system.

[0126] Step S302: Determine a target edge computing platform based on the target and the application scenario, and deploy edge computing nodes on the target edge computing platform.

[0127] In specific implementation, the target edge computing platform can be determined according to the goals and application scenarios, such as edge computing platforms such as factory automation and smart warehouses.

[0128] Edge computing nodes typically have processing and storage capabilities, supporting real-time computing and data preprocessing. Common devices include embedded computers and industrial gateways. Edge computing nodes can be deployed on the target edge computing platform to integrate the OPC UA / MTConnect industrial protocol stack, enabling plug-and-play for devices such as PLCs, AGVs, and smart shelves. The OPC UA protocol stack provides a standardized communication interface for industrial automation equipment, ensuring data interoperability between devices. The OPC UA protocol supports real-time data exchange between devices and cloud platforms and data centers. The MTConnect protocol stack is a communication protocol specifically designed for manufacturing equipment, and is particularly suitable for production lines, robots, and automated control systems. It ensures that production equipment (such as PLCs) and robots (such as AGVs) can be interconnected through a unified interface and standard protocol.

[0129] For example, integrating the OPC UA / MTConnect industrial protocol stack can achieve plug-and-play of devices such as PLCs, AGVs, and smart shelves, or deploying edge computing nodes based on NVIDIA Jetson Xavier NX, integrating the OPC UA and MTConnect industrial protocol stacks, and achieving plug-and-play of Siemens PLCs, Yaskawa robots, and smart shelves.

[0130] Step S303: construct a spatiotemporal reference framework to synchronize the time of the edge computing nodes to obtain a synchronization result.

[0131] In practice, the IEEE 1588v2 precision clock protocol can be used to build a space-time reference framework, ensuring μs-level time synchronization among distributed nodes. IEEE 1588v2 is a standard protocol for clock synchronization in networks, providing highly precise time synchronization with microsecond accuracy. It is used in distributed systems with high real-time requirements. Building a space-time reference framework involves: selecting a clock source: choosing an appropriate time source based on actual needs. Common choices include using GPS or atomic clocks as the master clock source, which is transmitted to each distributed node via the network; configuring the network topology: ensuring that all nodes are connected through IEEE 1588v2-compatible network switches to form a stable time synchronization network; clock synchronization and calibration: using the IEEE 1588v2 protocol, ensuring μs-level time synchronization among all nodes, meeting the real-time and accuracy requirements of digital twin systems; and verifying synchronization accuracy, including latency testing and fault detection and recovery. Latency testing involves performing latency testing and clock calibration on each node to ensure that clock deviations are within acceptable limits. Fault detection and recovery can automatically resynchronize time in the event of network delay or failure, ensuring system stability and reliability.

[0132] For example, the IEEE 1588v2 precision clock protocol is used to ensure that distributed nodes achieve 10 microsecond time synchronization accuracy.

[0133] Step S304: construct a multimodal encoder based on the Transformer architecture based on data of different modalities.

[0134] In practice, a multimodal encoder based on the Transformer architecture can be constructed based on data from different modalities. Multimodal learning refers to the integration of data from different modalities (such as text, images, and audio) into a unified representation space. The Transformer architecture can efficiently process a variety of data types, such as video streams, point cloud data, and RFID signals. Therefore, a joint embedding space can be designed based on data from different modalities to develop a multimodal encoder.

[0135] In a feasible implementation, step S304 may include steps B11 to B14:

[0136] Step B11: preprocessing and feature extraction of data of different modalities to obtain feature data;

[0137] It should be noted that data of different modalities can be preprocessed and feature extracted first. Different modal data include video streams, point cloud data, and RFID signals. Specific preprocessing and feature extraction include: using convolutional neural networks (CNN) or other video processing methods to extract spatial features and time series features from video streams, and converting them into a format suitable for Transformer input, and performing feature extraction on 3D point cloud data through point cloud processing technology (such as PointNet). Point cloud data is usually very high-dimensional and requires dimensionality reduction and transformation to be input into the Transformer network; converting the read data of the RFID signal into digital form, and extracting features related to time and space. This data can come from tag recognition, signal strength, etc. of RFID sensors. Feature data is obtained by preprocessing and feature extraction of the data.

[0138] Step B12: Mapping the feature data to an embedding space through an initial multimodal encoder, so that the Transformer model processes the feature data and learns the correlation between different modalities;

[0139] In a specific implementation, the feature data can be mapped to a shared embedding space through the initial multimodal encoder, so that the feature data can be processed through the Transformer model and the correlation between different modalities can be learned.

[0140] Step B13: assigning different weights to the feature data of different modalities through a self-attention mechanism to obtain weighted data;

[0141] At the same time, the self-attention mechanism can be used to assign different weights to feature data of different modalities, so as to facilitate focusing on key features and obtain weighted data.

[0142] Step B14: Obtain an embedded representation of the feature data based on the embedding space, and optimize the Transformer model through a joint training method based on the weight data to generate a multimodal encoder based on the Transformer architecture.

[0143] It should be noted that the embedded representation of feature data can be obtained based on the embedding space, so that the Transformer model can be optimized through a joint training method. During the training optimization, a suitable loss function can be designed to ensure that the model can effectively integrate multiple data types and obtain a multimodal encoder based on the Transformer architecture.

[0144] Specifically, by developing a multimodal encoder based on the Transformer architecture, the joint embedding representation of video streams, point cloud data and RFID signals can be achieved. For example, the joint embedding representation of video streams, point cloud data and RFID signals can be achieved, with an embedding vector dimension of 512.

[0145] Step S305: Generate a digital twin base based on the synchronization result and the multimodal encoder.

[0146] In specific implementations, the synchronization results and the multimodal encoder can be integrated and deployed to generate a digital twin base. The multimodal encoder provides powerful multimodal data processing capabilities for the digital twin system.

[0147] This embodiment analyzes the requirements for building the logistics data to obtain the goals and application scenarios of the digital twin base; determines the target edge computing platform based on the goals and application scenarios, and deploys edge computing nodes on the target edge computing platform; constructs a spatiotemporal reference framework to synchronize the time of the edge computing nodes to obtain synchronization results; constructs a multimodal encoder based on the Transformer architecture based on data of different modalities; and generates a digital twin base based on the synchronization results and the multimodal encoder. By analyzing the requirements for building logistics data, selecting a suitable edge computing platform, performing spatiotemporal synchronization, multimodal data fusion, and generating a digital twin base, the entire logistics system can achieve more efficient, accurate, and intelligent management.

[0148] Based on the first embodiment of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 4 , step S40 includes steps S401 to S403:

[0149] Step S401: Establishing an intelligent data pre-processing architecture based on the logistics data construction requirements.

[0150] It should be noted that the logistics data construction needs can be analyzed to determine the specific process and establish an intelligent data preprocessing architecture, which sets the specific data processing process and framework.

[0151] Step S402: Deploy the frequency domain feature extraction algorithm of wavelet packet transform, the anomaly detection module of multi-dimensional sensor data joint anomaly diagnosis, and the logistics equipment knowledge graph for logistics equipment data storage on the intelligent data preprocessing architecture to obtain the deployment result.

[0152] In specific implementations, a wavelet packet transform (WPT) frequency domain feature extraction algorithm can be deployed within the intelligent data preprocessing architecture to extract frequency domain features. This application replaces the traditional Fourier transform for non-stationary vibration signal analysis. For example, the Daubechies wavelet packet transform (WPT) is used for frequency domain feature extraction, with a five-level wavelet packet decomposition. By introducing a hybrid wavelet packet-deep learning algorithm, the accuracy of package damage identification has been increased from 92.4% to 99.1%, optimizing data cleaning and integration algorithms and improving data accuracy and consistency.

[0153] In the specific implementation, an anomaly detection model is deployed to perform joint anomaly diagnosis on multi-dimensional sensor data. For example, the LSTM-Autoencoder model is used to implement joint anomaly diagnosis of multi-dimensional sensor data, thereby improving the accuracy and efficiency of data processing. Specifically, the anomaly detection module uses the LSTM-Autoencoder model to implement joint anomaly diagnosis of multi-dimensional sensor data. The LSTM hidden layer dimension is 128, and the reconstruction error threshold is 0.05.

[0154] It should be noted that data related to logistics equipment can be stored to build a logistics equipment knowledge graph. By deploying frequency domain feature extraction algorithms, anomaly detection modules, and logistics equipment knowledge graphs, a dynamic data governance process can be formed.

[0155] In a feasible implementation, the construction of the logistics equipment knowledge graph includes:

[0156] According to the preset screening rules, the quantity of old equipment with the same equipment demand and the same equipment on hand is processed to obtain the logistics equipment metadata;

[0157] Get operation manuals and troubleshooting cases;

[0158] The logistics equipment metadata, the operation manual and the fault case are converted into RDF triples for storage to generate a logistics equipment knowledge graph.

[0159] It should be noted that the preset screening rules are rules for adjusting the number of old equipment. The logistics equipment metadata includes the demand quantity of the same equipment and the existing quantity of the same equipment. The demand quantity of the same equipment refers to the number of the same logistics equipment required by all processes; the existing quantity of the same equipment refers to the number of the same equipment currently available in all processes.

[0160] When the ratio of existing equipment to demand for the same equipment is ≥ 1.3, the amount of old equipment is reduced. If the amount of old equipment contains decimals, it is rounded up. If there are no old equipment left, the number of times and the usage time of randomly selected equipment are reduced. The benefit of this design is that it can store enough newer equipment. When certain processes require new equipment or newer equipment to ensure reliability, these newer equipment can be quickly deployed to support them. This avoids the situation where the logistics system is completely filled with old equipment in the future, and when newer equipment is needed, it has to be purchased in large quantities, which is a waste of money.

[0161] When the ratio of existing equipment to demand for the same equipment is ≤ 1.1, the old equipment quantity is increased. If the old equipment quantity contains a decimal, it is rounded up. If there is no old equipment, the number of uses and usage time of randomly selected equipment are increased. The benefit of this design is that it prevents all logistics equipment from entering the scrap period at the same time. When certain processes require new or newer equipment to ensure reliability, the newer equipment that has been saved can be quickly called upon to provide support. By designing redundancy for old equipment, the smooth and stable operation of the logistics system is fully guaranteed.

[0162] Old equipment refers to logistics equipment with a theoretical remaining service life of less than 20% or an actual remaining service life of less than six months, whichever is smaller. For example, an AGV has a theoretical service life of five years, but has been in use for three years, leaving 40% of its theoretical service life. Due to frequent use in high-temperature environments, the AGV's self-diagnosis indicates that it can only be used for five months, making it considered old equipment. If the ratio of existing equipment to demand for the same equipment is less than 1.3, and the actual remaining service life of the old equipment is ≤3%, the old equipment is considered redundant and removed from regular production use. Instead, it is stored as emergency equipment for later use in emergencies. If the emergency equipment has been in storage for more than one year and the actual remaining service life of the old equipment is ≤3%, the redundant equipment, which has been stored for more than one year, is put into operation and the new redundant equipment is stored in the warehouse. Logistics equipment with a service life of ≤3% is almost ready for scrapping. However, under certain circumstances, there may be a temporary need to add more equipment, but new equipment is expensive. Using old equipment as redundancy can effectively solve this problem. Scenarios for temporary equipment additions include building new production lines, adjusting existing lines, and workshop accidents. There are two ways to determine the actual remaining service life ratio. One is to calculate the remaining ratio by self-detection of the equipment, and the second is to manually evaluate the remaining ratio.

[0163] By performing relevant processing on old equipment, the final logistics equipment metadata is obtained.

[0164] In specific implementation, operation manuals and fault cases can also be obtained. Operation manuals are documents that guide users on how to use products, systems or software. Fault cases are documents that record specific problems and fault conditions that have occurred. They usually include a detailed description of the fault phenomenon, conditions for occurrence, causes, solutions and preventive measures. Physical device metadata, operation manuals and fault cases can be converted into RDF triples for storage. RDF (Resource Description Framework) triples are a structured way to represent data and are widely used in fields such as the Semantic Web and knowledge graphs, thereby constructing a physical device knowledge graph.

[0165] For example, logistics equipment metadata, operating manuals, and fault cases are converted into RDF triple storage, and the number of knowledge graph entities is about 100,000.

[0166] Step S403: Generate a dynamic data governance process according to the deployment result.

[0167] In specific implementation, a dynamic data governance process can be jointly generated through the deployed frequency domain feature extraction algorithm, anomaly detection module and physical equipment knowledge graph, so that the logistics data can be directly processed through the dynamic data governance process during subsequent logistics data processing.

[0168] This embodiment establishes an intelligent data preprocessing architecture based on the logistics data construction requirements; deploys the frequency domain feature extraction algorithm of wavelet packet transform, the anomaly detection module of multi-dimensional sensor data joint anomaly diagnosis, and the logistics equipment knowledge graph of logistics equipment data storage on the intelligent data preprocessing architecture to obtain deployment results; generates a dynamic data governance process based on the deployment results. Wavelet packet transform can decompose data at multiple levels in the frequency domain and extract more detailed features, which is especially important for complex time series data (such as sensor data of logistics equipment). It can significantly improve the accuracy of data analysis. By combining the anomaly detection module, it can comprehensively analyze the data from each sensor and promptly discover potential equipment failures or operational anomalies. By constructing a knowledge graph of logistics equipment, all operating data, historical failures, maintenance records, usage and other information of the equipment are structured to form a knowledge network. This makes it easy to store, query and analyze data, helping to quickly identify potential failure modes and maintenance needs.

[0169] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the method of constructing the digital space of metaverse logistics in this application. More simple transformations based on this technical concept are all within the scope of protection of this application.

[0170] This application also provides a metaverse logistics digital space construction device, please refer to Figure 5 , the metaverse logistics digital space construction device includes:

[0171] The acquisition module 10 is used to obtain logistics data construction requirements.

[0172] The construction module 20 is used to construct demand and obtain multiple dimensional data according to the logistics data, and establish a three-dimensional demand matrix model based on the multiple dimensional data.

[0173] The determination module 30 is used to determine the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and to construct the digital twin base according to the goals and the application scenarios.

[0174] The construction module 20 is also used to construct a dynamic data governance process based on the logistics data construction requirements. The dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection and logistics equipment knowledge graph construction.

[0175] The generation module 40 is used to generate a metaverse interaction space based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process.

[0176] The Metaverse Logistics Digital Space Construction Device provided by this application adopts the Metaverse Logistics Digital Space Construction Method in the above-mentioned embodiment, which can solve the technical problem that the existing logistics management system has difficulty in realizing efficient integration of multi-source heterogeneous data, resulting in time delays in information transmission, inability to support real-time decision-making, and inability to provide users with an immersive interactive experience. Compared with the existing technology, the beneficial effects of the Metaverse Logistics Digital Space Construction Device provided by this application are the same as the beneficial effects of the Metaverse Logistics Digital Space Construction Method provided by the above-mentioned embodiment, and the other technical features of the Metaverse Logistics Digital Space Construction Device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0177] The present application provides a metaverse logistics digital space construction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the metaverse logistics digital space construction method in the above-mentioned embodiment one.

[0178] Reference below Figure 6, which shows a schematic diagram of the structure of a Metaverse Logistics Digital Space Construction Device suitable for implementing the embodiments of the present application. The Metaverse Logistics Digital Space Construction Device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The metaverse logistics digital space construction device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of this application.

[0179] like Figure 6 As shown, the Metaverse Logistics Digital Space Construction Device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 into RAM (Random Access Memory) 1004. Various programs and data required for the operation of the Metaverse Logistics Digital Space Construction Device are also stored in RAM 1004. The processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, an LCD (Liquid Crystal Display), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the Metaverse Logistics Digital Space Construction Device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows the Metaverse Logistics Digital Space Construction Device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0180] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0181] The Metaverse Logistics Digital Space Construction Device provided by this application adopts the Metaverse Logistics Digital Space Construction Method in the above-mentioned embodiment, which can solve the technical problem that the existing logistics management system has difficulty in realizing efficient integration of multi-source heterogeneous data, resulting in time delays in information transmission, inability to support real-time decision-making, and inability to provide users with an immersive interactive experience. Compared with the existing technology, the beneficial effects of the Metaverse Logistics Digital Space Construction Device provided by this application are the same as the beneficial effects of the Metaverse Logistics Digital Space Construction Method provided by the above-mentioned embodiment, and the other technical features of the Metaverse Logistics Digital Space Construction Device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0182] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0183] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0184] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the metaverse logistics digital space construction method in the above-mentioned embodiment.

[0185] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0186] The above-mentioned computer-readable storage medium may be included in the Metaverse Logistics Digital Space Construction Device; or it may exist independently without being assembled into the Metaverse Logistics Digital Space Construction Device.

[0187] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the Metaverse Logistics Digital Space Construction Device, the Metaverse Logistics Digital Space Construction Device: obtains logistics data construction requirements;

[0188] According to the logistics data construction requirements, multiple dimensional data are obtained, and a three-dimensional demand matrix model is established based on the multiple dimensional data; based on the logistics data construction requirements, the goals and application scenarios of the digital twin base are determined, and the digital twin base is constructed according to the goals and the application scenarios; based on the logistics data construction requirements, a dynamic data governance process is constructed, and the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection and logistics equipment knowledge graph construction; based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process, a metaverse interaction space is generated.

[0189] The computer program code for performing the operations of the present application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0190] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0191] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0192] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., a computer program) for executing the above-mentioned method for constructing a digital space for metaverse logistics. It can solve the technical problems that the existing logistics management system has difficulty in realizing efficient integration of multi-source heterogeneous data, resulting in time delays in information transmission, inability to support real-time decision-making, and inability to provide users with an immersive interactive experience. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the method for constructing a digital space for metaverse logistics provided in the above-mentioned embodiment, and will not be elaborated here.

[0193] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for constructing a metaverse logistics digital space.

[0194] The computer program product provided in this application can address the technical issues that existing logistics management systems face, such as difficulty efficiently integrating multi-source heterogeneous data, resulting in information transmission delays, an inability to support real-time decision-making, and an inability to provide users with an immersive interactive experience. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the method for constructing a metaverse logistics digital space provided in the aforementioned embodiments, and are not further elaborated here.

[0195] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for constructing a digital space for metaverse logistics, characterized in that: The method for constructing the Metaverse Logistics Digital Space includes: Obtain logistics data construction requirements; Acquire multiple dimensional data based on the logistics data to build demand, and establish a three-dimensional demand matrix model based on the multiple dimensional data; Determining the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and constructing the digital twin base according to the goals and the application scenarios; Building a dynamic data governance process based on the logistics data construction requirements, the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection and logistics equipment knowledge graph construction; A metaverse interaction space is generated based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process.

2. The method according to claim 1, wherein The steps of acquiring multiple dimensional data according to the logistics data and establishing a three-dimensional demand matrix model based on the multiple dimensional data include: Determining a plurality of dimensional data according to the logistics data construction requirements, wherein the plurality of dimensional data includes a spatial dimension, a modal dimension, and an efficiency dimension; A three-dimensional demand matrix model is established according to the spatial dimension, the modal dimension, and the effectiveness dimension.

3. The method according to claim 2, wherein The step of establishing a three-dimensional demand matrix model according to the spatial dimension, the modal dimension, and the effectiveness dimension includes: Dividing the physical unit into a storage physical unit, a packaging physical unit, and a transportation physical unit according to the spatial dimension to obtain a spatial dimension division result; Defining multi-source data acquisition requirements according to the modal dimension, wherein the multi-source data acquisition requirements include video stream data acquisition requirements, mechanical data acquisition requirements, and temperature and humidity data acquisition requirements; Setting performance indicators according to the performance dimensions, the performance indicators including a real-time response threshold indicator, a data cleaning accuracy indicator, and a system availability performance indicator; A three-dimensional demand matrix model is constructed according to the spatial dimension division result, the multi-source data collection requirements and the performance index.

4. The method according to claim 1, wherein The steps of determining the goals and application scenarios of the digital twin base based on the logistics data construction requirements and constructing the digital twin base according to the goals and the application scenarios include: Analyze the requirements for building logistics data to obtain the goals and application scenarios of the digital twin base; Determine a target edge computing platform based on the target and the application scenario, and deploy edge computing nodes on the target edge computing platform; Constructing a spatiotemporal reference framework to synchronize the time of the edge computing nodes and obtain a synchronization result; Build a multimodal encoder based on the Transformer architecture based on data of different modalities; A digital twin base is generated according to the synchronization result and the multimodal encoder.

5. The method according to claim 4, wherein The steps of constructing a multimodal encoder based on the Transformer architecture based on data of different modalities include: Preprocess and extract features of data of different modalities to obtain feature data; Mapping the feature data to an embedding space through an initial multimodal encoder so that a Transformer model processes the feature data and learns the correlation between different modalities; Assigning different weights to the feature data of different modalities through a self-attention mechanism to obtain weighted data; An embedded representation of the feature data is obtained based on the embedding space, and the Transformer model is optimized through a joint training method based on the weight data to generate a multimodal encoder based on the Transformer architecture.

6. The method according to claim 1, wherein The step of building a dynamic data governance process based on the logistics data building requirements includes: Establishing an intelligent data pre-processing architecture based on the logistics data construction requirements; Deploy a frequency domain feature extraction algorithm of wavelet packet transform, an anomaly detection module for multi-dimensional sensor data joint anomaly diagnosis, and a logistics equipment knowledge graph for logistics equipment data storage on the intelligent data preprocessing architecture to obtain deployment results; Generate a dynamic data governance process based on the deployment results.

7. The method according to claim 6, wherein The construction of the logistics equipment knowledge graph includes: According to the preset screening rules, the quantity of old equipment with the same equipment demand and the same equipment on hand is processed to obtain the logistics equipment metadata; Get operation manuals and troubleshooting cases; The logistics equipment metadata, the operation manual and the fault case are converted into RDF triples for storage to generate a logistics equipment knowledge graph.

8. The method according to any one of claims 1 to 7, characterized in that The step of generating a metaverse interaction space based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process includes: Creating a virtual physical image layer based on the three-dimensional demand matrix model, the digital twin base, and the dynamic data governance process; Build event-driven data pipelines based on distributed stream processing platforms to generate digital threads; Developing mixed reality interfaces through mixed reality headsets and force feedback gloves; A metaverse interaction space is generated according to the virtual physical mirror layer, the digital main line, and the mixed reality interface.

9. A device for constructing a digital space for metaverse logistics, characterized in that: The device comprises: Acquisition module, used to obtain logistics data construction requirements; A construction module, configured to acquire a plurality of dimensional data according to the logistics data construction demand, and establish a three-dimensional demand matrix model based on the plurality of dimensional data; A determination module, configured to determine the goals and application scenarios of the digital twin base based on the logistics data construction requirements, and to construct the digital twin base according to the goals and the application scenarios; The construction module is further used to construct a dynamic data governance process based on the logistics data construction requirements, and the dynamic data governance process includes intelligent data preprocessing, frequency domain feature extraction, anomaly detection, and logistics equipment knowledge graph construction; A generation module is used to generate a metaverse interaction space based on the three-dimensional demand matrix model, the digital twin base and the dynamic data governance process.

10. A device for constructing a digital space for metaverse logistics, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for constructing a metaverse logistics digital space as described in any one of claims 1 to 8.

Images