Digital twinborn mixed cloud-side collaborative intelligent real estate building group operation and maintenance intelligent system

Abstract

The invention relates to the field of building intellectualization, in particular to a digital twinborn mixed cloud edge collaborative intelligent house building group operation and maintenance intelligent system, which establishes a digital twinborn scene database by collecting building basic information, equipment operation data and environmental parameters, synchronizes the digital twinborn scene database to edge equipment, and uses BIM, GIS, Internet of Things, 5G and AI technologies to establish a digital twinborn scene database, so as to realize the intelligent operation and maintenance of a building group. A virtual-real combined digital intelligent building scene is constructed, real-time synchronization of a virtual scene and a physical environment is realized through AR / VR equipment, and an operation and maintenance module comprises multi-source heterogeneous data fusion, edge intelligent analysis decision, adaptive model training and iterative optimization, a predictive maintenance algorithm of virtual-real mapping and a multi-level collaborative decision and autonomous scheduling mechanism. And the monitoring module monitors the state and operation condition of the edge equipment, provides data service and supports visualization of management decisions, and the system effectively improves the intelligence and digitization level of operation and maintenance of the building group.

Description

Technical Field

[0001] The present invention relates to the field of building intelligence, and in particular to a digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system, which belongs to the cross-application technical field of smart buildings, Internet of Things technology, artificial intelligence and cloud-edge collaborative computing. Background Art

[0002] With the acceleration of urbanization and the expansion of building complexes, traditional building operation and maintenance management models are no longer adapting to the management needs of today's complex building complexes. Traditional building operation and maintenance suffers from the following typical problems: delayed response to equipment failures, with maintenance often relying on reactive approaches; decentralized operation and maintenance management, with each system operating independently and lacking coordination; low data utilization, making it impossible to form data-driven decisions; high labor costs and low maintenance efficiency; severe energy waste and high operating costs; and difficulty in predicting and preventing safety risks.

[0003] Existing building operation and maintenance systems typically employ a centralized management approach, centrally monitoring and managing equipment across multiple buildings. However, this approach presents several key issues: First, centralized systems struggle to cope with the complexity of large-scale building complexes, resulting in slow system response times; second, they lack real-time data analysis and prediction capabilities, preventing the early detection of potential failures; third, data silos exist between different building systems, hindering collaborative decision-making; and finally, the system suffers from poor scalability, making it difficult to adapt to the dynamic changes of the building complex.

[0004] The development of smart buildings has evolved from the construction of intelligent systems for individual buildings to the construction and operation and maintenance of intelligent systems for building complexes. However, there is still a lack of comprehensive intelligent operation and maintenance systems that effectively integrate advanced technologies such as digital twins, cloud-edge collaboration, and predictive maintenance. Faced with the complexities of building complexes, there is an urgent need to break through traditional boundaries and develop a smart building complex operation and maintenance system based on digital twin technology, combined with a cloud-edge collaborative architecture, and enabling intelligent predictive maintenance. Summary of the Invention

[0005] The present invention aims to solve the above-mentioned problems existing in the prior art and provide a digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system. The system constructs a virtual mapping of the building complex through digital twin technology, combines the cloud-edge collaborative architecture to achieve efficient data processing and decision-making, and realizes predictive maintenance through intelligent algorithms, thereby greatly improving the intelligence level and efficiency of building complex operation and maintenance.

[0006] The present invention proposes a digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system, including:

[0007] The collection module is used to collect basic building information, equipment operation data and environmental parameters of smart real estate buildings;

[0008] A storage module is in communication with the acquisition module, and is used to transmit the collected data to the cloud to establish a digital twin scene database, and synchronize the data in the digital twin scene database to the edge device;

[0009] A construction module, communicatively connected to the storage module, configured to establish a digital twin building complex model based on the data in the digital twin scene database, and to establish a digital twin scene through the digital twin building complex model;

[0010] A scene module, which is in communication with the building module and is used to build a digital smart building scene that combines virtuality and reality using BIM, GIS, the Internet of Things, 5G technology, and AI technology;

[0011] A virtual-reality synchronization module, in communication with the scene module, is used to present the physical world dynamics in the digital smart building scene using AR / VR devices, thereby achieving real-time synchronization between the virtual scene and the physical environment;

[0012] An operation and maintenance module, which is in communication with the virtual-reality synchronization module and is used to build a digital twin operation and maintenance brain. The digital twin operation and maintenance brain includes a multi-source heterogeneous data fusion and real-time processing mechanism, an edge intelligent analysis and decision-making framework, an adaptive model training and iterative optimization system, a predictive maintenance algorithm for virtual-reality mapping, and a multi-level collaborative decision-making and autonomous scheduling mechanism.

[0013] The monitoring module is communicated with the operation and maintenance module and is used to monitor the status and operation of edge devices, form monitoring reports, and simulate the actual operation and maintenance scenarios of the building complex based on the data through the digital twin building complex model to provide data services for the intelligent operation and maintenance of the building complex.

[0014] Preferably, the multi-source heterogeneous data fusion and real-time processing mechanism includes:

[0015] Multi-source data collection architecture for collecting physical layer sensor data, edge layer processing data, and cloud-aggregated data;

[0016] A data adapter, communicating with the multi-source data acquisition architecture, is used to unify and standardize the formats of BIM, GIS, and IoT device data;

[0017] a spatiotemporal index data structure, in communication with the data adapter, for unifying data from different sources and at different sampling rates into a spatiotemporal dimension;

[0018] a data quality assessment algorithm, in communication with the spatiotemporal index data structure, for performing real-time cleaning and anomaly detection on the sensor data;

[0019] The data caching and distribution mechanism is in communication with the data quality assessment algorithm and is used to perform hierarchical processing based on the importance and timeliness of the data.

[0020] Preferably, the edge intelligent analysis and decision framework includes:

[0021] A lightweight edge AI inference engine to support real-time analysis of device status and fault prediction;

[0022] An autonomous decision-making mechanism for edge nodes, communicating with the lightweight edge AI inference engine, for making local decisions based on preset rules and historical data;

[0023] A dynamic scheduling algorithm for edge computing resources, in communication with the autonomous decision-making mechanism of the edge nodes, for adaptively allocating resources based on task priority and computing load;

[0024] An edge security isolation mechanism, communicating with the edge computing resource dynamic scheduling algorithm, is used to ensure that sensitive data is processed locally and reduce data transmission risks;

[0025] An edge cache optimization strategy is communicated with the edge security isolation mechanism and is used to intelligently cache data based on access frequency and data importance.

[0026] Preferably, the adaptive model training and iterative optimization system includes:

[0027] An incremental learning framework that allows models to be updated locally on edge nodes without requiring full retraining.

[0028] Model compression technology, in communication with the incremental learning framework, is used to compress complex models trained in the cloud into executable versions for edge devices;

[0029] A federated learning mechanism, in communication with the model compression technology, is used to enable multiple edge nodes to train collaboratively without sharing raw data;

[0030] A model performance monitoring system, communicating with the federated learning mechanism, for real-time evaluation of model prediction accuracy and triggering updates;

[0031] A model version management mechanism communicates with the model performance monitoring system to support model rollback and A / B testing.

[0032] Preferably, the predictive maintenance algorithm of virtual-real mapping includes:

[0033] A digital twin building equipment health assessment model, which integrates physical models and data-driven models to assess equipment health status;

[0034] An equipment remaining life prediction algorithm, in communication with the digital twin building equipment health assessment model, for predicting the remaining life based on historical equipment operating data and maintenance records;

[0035] a multi-dimensional failure pattern recognition system, in communication with the equipment remaining life prediction algorithm, for identifying complex failure patterns and potential risks;

[0036] a dynamic maintenance strategy generator, in communication with the multi-dimensional fault pattern recognition system, for intelligently planning maintenance time and resources based on prediction results;

[0037] A virtual scenario fault simulation system is communicated with the dynamic maintenance strategy generator and is used to verify the maintenance plan in a digital twin environment.

[0038] Preferably, the multi-level collaborative decision-making and autonomous scheduling mechanism includes:

[0039] A hierarchical decision-making framework is used to clarify the decision-making authority and coordination mechanism of the cloud layer, edge layer, and end layer;

[0040] a conflict resolution algorithm, in communication with the hierarchical decision framework, for automatically coordinating when conflicts exist among decisions at different levels;

[0041] A task splitting and distribution system, in communication with the conflict resolution algorithm, is used to decompose complex operation and maintenance tasks into subtasks that can be executed at different levels;

[0042] Resource pooling management, communicating with the task splitting and distribution system, is used to dynamically allocate computing, storage, and network resources according to task requirements;

[0043] An autonomous scheduling optimizer is in communication with the resource pooling management and is used to optimize the scheduling strategy based on task priority, resource availability and energy consumption targets.

[0044] Preferably, the system further comprises:

[0045] A communication module is connected to the operation and maintenance module and the monitoring module, and is used to connect with various system devices in the smart building, and transmit the acquired smart building equipment operation and maintenance data and building complex equipment operation data to the cloud-edge collaborative architecture to achieve data synchronization;

[0046] The communication module realizes the collection and transmission of building complex operation and maintenance data by establishing an API connection.

[0047] Preferably, the basic building information, equipment operation data and environmental parameters of the smart real estate building complex include:

[0048] Basic building information, including the building's floor plan, elevation, structural diagram, and equipment distribution diagram;

[0049] Building operation and maintenance information, including equipment operating parameters, energy consumption data, and maintenance records;

[0050] Building equipment information, including equipment model, parameter specifications and operating status;

[0051] Public area information, including personnel flow, environmental parameters, and security status;

[0052] Building complex information, including the overall layout of the building complex, their relationships and shared facility data.

[0053] Preferably, the cloud layer architecture of the system includes:

[0054] Cloud basic service layer, used to provide basic computing, storage and network resources;

[0055] The platform service layer is connected to the cloud-based service layer to provide data processing, model training and knowledge base management;

[0056] The application service layer is connected to the platform service layer for providing operation and maintenance decision support, resource scheduling and user interaction interface.

[0057] Preferably, the edge layer architecture of the system includes:

[0058] Intelligent access control layer, used to implement personnel access control and identity authentication;

[0059] An intelligent machine control layer, communicating with the intelligent access control layer, for managing intelligent devices and robots;

[0060] A robot brain bank layer, communicating with the intelligent machine control layer, for processing visual information and controlling robot behavior;

[0061] A data processing and service layer, communicating with the robot brain bank layer, for performing data preprocessing and edge analysis;

[0062] Among them, the intelligent access control layer, the intelligent machine control layer, the robot brain bank layer and the data processing and service layer are all communicatively connected with the cloud layer and the building module.

[0063] The beneficial effects of the present invention include:

[0064] 1. Achieve fully digital management of building complexes: Through digital twin technology, build a digital model of the building complex, achieve real-time mapping and interaction between the physical and virtual worlds, and provide visual support for management decisions.

[0065] 2. Improved operation and maintenance efficiency: Through predictive maintenance algorithms, the system can predict potential equipment failures in advance, transforming traditional passive responses into proactive prevention, reducing equipment failure rates by 35% and maintenance costs by 30%.

[0066] 3. Reduce energy consumption: Through intelligent control and management, optimize energy use strategies to reduce building energy consumption by 15-30% and reduce peak load by 20%.

[0067] 4. Improve security: Through intelligent security and access control management, all-round monitoring of personnel, equipment and environment is achieved, reducing security incidents by 50% and shortening emergency response time by 60%.

[0068] 5. Optimize resource allocation: Through multi-level collaborative decision-making and autonomous scheduling mechanisms, optimize the allocation of human and material resources, increase resource utilization by 35%, and improve operation and maintenance quality by 25%.

[0069] 6. Promote wealth creation: Reduce operation and maintenance costs through intelligent operation and maintenance systems, so that high-quality construction services can benefit a wider range of people; at the same time, create high-quality jobs, enhance the overall value of the industrial chain, and provide technical support for the realization of joint wealth creation. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a schematic diagram of the overall architecture of the digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system of the present invention;

[0071] Figure 2 It is a data flow chart of the system of the present invention;

[0072] Figure 3 Schematic diagram of multi-source heterogeneous data fusion and real-time processing mechanism in the system of the present invention;

[0073] Figure 4 Schematic diagram of the edge intelligence analysis and decision-making framework in the system of the present invention;

[0074] Figure 5 This is a flow chart of the adaptive model training and iterative optimization system in the system of the present invention;

[0075] Figure 6 Schematic diagram of the predictive maintenance algorithm for virtual-real mapping in the system of the present invention;

[0076] Figure 7 Schematic diagram of the multi-level collaborative decision-making and autonomous scheduling mechanism in the system of the present invention;

[0077] Figure 8 Schematic diagram of an embodiment of the system of the present invention applied to energy consumption management of intelligent buildings;

[0078] Figure 9A schematic diagram of an embodiment of the present invention system applied to equipment failure prediction and maintenance;

[0079] Figure 10 The figure is a schematic diagram of an embodiment of the system of the present invention applied to intelligent security and access control management. DETAILED DESCRIPTION

[0080] Please refer to the attached Figure 1-10 The following clearly and completely describes the technical solution of the present invention in conjunction with the accompanying drawings and specific embodiments. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0081] like Figure 1 As shown, the digital twin hybrid cloud-edge collaborative intelligent real estate complex operation and maintenance system provided by the present invention includes an acquisition module 1, a storage module 2, a construction module 3, a scenario module 4, a virtual-reality synchronization module 5, an operation and maintenance module 6, a monitoring module 7, and a communication module 8. The system adopts a three-layer "cloud-edge-end" collaborative architecture, with a digital twin operation and maintenance brain at its core, to achieve intelligent operation and maintenance management of smart building complexes.

[0082] The cloud layer architecture of the system of the present invention includes: a cloud layer basic service layer 91, a platform service layer 92 and an application service layer 93.

[0083] The Cloud Basic Services Layer 91 provides basic computing, storage, and network resources. In one embodiment of the present invention, the Cloud Basic Services Layer 91 utilizes a distributed computing architecture, comprising a computing resource pool, a storage resource pool, and a network resource pool. The computing resource pool consists of multiple high-performance servers and supports elastic scalability. The storage resource pool includes block storage, file storage, and object storage to meet the storage needs of different data types. The network resource pool provides high-speed, secure network connections to ensure rapid data transmission.

[0084] The platform service layer 92 communicates with the cloud-based basic service layer 91 and provides data processing, model training, and knowledge base management. Preferably, the platform service layer 92 includes a big data processing engine, an artificial intelligence training platform, and a knowledge graph management system. The big data processing engine supports batch and stream processing, capable of processing over 100,000 data records per second. The artificial intelligence training platform provides model training, optimization, and management capabilities, supporting deep learning and machine learning algorithms. The knowledge graph management system stores building domain knowledge and equipment maintenance experience, forming a searchable knowledge base.

[0085] The application service layer 93 communicates with the platform service layer 92 and provides operational decision support, resource scheduling, and a user interface. In this embodiment of the present invention, the application service layer 93 includes a decision support system, a resource scheduling system, and a user interface system. The decision support system provides operational decision recommendations based on data analysis results; the resource scheduling system optimizes the allocation of human and material resources; and the user interface system provides web and mobile access interfaces, supporting visual data display and interactive operations.

[0086] The edge layer architecture of the system of the present invention includes: an intelligent access control layer 101, an intelligent machine control layer 102, a robot brain library layer 103 and a data processing and service layer 104.

[0087] The intelligent access control layer 101 is used to implement personnel access control and identity authentication. In a specific embodiment of the present invention, the intelligent access control layer 101 includes a multimodal identity recognition system and a visitor management system. The multimodal identity recognition system integrates multiple authentication methods such as facial recognition, IC card recognition, and fingerprint recognition, with an accuracy rate of 99.7%. The visitor management system supports appointment registration, temporary permission allocation, and visit trajectory recording.

[0088] The intelligent machine control layer 102 communicates with the intelligent access control layer 101 and manages intelligent devices and robots. Preferably, the intelligent machine control layer 102 includes a device control system and a robot management system. The device control system implements intelligent control of building equipment such as air conditioning, lighting, and elevators; the robot management system coordinates the work of multiple robots, including task allocation, path planning, and status monitoring.

[0089] The robot brain layer 103 is in communication with the intelligent machine control layer 102 and is responsible for processing visual information and controlling robot behavior. In one embodiment of the present invention, the robot brain layer 103 includes a visual analysis system and a behavioral control system. The visual analysis system processes image data collected by the robot's camera to identify device status and environmental changes. The behavioral control system generates control instructions based on the analysis results, guiding the robot to perform tasks such as inspection and measurement.

[0090] The data processing and service layer 104 is connected to the robot brain bank layer 103 and is used to perform data preprocessing and edge analysis. Furthermore, the data processing and service layer 104 includes a data preprocessing engine and an edge analysis engine. The data preprocessing engine filters, standardizes, and time-aligns the collected raw data; the edge analysis engine executes lightweight analysis algorithms at edge nodes to generate preliminary analysis results.

[0091] At the same time, the intelligent access control layer 101, the intelligent machine control layer 102, the robot brain bank layer 103 and the data processing and service layer 104 are all connected to the cloud layer and the building module 3 to achieve a two-way flow of data and control information.

[0092] The system of the present invention includes multiple functional modules. The functions and implementation methods of each module will be described in detail below:

[0093] Collection Module 1 is used to collect basic building information, equipment operating data, and environmental parameters of the smart real estate complex. In a specific implementation of the present invention, Collection Module 1 includes a sensor network, a data collection gateway, and a data quality control unit. The sensor network consists of temperature, humidity, pressure, flow, current, voltage, and other sensors distributed throughout the complex. The sampling frequency can be dynamically adjusted based on the importance of the data, typically 1-10 times per second. The data collection gateway uses the lightweight Internet of Things protocol (MQTT / CoAP) to collect sensor data. The data quality control unit performs preliminary verification of the collected data and filters out any obvious errors.

[0094] Storage module 2 is in communication with acquisition module 1 and is used to transmit collected data to the cloud to establish a digital twin scenario database and synchronize the data in the digital twin scenario database to edge devices. Preferably, storage module 2 adopts a tiered storage strategy, storing hot data in high-speed storage devices and transferring cold data to low-cost storage devices. Data synchronization uses an incremental synchronization method, synchronizing only the changed data, reducing the network transmission burden.

[0095] Construction module 3 is in communication with storage module 2 and is used to create a digital twin building complex model based on the data in the digital twin scene database, and to establish a digital twin scene using the digital twin building complex model. In an embodiment of the present invention, construction module 3 integrates BIM (Building Information Modeling) and GIS (Geographic Information System) technologies to construct a comprehensive digital model that includes geometric, semantic, and relational information. The model construction process includes three levels: spatial structure modeling, equipment system modeling, and operational status modeling.

[0096] Scenario Module 4 communicates with Construction Module 3 and is used to construct digital intelligent building scenarios that integrate virtual and real elements using BIM, GIS, the Internet of Things, 5G, and AI technologies. Furthermore, Scenario Module 4 enables multi-dimensional scenario construction, including physical structure scenarios, equipment system scenarios, human activity scenarios, and environmental parameter scenarios. Scenario construction utilizes a modular design, supporting rapid scenario updates and reconstruction.

[0097] The virtual-reality synchronization module 5 is in communication with the scene module 4 and is used to use AR / VR devices to present the dynamics of the physical world in the digital intelligent building scene, achieving real-time synchronization between the virtual scene and the physical environment. In one embodiment of the present invention, the virtual-reality synchronization module 5 uses real-time data stream processing technology to synchronize changes in the physical world to the virtual scene with low latency (typically less than 100 milliseconds). At the same time, spatial positioning technology is used to achieve precise positioning of the AR / VR device in the physical space, supporting interactive operations and information overlay display.

[0098] Operation and maintenance module 6 communicates with virtual-reality synchronization module 5 to build the digital twin's operation and maintenance brain. This brain includes a multi-source heterogeneous data fusion and real-time processing mechanism, an edge intelligence analysis and decision-making framework, an adaptive model training and iterative optimization system, a predictive maintenance algorithm for virtual-reality mapping, and a multi-level collaborative decision-making and autonomous scheduling mechanism. Operation and maintenance module 6 is the core of the system and will be described in detail in subsequent sections.

[0099] The monitoring module 7 is in communication with the operation and maintenance module 6 and is used to monitor the status and operation of edge devices, generate monitoring reports, and simulate the actual operation and maintenance scenarios of the building complex based on data through the digital twin building complex model, providing data services for the intelligent operation and maintenance of the building complex. Preferably, the monitoring module 7 includes a device status monitoring unit, an operation data analysis unit, and a report generation unit. The device status monitoring unit monitors the working status and health of the equipment in real time; the operation data analysis unit performs statistical analysis on historical operation data to identify abnormal patterns and optimization opportunities; and the report generation unit automatically generates daily, weekly, and monthly reports and supports custom report templates and indicators.

[0100] The communication module 8 is connected to the operation and maintenance module 6 and the monitoring module 7, and is used to connect to various system devices in the smart building, transmitting the acquired smart building equipment operation and maintenance data and building complex equipment operation data to the cloud-edge collaborative architecture to achieve data synchronization. In an embodiment of the present invention, the communication module 8 realizes the collection and transmission of building complex operation and maintenance data by establishing an API connection. The communication module 8 supports multiple communication protocols, including MQTT, HTTP, WebSocket, etc., to ensure compatibility with different systems and devices; it also implements communication encryption and identity authentication to ensure data transmission security.

[0101] The basic building information, equipment operation data and environmental parameters of the smart real estate building complex include: basic building information, building operation and maintenance information, building equipment information, public area information and building complex information.

[0102] Basic building information includes the building's floor plan, elevation, structural diagram, and equipment layout. This information is usually stored in the form of CAD drawings, BIM models, or 3D scan data, which serves as the foundation for building digital twin models.

[0103] Building operation and maintenance information includes equipment operating parameters, energy consumption data, and maintenance records. Equipment operating parameters include physical quantities such as temperature, pressure, flow, voltage, and current, typically stored as time series data. Energy consumption data includes electricity, water, and gas consumption, calculated by hour, day, and month. Maintenance records include maintenance time, maintenance content, maintenance personnel, and maintenance results.

[0104] Building equipment information includes equipment model, parameter specifications, and operating status. Equipment model and parameter specifications are stored as static information in the equipment information library; operating status is updated in real time as dynamic information to reflect the current working status of the equipment.

[0105] Public area information includes personnel flow, environmental parameters, and security status. Personnel flow data is collected through traffic sensors, cameras, and access control systems and used to analyze public area usage. Environmental parameters include temperature, humidity, light, noise, air quality, and other indicators. Security status includes information on the status of fire protection, monitoring, and alarm systems.

[0106] Building complex information includes the overall layout, relationships, and shared facilities. The overall layout describes the spatial location and relative relationships of buildings; relationships between buildings include functional connections and resource sharing; and shared facilities include information on shared roads, squares, green spaces, parking lots, and other public facilities.

[0107] At the heart of this invention is the Digital Twin Operations Brain, which integrates multiple innovative technologies to enable intelligent operations and management of building complexes. The following details the five core technologies of the Digital Twin Operations Brain.

[0108] The multi-source heterogeneous data fusion and real-time processing mechanism includes: multi-source data acquisition architecture, data adapter, spatiotemporal index data structure, data quality assessment algorithm and data caching and distribution mechanism.

[0109] The multi-source data acquisition architecture is used to collect physical layer sensor data, edge layer processing data, and cloud-aggregated data. In an embodiment of the present invention, physical layer data acquisition adopts a hierarchical and partitioned deployment strategy, and optimizes the sensor network layout based on the building's structural characteristics and equipment distribution. The sensor sampling frequency is dynamically adjusted according to the importance and change rate of the data. The sampling frequency of key equipment is 5-10 times / second, and that of general equipment is 1-3 times / second. Edge layer data preprocessing is performed at the data acquisition gateway, including range checking, consistency verification, and timing continuity analysis, effectively reducing the amount of invalid data transmission. Cloud data aggregation uses a distributed timestamp protocol to ensure the time consistency of data from different sources, with the error controlled within 10 milliseconds.

[0110] The data adapter communicates with the multi-source data acquisition architecture to achieve format unification and standardized processing of BIM, GIS, and IoT device data. Preferably, the data adapter includes multiple data conversion modules that support conversion between common data formats such as JSON, XML, and CSV. For BIM data, it supports parsing and conversion of formats such as IFC and RVT; for GIS data, it supports processing of formats such as Shapefile and GeoJSON; and for IoT device data, it supports parsing of protocol data such as MQTT and CoAP. The data adapter also implements unit standardization, unifying different units of measurement into the international standard unit system.

[0111] The spatiotemporal index data structure is connected to the data adapter for unifying data from different sources and at different sampling rates into the spatiotemporal dimension. In an embodiment of the present invention, the spatiotemporal index data structure uses a combination of multi-granularity time indexing and hierarchical spatial indexing. The time dimension index supports time granularity queries at different levels, such as seconds, minutes, hours, and days. The spatial dimension index is based on a hierarchical index structure designed based on the physical structure of the building, including multiple levels such as building complexes, buildings, floors, areas, and equipment. The spatiotemporal joint index structure can be expressed as:

[0112] ,

[0113] in: is the spatiotemporal joint index, is the time index, Indicates the time granularity level, is the spatial index, Represents the spatial level, is the data value, Indicates a data type.

[0114] The data quality assessment algorithm is connected to the spatiotemporal index data structure and is used to perform real-time cleaning and anomaly detection on the sensor data. Preferably, the data quality assessment algorithm includes three steps: integrity check, accuracy verification, and consistency analysis. The integrity check identifies missing data and incomplete records, the accuracy verification finds outliers through range checking and pattern matching, and the consistency analysis ensures data consistency by cross-validating relevant data from different sources. The data quality score calculation formula is:

[0115] ,

[0116] in: Score the data quality, Score for completeness, Score for accuracy, is the consistency score, 、 、 is the weight coefficient and satisfies In the embodiment of the present invention, it is usually set , , , because accuracy has a greater impact on subsequent analysis.

[0117] The data caching and distribution mechanism is connected to the data quality assessment algorithm to perform hierarchical processing based on data importance and timeliness. In an embodiment of the present invention, data caching adopts a multi-level caching strategy, including memory cache, local storage cache and cloud storage. The data importance score is calculated based on device importance, data change rate and application requirements:

[0118] ,

[0119] in: Score the importance of the data. Rate the importance of the equipment (1-10, 10 being the most important), is the data change rate, is the frequency with which data is requested by the application, 、 、 is the weight coefficient and satisfies According to actual application experience, it is usually set =0.5, =0.3, =0.2, because device importance has the greatest impact on data importance.

[0120] The edge intelligent analysis and decision-making framework includes: a lightweight edge AI inference engine, an autonomous decision-making mechanism for edge nodes, a dynamic scheduling algorithm for edge computing resources, an edge security isolation mechanism, and an edge cache optimization strategy.

[0121] The lightweight edge AI inference engine is used to support real-time analysis of device status and fault prediction. In an embodiment of the present invention, the lightweight edge AI inference engine compresses complex models trained in the cloud into an executable version for edge devices based on model compression technology. Model compression uses parameter quantization, structural pruning, and knowledge distillation technologies to significantly reduce the model size and computational complexity while maintaining model accuracy. Parameter quantization converts 32-bit floating point numbers into 8-bit integers, reducing storage space by 75%; structural pruning reduces model parameters by 30-50% by removing unimportant network connections; knowledge distillation transfers the knowledge of a large teacher model to a small student model, reducing the model size while maintaining performance.

[0122] The edge node's autonomous decision-making mechanism communicates with a lightweight edge AI inference engine to make local decisions based on preset rules and historical data. Preferably, the edge node's autonomous decision-making mechanism includes a rules engine and a lightweight decision tree evaluation system. The rules engine makes rapid decisions based on preset business rules, suitable for specific scenarios. The decision tree evaluation system constructs a multi-layer decision tree based on device characteristics and operating environment, supporting more complex decision logic. During the decision-making process, the system clearly defines the scope of local decision-making and the situations that need to be reported to the cloud, ensuring the security and effectiveness of decisions.

[0123] The edge computing resource dynamic scheduling algorithm is connected to the edge node autonomous decision-making mechanism to adaptively allocate resources based on task priority and computing load. In an embodiment of the present invention, the edge computing resource dynamic scheduling algorithm adopts a priority-based multi-level queue scheduling strategy combined with a load-aware resource allocation mechanism. Task priority evaluation takes into account task importance, urgency, and resource requirements, and the calculation formula is:

[0124] ,

[0125] in: is the task priority, For the importance of the task (1-10, 10 is the most important), is the urgency of the task (0-1, 1 is the most urgent), is the task resource requirement ratio (0-1), 、 、 is the weight coefficient and satisfies According to actual application experience, it is usually set ,That is, importance and urgency have the same impact on priority and are greater than the impact of resource requirements.

[0126] The edge security isolation mechanism communicates with the dynamic scheduling algorithm for edge computing resources to ensure local processing of sensitive data and reduce data transmission risks. Preferably, the edge security isolation mechanism utilizes application sandboxing technology and access control mechanisms. Application sandboxing ensures secure isolation between different functional modules, preventing malicious code or erroneous operations from impacting system stability. The access control mechanism uses fine-grained, role-based permission control to ensure that only authorized users and programs can access sensitive data. Furthermore, the system automatically identifies and tags data containing sensitive information, prioritizing processing at the edge node and transmitting only necessary processing results rather than the original data.

[0127] The edge cache optimization strategy is connected to the edge security isolation mechanism and is used to intelligently cache data based on access frequency and data importance. In an embodiment of the present invention, the edge cache optimization strategy adopts an improved LRU-K algorithm that takes into account data access frequency, access pattern, and data importance. The cache priority calculation formula is:

[0128] ,

[0129] in: is the cache priority, is the access frequency, is the number of historical visits, For data importance, is the importance weight coefficient. After practical verification, setting A good balance can be achieved between access efficiency and priority caching of important data.

[0130] The adaptive model training and iterative optimization system includes: incremental learning framework, model compression technology, federated learning mechanism, model performance monitoring system and model version management mechanism.

[0131] The incremental learning framework is used to support local updates of the model at the edge node without the need for complete retraining. In an embodiment of the present invention, the incremental learning framework adopts a parameter difference learning method to update only the parameters in the model that are related to the new data, rather than all parameters. This method greatly reduces the amount of computation and memory requirements, enabling edge devices to perform local model updates. The incremental learning process includes three steps: local sample collection, differential parameter calculation, and local model update. Local sample collection is based on a data value assessment mechanism, giving priority to samples with large amounts of information; differential parameter calculation uses gradient sparsification technology to only calculate and transmit parameters that have changed significantly; local model updates use a low learning rate strategy to avoid excessive impact of new data on model performance.

[0132] The model compression technology is communicatively connected to the incremental learning framework and is used to compress complex models trained in the cloud into an executable version for edge devices. Preferably, the model compression technology includes three aspects: network structure simplification, weight quantization, and computational optimization. Network structure simplification reduces the model size by deleting redundant connections and layers; weight quantization converts 32-bit floating point numbers into integers of 8 bits or less, reducing storage space and computational complexity; computational optimization optimizes the calculation process based on the target hardware characteristics and improves execution efficiency. In an embodiment of the present invention, the model compression ratio typically reaches 10:1 to 20:1, and the accuracy of the compressed model remains above 95% of the original model.

[0133] The federated learning mechanism is connected to the model compression technology to enable multiple edge nodes to train collaboratively without sharing the original data. In an embodiment of the present invention, the federated learning mechanism adopts a secure aggregation algorithm to aggregate model updates while protecting the privacy of the original data. The federated learning process includes five steps: node selection, local training, gradient encryption, parameter aggregation, and model update. Node selection selects participating nodes based on data quality and computing power; local training uses local data for model training at each node; gradient encryption uses homomorphic encryption technology to protect gradient information; parameter aggregation is completed in the cloud, aggregating the encrypted gradients of multiple nodes; model update applies the aggregation results to the global model. The objective function of federated learning can be expressed as:

[0134] ,

[0135] in: is the global loss function, are model parameters, is the number of participating nodes, For nodes The number of samples, is the total sample size, For nodes The local loss function.

[0136] The model performance monitoring system is connected to the federated learning mechanism for real-time evaluation of the model's prediction accuracy and triggering updates. Preferably, the model performance monitoring system includes three functional modules: performance indicator tracking, anomaly detection, and update triggering. Performance indicator tracking continuously records the model's accuracy, precision, recall, and other indicators; anomaly detection identifies situations where the model's performance has significantly degraded; and update triggering determines whether to initiate the model update process based on preset rules. Performance evaluation uses a sliding window mechanism to calculate the average performance of the last N predictions to avoid unnecessary updates caused by short-term fluctuations. The update trigger conditions are usually set as follows: the performance indicator drops by more than 10% and lasts for more than 3 days, or the cumulative number of incorrect predictions exceeds a preset threshold.

[0137] The model version management mechanism is in communication with the model performance monitoring system to support model rollback and A / B testing. In an embodiment of the present invention, the model version management mechanism adopts a distributed version control system to record the versions and performance indicators of all model updates. Version management includes four aspects: version identification, performance recording, deployment tracking, and rollback mechanism. The version identification adopts a semantic version number to facilitate the identification of major versions and minor updates of the model; the performance recording saves the performance indicators of each version of the model in different scenarios; the deployment tracking records the deployment status and usage of the model; and the rollback mechanism supports rapid recovery to the previous stable version when the new model performs poorly. The A / B testing framework allows different versions of the model to be deployed simultaneously for comparative testing to evaluate the actual effect of the new model.

[0138] The predictive maintenance algorithm of virtual-reality mapping includes: digital twin building equipment health assessment model, equipment remaining life prediction algorithm, multidimensional fault pattern recognition system, dynamic maintenance strategy generator and virtual scene fault simulation system.

[0139] The digital twin building equipment health assessment model is used to integrate physical models and data-driven models to assess equipment health. In an embodiment of the present invention, the health assessment model adopts a dual-model fusion architecture, combining the advantages of physical law models and data-driven models. The physical model is based on the working principles and physical laws of the equipment to establish a mathematical model that describes the normal working state of the equipment; the data-driven model is based on historical data to learn the statistical laws and abnormal patterns of equipment operation. The health score calculation formula is:

[0140] ,

[0141] in: Score the device health (0-100, 100 is the healthiest), Score the physical model, Scoring data-driven models, and is the weight coefficient and satisfies According to actual application experience, different weights are set for different types of equipment. For mechanical equipment, , because the physical model is more accurate in describing mechanical equipment; for electrical equipment, it is usually set ,Because the data driven model is more sensitive to anomaly detection of electrical ,equipment.

[0142] The equipment remaining life prediction algorithm is communicated with the digital twin building equipment health assessment model to predict the remaining life based on the equipment's historical operating data and maintenance records. Preferably, the remaining life prediction algorithm adopts a life prediction method based on a degradation model, combining the equipment type characteristics and the use environment to establish a life model. The prediction process includes three steps: key parameter identification, degradation rate assessment, and life prediction. Key parameter identification determines the key parameters that affect the equipment life through correlation analysis and expert knowledge; degradation rate assessment quantifies the degradation rate of key parameters through time series analysis; life prediction calculates the remaining life based on the current state and degradation trend. The remaining life calculation formula is:

[0143] ,

[0144] in: is the remaining useful life, is the fault threshold, is the current parameter value, is the degradation rate, The environmental impact factor considers the impact of environmental conditions such as temperature, humidity, and load on device life. It usually ranges from 0.8 to 1.2. A value greater than 1 indicates accelerated environmental degradation, while a value less than 1 indicates slower environmental degradation.

[0145] The multidimensional fault pattern recognition system is communicated with the equipment remaining life prediction algorithm to identify complex fault patterns and potential risks. In an embodiment of the present invention, the multidimensional fault pattern recognition system includes three functional modules: a fault pattern library, an abnormal pattern detection, and a fault correlation analysis. The fault pattern library establishes a characteristic pattern library of common equipment failures, which contains the typical characteristics and evolution process of various types of failures; the abnormal pattern detection is based on multidimensional time series analysis to identify abnormal behaviors that deviate from the normal operating mode; the fault correlation analysis uses graphical models and causal reasoning to identify the correlation between different equipment failures. Anomaly detection adopts a multidimensional anomaly detection algorithm based on an autoencoder, and the reconstruction error calculation formula is:

[0146] ,

[0147] in: is the reconstruction error, is the feature dimension, is the original eigenvalue, is the reconstruction eigenvalue. When the reconstruction error exceeds the preset threshold, the system is judged to be in an abnormal state. The threshold is usually set to 3 times the standard deviation of the reconstruction error in the normal state, that is, ,in is the mean of the reconstruction error under normal conditions, is the standard deviation.

[0148] The dynamic maintenance strategy generator is connected to the multi-dimensional fault pattern recognition system and is used to intelligently plan maintenance time and resources based on the prediction results. Preferably, the dynamic maintenance strategy generator includes three functional modules: preventive maintenance planning, maintenance task priority, and maintenance plan recommendation. The preventive maintenance plan is formulated based on the equipment status and prediction results; the maintenance task priority determines the maintenance priority according to the risk level and resource constraints; and the maintenance plan recommendation recommends the maintenance method and steps that are most suitable for the current situation. The maintenance priority calculation formula is:

[0149] ,

[0150] in: To maintain priority, is the failure cost, is the failure probability, is the remaining useful life, For maintenance cycle, is the resource cost, The first term in the formula takes the maximum value of 0 to ensure that new equipment or equipment that has just been maintained will not generate negative risk values. As a basic maintenance cost, it remains constant. Priority calculation comprehensively considers failure risk and resource constraints, balancing maintenance needs and resource utilization efficiency.

[0151] The virtual scenario fault simulation system is communicatively connected to the dynamic maintenance strategy generator and is used to verify the maintenance plan in the digital twin environment. In an embodiment of the present invention, the virtual scenario fault simulation system adopts a hybrid simulation method based on physical laws and historical data to simulate equipment failures and maintenance processes in a digital twin environment. The simulation process includes three steps: initial state setting, fault evolution simulation, and maintenance effect evaluation. The initial state setting is based on the actual state of the current equipment; the fault evolution simulation is based on the evolution law in the fault mode library; and the maintenance effect evaluation is performed by comparing the changes in the equipment state before and after maintenance. The simulation system supports comparative testing of multiple maintenance plans, evaluates the effects and costs of different plans, and provides a scientific basis for maintenance decisions.

[0152] The multi-level collaborative decision-making and autonomous scheduling mechanism includes: hierarchical decision-making framework, conflict resolution algorithm, task splitting and distribution system, resource pooling management and autonomous scheduling optimizer.

[0153] The hierarchical decision-making framework is used to clarify the respective decision-making authority and coordination mechanism of the cloud layer, edge layer and end layer. In an embodiment of the present invention, the hierarchical decision-making framework adopts a three-tier decision-making architecture based on responsibility and capability. The cloud layer is responsible for global policy formulation, resource planning and long-term optimization decision-making, and usually deals with decision-making problems with large data volumes, complex calculations and long time spans; the edge layer is responsible for regional coordination, short-term scheduling and equipment collaborative control, and deals with decision-making problems with multi-device collaboration, medium complexity and response time requirements of seconds; the end layer is responsible for device-level real-time control and emergency response, and deals with decision-making problems with single-device control, low complexity and response time requirements of milliseconds. The decision-making process includes four stages: information collection, solution generation, evaluation and selection, and execution supervision to ensure the scientific nature and effectiveness of the decision.

[0154] The conflict resolution algorithm is connected to the hierarchical decision framework and is used to automatically coordinate when conflicts arise between decisions at different levels. Preferably, the conflict resolution algorithm includes two functional modules: conflict detection and conflict coordination. Conflict detection identifies decision conflicts between different levels or parallel nodes by comparing decision results and analyzing impacts; conflict coordination resolves conflicts through preset priority rules and negotiation mechanisms. Conflict types include resource conflicts, time conflicts, and goal conflicts, and different resolution strategies are adopted for different types of conflicts. The conflict priority score calculation formula is:

[0155] ,

[0156] in: Score the conflict priority, is the decision-making level (cloud layer = 3, edge layer = 2, end layer = 1), is the degree of urgency (0-1, 1 is the most urgent), is the impact range (O-1, 1 is the widest impact), 、 、 is the weight coefficient and satisfies 1. In security-related decisions, it is usually necessary to set , giving priority to urgency; in resource scheduling decisions, it is usually set , giving priority to hierarchy and scope of influence.

[0157] The task splitting and distribution system is in communication with the conflict resolution algorithm and is used to decompose complex operation and maintenance tasks into subtasks that can be executed at different levels. In an embodiment of the present invention, the task splitting and distribution system adopts a task decomposition strategy based on function and timing to split complex tasks into subtasks that can be executed in parallel or serially. The task splitting process includes three steps: functional decomposition, timing scheduling, and parallel optimization. Functional decomposition splits complex tasks into subtasks according to functional modules; timing scheduling determines the execution order and dependencies of subtasks; parallel optimization identifies subtasks that can be executed in parallel to improve efficiency. Task distribution is based on execution capability assessment and matching calculation, and assigns subtasks to the most suitable execution unit. The execution capability score calculation formula is:

[0158] ,

[0159] in: Score your execution ability. For computing power, is the current load rate, is the task similarity (the degree of similarity with historical tasks), 、 、 is the weight coefficient and satisfies According to actual application experience, it is usually set ,That is, computing power and load conditions have the same impact on execution ability, and are greater than the impact of task similarity.

[0160] Resource pooling management is communicated with the task splitting and distribution system to dynamically allocate computing, storage, and network resources according to task requirements. Preferably, resource pooling management includes three functional modules: computing resource pool, storage resource pool, and network resource pool. The computing resource pool uniformly manages available computing resources at all levels, including cloud servers, edge computing nodes, and end device processors; the storage resource pool coordinates and manages distributed storage resources, including cloud databases, edge caches, and local storage; the network resource pool optimizes network bandwidth and connection resource allocation to ensure the priority of critical data transmission. Resource allocation adopts an advance allocation strategy based on demand forecasting, predicting future resource demand based on historical patterns, and scheduling additional resources in advance for expected peak periods.

[0161] The autonomous scheduling optimizer is in communication with the resource pooling management and is used to optimize the scheduling strategy based on task priority, resource availability, and energy consumption targets. In an embodiment of the present invention, the autonomous scheduling optimizer uses a multi-objective optimization scheduling algorithm to balance the three objectives of performance, energy consumption, and cost. The scheduling optimization objective function can be expressed as:

[0162] ,

[0163] in For comprehensive optimization goals, For the scheduling plan, is the performance objective function, is the energy consumption objective function, is the cost objective function, 、 、 is the weight coefficient and satisfies In key business scenarios, it is usually set , giving priority to performance; in daily operation and maintenance scenarios, usually set ,give priority to energy consumption and cost.,The scheduling strategy implementation process includes three steps of scheme generation,,scheme evaluation and scheme execution to ensure the scientificity and feasibility of,scheme scheme.

[0164] The system of the present invention is applicable to a variety of smart building complex operation and maintenance scenarios. The following takes three typical application scenarios as examples to illustrate the application effect of the system.

[0165] The system of the present invention is applied to the energy consumption management scenario of intelligent buildings to realize energy consumption monitoring and analysis, energy efficiency optimization control and abnormal energy consumption detection.

[0166] In terms of energy consumption monitoring and analysis, the system collects energy consumption data of various systems in the building complex through acquisition module 1, including consumption of electricity, water, gas, etc. The data collection frequency is 15 minutes / time, which meets the time granularity requirements of energy consumption analysis. The collected data is processed by multi-source heterogeneous data fusion and real-time processing mechanism to form a unified energy consumption data set. Based on the digital twin model, the system associates energy consumption data with information such as building structure and usage to establish a multi-dimensional energy consumption analysis model. Energy consumption analysis includes time dimension analysis (hours, days, weeks, months, years), space dimension analysis (floors, areas, equipment) and use dimension analysis (lighting, air conditioning, power, etc.), forming a comprehensive energy consumption portrait.

[0167] In terms of energy efficiency optimization and control, the system utilizes an edge-based intelligent analysis and decision-making framework to automatically adjust equipment operating parameters based on building usage and environmental conditions. Optimized control strategies include optimizing air conditioning temperature setpoints, dynamically adjusting lighting brightness, and optimizing equipment run time. The system utilizes a reinforcement learning algorithm to continuously optimize control strategies, minimizing energy consumption while ensuring comfort. Control commands are transmitted to the corresponding equipment via the communication module 8, enabling automatic control.

[0168] To detect abnormal energy consumption, the system uses a predictive maintenance algorithm based on virtual-to-real mapping to establish an energy consumption baseline model. This model compares actual energy consumption with expected energy consumption in real time, identifying abnormal energy consumption and its causes. This anomaly detection utilizes a hybrid approach based on statistics and machine learning, capable of identifying a variety of causes of abnormal energy consumption, including equipment failure, improper parameter settings, and unusual usage behavior.

[0169] Application Results: The system reduces building energy consumption by 15-30%, reduces peak load by 20%, and identifies energy-saving renovation opportunities within buildings, providing a basis for further optimization. For example, in a commercial building complex with a total floor area of ​​100,000 square meters, the system saves approximately 2 million kWh of electricity annually, reduces costs by over 1.2 million yuan, and reduces carbon emissions by 1,600 tons.

[0170] The system of the present invention is applied to equipment failure prediction and maintenance scenarios to achieve core equipment monitoring, failure prediction analysis and maintenance plan optimization.

[0171] Regarding core equipment monitoring, the system uses acquisition module 1 to comprehensively monitor critical equipment, collecting parameters such as temperature, pressure, flow, voltage, current, and vibration. The sampling frequency for key equipment is 5-10 times per second, while for general equipment it is 1-3 times per second. The collected data undergoes edge preprocessing and is transmitted to the cloud, forming a device operation database. Based on digital twin technology, the system constructs a virtual model of the equipment, displaying its operating status and health in real time.

[0172] In terms of fault prediction analysis, the system builds an equipment failure prediction model through adaptive model training and iterative optimization. Based on historical fault data and expert knowledge, the model learns the precursory characteristics and evolution patterns of equipment failures. Predictive analysis includes health status assessment, failure risk prediction, and remaining life estimation. The system can identify a variety of common fault types, such as bearing wear, motor overheating, and pump leakage, with a prediction accuracy exceeding 85%. The system typically provides one to seven days of advance warning, providing maintenance personnel with ample preparation time.

[0173] In terms of maintenance plan optimization, the system uses a multi-level collaborative decision-making and autonomous scheduling mechanism to optimize maintenance time and resource allocation based on equipment status and forecast results. This maintenance plan optimization considers factors such as equipment criticality, failure risk, maintenance cost, and resource availability to generate the optimal maintenance plan. The system supports multiple maintenance strategies, including condition-based maintenance, risk-based maintenance, and opportunity-based maintenance, allowing users to flexibly select the most appropriate maintenance strategy based on actual conditions.

[0174] Application Results: Through the application of this system, equipment failure rates have been reduced by 35%, maintenance costs by 30%, and equipment lifespans have been extended by 20-40%. For example, in a building complex containing 500 critical equipment units, the implementation of this system reduced the average annual number of failures from 150 to 98, the number of emergency repairs from 60 to 15, maintenance costs from 2 million yuan to 1.4 million yuan, and the average equipment lifespan from 10 years to 13 years.

[0175] The system of the present invention is applied to intelligent security and access control management scenarios to realize personnel access control, abnormal behavior detection and emergency response management.

[0176] Regarding access control, the system utilizes the intelligent access control layer 101 within the edge architecture to precisely manage access permissions. The system utilizes multimodal identity recognition technology, integrating multiple verification methods such as facial recognition, IC card recognition, and fingerprint recognition, achieving an accuracy rate of 99.7%. The visitor management system supports appointment registration, temporary access rights allocation, and access tracking, ensuring only authorized personnel can access designated areas. The system also provides differentiated access permissions based on time, area, and role, meeting the needs of varying security levels.

[0177] Regarding abnormal behavior detection, the system utilizes an edge intelligent analysis and decision-making framework to conduct real-time analysis of surveillance video and identify suspicious or unusual behavior. This abnormal behavior detection, based on deep learning algorithms, can identify unusual behavior patterns such as wandering, running, fighting, and climbing. The system employs a layered detection strategy, performing preliminary detection at edge nodes before uploading suspicious behavior to the cloud for precise analysis, balancing real-time performance with accuracy. Detection results are then used through a multi-level collaborative decision-making and autonomous scheduling mechanism to trigger appropriate security responses.

[0178] In terms of emergency response management, the system leverages a predictive maintenance algorithm based on virtual-reality mapping, along with a multi-level collaborative decision-making and autonomous scheduling mechanism, to achieve a coordinated response to emergencies. The system pre-configured multiple emergency plans, including those for fire, break-ins, and equipment failures. When a security threat is detected, the system automatically activates the corresponding plan, coordinating security equipment, notifying relevant personnel, and providing evacuation route guidance. Using digital twin technology, the system simulates the development of events and response effects in a virtual environment, providing support for decision-making.

[0179] Application Results: Through the application of this system, security incidents have been reduced by 50%, response time has been shortened by 60%, and management efficiency has been improved by 40%. Taking a building complex with an average daily traffic of 10,000 people as an example, after implementing this system, the average annual security incidents dropped from 80 to 40, the response time for security incidents was shortened from an average of 15 minutes to 6 minutes, and the number of access control personnel was reduced from 10 to 6, saving over 500,000 yuan in annual security costs.

[0180] In practical applications, the system of this invention significantly improves the intelligence level and efficiency of building complex operation and maintenance through the integration of digital twins, cloud-edge collaboration, and artificial intelligence technologies. The main value of the system is reflected in the following aspects:

[0181] First, the system has achieved a transformation from passive response to active prediction. Through predictive maintenance algorithms, it predicts potential equipment failures in advance, transforming traditional passive response into active prevention, significantly reducing sudden failures and emergency repairs, and improving equipment reliability and service life.

[0182] Secondly, the system optimizes resource allocation and utilization efficiency. Through multi-level collaborative decision-making and autonomous scheduling mechanisms, it achieves optimal allocation of human and material resources and improves resource utilization. Through intelligent control and management, it optimizes energy use strategies and reduces building energy consumption and operating costs.

[0183] Thirdly, the system improves the scientific nature and timeliness of management decisions. Through digital twin technology, it builds a digital model of the building complex, realizes real-time mapping and interaction between the physical world and the virtual world, and provides visual support for management decisions; through data-driven analysis, it explores the value of operation and maintenance data and provides a basis for scientific decision-making.

[0184] Finally, the system promotes the digital transformation and shared prosperity of the building operations industry. By reducing costs through intelligent operations and maintenance systems, high-quality building services can benefit a wider range of people, while also creating high-quality jobs and enhancing the overall value of the industry chain. The widespread application of the system will drive the digital and intelligent transformation of the building operations industry, elevating the industry's overall performance and achieving the unity of technological advancement, economic benefits, and social value.

[0185] The digital twin hybrid cloud-edge collaborative intelligent real estate building complex operation and maintenance system provided by this invention integrates digital twin, cloud-edge collaboration, artificial intelligence, and Internet of Things technologies to build a comprehensive, intelligent, and efficient building complex operation and maintenance management platform. The core of the system is the digital twin operation and maintenance brain, which integrates five innovative technologies: a multi-source heterogeneous data fusion and real-time processing mechanism, an edge intelligent analysis and decision-making framework, an adaptive model training and iterative optimization system, a predictive maintenance algorithm for virtual-reality mapping, and a multi-level collaborative decision-making and autonomous scheduling mechanism. This system achieves full digital management, predictive maintenance, intelligent decision-making, and optimized resource allocation for building complexes. The system has demonstrated significant application in multiple scenarios, including intelligent building energy consumption management, equipment failure prediction and maintenance, and intelligent security and access control management. It has significantly improved operation and maintenance efficiency, reduced operating costs, and extended equipment lifespan, while providing scientific decision-making support for building managers. This system is not only technologically advanced but also practical and scalable, representing the future development direction of the intelligent building operation and maintenance field.

Claims

1. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system is characterized by: include: The collection module is used to collect basic building information, equipment operation data and environmental parameters of smart real estate buildings; A storage module is in communication with the acquisition module, and is used to transmit the collected data to the cloud to establish a digital twin scene database, and synchronize the data in the digital twin scene database to the edge device; A construction module, communicatively connected to the storage module, configured to establish a digital twin building complex model based on the data in the digital twin scene database, and to establish a digital twin scene through the digital twin building complex model; A scene module, which is in communication with the building module and is used to build a digital smart building scene that combines virtuality and reality using BIM, GIS, the Internet of Things, 5G technology, and AI technology; A virtual-reality synchronization module, in communication with the scene module, is used to present the physical world dynamics in the digital smart building scene using AR / VR devices, thereby achieving real-time synchronization between the virtual scene and the physical environment; An operation and maintenance module, which is in communication with the virtual-reality synchronization module and is used to build a digital twin operation and maintenance brain. The digital twin operation and maintenance brain includes a multi-source heterogeneous data fusion and real-time processing mechanism, an edge intelligent analysis and decision-making framework, an adaptive model training and iterative optimization system, a predictive maintenance algorithm for virtual-reality mapping, and a multi-level collaborative decision-making and autonomous scheduling mechanism. The monitoring module is communicated with the operation and maintenance module and is used to monitor the status and operation of edge devices, form monitoring reports, and simulate the actual operation and maintenance scenarios of the building complex based on the data through the digital twin building complex model to provide data services for the intelligent operation and maintenance of the building complex.

2. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized by: The multi-source heterogeneous data fusion and real-time processing mechanism includes: Multi-source data collection architecture for collecting physical layer sensor data, edge layer processing data, and cloud-aggregated data; A data adapter, communicating with the multi-source data acquisition architecture, is used to unify and standardize the formats of BIM, GIS, and IoT device data; a spatiotemporal index data structure, in communication with the data adapter, for unifying data from different sources and at different sampling rates into a spatiotemporal dimension; a data quality assessment algorithm, in communication with the spatiotemporal index data structure, for performing real-time cleaning and anomaly detection on the sensor data; The data caching and distribution mechanism is in communication with the data quality assessment algorithm and is used to perform hierarchical processing based on the importance and timeliness of the data.

3. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized by: The edge intelligent analysis and decision-making framework includes: A lightweight edge AI inference engine to support real-time analysis of device status and fault prediction; An autonomous decision-making mechanism for edge nodes, communicating with the lightweight edge AI inference engine, for making local decisions based on preset rules and historical data; A dynamic scheduling algorithm for edge computing resources, in communication with the autonomous decision-making mechanism of the edge nodes, for adaptively allocating resources based on task priority and computing load; An edge security isolation mechanism, communicating with the edge computing resource dynamic scheduling algorithm, is used to ensure that sensitive data is processed locally and reduce data transmission risks; An edge cache optimization strategy is communicated with the edge security isolation mechanism and is used to intelligently cache data based on access frequency and data importance.

4. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized in that: The adaptive model training and iterative optimization system includes: An incremental learning framework that allows models to be updated locally on edge nodes without requiring full retraining. Model compression technology, in communication with the incremental learning framework, is used to compress complex models trained in the cloud into executable versions for edge devices; A federated learning mechanism, in communication with the model compression technology, is used to enable multiple edge nodes to train collaboratively without sharing raw data; A model performance monitoring system, communicating with the federated learning mechanism, for real-time evaluation of model prediction accuracy and triggering updates; A model version management mechanism communicates with the model performance monitoring system to support model rollback and A / B testing.

5. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized in that: The predictive maintenance algorithm of virtual-reality mapping includes: A digital twin building equipment health assessment model, which integrates physical models and data-driven models to assess equipment health status; An equipment remaining life prediction algorithm, in communication with the digital twin building equipment health assessment model, for predicting the remaining life based on historical equipment operating data and maintenance records; a multi-dimensional failure pattern recognition system, in communication with the equipment remaining life prediction algorithm, for identifying complex failure patterns and potential risks; a dynamic maintenance strategy generator, in communication with the multi-dimensional fault pattern recognition system, for intelligently planning maintenance time and resources based on prediction results; A virtual scenario fault simulation system is communicated with the dynamic maintenance strategy generator and is used to verify the maintenance plan in a digital twin environment.

6. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized in that: The multi-level collaborative decision-making and autonomous scheduling mechanism includes: A hierarchical decision-making framework is used to clarify the decision-making authority and coordination mechanism of the cloud layer, edge layer, and end layer; a conflict resolution algorithm, in communication with the hierarchical decision framework, for automatically coordinating when conflicts exist among decisions at different levels; A task splitting and distribution system, in communication with the conflict resolution algorithm, is used to decompose complex operation and maintenance tasks into subtasks that can be executed at different levels; Resource pooling management, communicating with the task splitting and distribution system, is used to dynamically allocate computing, storage, and network resources according to task requirements; An autonomous scheduling optimizer is in communication with the resource pooling management and is used to optimize the scheduling strategy based on task priority, resource availability and energy consumption targets.

7. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized by: The system further comprises: A communication module is connected to the operation and maintenance module and the monitoring module, and is used to connect with various system devices in the smart building, and transmit the acquired smart building equipment operation and maintenance data and building complex equipment operation data to the cloud-edge collaborative architecture to achieve data synchronization; The communication module realizes the collection and transmission of building complex operation and maintenance data by establishing an API connection.

8. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized by: The basic building information, equipment operation data and environmental parameters of the smart real estate building complex include: Basic building information, including the building's floor plan, elevation, structural diagram, and equipment distribution diagram; Building operation and maintenance information, including equipment operating parameters, energy consumption data, and maintenance records; Building equipment information, including equipment model, parameter specifications and operating status; Public area information, including personnel flow, environmental parameters, and security status; Building complex information, including the overall layout of the building complex, their relationships and shared facility data.

9. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized in that: The cloud layer architecture of the system includes: Cloud basic service layer, used to provide basic computing, storage and network resources; The platform service layer is connected to the cloud-based service layer to provide data processing, model training and knowledge base management; The application service layer is connected to the platform service layer for providing operation and maintenance decision support, resource scheduling and user interaction interface.

10. The digital twin hybrid cloud-edge collaborative smart real estate building complex operation and maintenance intelligent system according to claim 1 is characterized in that: The edge layer architecture of the system includes: Intelligent access control layer, used to implement personnel access control and identity authentication; An intelligent machine control layer, communicating with the intelligent access control layer, for managing intelligent devices and robots; A robot brain bank layer, communicating with the intelligent machine control layer, for processing visual information and controlling robot behavior; A data processing and service layer, communicating with the robot brain bank layer, for performing data preprocessing and edge analysis; Among them, the intelligent access control layer, the intelligent machine control layer, the robot brain bank layer and the data processing and service layer are all communicatively connected with the cloud layer and the building module.

Images