Comprehensive management method and system for smart park, and storage medium

Abstract

The invention relates to the technical field of data processing, and discloses a comprehensive management method and system for a smart park, and a storage medium. The method comprises the steps that environment, energy consumption and people flow data are collected through the Internet of Things, and a basic data set is obtained through edge node processing and semantic alignment; constructing a digital twin system by using a spatio-temporal data cube and a graphical mode; constructing a land digital identity system by adopting space-time coding and block chain technologies; performing anomaly identification and risk analysis on the activity data to obtain supervision early warning data; performing multi-dimensional analysis on the enterprise operation data to form an enterprise portrait; and presenting resource distribution through mixed reality, and analyzing cross-department data to obtain operation efficiency data. According to the invention, holographic perception, intelligent supervision and cooperative service of park elements are realized.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a comprehensive management method, system, and storage medium for smart parks. Background Art

[0002] A smart park is a modern industrial park that takes a geographic information digital platform as a carrier and uses emerging technologies such as digital twin, cloud computing, big data, Beidou positioning, blockchain, Internet of Things, and mixed reality to build an industrial ecosystem with systematicization, infrastructure networking, precise function services, and intelligent operation and development. In the prior art, the management of smart parks mainly collects park data by deploying various sensing devices, realizes the visual management of the park in combination with the geographic information system, and realizes the informatization management of elements such as enterprises, land, and personnel in the park through business systems. At the same time, the Internet of Things technology is used to monitor the equipment and facilities in the park in real time, realizing dynamic supervision in aspects such as park safety, environmental protection, and energy consumption.

[0003] However, the prior art has the following deficiencies: Since the business systems of each department in the park are relatively independent, the data standards are not unified, and various types of data are scattered in different information silos, it is difficult to achieve data interconnection and in-depth application. At the same time, there is a lack of intelligent analysis means for the massive multi-source heterogeneous data in the park, and it is impossible to effectively mine the data value, making it difficult to support the refined management and scientific decision-making of the park. In addition, the existing park management methods often focus on the informatization transformation of individual links, lacking overall planning and overall design, and it is difficult to meet the systematic and complex requirements of park management. Summary of the Invention

[0004] This application provides a comprehensive management method, system, and storage medium for smart parks, which are used to achieve holographic perception, intelligent supervision, and collaborative services of park elements.

[0005] In a first aspect, this application provides a comprehensive management method for a smart park. The comprehensive management method for the smart park includes: collecting environmental data, energy consumption data, and pedestrian flow data through an Internet of Things sensing network, performing noise reduction and compression processing on the environmental data, energy consumption data, and pedestrian flow data through an edge node, and performing semantic alignment on multi-source data through a knowledge association method to obtain a park basic data set;

[0006] According to the park basic data set, a three-dimensional model is constructed using a spatio-temporal data cube, and the element relationships are stored and organized in a graphical manner to obtain a park digital twin system;

[0007] According to the park digital twin system, a digital identity identification is generated for the land using a spatio-temporal coding method, and the land data is stored and shared authorized through blockchain to obtain a park land digital identity system and a park land coding system;

[0008] Based on the digital identity system and land coding system of the park, identify abnormal patterns in the activity data, analyze the risk propagation path, and obtain the intelligent supervision and early warning data of the park;

[0009] According to the intelligent supervision and early warning data of the park, conduct multi-dimensional analysis on the enterprise operation data and evaluate the operation effect to obtain the enterprise portrait data of the park;

[0010] According to the enterprise portrait data of the park, use mixed reality to visually present the resources and conduct comprehensive analysis on the cross-departmental data to obtain the operation efficiency data of the park.

[0011] In a second aspect, the present application provides a comprehensive management system for a smart park. The comprehensive management system for a smart park includes:

[0012] A collection module, configured to collect environmental data, energy consumption data, and pedestrian flow data through the Internet of Things perception network, perform noise reduction and compression processing on the environmental data, energy consumption data, and pedestrian flow data through edge nodes, and perform semantic alignment on multi-source data through a knowledge association method to obtain a basic data set of the park;

[0013] A construction module, configured to construct a three-dimensional model based on the basic data set of the park by using a spatio-temporal data cube, and store and organize the element relationships in a graphical manner to obtain a digital twin system of the park;

[0014] A generation module, configured to generate digital identity identification for the land according to the digital twin system of the park by using a spatio-temporal coding method, and perform evidence storage and sharing authorization on the land data through a blockchain to obtain a digital identity system and a land coding system of the park;

[0015] An identification module, configured to identify abnormal patterns in the activity data according to the digital identity system and land coding system of the park, and analyze the risk propagation path to obtain the intelligent supervision and early warning data of the park;

[0016] An analysis module, configured to conduct multi-dimensional analysis on the enterprise operation data according to the intelligent supervision and early warning data of the park, and evaluate the operation effect to obtain the enterprise portrait data of the park;

[0017] A visualization module, configured to visually present the resources in a mixed reality manner according to the enterprise portrait data of the park, and conduct comprehensive analysis on the cross-departmental data to obtain the operation efficiency data of the park.

[0018] The third aspect of the present application provides a computer-readable storage medium storing instructions, which, when running on a computer, cause the computer to execute the above-mentioned integrated management method for a smart park.

[0019] In the technical solution provided by the present application, a multi-dimensional data collection network for the park is established by deploying data collection devices such as Internet of Things sensors, Beidou positioning terminals, and high-definition cameras, realizing the comprehensive perception and real-time collection of park data. At the same time, edge computing nodes are set at the perception layer to perform noise reduction, duplicate removal, and compression processing on the original data, significantly improving the data transmission efficiency and storage utilization rate. By designing a data association analysis method based on a knowledge graph, the intelligent fusion of multi-source heterogeneous data is realized, providing a high-quality data foundation for subsequent analysis. And a multi-dimensional data organization method based on a spatio-temporal data cube is adopted to organize various types of park data according to three dimensions: time, space, and attributes, supporting flexible multi-dimensional analysis and visualization. At the same time, a relational model based on a graph database is designed to realize the efficient storage and fast query of complex relationships between various elements in the park, providing support for subsequent intelligent analysis. Based on this data organization method, park managers can quickly obtain and analyze the spatio-temporal distribution characteristics and change rules of various elements in the park. And through 3D modeling technology combined with high-precision laser point cloud data, a refined 3D model of infrastructure such as park buildings, roads, and pipe networks is constructed, and a dynamic update mechanism is established based on real-time collected sensing data to realize the real-time mapping between the physical space and the digital space. The designed digital twin engine integrates physical models, data models, and business models to realize the dynamic interaction and intelligent linkage of various elements in the park. This method realizes the interconnection and in-depth application of park data by constructing a unified data collection, storage, processing, and analysis framework, providing strong support for the refined management and scientific decision-making of the park. At the same time, by establishing a data analysis and supervision system, the intelligent level of park management is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a schematic diagram of an embodiment of the integrated management method for a smart park in an embodiment of the present application;

[0022] Figure 2 It is a schematic diagram of the element relationship diagram in an embodiment of the present application;

[0023] Figure 3Schematic diagram of enterprise classification in the embodiments of the present application;

[0024] Figure 4 Schematic diagram of an embodiment of the integrated management system for a smart park in the embodiments of the present application. Detailed implementation manners

[0025] The embodiments of the present application provide an integrated management method, system and storage medium for a smart park. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments described here can be implemented in an order different from that shown or described here. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] For ease of understanding, the specific processes of the embodiments of the present application are described below. Please refer to Figure 1 , an embodiment of the integrated management method for a smart park in the embodiments of the present application includes:

[0027] Step S101: Collect environmental data, energy consumption data and personnel flow data through the Internet of Things perception network, perform noise reduction and compression processing on the environmental data, energy consumption data and personnel flow data through edge nodes, and perform semantic alignment on multi-source data through a knowledge association method to obtain a basic dataset of the park;

[0028] Step S102: According to the basic dataset of the park, construct a three-dimensional model using a spatio-temporal data cube, and store and organize the element relationships in a graphical manner to obtain a digital twin system of the park;

[0029] Step S103: According to the digital twin system of the park, generate a digital identity identifier for the land using a spatio-temporal coding method, and perform evidence storage and sharing authorization on the land data through a blockchain to obtain a digital identity system of the park land and a coding system of the park land;

[0030] Step S104: According to the digital identity system of the park land and the coding system of the park land, identify abnormal patterns in the activity data and analyze the risk propagation path to obtain intelligent supervision and early warning data of the park;

[0031] Step S105: Based on the intelligent supervision and early warning data of the park, conduct multi-dimensional analysis on the business data of enterprises, and evaluate the business effects to obtain the portrait data of park enterprises.

[0032] Step S106: Based on the portrait data of park enterprises, use mixed reality to visually present resources and comprehensively analyze cross-departmental data to obtain the operation efficiency data of the park.

[0033] It can be understood that the execution subject of this application can be an integrated management system for smart parks, or a terminal or a server. Specifically, it is not limited here. This application embodiment is described by taking the server as the execution subject as an example.

[0034] Specifically, the operation data of the entire park is collected through the deployed Internet of Things perception network, including environmental data, energy consumption data, and pedestrian flow data. Environmental data is mainly collected through temperature and humidity sensors and air quality monitoring equipment; energy consumption data mainly collects the resource consumption of various infrastructure and enterprises through electricity meters, water meters, and gas meters; pedestrian flow data collects the personnel distribution and flow in the park through video surveillance equipment and infrared sensors. Each collection point is equipped with an edge node to perform noise reduction and compression processing on the collected raw data. Noise reduction processing mainly aims at the random fluctuations generated during the sensor collection process, and removes the mutation points through median filtering; compression processing uses differential coding to only record the change amount of adjacent time data. The knowledge association method standardizes the fields of data from different sources by establishing a unified data dictionary, such as unifying the data units of different energy consumption monitoring devices. Based on the basic data set of the park, a digital twin system of the park is constructed. The spatio-temporal data cube is a three-dimensional data organization method that organizes data in three dimensions: time, space, and attributes. In the spatial dimension, the park is divided into grid cells; in the time dimension, data is aggregated according to different granularities such as hours, days, and weeks; the attribute dimension includes various indicators such as environment, energy consumption, and pedestrian flow. The graphical method represents the relationship between various elements in the park through nodes and edges. Nodes represent entities such as buildings, equipment, and enterprises, and edges represent their physical connections or business associations.

[0035] The spatio-temporal coding method generates a unique digital identity for each piece of land. The coding rules comprehensively consider the geographical location, use attributes, and planning conditions of the land to generate a formatted coding string. Blockchain technology is used for the deposit and authorization management of land data. Each data change is recorded in a block, forming an immutable chain structure. At the same time, the access rights of data are controlled through smart contracts. Through the digital identity system and coding system of park land, the activity data in the park is analyzed. Abnormal activity patterns are identified, and real-time monitoring data is compared with historical data to find behaviors that deviate from the normal range. Then, the risk propagation path is analyzed, a risk propagation network model is established, and the diffusion process of risk in the spatial and business dimensions is calculated.

[0036] Conduct multi-dimensional analysis on enterprise operation data, combine indicators such as output value, tax revenue, and energy consumption to construct an enterprise portrait. Through calculating the weighted scores of various indicators, conduct a comprehensive evaluation of the enterprise. The evaluation dimensions include multiple aspects such as economic benefits, resource utilization efficiency, and environmental impact. Use mixed reality technology to visually display the analysis results. Overlay and display various types of indicator data in a three-dimensional scene, supporting multi-angle viewing and interactive operations. At the same time, integrate the business data of each department, establish a cross-departmental data sharing mechanism, and realize the quantitative assessment of the overall operation status of the park.

[0037] For example: The production workshop of an enterprise in a certain park collects power consumption data every 5 minutes through energy consumption monitoring equipment. After the edge node processes the data, it is found that the power consumption suddenly increases by 50%. The system automatically analyzes this abnormal situation and finds that similar situations also occur in surrounding enterprises. Combining weather data, it is judged that it is due to the increased air-conditioning load caused by high-temperature weather. Through enterprise portrait analysis, it is found that the energy consumption intensity of enterprises in this area is generally high, and it is recommended to optimize the air-conditioning system configuration. Intuitively display the energy consumption distribution on the mixed reality interface and push energy-saving transformation suggestions to relevant departments. The whole process reflects a complete closed-loop from data collection, analysis to decision-making support, giving full play to the advantages of park digital management.

[0038] In the embodiments of the present application, a multi-dimensional data acquisition network for the park is established by deploying data acquisition devices such as Internet of Things sensors, Beidou positioning terminals, and high-definition cameras, realizing the comprehensive perception and real-time acquisition of park data. At the same time, edge computing nodes are set in the perception layer to perform noise reduction, duplicate removal, and compression processing on the original data, significantly improving the data transmission efficiency and storage utilization rate. By designing a data association analysis method based on a knowledge graph, the intelligent fusion of multi-source heterogeneous data is realized, providing a high-quality data foundation for subsequent analysis. And a multi-dimensional data organization method based on a spatio-temporal data cube is adopted to organize various types of park data according to three dimensions: time, space, and attributes, supporting flexible multi-dimensional analysis and visualization. At the same time, a relationship model based on a graph database is designed to realize the efficient storage and rapid query of complex relationships between various elements in the park, providing support for subsequent intelligent analysis. Based on this data organization method, park managers can quickly obtain and analyze the spatio-temporal distribution characteristics and change rules of various elements in the park. And through 3D modeling technology combined with high-precision laser point cloud data, a refined 3D model of infrastructure such as park buildings, roads, and pipe networks is constructed. A dynamic update mechanism is established based on real-time collected sensing data to realize the real-time mapping between the physical space and the digital space. The designed digital twin engine integrates physical models, data models, and business models to realize the dynamic interaction and intelligent linkage of various elements in the park. This method realizes the interconnection and in-depth application of park data by constructing a unified data acquisition, storage, processing, and analysis framework, providing strong support for the refined management and scientific decision-making of the park. At the same time, by establishing a data analysis and supervision system, the intelligent level of park management is improved.

[0039] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0040] (1) Deploy the first group of sensors at key nodes in the park to collect ambient temperature and humidity data, deploy the second group of sensors to collect power consumption data and water consumption data, deploy the third group of sensors to collect personnel density data, and mark timestamps for the collected data to obtain the original perception data;

[0041] (2) Perform data preprocessing on the original perception data through edge nodes, group the original perception data according to time series, perform median filtering noise reduction processing on each group of data, and then perform data compression to obtain preprocessed data;

[0042] (3) Establish a data association rule library for the preprocessed data, map and correspond the attribute fields of environmental data, energy consumption data, and human flow data, and perform field standardization processing through the rule library to obtain standardized data;

[0043] (4) Build a semantic knowledge base based on standardized data, associate and map the business meanings of environmental data, energy consumption data, and pedestrian flow data, and unify the semantics of the data through semantic alignment methods to obtain the basic dataset of the park.

[0044] Specifically, the first group of sensors is responsible for collecting environmental temperature and humidity data, including temperature sensors and humidity sensors, which collect temperature values in degrees Celsius and relative humidity values in percentage units respectively, and the sampling frequency is set to once every 5 minutes. The second group of sensors is responsible for collecting energy consumption data, including smart electricity meters and smart water meters. The electricity meters record the electricity consumption in kilowatt-hours, and the water meters record the water consumption in cubic meters. The sampling frequency is once every 15 minutes. The third group of sensors is responsible for collecting pedestrian flow data, and records the number density per unit area through infrared sensors and cameras. The sampling frequency is once every 1 minute. Each piece of collected data will be appended with a timestamp in the format of "YYYY-MM-DD HH:mm:ss" to form the original perception data with time series characteristics. After receiving the original perception data, the edge node groups it according to the time series. For temperature and humidity data, one group is formed every hour, containing 12 sampling points; for energy consumption data, one group is formed every hour, containing 4 sampling points; for pedestrian flow data, one group is formed every hour, containing 60 sampling points. Median filtering and noise reduction processing use the sliding window method, and the window size is set according to the data type: a 5-point window is used for temperature and humidity data, a 3-point window is used for energy consumption data, and a 7-point window is used for pedestrian flow data. Sort the data points within each window according to the numerical size, and select the value at the middle position as the output of the window to filter out abnormal fluctuations. Data compression uses differential coding, which records the change amount of adjacent time data instead of the absolute value. When the change amount is less than the preset threshold, it is not recorded, thereby reducing the data storage volume.

[0045] For the preprocessed data, establish a data association rule base for field standardization processing. The temperature value of environmental data is uniformly converted to degrees Celsius, and the humidity value is uniformly converted to a percentage; the electricity consumption of energy consumption data is uniformly converted to kilowatt-hours, and the water consumption is uniformly converted to cubic meters; the pedestrian flow data is uniformly converted to the number density per square meter. The data association rule base defines the mapping relationships between different data sources, including unit conversion rules, numerical range constraints, data validity verification, etc. Field standardization processing ensures that all data conforms to the predefined format specifications. During the construction of the semantic knowledge base, define the business ontology model to describe the semantic relationships of various types of data in the park. The semantic attributes of environmental data include monitoring location, environmental index type, monitoring period, etc.; the semantic attributes of energy consumption data include energy type, measurement unit, user entity, etc.; the semantic attributes of pedestrian flow data include statistical area, population type, statistical period, etc. The semantic alignment method forms a semantically consistent basic dataset of the park by establishing concept mappings and unifying data from different sources into a standardized semantic framework.

[0046] For example, a temperature sensor installed in a manufacturing workshop in a certain park records a set of original data, including 12 consecutive 5-minute sampling points: {25.3, 25.4, 28.9, 25.5, 25.4, 25.3, 25.6, 25.4, 25.5, 29.1, 25.3, 25.4}. After receiving the data, the edge node uses a 5-point sliding window for median filtering. The median of the first window {25.3, 25.4, 28.9, 25.5, 25.4} is 25.4, and the smoothed data sequence is obtained by processing in turn. At the same time, differential coding is performed to record the temperature change. When the change is less than 0.5 degrees, it is not recorded. The data association rule library associates the temperature data with other environmental parameters, such as the humidity value at the same time period. The semantic knowledge library labels the temperature data as "the environmental temperature in Area A of the manufacturing workshop", associates it with the air conditioning control system and energy consumption management system of the workshop, and establishes a semantic association with the personnel distribution data in the workshop.

[0047] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0048] (1) Stratify the park basic data set according to the time dimension, space dimension, and attribute dimension, set time stamps and space coordinates for each layer of data, and form a spatio-temporal data cube;

[0049] (2) Model the terrain and landforms of the park according to the space coordinate information in the spatio-temporal data cube, and associate the geometric information and topological relationships of buildings, roads, and pipe networks to obtain the park space framework;

[0050] (3) Map the park space framework to the real-time data in the park basic data set, establish a data update index table, mark the dynamically changing data for real-time update, and generate dynamically associated data;

[0051] (4) Convert the element relationships in the dynamically associated data into the form of nodes and edges through a graphical interface, assign values to the node attributes and edge weights, and construct an element relationship graph;

[0052] (5) Hierarchically organize the element relationship graph, divide the nodes with similar attributes into subgraphs, establish the connection relationships between the subgraphs, and form a multi-level element structure;

[0053] (6) Integrate the multi-level element structure with the dynamically associated data, establish a data synchronization update mechanism and a status monitoring rule, and obtain the park digital twin system.

[0054] Specifically, the collected basic park datasets are stratified according to time, space, and attributes, and timestamps and spatial coordinates are set for each layer of data to form a spatio-temporal data cube. The spatio-temporal data cube is a three-dimensional data organizational structure, where the X-axis represents spatial longitude, the Y-axis represents spatial latitude, and the Z-axis represents the time series. The basic park datasets include the basic information and dynamic status data of entities such as enterprises, buildings, roads, personnel, and vehicles within the park. After stratification, the data organizes data in different time dimensions through timestamps, locates data at different spatial positions through spatial coordinates, and differentiates different types of data through attribute tags. The terrain and landform of the park are modeled based on the spatial coordinate information in the spatio-temporal data cube. The ground surface elevation point cloud data of the park is obtained through laser scanning, and an irregular triangular network is generated using the triangular meshing method to construct the digital terrain model of the park. Then, information such as the geometric contours and heights of buildings, parameters such as the centerlines and widths of roads, and features such as the burial depths and orientations of underground pipe networks are extracted to establish three-dimensional geometric models of entities such as buildings, roads, and pipe networks. At the same time, the spatial relationships between various entities are analyzed, such as the adjacency relationships between buildings, the connectivity of roads, and the connection relationships of pipe networks, to form topological relationship data. The geometric information and topological relationships are associated and integrated to obtain the park spatial framework. The park spatial framework is mapped and associated with real-time data. A data update index table is established to record information such as the identifiers, attributes, and statuses of each entity, and a data timeliness marker is set. When new real-time data is collected, the corresponding record is located in the index table based on the entity identifier, the data content is updated, and the timeliness marker is modified to achieve real-time update of dynamic data. For example, enterprise production data, personnel location data, environmental monitoring data, etc. all need to be updated in real time.

[0055] The dynamically associated data is converted into a graph structure through a graphical interface. Various entities within the park are used as nodes of the graph, and the relationships between the entities are used as edges to construct a feature relationship graph. As Figure 2 shown, it is a schematic diagram of the feature relationship graph in the embodiment of the present application, where the industrial association relationships between three enterprise nodes within the park are shown. Among them, the enterprise nodes are represented by circles and contain basic information such as enterprise names, registered capital, and number of employees. The industrial association relationships between enterprises are represented by lines of different thicknesses, and the values on the lines represent the association strength. A straight line is used to connect enterprise A and enterprise B, and enterprise B and enterprise C, indicating a direct industrial association; a curve is used to connect enterprise A and enterprise C, indicating an indirect industrial association. The thickness of the line thickens as the association strength increases, intuitively reflecting the tightness of the industrial association between enterprises. The node attributes include the basic characteristics and dynamic status of the entity, and the weight of the edge represents the strength of the relationship between entities. For example, the attributes of the enterprise node include registered capital, number of employees, production status, etc. The industrial association relationships between enterprises are used as edges to connect different enterprise nodes, and the weight of the edge is calculated according to the degree of industrial association.

[0056] Hierarchically organize the element relationship diagram. Using the graph clustering algorithm, nodes with similar attributes or close relationships are divided into subgraphs. For example, enterprises in the same industrial chain are clustered into an industrial cluster subgraph, and buildings in adjacent areas are clustered into a building complex subgraph. Analyze the association relationships between different subgraphs, establish connection edges between subgraphs, and form a multi-level element structure system. Hierarchical organization facilitates the implementation of park management and analysis at different granularities.

[0057] Integrate the multi-level element structure with dynamic association data to implement a digital twin system. Establish a data synchronization and update mechanism. When the basic data changes, the corresponding graph structure is automatically updated. Set status monitoring rules to detect abnormal status in real time and give early warnings. For example, if the energy consumption data of an enterprise increases abnormally, the system automatically analyzes its impact range, evaluates the risk level, and triggers the corresponding disposal process.

[0058] For example: Collect static information (registration information, business scope, etc.) and dynamic data (production status, energy consumption data, etc.) of enterprises in the area. Stratify the data according to time series, spatial distribution, and attribute types to construct a local spatio-temporal data cube. Based on the spatial coordinate information of the enterprises, extract the topographic features of the area where they are located, establish 3D models of entities such as enterprise factories and roads, and analyze the spatial association relationships between enterprises. Map the real-time collected production data, logistics data, etc. to the spatial framework and establish a data update mechanism. Construct an industrial association graph, with enterprises as nodes and industrial chain relationships as edges. The edge weights are determined according to the upstream and downstream association degrees. Conduct clustering analysis on the industrial association graph, divide closely related enterprise groups into industrial cluster subgraphs, and analyze the association relationships between different industrial clusters. Finally, integrate the hierarchical structure of the industrial clusters with dynamic data to achieve the collaborative supervision of industrial clusters. By analyzing the production data, logistics data, etc. of enterprises, identify weak links in the industrial chain and give early warnings of supply chain risks.

[0059] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0060] (1) Extract the land geographical location information, use attribute information, and planning condition information from the park digital twin system, organize the data according to time and space dimensions, and generate a land basic information table;

[0061] (2) Define the coding rules for each attribute in the land basic information table, map the geographical location information to grid coordinates, map the use attribute to function codes, and map the planning conditions to type codes to generate a land coding rule set;

[0062] (3) Uniquely encode each piece of land according to the land coding rule set, combine the spatio-temporal information and attribute information to generate a digital identity identifier, and establish a mapping relationship between the land basic information and the digital identity identifier to form land identity data;

[0063] (4) Organize the land identity data according to the block structure, generate a timestamp and a link pointer for each data block, construct a blockchain data structure, and verify the data validity through a consensus mechanism;

[0064] (5) Establish a data access permission table according to the blockchain data structure, set data viewing and modification permissions for different departments and users, and generate data sharing rules;

[0065] (6) Associate the data sharing rules with the blockchain data structure, establish a data interaction interface and a verification mechanism to obtain the park land digital identity system and the park land coding system.

[0066] Specifically, extract the geographical location information, use attribute information, and planning condition information of the land. The geographical location information includes spatial data such as longitude and latitude coordinates and altitude. The use attribute information includes basic attributes such as land use type and right of use. The planning condition information includes planning indicators such as floor area ratio, building density, and green space rate. Organize the data according to the time dimension, record the time series characteristics such as the generation time and update time of the land information; organize the data according to the space dimension, spatially divide the land blocks according to the geographical location, and generate a land basic information table containing complete attribute fields.

[0067] When defining the coding rules for the attributes in the land basic information table, the following mathematical model is adopted:

[0068] Coding rule corresponding to geographical location information and grid coordinates:

[0069] C loc =α·X + β·Y + γ·H

[0070] Among them, C loc represents the position coding value, X represents the longitude grid number, Y represents the latitude grid number, H represents the elevation value, and α, β, and γ are the corresponding weight coefficients respectively.

[0071] Coding rule corresponding to use attribute and function code:

[0072]

[0073] Among them, C use represents the use coding value, U i represents the identifier of the i-th use type, W i represents the corresponding weight coefficient, P iIndicates the priority coefficient, and n indicates the total number of use types.

[0074] Coding rules for the correspondence between planning conditions and type codes:

[0075] C plan = δ·FAR + ∈·BCR + ζ·GCR

[0076] Among them, C plan Indicates the planning coding value, FAR indicates the floor area ratio value, BCR indicates the building density value, GCR indicates the green space rate value, and δ, ∈, and ζ are the corresponding weight coefficients respectively.

[0077] Generate a unique coding for the land according to the coding rule set, and combine the spatio-temporal information and attribute information. The spatio-temporal information includes the spatial location coding and timestamp coding of the land parcel, and the attribute information includes the use coding and planning coding. Combine and calculate these coding values through the hash algorithm to generate a unique digital identity identifier. At the same time, establish a mapping relationship table between the land basic information and the digital identity identifier, record the corresponding relationship between the identifier and the actual attribute data, and form the land identity data. When organizing the land identity data according to the block structure, group and package the data into data blocks, and each data block contains multiple land identity records. Generate an incrementing serial number based on time as the timestamp for each data block, and calculate the characteristic value of the data block through the hash algorithm as the link pointer. Adjacent data blocks establish a link relationship through the pointer to form a blockchain-like data structure. Adopt a consensus mechanism based on proof of work to verify the validity of the newly generated data block to ensure the immutability of the data.

[0078] Establish a data access permission table according to the blockchain data structure, and set different data permissions for different user departments. The management department has data access and modification permissions, the business department has data query permissions within a specific range, and ordinary users can only access the public land basic information. The permission table records information such as user identity, permission level, and accessible data range to generate fine-grained data sharing rules. Associate the data sharing rules with the blockchain data structure and develop a data interaction interface. When a user requests access to data, verify the user's identity and permissions, and then return the corresponding data content according to the permission range. Data modification operations require multi-party consensus verification, and the modification records are added to the chain as new blocks to achieve full traceability of data operations. In this way, a digital identity system for the park land is constructed.

[0079] For example: Extract information such as the spatial coordinates, land use nature, and planning indicators of the plot from the digital twin system. Its spatial coordinate information includes longitude grid number 15, latitude grid number 28, and average altitude of 50 meters. Substitute these into the location coding formula to calculate the location code; the land use nature is industrial land, and the planning indicators include a floor area ratio of 2.0, building density of 60%, and green space rate of 15%. Substitute these into the use coding and planning coding formulas respectively to calculate the corresponding coding values. Combine these coding values into the digital identity identifier "INDP202312150001" and establish a mapping relationship with the land basic information. When the planning department needs to modify the floor area ratio of this plot, verify the department's authority, then update the planning code according to the new floor area ratio value, generate a new data block, and add it to the blockchain after verification through the consensus mechanism to achieve secure data update. Other departments can query the relevant information of this plot according to their respective authority scopes, such as the construction department queries the building density, and the environmental protection department queries the green space rate, etc. During the whole process, all data operations are recorded on the blockchain, forming a data update track.

[0080] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0081] (1) Extract land identification information according to the digital identity system of park land and the park land coding system, associate and match the land identification information with the park activity data, and generate an activity data association table;

[0082] (2) Conduct a time series analysis on the activity data association table, calculate the deviation between the activity indicators in each time window and the historical mean, establish an activity fluctuation interval, and form activity trend data;

[0083] (3) Mark the data exceeding the fluctuation interval in the activity trend data as abnormal points, conduct a spatio-temporal clustering analysis on the abnormal points, identify the spatial distribution characteristics of abnormal activities, and obtain an abnormal activity distribution map;

[0084] (4) Establish a risk node connection relationship according to the abnormal activity distribution map, calculate the risk transmission probability between nodes, construct a risk propagation network, and generate a risk propagation matrix;

[0085] (5) Trace the propagation path of the risk propagation matrix, identify key propagation nodes and main propagation paths, and form a risk propagation link diagram;

[0086] (6) Integrate the risk propagation link diagram with the abnormal activity distribution map, establish a risk warning rule, classify the risk level, and obtain the park intelligent supervision warning data.

[0087] Specifically, land identification information is extracted from the digital identity system of park land, including basic data such as land codes, spatial coordinates, and usage types. Park activity data mainly includes personnel activity data (such as pedestrian flow density, personnel trajectories), equipment activity data (such as energy consumption data, equipment operating status), environmental activity data (such as noise level, air quality), etc. Using the land identification information as an association key, different types of activity data are associated with the corresponding plots of land to generate an activity data association table containing fields such as timestamp, activity type, activity indicators, and plot identification. When performing time series analysis on the activity data, a fixed-size time window (such as 15 minutes) is selected to segment the data. Statistical features are calculated for the activity indicators within each time window, including mean, standard deviation, maximum value, minimum value, etc. By comparing with historical data for the same period, the deviation value between the current indicator and the historical mean is calculated. Based on the distribution characteristics of the deviation values, the upper and lower threshold values of the fluctuation range are set, and the indicator fluctuation range is divided into a normal range and an abnormal range. The change trend of the indicators within each time window is recorded to form trend data describing the characteristics of activity changes.

[0088] Mark abnormal points in the activity trend data. Specifically, the data points that exceed the normal fluctuation range are marked as abnormal samples. The density-based spatial clustering algorithm DBSCAN is used for clustering analysis of abnormal points. The clustering radius and the minimum number of samples are set as parameters, and the abnormal points with close spatial positions are grouped into the same cluster. By clustering analysis, the spatial distribution characteristics of abnormal activities are identified, including the dense areas, distribution ranges, propagation directions, etc. of the abnormal points, and a distribution map representing the spatial distribution law of abnormal activities is generated. When constructing a risk propagation network based on the abnormal activity distribution map, the following mathematical model is used:

[0089] Calculation formula for the risk transfer probability between risk nodes:

[0090]

[0091] Among them, R ij represents the risk transfer probability from node i to node j, D ij represents the number of abnormal events between the two nodes, M ij represents the historical maximum number of abnormal events, Q ij represents the spatial distance between the two nodes, N ij represents the maximum node distance in the network, K ij represents the degree of association between the two nodes, S ijDenote the maximum correlation strength, and let θ, λ, and μ be the weight coefficients respectively. Construct a risk propagation matrix based on the calculated risk transfer probability. Perform path tracing on the risk propagation matrix, and use the shortest path algorithm in graph theory (such as Dijkstra's algorithm) to analyze the risk propagation path. Represent the risk propagation network as a directed weighted graph, where the nodes represent risk sources and the weights of the edges represent the risk transfer probability. By calculating the shortest paths between different nodes, identify the key nodes (i.e., nodes with more in-degrees or out-degrees) and the main propagation paths (i.e., paths with higher risk transfer probabilities) of risk propagation. Represent the analysis results in the form of a directed graph to generate a risk propagation link graph.

[0092] Fuse the data of the risk propagation link graph and the abnormal activity distribution map, calculate the comprehensive risk index of each node, and establish a hierarchical early warning rule according to the magnitude of the risk index. The risk grading standard considers multiple factors such as the intensity, duration, and influence range of abnormal activities, divides the risk levels into different levels, and obtains the intelligent supervision early warning data of the park containing information such as risk source identification, propagation path, and early warning level.

[0093] For example: Extract the digital identity identifiers of all plots in the area, and associate the environmental monitoring data (including atmospheric pollutant concentrations, wastewater discharge amounts, etc.) with the plot identifiers. Segment the monitoring data with a 15-minute window, and calculate the change trends of various indicators. When it is detected that the VOCs concentration of Plot A exceeds the normal fluctuation range at a certain time point, mark it as an abnormal point. Through spatial clustering analysis, it is found that an abnormal activity intensive area is formed around Plot A. When constructing the risk propagation network, take Plot A as the risk source node, calculate the risk transfer probability with the surrounding plots, and construct a risk propagation matrix. Through path tracing, it is found that the risk mainly propagates to the southeast direction and is greatly affected by the air flow. According to factors such as the exceeding degree of the VOCs concentration, influence range, and propagation speed, determine that this event is of a relatively high risk level and issue an early warning.

[0094] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0095] (1) Associate and match the intelligent supervision early warning data of the park with the enterprise operation data, and extract the revenue data, tax data, and energy consumption data of each enterprise to form an enterprise basic index table;

[0096] (2) Establish an index calculation system according to the enterprise basic index table, calculate the ratio of the revenue data to the floor area to obtain the output value per mu, and calculate the ratio of the tax data to the revenue data to obtain the tax contribution rate, forming the enterprise core index data;

[0097] (3) Segment the core indicator data of the enterprise according to the time series, calculate the growth rate change trend of each time period, and compare and analyze it with the industry benchmark to generate an enterprise development trend chart;

[0098] (4) Assign weights to the indicator data in the enterprise development trend chart, perform weighted calculations on each indicator, and classify the enterprises according to the scores from high to low to obtain an enterprise evaluation grade table;

[0099] (5) Analyze the operation effects of enterprises at all levels in the enterprise evaluation grade table, calculate the input-output ratio, resource utilization rate, and environmental impact degree to form an enterprise efficiency evaluation table;

[0100] (6) Integrate the data of the enterprise efficiency evaluation table and the enterprise evaluation grade table, establish an enterprise comprehensive portrait index system, comprehensively depict the development status of the enterprise, and obtain the portrait data of the park enterprises.

[0101] Specifically, when correlating and matching the intelligent supervision and early warning data of the park with the enterprise operation data, relevant indicators are extracted from the enterprise's revenue statements, tax records, and energy consumption statistics. The revenue data includes sub-items such as the enterprise's main business income and other business income. The tax data includes various tax types such as enterprise income tax, value-added tax, and environmental protection tax. The energy consumption data includes sub-items such as electricity consumption, water resource use, and gas consumption. Based on the unified social credit code of the enterprise as the primary key, data from different sources are integrated to establish a basic indicator table containing complete indicators such as the enterprise's basic information, operation status, and resource consumption. When calculating the core indicators based on the enterprise basic indicator table, key indicators reflecting the enterprise's operation efficiency and resource utilization efficiency are selected for analysis. The output value per mu is calculated by dividing the enterprise's annual operating income by the actual occupied area, reflecting the output level per unit land area. The tax contribution rate is calculated by dividing the enterprise's annual total tax payment by the operating income, reflecting the degree of the enterprise's tax contribution. At the same time, combined with energy consumption intensity indicators (energy consumption per unit output value), environmental impact indicators (pollutant emissions per unit output value), etc., a core indicator data set that comprehensively reflects the enterprise's operation status is formed.

[0102] When conducting a time series analysis of the enterprise's core indicators, the data is segmented according to different time granularities such as monthly, quarterly, and annual. The month-on-month growth rate and year-on-year growth rate are calculated for the indicator values within each time period, and the changing trends of the growth rates are analyzed. At the same time, the average level data of the same industry is collected as the baseline, and the difference value between the enterprise's indicators and the industry benchmark is calculated to evaluate the enterprise's relative position in the industry. Through time series analysis, the periodic characteristics, trend characteristics, and abnormal fluctuations of the enterprise's development are identified, and a trend chart reflecting the enterprise's historical development track is generated. To comprehensively evaluate the enterprise, a multi-dimensional index weight system is introduced. According to the importance of different indicators to the enterprise's development, the weight coefficients of each indicator are set. The weight of indicators related to operating efficiency (such as output value per mu, profit margin, etc.) is relatively high, followed by indicators related to resource environment (such as energy consumption intensity, environmental impact degree, etc.), and the weight of other auxiliary indicators is relatively low. After normalizing and summing up the weighted indicators, the comprehensive score of the enterprise is obtained. According to the distribution characteristics of the scores, grading thresholds are set to divide the enterprises into different levels, forming an enterprise evaluation grade table, such as Figure 3 shown, which is a schematic diagram of the enterprise grading situation in the embodiment of this application. This diagram uses a hierarchical pyramid structure to display the grading situation of enterprises in the smart park, and classification is carried out based on the comprehensive evaluation results of multi-dimensional indicators such as output value per mu, tax contribution rate, and resource utilization rate of the enterprises. Among them, the top layer of the pyramid is Class A enterprises, representing high-quality enterprises that are outstanding in terms of operating efficiency, resource environment, and innovative development, with characteristics such as high efficiency, low consumption, and emphasis on innovation; the middle layer is Class B enterprises, with each indicator at the industry average level and good operating and resource utilization conditions; the bottom layer is Class C enterprises, which need to be further improved and enhanced in relevant indicators. When evaluating, the weight of operating efficiency indicators is 0.4, the weight of resource environment indicators is 0.3, the weight of innovative development indicators is 0.2, and the weight of other auxiliary indicators is 0.1. The comprehensive score of the enterprise is calculated through weighted calculation, and then its belonging level is determined.

[0103] During the enterprise efficiency evaluation process, the focus is on analyzing the resource input and output efficiency of the enterprise. The input-output ratio is calculated by the ratio of the total output value of the enterprise to the input costs of various resources. The resource utilization rate is calculated by the ratio of the actual resource consumption of the enterprise to the standard consumption quota. The environmental impact degree is calculated by the ratio of the pollutant emissions of the enterprise to the environmental carrying capacity. Combining these efficiency indicators forms an enterprise efficiency evaluation table, which comprehensively reflects the operating efficiency and sustainable development ability of the enterprise. The data of the enterprise efficiency evaluation table and the evaluation grade table are fused to construct a comprehensive portrait of the enterprise. The portrait index system includes multiple aspects such as the basic attribute dimension (enterprise scale, industry affiliation, etc.), operating ability dimension (growth rate, profitability, etc.), resource efficiency dimension (energy utilization, land utilization, etc.), environmental impact dimension (pollution emissions, treatment facilities, etc.), and innovative development dimension (R & D investment, number of patents, etc.), comprehensively depicting the development status of the enterprise.

[0104] For example: collect the company's revenue data, tax records and energy consumption data, and establish a basic indicator table. Through calculation, it is found that the company's per-mu output value and tax contribution rate are higher than the industry average. A time series analysis of the core indicator data in the past three years found that the company's operating indicators showed a steady upward trend, and the growth rate was higher than the industry benchmark. In the comprehensive evaluation, the weight of the operating efficiency indicator is 0.4, the weight of the resource and environmental indicator is 0.3, the weight of the innovation and development indicator is 0.2, and the weight of other indicators is 0.1. After weighted calculation, the company received a higher score. The performance evaluation shows that the company has a high resource utilization efficiency and the environmental governance facilities operate stably. In the corporate portrait, the company is portrayed as a typical high-quality enterprise with "high efficiency, low consumption, and emphasis on innovation."

[0105] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0106] (1) Spatially map the enterprise portrait data in the park according to the geographic location information, establish a resource distribution coordinate system, construct a three-dimensional scene for resource spatial distribution, and generate resource distribution scene data;

[0107] (2) Rendering the resource distribution scene data through the mixed reality scene engine, overlaying the enterprise operation indicator data in the form of floating labels to form an interactive resource display interface;

[0108] (3) Collect cross-departmental data on enterprise indicator data in the interactive resource display interface, establish a data sharing channel between departments, and collect and organize the business data of each department to obtain a cross-departmental data set;

[0109] (4) Decompose the cross-departmental data set into indicators, conduct correlation analysis on the business indicators of different departments, establish the logical relationship between the indicators, and form a cross-departmental data correlation diagram;

[0110] (5) Perform statistical calculations based on the cross-departmental data association diagram, conduct quantitative analysis of the overall operation status of the park, calculate resource utilization, operating costs, and service quality indicators, and generate operation analysis reports;

[0111] (6) Conduct a comprehensive evaluation of the various indicators in the operation analysis report, establish a park operation efficiency evaluation system, conduct multi-dimensional performance analysis, and obtain park operation efficiency data.

[0112] Specifically, when performing spatial mapping processing on the portrait data of park enterprises, the geographical location information of the enterprises is extracted, including spatial data such as plot coordinates, building outlines, and road networks. A unified geographic coordinate system is established, using the WGS84 coordinate system as the benchmark, and the enterprise location data is converted into standard longitude and latitude coordinates. The terrain and landform model of the park is constructed using 3D modeling technology, and on this basis, 3D models of infrastructure such as buildings, roads, and pipe networks are superimposed. The spatial location of each enterprise is calibrated to form resource distribution scenario data containing spatial coordinates and attribute information. The scenario data is rendered through mixed reality technology, which refers to the technology of integrating virtual information with the real scene. During the rendering process, material texturing and lighting calculations are performed on the 3D models to achieve a realistic visual effect. Then, the operation index data of the enterprises is added to the 3D scene in the form of floating labels, and the label content includes key indicators such as enterprise names, operating conditions, and energy consumption levels. Human-computer interaction is achieved through gesture recognition and voice control, supporting functions such as scene roaming, data query, and information display, forming an interactive resource display interface.

[0113] When collecting enterprise data in the interactive resource display interface across departments, it is necessary to interface with the business systems of multiple departments such as development and reform, economy and information technology, taxation, and environmental protection. Data sharing channels are established, including specifications such as data interface definitions, transmission protocols, and security policies. The types of data collected include enterprise registration information, production and operation data, tax payment records, environmental monitoring data, etc. The collected data is subjected to format conversion, field mapping, and quality verification, unifying the data standards and completing the collection and collation to form a standardized cross-departmental data set. When disassembling the cross-departmental data set into indicators, it is necessary to identify the correlation relationships between different business indicators. For example, there is a corresponding relationship between the production data and energy consumption data of an enterprise, and the operation data of environmental protection facilities is correlated with the pollutant emission data. The correlation degree between indicators is calculated through correlation analysis methods to construct an indicator relationship network. At the same time, the upstream and downstream dependence relationships of indicators are analyzed, such as the business indicator chain in links such as raw material procurement, production processing, and product sales, forming a cross-departmental data correlation diagram.

[0114] Quantitatively analyze the overall operation status of the park based on the data association diagram and calculate key operation indicators. The resource utilization rate indicators include land utilization rate, energy utilization rate, water resource utilization rate, etc., which are calculated by the ratio of the actual resource consumption of enterprises to the resource quota. The operation cost indicators include infrastructure maintenance cost, environmental governance cost, public service cost, etc., which are obtained by statistical summary of cost data. The service quality indicators include enterprise satisfaction, problem response time, service coverage rate, etc., which are obtained through questionnaire surveys and data statistics. Organize these quantitative indicators into an operation analysis report. Conduct multi-dimensional effectiveness evaluations on the operation analysis report and establish an evaluation system covering dimensions such as economic benefits, resource efficiency, environmental impact, and service level. The economic benefit dimension evaluates the optimization degree of the industrial structure and the quality of economic growth in the park. The resource efficiency dimension evaluates the intensive utilization level and recycling degree of resources in the park. The environmental impact dimension evaluates the effectiveness of pollution prevention and control and the ecological protection level in the park. The service level dimension evaluates the management efficiency and service capabilities in the park. Through comprehensive analysis of multi-dimensional indicators, form evaluation data reflecting the overall operation effectiveness of the park.

[0115] For example: Locate the enterprise distribution data within the industrial cluster in space and construct a three-dimensional scene including factories, roads, and pipe networks. Display real-time data such as the electricity load, water resource consumption, and operation of environmental protection facilities of enterprises in the mixed reality display interface. Collect the output value data of enterprises from the economic and information departments, collect tax data from the tax departments, and collect pollution discharge data from the environmental protection departments, and establish a data sharing mechanism. Analysis shows that there is a positive correlation between the electricity load of enterprises and the output value data, and a negative correlation between the operation of environmental protection facilities and the pollution discharge data. Calculate the resource utilization efficiency of the industrial cluster and find that with the improvement of the intelligent manufacturing level, the energy consumption per unit of output value decreases year by year. Through multi-dimensional evaluation, it is found that this industrial cluster has good economic benefits and resource utilization efficiency, the operation of environmental governance facilities is stable, and public services are strongly guaranteed, reflecting the high-quality development level of the park.

[0116] In a specific embodiment, the process of performing the step of decomposing indicators for the cross-departmental data set may specifically include the following steps:

[0117] (1) Label the cross-departmental data set according to business categories, extract data fields and identify data types for the business indicators of each department, and generate an indicator attribute table;

[0118] (2) Perform semantic parsing on the indicator fields in the indicator attribute table, establish an association relationship for indicators with similar business meanings through field mapping rules, and form an indicator semantic network;

[0119] (3) Extract the dependency relationships between indicators according to the indicator semantic network, establish upstream and downstream business process links, quantitatively calculate the influence degree between indicators, and obtain an indicator association strength matrix;

[0120] (4) Convert the index correlation strength matrix into a relational graph structure. Use the index as a node and the correlation strength as the edge weight to construct an index relationship topology graph;

[0121] (5) Conduct community detection on the index relationship topology graph, identify clusters of closely related indexes, divide business groups, and generate an index group distribution map;

[0122] (6) Integrate the index group distribution map with the index relationship topology graph, mark the business flow direction and data flow direction, and form a cross-department data correlation graph.

[0123] Specifically, during the processing of the cross-department data set, classify and label the data by business. Classify the data according to different business departments such as the development and reform department, the economic and information technology department, the tax department, and the environmental protection department, and extract the business index fields of each department. The extraction of data fields includes attribute information such as field name, data type, value range, and measurement unit. Identify the data characteristics of the fields through data exploration methods, such as numerical type, character type, date type, etc., and record the statistical characteristics of the data, including mean, variance, distribution type, etc., to generate an index attribute table containing complete field attribute information. When performing semantic analysis on the index fields, use normalized field naming processing. Extract keywords in the field name, establish a business term dictionary, and identify the business meaning of the field. Establish associations for indexes with similar semantics through field mapping rules, such as synonymous fields like "operating income" and "sales income", "power consumption" and "electricity consumption". Calculate the semantic similarity of the fields using a word vector model to construct a network structure reflecting the semantic association of the indexes. Calculate the correlation strength between different index pairs to form a correlation strength matrix.

[0124] When converting the correlation strength matrix into a graph structure, each business index serves as a node of the graph, and the correlation strength between indexes serves as the edge weight. Use the force-directed layout algorithm to perform visual layout on the graph. The distance between nodes with a larger correlation strength is closer, and the distance between nodes with a smaller correlation strength is farther. In this way, construct a topology graph that intuitively reflects the index relationship. When conducting community detection on the index relationship topology graph, use a community detection algorithm based on modularity. Calculate the density of the edges in the graph and divide the closely related indexes into the same community. For example, divide production-related indexes, energy consumption-related indexes, environmental protection-related indexes, etc. into different business groups. Analyze the connection relationships between different groups, identify key bridging indexes, and generate a group distribution map reflecting the index clustering characteristics.

[0125] Fuse the group distribution map with the topology map, and mark the business flow and data flow in the map. The business flow reflects the business logic in the enterprise's production and operation process, such as raw material procurement → production processing → product sales → tax payment, etc. The data flow reflects the data transfer process between departments, such as enterprise declaration → department review → data archiving, etc., to form an inter-departmental data association map.

[0126] For example: Extract the data fields of each department, such as the production data fields (output, output value, etc.) of the economic and information department, and the monitoring data fields (waste gas, waste water, etc.) of the environmental protection department. Through semantic analysis, it is found that there are associations between indicators such as "output" and "raw material consumption", "waste gas emission", etc. Calculate the association strength between indicators. For example, the influence strength of output change on raw material consumption is 0.8, and the influence strength on waste gas emission is 0.6. Visualize the indicator relationship as a topology map, and divide the production indicators, resource indicators, and environmental protection indicators into different groups through community detection. Mark the complete business process from raw material procurement to waste disposal in the association map, which reflects the department collaboration and data sharing mechanism in the enterprise production process.

[0127] The above describes the comprehensive management method for a smart park in the embodiments of the present application. Next, the comprehensive management system for a smart park in the embodiments of the present application will be described. Please refer to Figure 4 , an embodiment of the comprehensive management system for a smart park in the embodiments of the present application includes:

[0128] The acquisition module 201 is used to collect environmental data, energy consumption data, and pedestrian flow data through the Internet of Things perception network, perform noise reduction and compression processing on the environmental data, energy consumption data, and pedestrian flow data through the edge node, and perform semantic alignment on the multi-source data through the knowledge association method to obtain the park basic data set;

[0129] The construction module 202 is used to construct a three-dimensional model based on the park basic data set by using a spatio-temporal data cube, and store and organize the element relationships in a graphical manner to obtain the park digital twin system;

[0130] The generation module 203 is used to generate digital identity identifiers for the land according to the park digital twin system by using a spatio-temporal coding method, and perform evidence storage and sharing authorization on the land data through the blockchain to obtain the park land digital identity system and the park land coding system;

[0131] The recognition module 204 is used to identify abnormal patterns in the activity data according to the park land digital identity system and the park land coding system, and analyze the risk propagation path to obtain the park intelligent supervision and early warning data;

[0132] An analysis module 205, configured to perform multi-dimensional analysis on enterprise operation data according to the intelligent supervision and early warning data of the park, and evaluate the operation effect to obtain the portrait data of the park enterprises;

[0133] A visualization module 206, configured to visually present resources in a mixed reality manner according to the portrait data of the park enterprises, and comprehensively analyze cross-departmental data to obtain the operation efficiency data of the park.

[0134] Through the collaborative cooperation of the above-mentioned various components, a multi-dimensional data collection network for the park is established by deploying data collection devices such as Internet of Things sensors, Beidou positioning terminals, and high-definition cameras, realizing the comprehensive perception and real-time collection of park data. At the same time, edge computing nodes are set in the perception layer to perform noise reduction, duplicate removal, and compression processing on the original data, significantly improving the data transmission efficiency and storage utilization rate. By designing a data association analysis method based on a knowledge graph, the intelligent fusion of multi-source heterogeneous data is realized, providing a high-quality data foundation for subsequent analysis. And a multi-dimensional data organization method based on a spatio-temporal data cube is adopted to organize various types of park data according to three dimensions of time, space, and attributes, supporting flexible multi-dimensional analysis and visualization. At the same time, a relationship model based on a graph database is designed to realize the efficient storage and rapid query of complex relationships between various elements in the park, providing support for subsequent intelligent analysis. Based on this data organization method, park managers can quickly obtain and analyze the spatio-temporal distribution characteristics and change rules of various elements in the park. And through 3D modeling technology combined with high-precision laser point cloud data, a refined 3D model of infrastructure such as park buildings, roads, and pipe networks is constructed, and a dynamic update mechanism is established based on the real-time collected sensing data to realize the real-time mapping between the physical space and the digital space. The designed digital twin engine integrates physical models, data models, and business models to realize the dynamic interaction and intelligent linkage of various elements in the park. This method realizes the interconnection and in-depth application of park data by constructing a unified data collection, storage, processing, and analysis framework, providing strong support for the refined management and scientific decision-making of the park. At the same time, by establishing a data analysis and supervision system, the intelligent level of park management is improved.

[0135] The present application also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is made to execute the steps of the comprehensive management method for the smart park.

[0136] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0138] The above is the case. The above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A comprehensive management method for a smart park, characterized in that: The comprehensive management method for the smart park includes: Environmental data, energy consumption data and human flow data are collected through the IoT sensing network, and the environmental data, energy consumption data and human flow data are subjected to noise reduction and compression processing through edge nodes. The multi-source data are semantically aligned through the knowledge association method to obtain the basic data set of the park. Based on the basic data set of the park, a three-dimensional model is constructed using the spatiotemporal data cube, and the element relationships are stored and organized in a graphical way to obtain the digital twin system of the park; According to the digital twin system of the park, the space-time coding method is used to generate digital identity for the land, and the land data is stored and shared through the blockchain to obtain the digital identity system and coding system of the park land. According to the digital identity system and coding system of the park land, the abnormal pattern of activity data is identified, and the risk propagation path is analyzed to obtain the park intelligent supervision and early warning data; Based on the park's intelligent supervision and early warning data, we conduct a multi-dimensional analysis of the enterprise's operating data and evaluate the operating results to obtain the park's enterprise portrait data; Based on the enterprise portrait data of the park, resources are visualized using mixed reality, and cross-departmental data is comprehensively analyzed to obtain the park's operational efficiency data.

2. The integrated management method for a smart park according to claim 1, characterized in that: The environmental data, energy consumption data and human flow data are collected through the IoT sensing network, and the environmental data, energy consumption data and human flow data are subjected to noise reduction and compression processing through edge nodes, and multi-source data are semantically aligned through the knowledge association method to obtain the park basic data set, including: The first group of sensors are deployed at key nodes in the park to collect environmental temperature and humidity data, the second group of sensors are deployed to collect power consumption data and water consumption data, and the third group of sensors are deployed to collect personnel density data. The collected data are timestamped to obtain the original perception data. Performing data preprocessing on the original sensed data through the edge node, grouping the original sensed data according to time sequence, performing median filtering noise reduction processing on each group of data, and then performing data compression to obtain preprocessed data; A data association rule base is established for the pre-processed data, the attribute fields of the environmental data, energy consumption data and human flow data are mapped to each other, and the fields are unified through the rule base to obtain standardized data; A semantic knowledge base is constructed based on the standardized data, the business meanings of environmental data, energy consumption data and passenger flow data are associated and mapped, and the data are semantically unified through a semantic alignment method to obtain a basic data set for the park.

3. The comprehensive management method for a smart park according to claim 1, characterized in that: The three-dimensional model is constructed based on the basic data set of the park using the spatiotemporal data cube, and the element relationship is stored and organized in a graphical manner to obtain the park digital twin system, including: The park basic data set is layered according to the time dimension, space dimension and attribute dimension, and a timestamp and space coordinates are set for each layer of data to form a spatiotemporal data cube; Modeling the topography of the park according to the spatial coordinate information in the spatiotemporal data cube, and associating the geometric information and topological relationships of buildings, roads, and pipe networks to obtain a park spatial framework; Mapping the park spatial framework with the real-time data in the park basic data set, establishing a data update index table, marking dynamically changing data for real-time update, and generating dynamic associated data; The element relationships in the dynamic association data are converted into the form of nodes and edges through a graphical interface, node attributes and edge weights are assigned and calculated, and an element relationship graph is constructed; The element relationship graph is hierarchically organized, nodes with similar attributes are divided into subgraphs, and connection relationships between subgraphs are established to form a multi-level element structure; The multi-level element structure is integrated with the dynamic associated data, a data synchronization update mechanism and status monitoring rules are established, and a digital twin system of the park is obtained.

4. The comprehensive management method for a smart park according to claim 1, characterized in that: According to the digital twin system of the park, the space-time coding method is used to generate digital identity for the land, and the land data is stored and shared through the blockchain to obtain the digital identity system and coding system of the park land, including: Extract the geographical location information, usage attribute information, and planning condition information of the land from the digital twin system of the park, organize the data according to the time and space dimensions, and generate a basic land information table; Define coding rules for various attributes in the land basic information table, correspond geographic location information to grid coordinates, correspond use attributes to function codes, correspond planning conditions to type codes, and generate a land coding rule set; Uniquely encode each piece of land according to the land encoding rule set, combine the spatiotemporal information and attribute information to generate a digital identity, and establish a mapping relationship between the basic land information and the digital identity to form land identity data; Organizing the land identity data according to the block structure, generating a timestamp and link pointer for each data block, constructing a blockchain data structure, and verifying the validity of the data through a consensus mechanism; Establish a data access permission table based on the blockchain data structure, set data viewing and modification permissions for different departments and users, and generate data sharing rules; The data sharing rules are associated with the blockchain data structure, a data interaction interface and verification mechanism are established, and the park land digital identity system and park land coding system are obtained.

5. The comprehensive management method for a smart park according to claim 1, characterized in that: According to the digital identification system and coding system of the park land, the activity data is identified with abnormal patterns, and the risk propagation path is analyzed to obtain the park intelligent supervision and early warning data, including: Extract land identification information based on the park land digital identity system and the park land coding system, associate and match the land identification information with the park activity data, and generate an activity data association table; Performing time series analysis on the activity data association table, calculating the deviation of the activity index in each time window from the historical mean, establishing the activity fluctuation range, and forming activity trend data; Marking data in the activity trend data that exceeds the fluctuation range as abnormal points, performing spatiotemporal clustering analysis on the abnormal points, identifying the spatial distribution characteristics of abnormal activities, and obtaining an abnormal activity distribution map; Establishing risk node connection relationships according to the abnormal activity distribution graph, calculating the risk transmission probability between nodes, constructing a risk propagation network, and generating a risk propagation matrix; Tracing the propagation path of the risk propagation matrix, identifying key propagation nodes and main propagation paths, and forming a risk propagation link diagram; The risk propagation link diagram is integrated with the abnormal activity distribution diagram, risk warning rules are established, risk levels are divided, and intelligent supervision and warning data for the park are obtained.

6. The comprehensive management method for a smart park according to claim 1, characterized in that: According to the park's intelligent supervision and early warning data, the enterprise's operating data is analyzed in multiple dimensions, and the operating results are evaluated to obtain the park's enterprise portrait data, including: Correlate and match the park intelligent supervision and early warning data with the enterprise operation data, and extract the revenue data, tax data, and energy consumption data of each enterprise to form a basic indicator table for the enterprise; Establish an indicator calculation system based on the basic indicator table of the enterprise, calculate the ratio of revenue data to land area to obtain the per-mu output value, calculate the ratio of tax data to revenue data to obtain the tax contribution rate, and form the core indicator data of the enterprise; Segment the core indicator data of the enterprise according to the time series, calculate the growth rate change trend of each time period, and compare and analyze it with the industry benchmark to generate an enterprise development trend chart; Assign weights to the indicator data in the enterprise development trend chart, perform weighted calculation on each indicator, and grade the enterprises according to the scores to obtain an enterprise evaluation grade table; Conducting business performance analysis on enterprises at all levels in the enterprise evaluation grade table, calculating input-output ratio, resource utilization rate, and environmental impact, and forming an enterprise performance evaluation table; The enterprise performance evaluation form and the enterprise assessment grade form are integrated to establish an enterprise comprehensive portrait index system, comprehensively characterize the enterprise development status, and obtain the park enterprise portrait data.

7. The integrated management method for a smart park according to claim 1, characterized in that: According to the enterprise portrait data of the park, resources are visualized in a mixed reality way, and cross-departmental data is comprehensively analyzed to obtain park operation efficiency data, including: The park enterprise portrait data is spatially mapped according to the geographic location information, a resource distribution coordinate system is established, a three-dimensional scene of resource spatial distribution is constructed, and resource distribution scene data is generated; The resource distribution scene data is rendered by a mixed reality scene engine, and the enterprise operation indicator data is superimposed and displayed in the form of floating labels to form an interactive resource display interface; Conduct cross-departmental data collection on the enterprise indicator data in the interactive resource display interface, establish a data sharing channel between departments, and collect and organize the business data of each department to obtain a cross-departmental data set; Decomposing the cross-departmental data set into indicators, conducting correlation analysis on the business indicators of different departments, establishing logical relationships between the indicators, and forming a cross-departmental data correlation diagram; Perform statistical calculations based on the cross-departmental data association diagram, conduct quantitative analysis on the overall operation status of the park, calculate resource utilization, operating costs, and service quality indicators, and generate an operation analysis report; Comprehensively evaluate the various indicators in the operation analysis report, establish a park operation efficiency evaluation system, conduct multi-dimensional efficiency analysis, and obtain park operation efficiency data.

8. The integrated management method for a smart park according to claim 7, characterized in that: The cross-departmental data set is decomposed into indicators, the business indicators of different departments are analyzed for correlation, the logical relationship between the indicators is established, and a cross-departmental data correlation diagram is formed, including: Annotate the cross-departmental data set according to business classification, extract data fields and identify types of business indicators of each department, and generate an indicator attribute table; Performing semantic analysis on the indicator fields in the indicator attribute table, establishing association relationships between indicators with similar business meanings through field mapping rules, and forming an indicator semantic network; Extract the dependency relationship between indicators according to the indicator semantic network, establish upstream and downstream business process links, quantify the impact degree between indicators, and obtain the indicator association strength matrix; The indicator association strength matrix is ​​converted into a relationship graph structure, and the indicator relationship topology graph is constructed with the indicator as the node and the association strength as the edge weight; Perform community discovery on the indicator relationship topology map, identify closely related indicator clusters, divide business groups, and generate an indicator group distribution map; The indicator group distribution map is integrated with the indicator relationship topology map, and the business flow and data flow are marked to form a cross-departmental data association map.

9. An integrated management system for a smart park, used to implement the integrated management method for a smart park as described in any one of claims 1 to 8, characterized in that: The integrated management system for the smart park includes: The acquisition module is used to collect environmental data, energy consumption data and human flow data through the IoT sensing network, perform noise reduction and compression processing on the environmental data, energy consumption data and human flow data through edge nodes, and semantically align multi-source data through knowledge association methods to obtain the basic data set of the park; The construction module is used to construct a three-dimensional model based on the basic data set of the park using the spatiotemporal data cube, and store and organize the element relationships in a graphical way to obtain the digital twin system of the park; The generation module is used to generate digital identity for land using the spatiotemporal coding method based on the digital twin system of the park, and to store and share land data through blockchain to obtain the digital identity system and coding system of the park land; The identification module is used to identify abnormal patterns in activity data based on the park land digital identity system and the park land coding system, and analyze the risk propagation path to obtain the park intelligent supervision and early warning data; The analysis module is used to conduct multi-dimensional analysis of enterprise operation data based on the park's intelligent supervision and early warning data, and evaluate the operation results to obtain the park's enterprise portrait data; The visual module is used to visualize resources in a mixed reality manner based on the enterprise portrait data of the park, and to conduct a comprehensive analysis of cross-departmental data to obtain park operation efficiency data.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the comprehensive management method for a smart park as described in any one of claims 1-8 is implemented.

Images