A standardized management method and management system applied to water conservancy projects

Abstract

This invention provides a standardized management method and system for water conservancy projects. The method specifically includes the following steps: dividing the production area of ​​the target water conservancy project into multiple unit grids; collecting environmental data and outdoor production operation data of the outdoor production area and indoor production operation data of the indoor production area within each unit grid; constructing a multi-dimensional data graph network; determining the outdoor safety risk level of the outdoor production area based on production risk correlation characteristics; determining the indoor safety risk level of the indoor production area based on indoor production operation data; calculating the grid production safety risk level of each unit grid; summarizing the grid production safety risk levels of all unit grids and weighting them to obtain the engineering production safety risk level of the target water conservancy project; and determining the corresponding risk standardization management strategy for the target water conservancy project based on the engineering production safety risk level. This invention has the effect of efficiently and objectively integrating and analyzing multi-source production data.

Description

Technical Field

[0001] This invention belongs to the field of water conservancy safety management technology, specifically relating to a standardized management method and management system applied to water conservancy projects. Background Technology

[0002] In the water conservancy industry, water conservancy projects, as a crucial component of infrastructure, are characterized by large scale, involvement of multiple professional disciplines, high safety requirements, and broad socio-economic impacts. Simultaneously, they face the challenges posed by complex geological and climatic conditions to project safety, water quality safety, and water supply safety. With socio-economic development and increasing demands for infrastructure functions, the number and scale of existing water conservancy projects are continuously expanding, and system integration capabilities are constantly strengthening, placing higher demands on high-level safe operation. Traditional safety management methods largely rely on manual monitoring of production data, and the analysis and processing of production environment data often depend on subjective human judgment. However, traditional methods are increasingly inadequate to cope with the increasingly complex production environment and risk factors. Especially in large-scale, multi-regional water conservancy projects, a large amount of multi-source production monitoring data exists. How to efficiently and objectively integrate and analyze multi-source data, monitor the production process in real time, accurately assess safety risks, and implement standardized management has become the new direction for the development of the water conservancy industry. Summary of the Invention

[0003] This invention provides a standardized management method and system for water conservancy projects, in order to solve the problem of difficulty in efficiently and objectively integrating and analyzing multi-source data in large-scale, multi-regional water conservancy projects.

[0004] In a first aspect, the present invention provides a standardized management method for water conservancy projects, the method comprising the following steps:

[0005] The production area of ​​the target water conservancy project is divided into multiple unit grids according to the project scope;

[0006] For each of the unit grids, environmental data and outdoor production operation data of the outdoor production area in the unit grid are collected, and indoor production operation data of the indoor production area in the unit grid are obtained.

[0007] A multidimensional data graph network is constructed by combining the environmental data and the outdoor production operation data;

[0008] Based on the multidimensional data graph network, the production risk correlation features between the environmental data and the outdoor production operation data are extracted, and the outdoor safety risk level of the outdoor production area is determined according to the production risk correlation features.

[0009] The indoor safety risk level of the indoor production area is determined by combining BIM technology and image recognition technology and based on the indoor production operation data.

[0010] The grid production safety risk level of the unit grid is calculated based on the outdoor safety risk level and the indoor safety risk level.

[0011] The production safety risk levels of all the aforementioned unit grids are summarized, and the engineering production safety risk level of the target water conservancy project is obtained by weighted calculation.

[0012] Based on the aforementioned engineering production safety risk level, a standardized risk management strategy is determined for the target water conservancy project.

[0013] Optionally, before constructing the multidimensional data graph network by combining the environmental data and the outdoor production operation data, the following steps are also included:

[0014] Historical climate environment data, historical geological environment data, and historical outdoor production and operation data of projects of the same type as the target water conservancy project are crawled, and the historical climate environment data, historical geological environment data, and historical outdoor production and operation data are preprocessed.

[0015] Historical climate characteristics, historical geological characteristics, and historical outdoor production characteristics are extracted from the historical climate and environmental data, the historical geological environmental data, and the historical outdoor production and operation data, respectively.

[0016] A first multiple regression analysis model is constructed by combining the historical climate characteristics and the historical geological characteristics. The first risk characteristic correlation matrix between the historical climate characteristics and the historical geological characteristics is then analyzed using the first multiple regression analysis model.

[0017] A second multiple regression analysis model is constructed by combining the historical geological features and the historical outdoor production features. The second risk feature correlation matrix between the historical geological features and the historical outdoor production features is then analyzed using the second multiple regression analysis model.

[0018] Based on the historical geological characteristics, the first risk feature correlation matrix and the second risk feature correlation matrix are fused to obtain a fused risk feature correlation matrix.

[0019] A third multiple regression analysis model is constructed by combining the historical climate characteristics and the historical outdoor production characteristics. The third risk characteristic correlation matrix between the historical climate characteristics and the historical outdoor production characteristics is then analyzed using the third multiple regression analysis model.

[0020] Optionally, the environmental data includes climate environmental data and geological environmental data, and the step of constructing a multidimensional data graph network by combining the environmental data and the outdoor production operation data includes the following steps:

[0021] Preprocess the climate and environmental data, the geological and environmental data, and the outdoor production and operation data;

[0022] The target climate characteristics, target geological characteristics, and target outdoor production characteristics are extracted from the climate environment data, the geological environment data, and the outdoor production operation data, respectively.

[0023] The target climate features, target geological features, and target outdoor production features are uniformly projected to the same target feature space through a preset feature transformation function, and corresponding target climate feature nodes, target geological feature nodes, and target outdoor production feature nodes are generated in the target feature space respectively.

[0024] Based on the fused risk feature correlation matrix, a first correlation node edge is generated between the target geological feature node and the target outdoor production feature node in the target feature space;

[0025] Based on the third risk feature correlation matrix, a second correlation node edge is generated between the target climate node and the target outdoor production feature node in the target feature space, resulting in a multidimensional data graph network.

[0026] Optionally, the step of extracting production risk correlation features between the environmental data and the outdoor production operation data based on the multidimensional data graph network, and determining the outdoor safety risk level of the outdoor production area based on the production risk correlation features, includes the following steps:

[0027] According to the generation order of the target outdoor production feature nodes in the multidimensional data graph network, each target outdoor production feature node is marked as a central target node in turn, until all target outdoor production feature nodes are marked as the central target node only once.

[0028] Whenever the target outdoor production feature node is marked as the central target node, the node risk correlation degree calculation step and the node community density calculation step are performed on the central target node to obtain the node risk correlation degree and the node community density of the central target node.

[0029] A production risk correlation value is calculated by combining the risk correlation degree of all the nodes and the community density of the nodes, and the production risk correlation value is used as the production risk correlation feature between the environmental data and the outdoor production operation data.

[0030] The outdoor safety risk level of the outdoor production area is determined based on the production risk correlation characteristics and the preset risk level rules.

[0031] Optionally, the node risk correlation calculation step includes the following steps:

[0032] The geological node correlation degree between the central target node and each adjacent target geological feature node is calculated using the fused risk feature correlation matrix.

[0033] Based on the first associated node edge, count the number of first node edges between the adjacent target geological feature node and all other target outdoor production feature nodes;

[0034] The geological node degree of the adjacent target geological feature node is calculated using the edges of the first associated node;

[0035] The geological node risk correlation degree of the central target node is calculated by combining the geological node correlation degree, the number of edges of the first node, and the degree of the geological node;

[0036] The climate node correlation degree between the central target node and each adjacent target climate feature node is calculated using the third risk feature correlation matrix.

[0037] The climate node degree of the adjacent target climate feature node is calculated using the edges of the second associated node;

[0038] The climate node risk correlation degree of the central target node is calculated by combining the climate node correlation degree and the climate node degree.

[0039] The node risk correlation degree of the central target node is obtained by summing the risk correlation degree of the geological node and the risk correlation degree of the climate node.

[0040] Optionally, the formula for calculating the risk correlation degree of the geological nodes is as follows:

[0041]

[0042] In the formula: Represents the i-th central target node V i The geological node risk correlation degree, m represents the central target node V. i Adjacent target geological feature nodes The number of nodes, The fusion risk feature correlation matrix A represents... R The matrix element corresponding to the i-th row and j-th column, ξ(·,·) represents the correlation calculation function, γ represents the geological weight parameter, and L i，j The central target node V representsi The j-th adjacent target geological feature node The number of edges of the first node. Indicates the adjacent target geological feature nodes The degree of the geological nodes;

[0043] The formula for calculating the risk correlation of the climate nodes is as follows:

[0044]

[0045] In the formula: Represents the i-th central target node V i The climate node risk correlation degree, t represents the central target node V i Adjacent target climate feature nodes The number of nodes, The third risk feature correlation matrix A represents... 3 In the matrix, the element corresponding to the i-th row and k-th column is ξ(·,·), which represents the correlation calculation function, and η represents the climate weight parameter. Represents the kth adjacent target geological feature node The degree of the geological nodes.

[0046] Optionally, the formula for calculating the node community density is as follows:

[0047]

[0048] In the formula: P i Represents the i-th central target node V i The node community density, M represents the total number of node edges in the multidimensional data graph network, d(V i ) represents the central target node V i The degree of the node.

[0049] Optionally, the formula for calculating the production risk correlation value is as follows:

[0050]

[0051] In the formula: Y represents the production risk correlation value, n represents the number of nodes of the target outdoor production feature node, and δ represents the correlation value weight parameter.

[0052] Optionally, the indoor production operation data includes indoor production area drawing data and indoor image data. The indoor production area drawing data pre-marks indoor hazardous areas. The step of combining BIM technology and image recognition technology and determining the indoor safety risk level of the indoor production area based on the indoor production operation data includes the following steps:

[0053] Based on the drawings of the indoor production area, an indoor engineering BIM model of the indoor production area is generated using BIM technology;

[0054] Based on the indoor hazardous areas pre-marked in the indoor production area drawing data, a corresponding model hazardous area is generated in the indoor engineering BIM model;

[0055] The percentage of hazardous areas in the model is calculated within the BIM model of the indoor engineering project.

[0056] Image recognition technology is used to identify indoor risk points in the indoor image data, and the number of hazard sources at the indoor risk points is counted.

[0057] The indoor safety risk level of the indoor production area is determined by combining the area proportion and the number of hazardous sources.

[0058] In a second aspect, the present invention also provides a standardized management system for water conservancy projects, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the standardized management method for water conservancy projects as described in the first aspect.

[0059] The beneficial effects of this invention are:

[0060] By dividing the production area of ​​the target water conservancy project into multiple unit grids, the scope of risk assessment can be refined, allowing for the accurate identification and quantification of specific risk factors in each grid. Collecting environmental and operational data from outdoor production areas, as well as production data from indoor production areas, ensures the comprehensiveness and diversity of the data. Combining BIM and image recognition technologies enables comprehensive monitoring and analysis of both indoor and outdoor production environments, thereby improving the accuracy of risk assessment. By constructing a multi-dimensional data graph network and combining environmental and production data, the correlation characteristics of production risks are extracted, enabling a systematic and objective analysis of multi-source data and the identification of potential production risks. This data-driven risk management approach relies on a large amount of real-time and historical data, allowing for dynamic adjustment and optimization of the risk assessment model, ensuring the scientific rigor and effectiveness of risk management. Compared to traditional experience-based and manual monitoring methods, the data-driven approach significantly improves the efficiency of risk management while mitigating the impact of subjective factors on data processing accuracy. Attached Figure Description

[0061] Figure 1 This is a flowchart illustrating a standardized management method applied to water conservancy projects in one embodiment of this application.

[0062] Figure 2 This is a flowchart illustrating the process of constructing a risk feature association matrix in one embodiment of this application.

[0063] Figure 3 This is a schematic diagram illustrating the process of constructing a multidimensional data graph network in one embodiment of this application. Detailed Implementation

[0064] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0065] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0066] The standardized management method for water conservancy projects disclosed in this invention is specifically applied to water conservancy projects and is part of the standardized management of intelligent water conservancy projects. Promoting the informatization and intelligentization of project management and building a standardized management system for project operation that drives high-quality development of water conservancy will help strengthen project safety management, eliminate major safety hazards, implement management responsibilities, improve management systems, enhance management capabilities, and establish a long-term management mechanism for the sound operation of water conservancy projects.

[0067] The standardized management of intelligent water conservancy projects needs to meet the following requirements:

[0068] (I) Project Status: The current status of the project meets the design standards and there are no safety hazards; the main buildings and supporting facilities are operating normally and the operating parameters meet the requirements of current specifications; the metal structure and electromechanical equipment are operating normally and safely and reliably; the monitoring and control facilities are set up reasonably, are intact and effective, and meet the needs of mastering the safety status of the project; the project appearance is intact, the management area is clean and tidy, and the signs are standardized and eye-catching.

[0069] (II) Safety Management: The project is registered in accordance with regulations, and the information is complete, accurate, and updated in a timely manner; safety assessments are carried out in accordance with regulations, and timely measures are taken to address the issues; the scope of project management and protection is delineated and announced, important boundary markers are complete and clearly visible, and there are no illegal buildings or activities that endanger the safety of the project; the safety management responsibility system is implemented, and the division of responsibilities among job positions is clear; the flood control organization system is sound, the emergency plan is complete and feasible, the flood control materials are managed in a standardized manner, and the project's measures to ensure safe passage through the flood season are implemented.

[0070] (III) Operation and maintenance: The system for maintenance work, including project inspection, monitoring, operation, maintenance and biological control, is complete, the behavior is standardized, and the records are complete. Key systems and operating procedures are clearly displayed on the wall. Potential hazards in the project are investigated and rectified in a timely manner, and closed-loop management of ledgers is implemented. The scheduling and operation procedures and plans are submitted for approval according to procedures and strictly followed.

[0071] (iv) Management guarantee: The management system is smooth, the property rights of the project are clear, and the management responsibility is implemented; personnel funds and maintenance funds are in place and their use and management are standardized; the job positions are reasonably set up, the responsibilities of the personnel are clear and they have the ability to perform their duties; the rules and regulations meet the management needs and are constantly improved, with complete content, clear requirements and strict implementation; the office facilities and equipment are complete and the archives are managed in an orderly manner.

[0072] (V) Information technology construction: Establish an information platform for engineering management, with complete and timely updates of basic engineering information, monitoring and control information, and management information, and achieve information integration, sharing and interconnection with platforms at all levels; integrate and access engineering information such as rainfall and water conditions and safety monitoring and control to achieve online supervision and automated control, apply intelligent inspection equipment to improve the ability to automatically identify, assess and warn of hazards; and have sound network security and data protection systems and comprehensive protection measures.

[0073] Based on the above requirements, and according to the actual situation of engineering operation and management, management matters related to project status, safety management, operation and maintenance, management support, and information technology construction are sorted out. Combined with relevant management systems and technical standards and specifications, standardized management systems are determined, and a standard system for water conservancy project operation and management is constructed. This standard system specifically includes multiple dimensions, such as technical standards and management standards. For example, the technical standards system specifically involves multiple dimensions in the production and operation process of water conservancy projects, which can be summarized as follows:

[0074] 1. Engineering operation and scheduling technology: including but not limited to hydraulic structures, metal structures, electromechanical equipment, main equipment, power generation and transmission equipment and facilities, water and rainfall facilities, water quality monitoring systems, safety monitoring systems, video surveillance systems, water and power supply equipment and facilities, irrigation equipment and facilities, scheduling procedures and control plan preparation, flood control scheduling, irrigation scheduling, water supply scheduling, power generation scheduling, sediment scheduling, shipping scheduling, ecological scheduling, and water release early warning.

[0075] 2. Maintenance and upkeep: including but not limited to hydraulic structures, metal structures, electromechanical equipment, main equipment, power generation and transmission equipment and facilities, water and rainwater monitoring facilities, water quality monitoring systems, safety monitoring systems, video surveillance systems, water and power supply equipment and facilities, irrigation equipment and facilities, etc.

[0076] 3. Equipment and facility upgrades and materials: including but not limited to the technical requirements for equipment and facility selection, the technical requirements for equipment and facility installation and commissioning, the requirements for implementation and acceptance of equipment and facility upgrades and renovations, and the technical requirements for the procurement of spare parts and materials.

[0077] 4. Dimensions of testing and identification: including but not limited to measurement methods, inspection methods, test methods, hydraulic engineering and hydrology inspection, metal structure and electromechanical inspection, dispatching and operation inspection, water quality inspection, information technology inspection, energy conservation inspection, environmental protection inspection, power production inspection, water supply and irrigation inspection, inspection and calibration of measuring equipment and facilities, metal structure identification, safety monitoring system identification, safety identification, and safety evaluation.

[0078] 5. Water conservation and soil and water conservation dimensions: including but not limited to general standards, water resource conservation and intensive utilization, and soil and water conservation.

[0079] 6. Safety and Occupational Health Dimension: This includes, but is not limited to, general standards, engineering safety, flood control and disaster relief, production safety, operational safety, emergency response, prevention and control of biological and animal hazards such as termites, cybersecurity, forecasting and early warning, accident analysis, accident investigation, and occupational health.

[0080] 7. Operational and production quality dimensions: including but not limited to the control of operation and maintenance indicators of hydraulic structures, metal structures, electromechanical equipment, main equipment, power generation and transmission equipment and facilities, water and rainfall facilities, water quality monitoring systems, safety monitoring systems, video surveillance systems, water and power supply equipment and facilities, irrigation equipment and facilities, as well as the quality control of flood control scheduling, irrigation scheduling, water supply scheduling, power generation scheduling, sediment scheduling, shipping scheduling, ecological scheduling, and water release early warning scheduling.

[0081] 8. Marketing and service dimensions: including but not limited to water supply quantity and quality indicators, and performance and technical parameters of electrical products such as voltage, frequency, harmonics, and reliability.

[0082] 9. Information and network dimension: including but not limited to general standards, engineering management, science and technology, archives, information application, communication networks, digital twins, etc.

[0083] Figure 1 This is a flowchart illustrating a standardized management method applied to water conservancy projects in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps. For example Figure 1 As shown, the standardized management method for water conservancy projects disclosed in this invention specifically includes the following steps:

[0084] S101. Divide the production area of ​​the target water conservancy project into multiple unit grids according to the project scope.

[0085] Firstly, based on the overall project plan and geographic information, Geographic Information System (GIS) technology can be used for regional division. GIS technology can process and analyze spatial data. By inputting information such as the geographical location, terrain features, and production plans of the production area into the system, a detailed regional division scheme can be generated. Specifically, the entire production area can be divided into several grids, the size of which can be adjusted according to actual needs. Common grid sizes are 50m x 50m or 100m x 100m. When dividing the grid, several factors need to be considered, such as terrain changes, production difficulty, and environmental impact. For example, in areas with complex terrain, the grids can be smaller to allow for more accurate data collection and risk assessment; while in areas with flat terrain and a stable environment, the grids can be appropriately enlarged to improve data collection efficiency. Furthermore, production progress and plans also need to be considered, dividing areas with faster production progress into independent grids for centralized management and data collection.

[0086] To ensure the grid division is practically feasible, production planning maps and topographic maps can be overlaid in the GIS system to visualize the division results and make adjustments as needed. Different production projects can be divided into independent grids for separate data collection and management. After grid division, each grid needs to be numbered and labeled to generate a detailed grid division map. This map serves as the basis for subsequent data collection and risk assessment, ensuring that data collection and management for each grid are based on verifiable data. Furthermore, the grid division map can be imported into the production management system, combined with production progress and plans, to update and manage the production status of each grid in real time.

[0087] S102. For each cell grid, collect environmental data and outdoor production operation data of the outdoor production area in the cell grid, and obtain indoor production operation data of the indoor production area in the cell grid.

[0088] Specifically, the outdoor production area can be any one or more of the following areas:

[0089] Water intake project area: includes facilities such as water intake points, pumping stations, and water diversion channels, used to obtain water resources from rivers, lakes, or groundwater sources.

[0090] Water conveyance project area: including water pipelines, water tunnels, water canals, etc., used to transport water from the water intake point to the place where it is needed.

[0091] Water storage project areas include reservoirs, regulating ponds, dams, etc., used to store and regulate water resources.

[0092] Drainage engineering area: including drainage ditches, drainage pipes, drainage pumping stations, etc., used to discharge excess water and prevent water accumulation and flooding.

[0093] Irrigation engineering areas: including irrigation canals, sprinkler irrigation systems, drip irrigation systems, etc., used for agricultural irrigation.

[0094] Flood control engineering areas include flood control dikes, flood walls, and flood discharge channels, which are used to prevent flood disasters.

[0095] Hydropower engineering area: including hydropower stations, generator sets, transmission lines, etc., used to generate electricity using water energy.

[0096] Water treatment facilities area: including sedimentation tanks, filtration tanks, disinfection facilities, etc., used for water treatment and purification.

[0097] The indoor production area can specifically be any one or more of the following areas:

[0098] Control center area: Used to monitor and control the operation of the entire water conservancy project, including monitoring equipment, control systems, communication equipment, etc.

[0099] The machine room area includes pump rooms, generator rooms, etc., where various mechanical equipment is installed and maintained.

[0100] Experimental area: used for water quality testing, material testing, etc., including various testing instruments and experimental equipment.

[0101] Office area: including offices and meeting rooms for managers and technical personnel.

[0102] Repair workshop area: Used for equipment repair and maintenance, including various tools and repair equipment.

[0103] Warehouse area: Used for storing various equipment, materials and spare parts.

[0104] Employee living area: including canteen, dormitory, rest room, etc., providing a place for employees to live and rest.

[0105] Training area: Used for employee training and technical exchange, including training equipment and materials.

[0106] For outdoor production areas, environmental data collection is a crucial step. This data includes meteorological data (such as temperature, humidity, wind speed, and rainfall), geological data (such as soil type and geological structure), and hydrological data (such as water level changes and flow velocity). Meteorological data can be collected in real time through weather stations or sensors installed at the production site. These devices can automatically record and transmit data to a central database. Geological data can be obtained through on-site exploration and geological surveys, using geological drilling equipment and soil analysis instruments to record the geological characteristics of each grid in detail. Hydrological data can be obtained through hydrological monitoring equipment installed near rivers, lakes, and other bodies of water. These devices can monitor water level changes and flow velocity in real time. Outdoor production operation data is equally important, including production progress at each stage, equipment usage, and personnel distribution. Production progress data can be recorded through a production management system, with daily updates. Equipment usage can be monitored through sensors installed on the equipment, recording the operating time and working status of each piece of equipment. Personnel distribution data can be obtained through a personnel positioning system, using GPS or RFID technology to record the location and working status of each production worker in real time.

[0107] For indoor production areas, it is necessary to collect indoor production operation data, including indoor building structure data, indoor production equipment data, and production process data. Building structure data can be obtained through BIM (Building Information Modeling) technology, which can provide detailed information on building structure and production processes, including the dimensions, materials, and locations of each component. Process data can be obtained through production site monitoring equipment and production logs, recording the specific operations and completion status of each process. During data collection, it is essential to ensure the accuracy and timeliness of the data. This can be achieved by establishing data collection standards and procedures to ensure that each data point has a clear collection method and recording method. For example, meteorological data needs to be recorded hourly, geological data needs to be recorded immediately after each exploration, and production progress data needs to be updated daily. To improve the efficiency and accuracy of data collection, automated data collection equipment and systems can be used to reduce manual intervention and errors.

[0108] S103. Construct a multi-dimensional data graph network by combining environmental data and outdoor production operation data.

[0109] The purpose of this step is to systematically represent the multidimensional data relationships at the production site through a multidimensional data graph network, providing data support for subsequent risk assessment. A multidimensional data graph network is a graph structure that can represent the relationships between multidimensional data, where nodes represent different data points (such as environmental data points, production data points, etc.), and edges represent the relationships between these data points. Graph database technology can be used to construct a multidimensional data graph network. First, the collected environmental and production data are entered into the graph database as nodes. Each node contains detailed data attributes; for example, meteorological data nodes include attributes such as temperature, humidity, and wind speed, while production progress nodes include attributes such as production progress percentage and production stage. Then, edges are constructed based on the relationships between the data (such as temporal, spatial, and causal relationships). For example, meteorological data and production progress data within the same time period can be connected to represent the impact of meteorological conditions on production progress within that time period; geological data from adjacent grids can also be connected to represent the spatial relationships of geological conditions.

[0110] When constructing a multidimensional data graph network, both the temporal and spatial dimensions of the data need to be considered. The temporal dimension can be achieved by recording the collection time of each data point using timestamps, ensuring the data's temporal sequence. The spatial dimension can be achieved by recording the location of each data point using coordinate information, ensuring the spatial correlation of the data. For example, a meteorological data node can include a timestamp and coordinate information, indicating the data collection time and location; a production progress node can include the production stage and location, representing the temporal and spatial information of the production process. This method of constructing a multidimensional data graph network can comprehensively and systematically represent the multidimensional data relationships at the production site, providing reliable data support for subsequent risk assessment. Multidimensional data graph networks not only intuitively display the complex relationships between data but also, through the query and analysis functions of graph databases, can delve deeper into the potential correlations and patterns between data.

[0111] S104. Extract the production risk correlation characteristics between environmental data and outdoor production operation data based on multidimensional data graph network, and determine the outdoor safety risk level of outdoor production area based on the production risk correlation characteristics.

[0112] Among these, production risk correlation characteristics refer to feature indicators that reflect the impact of environmental conditions on production safety, such as the impact of high temperatures on the health of production personnel and the impact of strong winds on the stability of production equipment. Methods for extracting these characteristics can employ data mining and machine learning techniques. By conducting in-depth analysis of the nodes and edges of a multidimensional data graph network, important risk correlation characteristics can be identified. Firstly, clustering analysis techniques can be used to group similar production risk events together, identifying common risk patterns. Clustering analysis of meteorological and production accident data can identify high-incidence periods of production accidents under high temperatures, thereby determining the impact characteristics of high temperatures on production safety. Clustering analysis can employ algorithms such as K-means and hierarchical clustering, selecting appropriate algorithms and parameters based on the characteristics and distribution of the data.

[0113] Secondly, regression analysis techniques can be used to establish quantitative models of the relationship between environmental conditions and production safety risks. For example, by performing regression analysis on meteorological data and production progress data, a regression model can be established to assess the impact of meteorological conditions on production progress, quantifying the changes in production progress under different meteorological conditions. Regression analysis can employ models such as linear regression and logistic regression, selecting appropriate models and parameters based on the characteristics and relationships of the data. After extracting the characteristics associated with production risks, these characteristics can be used to assess the safety risks of outdoor production areas and determine their outdoor safety risk levels. Risk levels can be determined using a graded scoring method, calculating a comprehensive risk score based on the weight and degree of influence of different risk characteristics, and classifying it into different risk levels (such as low risk, general risk, significant risk, major risk, etc.).

[0114] S105. Combine BIM technology and image recognition technology and determine the indoor safety risk level of the indoor production area based on indoor production operation data.

[0115] BIM (Building Information Modeling) technology provides detailed information on building structures and production processes. Analysis of the BIM model can identify potential production safety risks. The BIM model allows viewing the design and installation of each component, identifying structural weaknesses and substandard materials. Furthermore, BIM technology provides a visual representation of production progress and plans, helping production managers gain a comprehensive understanding of the actual situation on the production site. Image recognition technology, on the other hand, analyzes images of the production site to monitor production progress and personnel behavior in real time, identifying potential safety hazards. Analysis of production site monitoring videos can determine whether personnel are wearing safety helmets and adhering to safe operating procedures. Image recognition technology can employ deep learning algorithms, training on a large number of production site images to build a high-precision image recognition model, enabling real-time monitoring and risk identification of the production site.

[0116] Based on the analysis results of BIM and image recognition technologies, a comprehensive assessment of the safety risks in indoor production areas can be conducted to determine their indoor safety risk levels. The risk level can be determined using a graded scoring method. A comprehensive risk score is calculated based on the weight and impact of different risk characteristics, and then classified into different risk levels (such as low risk, moderate risk, significant risk, and major risk). For example, different weights can be assigned to risk characteristics such as the stability of the building structure, the quality of production materials, and the operational behavior of production personnel, and then a comprehensive risk score can be calculated, classifying it into three levels: low risk, moderate risk, significant risk, and major risk.

[0117] S106. The grid production safety risk level of the unit grid is calculated based on the outdoor safety risk level and the indoor safety risk level.

[0118] After determining the outdoor and indoor safety risk levels for each grid unit, these two risk levels need to be comprehensively calculated to obtain the overall production safety risk level of the grid unit. The purpose of this step is to determine the overall production safety risk level of each grid unit by comprehensively analyzing the risk characteristics of outdoor and indoor production areas, providing a basis for subsequent safety management. The comprehensive calculation method can use a weighted average approach, assigning different weights to outdoor and indoor production areas based on their risk characteristics and impact levels, and then calculating the weighted average. When determining the weights, the risk characteristics and impact levels of both outdoor and indoor production areas need to be considered. For example, for outdoor production areas, environmental factors such as meteorological and geological conditions have a greater impact on production safety and can be assigned higher weights; for indoor production areas, factors such as building structure and production materials have a greater impact on production safety and can be assigned higher weights. Furthermore, production progress and plans also need to be considered, assigning higher weights to areas with faster production progress to ensure that key and challenging aspects of safety management during production are adequately addressed. After calculating the weighted average, the overall risk level of the grid needs to be graded and scored, and it is divided into different risk levels (such as low risk, general risk, relatively high risk, major risk, etc.).

[0119] S107. Summarize the grid production safety risk levels of all unit grids and calculate the weighted production safety risk level of the target water conservancy project.

[0120] After calculating the production safety risk level of each unit grid, the risk levels of all unit grids need to be aggregated to calculate the overall production safety risk level of the target water conservancy project. The aggregation method can employ a weighted calculation approach, assigning different weights to each grid based on its risk characteristics and impact level, and then calculating a weighted average. For example, different weights can be set based on factors such as the area, production progress, and production difficulty of each grid, and then a weighted average can be calculated based on these weights and the grid's risk level to obtain the overall project's comprehensive risk level. The comprehensive risk level can be classified using a similar grading and scoring method, dividing the weighted average into different risk levels (such as low risk, general risk, relatively high risk, major risk, etc.) to determine the overall production safety risk level of the target water conservancy project.

[0121] S108. Determine the risk standardization management strategy corresponding to the target water conservancy project based on the engineering production safety risk level.

[0122] After determining the overall production safety risk level of the target water conservancy project, it is necessary to formulate corresponding standardized risk management based on this risk level. Standardized risk management refers to developing unified management standards and operational guidelines for different risk levels to ensure production safety. The formulation of management strategies can refer to industry standards and best practices. For example, for projects with high risk levels, stricter safety management measures can be developed, such as increasing the frequency of safety inspections, strengthening production personnel training, and equipping more safety equipment; for projects with general risk levels, appropriate safety management measures can be developed, such as regular safety inspections, strengthening on-site production monitoring, and implementing safe operating procedures; for projects with low risk levels, basic safety management measures can be developed, such as routine safety inspections and ensuring that production personnel comply with basic safe operating procedures. By developing and implementing standardized risk management, production safety risks can be effectively reduced, ensuring the smooth progress of water conservancy projects.

[0123] Specifically, within the same target water conservancy project, in addition to the standardized management of risks generated from the analysis of project production safety, there are also standardized management of other risks from various dimensions. The purpose of implementing standardized management of all risks is to meet the evaluation standards for standardized management of water conservancy projects. Specifically, if the target water conservancy project is a large or medium-sized reservoir project, then after implementing standardized management of all risks, it needs to meet the evaluation standards for standardized management of large and medium-sized reservoir projects. Below are some examples of these standards:

[0124] 1. Project Appearance and Environment: The project is in good condition and has a clean appearance. The project management area is clean and orderly with no garbage accumulation. The project management area has a high degree of greening, good soil and water conservation, and a good aquatic ecological environment.

[0125] 2. Water-retaining structures: The main dam and secondary dam are intact, the dam surface and slope protection are flat, and the dam body deformation and seepage are normal; the wave wall, filter body, corridor, and drainage ditch are intact; the deformation and seepage at the junction with the banks and other structures are normal; there are no tall weeds, trees, caves, or termite damage.

[0126] 3. Spillway structures: The spillway and spillway tunnel are in good condition with unobstructed inlets and outlets. The gate chamber, bottom slab, sidewalls, and energy dissipation structures are in good condition and operating normally. The deformation and seepage at the junctions with the dam body and slopes are normal.

[0127] 4. Water conveyance (diversion) structures: The water intake tower and water conveyance tunnel (culvert) are intact, the inlet and outlet structures are normal, the deformation and seepage at the junction with the dam body and slope are normal, and there are no obvious hidden dangers in the culverts buried under the dam.

[0128] 5. Metal Structure and Electromechanical Equipment: The gate and hoist facilities are in good condition and operating normally; the gate slot, wire rope, screw, hydraulic components, support, and water stop are normal; the electrical equipment and power supply are normal; and the backup power supply is well guaranteed; the hoist room meets the operating requirements, and safety inspections and equipment level assessments of the gate and hoist are carried out regularly.

[0129] If the target water conservancy project is a large or medium-sized sluice gate project, then after implementing standardized management of all risks, it needs to meet the evaluation standards for standardized management of large and medium-sized sluice gate projects. The following are some examples of the standards:

[0130] 1. Project Appearance and Environment: The project is in good condition overall and has a clean appearance. The project management area is clean and orderly. The project management area has a high degree of greening, good soil and water conservation, and good water quality and aquatic ecological environment.

[0131] 2. Lock chamber: The lock chamber structure (gate piers, bottom slab, side walls, etc.) and the connecting structures on both banks are safe, without any safety defects such as tilting, cracking, or uneven settlement; the energy dissipation, scour prevention, and seepage prevention and drainage facilities are complete and operating normally; the surface of the lock chamber structure is free from damage, exposed reinforcement, erosion, and cracking; there are no floating objects in the lock chamber, and no obvious siltation in the upstream and downstream connecting sections.

[0132] 3. Gate: The gate opens and closes smoothly, stops water normally, has a clean surface, no cracks, no obvious deformation, jamming, or corrosion, and the embedded parts, load-bearing components, and traveling support parts are free of defects. The water-stopping device is reliably sealed. The lifting lugs are free of cracks or rust. Safety inspections and equipment level assessments are carried out as required. Anti-freezing measures are taken for the gate during freezing periods.

[0133] 4. Gate hoists and electromechanical equipment: The gate hoists are clean, operate smoothly, and are free from rust, oil leaks, damage, etc. The wire ropes, screws, or hydraulic components are normal, and the protection and limit devices are effective; the electromechanical equipment is intact and operates normally, and the electrical equipment, indicating instruments, lightning protection facilities, grounding, etc. are regularly inspected as required, with no safety hazards; the wiring is neat, secure, and clearly labeled; safety inspections and equipment level assessments are carried out as required; the backup power supply is reliable.

[0134] 5. Upstream and downstream river channels and dikes: There is no obvious siltation or erosion in the upstream and downstream river channels; the dikes on both banks are intact and in good condition.

[0135] If the target water conservancy project is a large or medium-sized irrigation and drainage pumping station project, then after implementing standardized management of all risks, it needs to meet the evaluation standards for standardized management of large and medium-sized irrigation and drainage pumping station projects. The following are some examples of the standards:

[0136] 1. Safety Facilities and Equipment Management: Conduct daily inspections and periodic checks of engineering safety facilities and equipment (including fire-fighting equipment), and regularly perform maintenance, testing, and replacement to ensure they are complete and in good working order. Personal protective equipment (PPE) should meet safety production requirements.

[0137] 2. Dispatch and Control Management: Develop pump station operation, dispatch, and control plans (including joint dispatch with other water conservancy projects). Relevant content concerning flood control and drought relief work should be submitted for approval or filing as required. Strictly implement operation and dispatch instructions and control plans, and maintain complete records. Achieve safe, efficient, and economical operation of the pump station.

[0138] 3. Information Platform Construction: Establish an information platform for engineering operation and management to achieve automated operation, information-based management, and online monitoring of the project; and update project and operation information in a timely and dynamic manner.

[0139] 4. Automated Monitoring and Early Warning: The management information platform operates reliably, with well-maintained equipment and high utilization rate. Key information such as project conditions, water and rainfall conditions, operation monitoring, safety monitoring, and video surveillance are integrated into the information platform for dynamic management; when monitoring data is abnormal, it can automatically identify potential hazards and provide timely forecasts and early warnings.

[0140] If the target water conservancy project is a dike project, then after implementing standardized risk management, it needs to meet the evaluation standards for standardized management of dike projects. The following are some examples of the standards:

[0141] 1. Embankment body: The cross-section of the embankment body and the width of the embankment protection area shall meet the design or completion acceptance standards; the embankment shoulder line shall be straight and rounded, and the embankment slope shall be smooth; the embankment body shall be free of cracks, gullies, holes, and debris and garbage; the boundaries of the embankment protection area shall be clearly defined.

[0142] 2. Embankment Roads: Embankment roads are unobstructed and meet the requirements for traffic access during flood control and emergency rescue; the road surface of the embankment top (rear slope, flood control road) is intact and flat, without potholes, obvious depressions and undulations, and there is no water accumulation after rain; the intersection of the auxiliary road to the embankment and the embankment slope is straight and regular, and there is no erosion of the embankment body.

[0143] 3. Embankment protection works: Embankment protection works (slope protection, bank protection, groynes, toe protection, etc.) are free from defects, collapses, and loosening; the embankment surface is flat; the slope protection is smooth.

[0144] 4. Structures penetrating the dike: There are no major hidden dangers in the dike sections with structures penetrating the dike; the structures penetrating the dike (bridges, culverts, various pipelines, etc.) meet the requirements for safe operation; the metal structures and opening and closing equipment are well maintained and operate flexibly; the concrete shows no signs of aging or damage; the connection between the dike body and the structures is reliable, and there are no hidden dangers, uneven settlement cracks, voids, or leakage at the joints.

[0145] 5. Biological protection engineering: Trees and grasses are planted reasonably within the project management area, and a biological protection system is formed in areas suitable for planting protective forests; the turf on the dike (dam) slope is neat and free of tall weeds; the turf on each side of the dike shoulder (except for those with dike shoulder embankments) is more than 0.5m wide; the forest loss rate is less than 5%, and there are no diseases or pests.

[0146] 6. Drainage system: The drainage system is unobstructed; all types of drainage ditches, pressure relief wells and seepage drainage ditches are complete and unobstructed as required, and weeds and debris in the ditches are cleared in a timely manner without blockage or damage.

[0147] If the target water conservancy project is a water diversion project, then after implementing standardized management of all risks, it needs to meet the evaluation standards for standardized management of water diversion projects. The following are some examples of the standards:

[0148] 1. Engineering Facilities: All buildings are structurally sound, without tilting, collapse, cracks, landslides, uneven settlement, etc., and have a clean appearance. All equipment is in good condition, without obvious oil leaks, rust, etc., and is operating normally. The project has the conditions for maintenance and upkeep, with reasonable maintenance space and complete maintenance facilities.

[0149] 2. Monitoring Infrastructure: All hydrological monitoring stations are appropriately located, with stable and intact structures and well-functioning equipment; the hydrological monitoring system operates normally, and the technical indicators such as data measurement accuracy, frequency, and timeliness meet requirements. Water quality and water environment monitoring facilities are appropriately located, with stable and intact structures and well-functioning equipment; the water quality monitoring system operates normally, and the technical indicators such as data measurement accuracy, frequency, and timeliness meet requirements. All engineering safety monitoring projects are appropriately located, and the monitoring facilities and equipment operate normally. All monitoring data are compiled in a timely, complete, and accurate manner, meeting requirements.

[0150] If the target water conservancy project is a canal (aqueduct) project, then after implementing standardized risk management, it needs to meet the standardized management evaluation standards for canal (aqueduct) projects. The following are some examples of the standards:

[0151] 1. Project Appearance and Environment: The project is in good condition, safe, and operating normally, with unimpeded water supply. There is no debris, siltation, illegal construction, or activities that endanger the safety of the project within the management area.

[0152] 2. Canal (Embankment) Engineering: The top, shoulders, and intersections of the canal (embankment) should be flat, firm, and free of weeds and debris. The canal (embankment) slope should maintain the designed slope, with a smooth surface, free of rain-soaked ditches, steep slopes, caves, pits, and debris. Platforms should maintain the designed width, with a flat surface, and the height difference between the inner and outer edges of the platform should meet design requirements. The revetment should maintain a smooth surface, with intact concrete or block structures, tight joints, and no loosening, collapse, detachment, or gaps. It should be free of weeds and debris, and the slope should be clean and intact. The canal (embankment) slope should be free of animal burrows and signs of activity. The bottom slab should be free of cracks and damage, and drainage facilities such as drainage ditches and check valves should be intact and unobstructed. The protective layer of the seepage prevention facilities should be intact. The boundaries of the revetment area should be clearly defined, the ground should be flat, and free of debris. Structures crossing or spanning the canal should meet safety operation requirements, the connection between the canal body and the structures should be reliable, and there should be no hidden dangers at the joints.

[0153] 3. Aqueduct Project: The concrete structures of the inlet / outlet and channel body are intact, without cracks, erosion, leakage, or carbonation; there is no exposed rebar or rust; water flow is smooth, without debris accumulation, and the flow pattern is stable with no abnormal scouring; the joint sealing and seepage prevention structures are intact and without leakage. The concrete structures of the piers and abutments are intact, without cracks, erosion, leakage, or carbonation; there is no exposed rebar or rust; the piers show no severe scouring, and the backfill soil around the foundations shows no settlement or voids. The supports are intact, without deformation or misalignment. The working bridge, railings, and safety gates are intact.

[0154] 4. Biological protection engineering: The turf on the canal (embankment) slopes should be neat, without gaps or weeds, and maintained in a complete and aesthetically pleasing manner. The species, layout, and survival rate of trees within the project management area should meet the requirements. Appropriate protective measures should be taken in areas where there are potential plant or animal hazards that could cause engineering problems.

[0155] If the target water conservancy project is a culvert (tunnel, inverted siphon) project, then after implementing standardized risk management, it needs to meet the standardized management evaluation standards for culvert (tunnel, inverted siphon) projects. Below are some examples of these standards:

[0156] 1. Project Appearance and Environment: The project is in good condition, safe, and operating normally, with unimpeded water supply. There are no debris piled up, illegal buildings, or activities that endanger the safety of the project within the management area.

[0157] 2. Culvert Engineering: The protective facilities on the top of the culvert are intact, with no large accumulation of slag, stones, or other debris. The backfill near the culvert is intact, without dampness, subsidence, or erosion pits. There is no water seepage in the culvert section or structural joints, and no broken threads in the PCCP pipe; the movement or misalignment of adjacent culvert sections is within the allowable range, and the anti-seepage and anti-corrosion materials are intact. Ventilation holes, inspection holes, etc., are intact, and the park's perimeter walls or isolation netting, including water-retaining weirs, connecting wells, inspection holes, and ventilation holes, are intact.

[0158] 3. Tunnel Engineering: The entrance and exit slopes are stable and intact. The tunnel support structure is intact, the drainage system is intact, and drainage is normal. There are no obvious deformations, seepage, water inrushes, or landslides on the surface and at the tunnel entrance slopes. The sealing body is intact without cracks, deformation, or obvious seepage. There are no natural or human activities along the tunnel (culvert) route that would cause significant changes in geology or geomorphology.

[0159] 4. Underpass Project: Settlement, displacement, and tilt of the inlet and outlet wing walls meet requirements; the inlet and outlet platforms are intact, with no subsidence or cracking; the connection between the inlet / outlet and the canal embankment is intact, with no scouring, hollowing, or collapse. The drainage pipes of the inlet and outlet wing walls are intact and unobstructed; the inlet / outlet connection sections are unobstructed and free of blockages; there is no water leakage inside the pipes. There is no uneven settlement between adjacent pipe sections, and the backfill soil near the pipe sections shows no signs of collapse.

[0160] 5. Metal Structure and Electromechanical Equipment: The gate and hoisting system are intact and operating normally. The gate slots, wire ropes, screws, hydraulic components, supports, and waterstops are all in good working order. Electrical equipment and power supply are functioning normally, and backup power supply is adequately guaranteed. The hoisting room meets operational requirements, and regular safety inspections and equipment rating assessments are conducted for the gates and hoists.

[0161] In one embodiment, reference is made to Figure 2 The following steps are included before step S103:

[0162] Crawl historical climate and environmental data, historical geological and environmental data, and historical outdoor production and operation data of projects of the same type as the target water conservancy project, and preprocess the historical climate and environmental data, historical geological and environmental data, and historical outdoor production and operation data.

[0163] Historical climate characteristics, historical geological characteristics, and historical outdoor production characteristics were extracted from historical climate and environmental data, historical geological environmental data, and historical outdoor production and operation data, respectively.

[0164] A first-order multiple regression analysis model was constructed by combining historical climate characteristics and historical geological characteristics. The first-order risk characteristic correlation matrix between historical climate characteristics and historical geological characteristics was then analyzed and constructed using the first-order multiple regression analysis model.

[0165] A second multiple regression analysis model was constructed by combining historical geological features and historical outdoor production features. The second risk feature correlation matrix between historical geological features and historical outdoor production features was then analyzed and constructed using the second multiple regression analysis model.

[0166] Based on historical geological characteristics, the first risk feature correlation matrix and the second risk feature correlation matrix are fused to obtain the fused risk feature correlation matrix.

[0167] A third multiple regression analysis model was constructed by combining historical climate characteristics and historical outdoor production characteristics. The third risk characteristic correlation matrix between historical climate characteristics and historical outdoor production characteristics was then analyzed and constructed through the third multiple regression analysis model.

[0168] In this implementation, the data first needs to be acquired from multiple data sources, including government meteorological departments, geological exploration institutions, and engineering production record databases. By writing web crawler programs, relevant data can be automatically extracted from these data sources. For example, using Python's BeautifulSoup library and Scrapy framework, historical climate data from web pages can be effectively scraped, including information such as temperature, air pressure, precipitation, wind speed, humidity, evaporation, solar radiation, and solar radiation intensity. Geological environmental data can be extracted from geological survey reports and geological exploration data, including information such as soil type, geological structure, and groundwater level. Outdoor production operation data can be obtained from engineering project management systems, including production progress, production processes, and equipment usage.

[0169] After data crawling is complete, preprocessing is required. Preprocessing steps include data cleaning, data format conversion, and data standardization. Data cleaning removes noise and outliers, such as deleting missing values ​​and correcting erroneous records. Data format conversion transforms data from different sources into a unified format for subsequent analysis. Data standardization normalizes data of different dimensions, allowing for comparison and analysis on the same scale. The Z-score standardization method can be used, subtracting the mean from each feature's data and dividing by the standard deviation to ensure it conforms to a standard normal distribution. These preprocessing steps ensure the quality and consistency of historical climate and environmental data, historical geological and environmental data, and historical outdoor production and operation data, laying a solid foundation for subsequent feature extraction and model building.

[0170] Extracting features from preprocessed historical data is a crucial step in data analysis. First, climate features are extracted from historical climate and environmental data. These features can include annual average temperature, annual precipitation, and the frequency of extreme weather events. Statistical analysis methods, such as calculating the mean, variance, and extreme values, can be used to obtain these climate features. Next, geological features are extracted from historical geological environmental data. These features can include the distribution of soil types, the types and distribution of geological structures, and changes in groundwater levels. Spatial analysis methods for geological data, such as geological profile analysis and geological model construction, can be used to extract these geological features. Then, production features are extracted from historical outdoor production and operation data. These features can include production progress, production processes, equipment usage, and accident rates. Statistical analysis of production record data can yield these production features. Through these feature extraction steps, complex raw data can be transformed into easily analyzable and understandable feature data. This feature data provides the necessary input for the subsequent construction of multiple regression analysis models.

[0171] The purpose of constructing the first multiple regression analysis model is to analyze the relationship between historical climate characteristics and historical geological characteristics, and to build a risk characteristic correlation matrix between them. First, the extracted historical climate characteristics and historical geological characteristics are needed as input data. A multiple regression analysis model is a statistical method used to study the linear relationship between multiple independent variables and a dependent variable. Here, historical climate characteristics can be used as independent variables, and historical geological characteristics as dependent variables. The specific steps include: First, storing the historical climate characteristic and historical geological characteristic data in matrices X and Y, respectively. Then, using a linear regression model to fit the data, the regression coefficients are obtained. The regression coefficients reflect the degree of influence of each climate characteristic on the geological characteristic. By fitting the model, a regression coefficient matrix can be obtained, which reflects the degree of influence of each climate characteristic on each geological characteristic. Organizing these regression coefficients into a correlation matrix constitutes the first risk characteristic correlation matrix. This matrix can help analyze the potential impacts of climate change on the geological environment, providing a scientific basis for risk assessment and management.

[0172] The purpose of constructing the second multiple regression analysis model is to analyze the relationship between historical geological features and historical outdoor production features, and to build a risk feature correlation matrix between them. Similar to the previous process, historical geological features are used as independent variables, and historical outdoor production features are used as dependent variables. The steps for constructing the multiple regression analysis model are also similar to those described above. First, the data on historical geological features and historical outdoor production features are stored in matrices X and Y, respectively. Then, a linear regression model is used to fit the data, obtaining regression coefficients. The regression coefficients reflect the degree of influence of each geological feature on the production feature. By fitting the model, a regression coefficient matrix can be obtained, which reflects the degree of influence of each geological feature on each production feature. These regression coefficients are organized into a correlation matrix, which is the second risk feature correlation matrix. This matrix can help analyze the potential impact of the geological environment on the production process, providing a scientific basis for production risk assessment and management.

[0173] Matrix fusion combines the first and second risk characteristic correlation matrices to obtain a comprehensive risk characteristic correlation matrix. First, it's necessary to ensure that the two matrices have consistent dimensions, meaning their rows and columns represent the same features. Matrix fusion integrates the information from the two matrices to obtain a more comprehensive risk characteristic correlation matrix. This fused matrix can reflect the complex relationships between climatic, geological, and production characteristics, providing a more comprehensive basis for risk assessment and management.

[0174] The purpose of constructing the third multiple regression analysis model is to analyze the relationship between historical climate characteristics and historical outdoor production characteristics, and to build a risk characteristic correlation matrix between them. First, the extracted historical climate characteristics and historical outdoor production characteristics are used as input data. Similar to the previous steps, historical climate characteristics are used as independent variables, and historical outdoor production characteristics as dependent variables. The construction steps of the multiple regression analysis model are similar to those before. First, the historical climate characteristic and historical outdoor production characteristic data are stored in matrices X and Y, respectively. Then, a linear regression model is used to fit the data to obtain regression coefficients. The regression coefficients reflect the degree of influence of each climate characteristic on the production characteristic. By fitting the model, a regression coefficient matrix can be obtained, which reflects the degree of influence of each climate characteristic on each production characteristic. These regression coefficients are organized into a correlation matrix, which is the third risk characteristic correlation matrix. This matrix can help analyze the potential impact of climate change on the production process, providing a scientific basis for production risk assessment and management.

[0175] In one embodiment, the environmental data includes climate environmental data and geological environmental data, referring to... Figure 3 Step S103 specifically includes the following steps:

[0176] Preprocessing climate and environmental data, geological environmental data, and outdoor production and operation data;

[0177] The target climate characteristics, target geological characteristics, and target outdoor production characteristics are extracted from climate environment data, geological environment data, and outdoor production operation data, respectively.

[0178] The target climate features, target geological features, and target outdoor production features are uniformly projected to the same target feature space through a preset feature transformation function, and corresponding target climate feature nodes, target geological feature nodes, and target outdoor production feature nodes are generated in the target feature space respectively.

[0179] Based on the fusion risk feature correlation matrix, the first correlation node edge between the target geological feature node and the target outdoor production feature node is generated in the target feature space;

[0180] Based on the third risk feature correlation matrix, a second correlation node edge is generated between the target climate node and the target outdoor production feature node in the target feature space, resulting in a multidimensional data graph network.

[0181] In this implementation, the preprocessing of climate environment data, geological environment data, and outdoor production operation data first requires cleaning, standardization, and normalization. Data cleaning aims to remove noise and outliers, ensuring data accuracy and consistency. Statistical analysis methods can be used to identify and handle outliers, such as using box plots. Standardization involves converting data with different units and dimensions to the same scale for subsequent analysis and processing. This can be achieved using Z-score normalization, which subtracts the mean from each data point and divides by the standard deviation. Normalization scales the data to a specific range (e.g., 0 to 1), which can be achieved using min-max normalization, subtracting the minimum value from each data point and dividing by the difference between the maximum and minimum values. After these preprocessing steps, the climate environment data, geological environment data, and outdoor production operation data become more standardized and consistent, laying a solid foundation for subsequent data analysis and feature extraction.

[0182] In extracting target climate features, target geological features, and target outdoor production features from climate and environmental data, geological environmental data, and outdoor production operation data, it is necessary to first identify the most representative and relevant features in each type of data. For climate and environmental data, target climate features that can be extracted include temperature, humidity, precipitation, and wind speed. These features can be extracted using time series analysis and statistical methods, such as using moving averages and smoothing techniques to eliminate short-term fluctuations and extract long-term trend features. For geological environmental data, target geological features that can be extracted include soil type, geological structure, and groundwater level. These features can be extracted and analyzed using geological exploration and geophysical measurement data. For outdoor production operation data, target outdoor production features that can be extracted include production progress, equipment status, and the number of production personnel. These features can be extracted and analyzed using real-time monitoring data and production logs from the production site. The target features extracted using the above methods can comprehensively reflect the actual situation of climate, geology, and production, providing rich information for subsequent feature transformation and analysis.

[0183] In the process of uniformly projecting target climate features, target geological features, and target outdoor production features into the same target feature space using a pre-defined feature transformation function, it is necessary to design and apply specific feature transformation functions to ensure that different types of features can be compared and analyzed in the same feature space. Feature transformation functions can be implemented using linear transformations, nonlinear transformations, or deep learning models. Linear transformations can be achieved through matrix multiplication, for example, multiplying the feature vector with the transformation matrix to obtain the projected feature vector. Nonlinear transformations can be achieved through kernel functions, such as using a Gaussian kernel to map the feature vector to a high-dimensional space. Deep learning models can learn feature transformation functions by training neural networks, for example, using an autoencoder to encode the input features into a low-dimensional representation. In the uniformly projected target feature space, corresponding target climate feature nodes, target geological feature nodes, and target outdoor production feature nodes can be generated. These nodes have the same dimension and scale in the feature space, facilitating subsequent association analysis and graph network construction.

[0184] In the process of generating the first associated node edges between target geological feature nodes and target outdoor production feature nodes in the target feature space based on the fused risk feature correlation matrix, it is necessary to first construct the fused risk feature correlation matrix. This matrix can be generated by calculating the correlation or similarity between the target geological features and the target outdoor production features. The correlation can be calculated using the Pearson Correlation Coefficient, which is the ratio of the covariance to the standard deviation of two feature vectors. The similarity can be calculated using Cosine Similarity, which is the ratio of the dot product of two feature vectors to their magnitude. The correlation or similarity matrix obtained by calculation can determine the correlation strength between the target geological feature nodes and the target outdoor production feature nodes. Based on the magnitude of the correlation strength, the first associated node edges can be generated in the target feature space. These edges represent the potential risk correlation between geological features and production features. In this way, the impact of the geological environment on production activities can be identified and analyzed, providing an important basis for production risk management.

[0185] In the process of generating second-level association nodes between target climate nodes and target outdoor production feature nodes in the target feature space based on the third-level risk feature association matrix, it is necessary to first construct the third-level risk feature association matrix. This matrix can be generated by calculating the correlation or similarity between the target climate features and the target outdoor production features. The correlation can be calculated using the Spearman Rank Correlation Coefficient, which is the ratio of the difference in rank of two feature vectors to their standard deviation. The similarity can be calculated using the Jaccard Similarity Coefficient, which is the ratio of the intersection to the union of two feature sets. The correlation or similarity matrix obtained from the calculation can determine the strength of the association between the target climate feature nodes and the target outdoor production feature nodes. Based on the magnitude of the association strength, second-level association nodes can be generated in the target feature space. These edges represent the potential risk associations between climate features and production features. In this way, the impact of the climate environment on production activities can be identified and analyzed, providing an important basis for production risk management.

[0186] Ultimately, the multidimensional data graph network generated through the above steps unifies climate, geological, and production characteristics into a comprehensive feature space, and reflects the risk relationships between these characteristics through the edges of associated nodes. This multidimensional data graph network not only comprehensively reflects the actual conditions of climate, geology, and production, but also enables in-depth risk analysis and prediction through graph structure analysis methods (such as graph convolutional networks). In this way, a scientific basis can be provided for risk management and decision-making in production projects, improving production safety and efficiency.

[0187] In one embodiment, step S104 specifically includes the following steps:

[0188] According to the generation order of the target outdoor production feature nodes in the multidimensional data graph network, each target outdoor production feature node is marked as the central target node in turn, until all target outdoor production feature nodes are marked as the central target node once.

[0189] Whenever a target outdoor production feature node is marked as a central target node, the node risk correlation degree calculation step and the node community density calculation step are performed on the central target node to obtain the node risk correlation degree and node community density of the central target node.

[0190] The production risk correlation value is calculated by combining the risk correlation degree of all nodes and the tightness of the node community, and the production risk correlation value is used as the production risk correlation feature between environmental data and outdoor production operation data.

[0191] The outdoor safety risk level of the outdoor production area is determined based on the characteristics of production risk association and the preset risk level rules.

[0192] In this embodiment, the generation order of target outdoor production feature nodes in the multidimensional data graph network can be determined based on timestamps or other specific rules. First, each target outdoor production feature node is traversed sequentially according to its generation order, and the currently traversed node is marked as the central target node. This ensures that each node is marked exactly once during the traversal, avoiding duplicate marking or omissions. Whenever a target outdoor production feature node is marked as the central target node, a node risk correlation calculation step and a node community density calculation step are performed on the central target node to obtain its node risk correlation and node community density. The node risk correlation calculation step aims to assess the strength of the risk correlation between the central target node and other nodes. This can be achieved by calculating the edge weights or correlation coefficients between the central target node and other nodes.

[0193] The node community density calculation step aims to assess the degree of closeness between the central target node and its first-order neighbor nodes. In this embodiment, the formula for calculating node community density is as follows:

[0194]

[0195] In the formula: P i V represents the i-th central target node. i The node community density, M represents the total number of nodes and edges in the multidimensional data graph network, d(V i ) represents the central target node V i The degree of the node.

[0196] The production risk correlation value is calculated by combining the risk correlation degree of all nodes and the density of node communities, and this value is used as the production risk correlation feature between environmental data and outdoor production operation data. In this embodiment, the formula for calculating the production risk correlation value is as follows:

[0197]

[0198] In the formula: Y represents the production risk correlation value, n represents the number of nodes of the target outdoor production characteristic node, and δ represents the correlation value weight parameter.

[0199] The production risk correlation value reflects the overall risk correlation characteristics between environmental data and outdoor production operation data, and can serve as an important indicator for production risk assessment. In this way, the complex relationships in a multidimensional data graph network can be transformed into a single risk characteristic value, facilitating subsequent risk level assessment.

[0200] The outdoor safety risk level of outdoor production areas is determined based on the characteristics of production risk correlation and pre-defined risk level rules. These risk level rules, developed based on production safety standards and practical experience, typically include several risk levels (e.g., low risk, moderate risk, significant risk, major risk) and their corresponding threshold ranges. First, the production risk correlation value is compared with the pre-defined risk level thresholds to determine its corresponding risk level. For example, if the production risk correlation value is less than a certain threshold, it is classified as low risk; if it falls between two thresholds, it is classified as moderate risk; and if it exceeds a certain threshold, it is classified as major risk. This method transforms complex production risk correlation characteristics into simple and clear risk levels, providing an intuitive reference for production safety management. Finally, through these steps, the safety risk level of outdoor production areas can be systematically assessed, helping production managers identify potential risks, develop corresponding prevention and response measures, and improve production safety and efficiency.

[0201] In one implementation, the node risk correlation calculation step includes the following steps:

[0202] The geological node correlation degree between the central target node and each adjacent target geological feature node is calculated by integrating the risk feature correlation matrix.

[0203] Based on the first associated node edge, count the number of first node edges between adjacent target geological feature nodes and all other target outdoor production feature nodes;

[0204] The geological node degree of adjacent target geological feature nodes is calculated using the edges of the first associated node;

[0205] The geological node risk correlation degree of the central target node is calculated by combining the geological node correlation degree, the number of edges of the first node, and the degree of the geological node.

[0206] The climate node correlation degree between the central target node and each adjacent target climate feature node is calculated using the third risk feature correlation matrix.

[0207] The climate node degree of adjacent target climate feature nodes is calculated using the edges of the second associated node;

[0208] The climate node risk correlation degree of the central target node is calculated by combining the climate node correlation degree and the climate node degree.

[0209] The node risk correlation of the central target node is obtained by summing the risk correlation of the geological node and the risk correlation of the climate node.

[0210] In this embodiment, the formula for calculating the risk correlation degree of geological nodes is as follows:

[0211]

[0212] In the formula: V represents the i-th central target node. i The geological node risk correlation degree, where m represents the central target node V. i Adjacent target geological feature nodes The number of nodes, Represents the correlation matrix A of integrated risk characteristics R The matrix element corresponding to the i-th row and j-th column, ξ(·,·) represents the correlation calculation function, γ represents the geological weight parameter, and L i，j Represents the central target node V i The j-th adjacent target geological feature node The number of edges to the first node. Indicates adjacent target geological feature nodes Geological node degree;

[0213] The formula for calculating the correlation between climate node risks is as follows:

[0214]

[0215] In the formula: V represents the i-th central target node. i Climate node risk correlation, t represents the central target node V i Adjacent target climate feature nodes The number of nodes, Represents the third risk characteristic correlation matrix A 3 In the matrix, the element corresponding to the i-th row and k-th column is ξ(·,·), which represents the correlation calculation function, and η represents the climate weight parameter. Represents the k-th adjacent target geological feature node The degree of the geological nodes.

[0216] In one embodiment, the indoor production operation data includes indoor production area drawing data and indoor image data. The indoor production area drawing data pre-marks indoor hazardous areas. Step S105 specifically includes the following steps:

[0217] Based on the drawings of the indoor production area, an indoor engineering BIM model of the indoor production area is generated using BIM technology;

[0218] Based on the indoor hazardous areas pre-marked in the indoor production area drawings, the corresponding model hazardous areas are generated in the indoor engineering BIM model;

[0219] The percentage of hazardous areas in the BIM model of indoor engineering projects according to statistical models;

[0220] Image recognition technology is used to identify indoor risk points in indoor image data and to count the number of hazard sources at these indoor risk points.

[0221] The indoor safety risk level of the indoor production area is determined by combining the area proportion and the number of hazardous sources.

[0222] In this implementation, the indoor production area drawing data typically includes detailed information such as building structure, room layout, and pipeline arrangement. This drawing data can be 2D drawings in CAD format or other digital design files. Using BIM (Building Information Modeling) technology, this 2D drawing data is converted into a 3D digital model. BIM technology integrates the building's geometric information, physical characteristics, and functional characteristics to generate a highly accurate 3D model. In practice, the 2D drawing data is first imported into BIM software (such as Revit or Archicad), and then the 3D model is gradually constructed based on the dimensions, locations, and other information in the drawing data. During this process, attention must be paid to the accuracy and detail of each component to ensure that the generated BIM model is consistent with the actual building.

[0223] Indoor production area drawings typically mark potential hazardous areas, such as high-temperature areas, flammable and explosive areas, and electrical equipment areas. This hazardous area information is imported into the indoor engineering BIM model, generating corresponding model hazardous zones. In practice, the annotation and labeling functions of BIM software can be used to attach hazardous area information to the corresponding model components. For example, a certain area can be marked as a high-temperature area in the BIM model, and corresponding warning signs and color codes can be set. This allows for a clear visual representation of the location and extent of each hazardous area in the 3D model.

[0224] Next, we will calculate the proportion of hazardous areas in the BIM model of the interior project. This proportion is a crucial indicator for assessing the percentage of hazardous areas within the overall interior project. In practice, the measurement and calculation functions of BIM software can be used to calculate the area or volume of hazardous areas in the model, and then compared with the total area or volume of the entire interior project BIM model to determine the proportion of hazardous areas. This method quantifies the proportion of hazardous areas within the entire interior project, providing a quantitative basis for subsequent risk assessment. The statistical results of the proportion can visually reflect the distribution and density of hazardous areas.

[0225] Image recognition technology is used to identify indoor risk points in indoor image data. Indoor risk points specifically refer to potential hazards within a building, and the number of these hazards is counted. Image recognition technology utilizes computer vision and machine learning algorithms to identify and classify objects from images. In practice, indoor image data can be acquired using cameras or other image acquisition devices. Then, image recognition algorithms (such as convolutional neural networks, CNNs) are used to process and analyze the images to identify hazards. For example, an image recognition model can be trained to identify hazards such as flammable materials, chemicals, and electrical equipment in images. After identifying the hazards, their numbers can be counted. In this way, the number of indoor risk points can be automatically identified and counted, providing data support for subsequent risk assessments. The application of image recognition technology can significantly improve the efficiency and accuracy of hazard identification, reducing the workload and errors associated with manual identification.

[0226] The indoor safety risk level of an indoor production area is determined by combining the area's proportion and the number of hazardous sources. The indoor safety risk level is a crucial indicator for comprehensively assessing the potential risks of an indoor production area. In practice, the risk level of the indoor production area can be determined by comprehensively calculating the area's proportion and the number of hazardous sources according to preset risk level rules. For example, preset risk level rules may include several levels (such as low risk, general risk, significant risk, and major risk) and their corresponding threshold ranges. First, the area's proportion and the number of hazardous sources are standardized to ensure their values ​​are between 0 and 1. Then, according to preset weighting parameters, the area's proportion and the number of hazardous sources are weighted and averaged to obtain a comprehensive risk score.

[0227] The present invention also discloses a standardized management system for water conservancy projects, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the standardized management method for water conservancy projects described in any of the above embodiments.

[0228] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it in this regard.

[0229] The memory can be an internal storage unit of a computer device, such as a hard disk or RAM, or an external storage device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) provided on the computer device. Furthermore, the memory can be a combination of internal storage units and external storage devices of a computer device. The memory is used to store computer programs and other programs and data required by the computer device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0230] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of protection of this application is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0231] One or more embodiments in this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of this application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments in this application should be included within the protection scope of this application.

Claims

1. A standardized management method applied to water conservancy projects, characterized in that, The method comprises the following steps: dividing a production area of a target water conservancy project into a plurality of unit grids according to an engineering scope of the target water conservancy project; for each unit grid, collecting environmental data and outdoor production operation data of an outdoor production area in the unit grid, and obtaining indoor production operation data of an indoor production area in the unit grid; constructing a multi-dimensional data graph network in combination with the environmental data and the outdoor production operation data; in an order of generation of target outdoor production characteristic nodes in the multi-dimensional data graph network, sequentially marking each target outdoor production characteristic node as a central target node until all target outdoor production characteristic nodes are marked as and only as the central target node once; whenever a target outdoor production characteristic node is marked as the central target node, performing a node risk correlation degree calculation step and a node community tightness calculation step on the central target node to obtain a node risk correlation degree and a node community tightness of the central target node; combining all node risk correlation degrees and node community tightnesses to calculate a production risk correlation value, and taking the production risk correlation value as a production risk correlation feature between the environmental data and the outdoor production operation data; determining an outdoor safety risk level of the outdoor production area based on the production risk correlation feature and based on a preset risk level rule; determining an indoor safety risk level of the indoor production area in combination with BIM technology and image recognition technology and based on the indoor production operation data; calculating a grid production safety risk level of the unit grid according to the outdoor safety risk level and the indoor safety risk level; summarizing the grid production safety risk levels of all unit grids and performing a weighted calculation to obtain an engineering production safety risk level of the target water conservancy project; determining a risk standardization management strategy corresponding to the target water conservancy project based on the engineering production safety risk level.

2. The standardized management method for hydraulic engineering according to claim 1, characterized in that, Before the step of constructing a multi-dimensional data graph network in combination with the environmental data and the outdoor production operation data, the method further comprises the following steps: crawling historical climate environmental data, historical geological environmental data and historical outdoor production operation data of a same type of project as the target water conservancy project, and preprocessing the historical climate environmental data, the historical geological environmental data and the historical outdoor production operation data; extracting historical climate features, historical geological features and historical outdoor production features from the historical climate environmental data, the historical geological environmental data and the historical outdoor production operation data, respectively; constructing a first multiple regression analysis model in combination with the historical climate features and the historical geological features, and analyzing and constructing a first risk feature correlation matrix between the historical climate features and the historical geological features by using the first multiple regression analysis model; constructing a second multiple regression analysis model in combination with the historical geological features and the historical outdoor production features, and analyzing and constructing a second risk feature correlation matrix between the historical geological features and the historical outdoor production features by using the second multiple regression analysis model; matrix fusion is performed on the first risk feature association matrix and the second risk feature association matrix based on the historical geological features to obtain a fused risk feature association matrix; a third risk feature association matrix between the historical climate features and the historical outdoor production features is analyzed and constructed through a third multiple regression analysis model constructed in combination with the historical climate features and the historical outdoor production features.

3. The standardized management method for hydraulic works according to claim 2, characterized in that, The environmental data includes climate environmental data and geological environmental data, and the step of constructing a multidimensional data graph network in combination with the environmental data and the outdoor production operation data includes the following steps: The climate environmental data, the geological environmental data, and the outdoor production operation data are preprocessed. Target climate features, target geological features, and target outdoor production features are extracted from the climate environmental data, the geological environmental data, and the outdoor production operation data respectively. The target climate features, the target geological features, and the target outdoor production features are uniformly projected to the same target feature space through a preset feature conversion function, and corresponding target climate feature nodes, target geological feature nodes, and target outdoor production feature nodes are generated in the target feature space respectively. A first associated node edge between the target geological feature nodes and the target outdoor production feature nodes in the target feature space is generated based on the fused risk feature association matrix. A second associated node edge between the target climate feature nodes and the target outdoor production feature nodes in the target feature space is generated based on the third risk feature association matrix, to obtain a multidimensional data graph network.

4. The standardized management method for waterworks according to claim 1, characterized in that, The node risk association degree calculation step includes the following steps: Geological node association degrees between the center target node and each adjacent target geological feature node are calculated through the fused risk feature association matrix. The number of first node edges between the adjacent target geological feature nodes and all other target outdoor production feature nodes is counted based on the first associated node edge. The geological node degree of the adjacent target geological feature node is calculated using the first associated node edge. The geological node risk association degree of the center target node is calculated in combination with the geological node association degree, the number of first node edges, and the geological node degree. Climate node association degrees between the center target node and each adjacent target climate feature node are calculated through the third risk feature association matrix. The climate node degree of the adjacent target climate feature node is calculated using the second associated node edge. The climate node risk association degree of the center target node is calculated in combination with the climate node association degree and the climate node degree. The sum of the geological node risk association degree and the climate node risk association degree is calculated to obtain the node risk association degree of the center target node.

5. The standardized management method for hydraulic works according to claim 4, characterized in that, The calculation formula of the geological node risk association degree is as follows: ； In the formula: Indicates the first The central target node The risk correlation of the geological nodes, Indicates the central target node Adjacent target geological feature nodes The number of nodes, Represents the correlation matrix of the fused risk features The Middle Line 1 The matrix elements corresponding to the columns, This represents the function for calculating the correlation degree. Represents geological weight parameters, Indicates the central target node The The adjacent target geological feature nodes The number of edges of the first node. Indicates the adjacent target geological feature nodes The degree of the geological nodes; The calculation formula of the climate node risk association degree is as follows: ； In the formula: represents the climate node risk correlation degree of the i-th central target node represents the number of adjacent target climate feature nodes of the central target node represents the matrix element corresponding to the i-th row and the j-th column in the third risk feature correlation matrix represents a correlation degree calculation function, represents a climate weight parameter, represents the geological node degree of the i-th adjacent target geological feature node ​​​​​​​​​ 6. The standardized management method for hydraulic works according to claim 5, characterized in that, The calculation formula of the node community tightness is as follows: ； wherein: denotes the node community density of the central target node , denotes the total number of node edges in the multidimensional data graph network, denotes the node degree of the central target node 7. The standardized management method for hydraulic works according to claim 6, characterized in that, The calculation formula of the production risk association value is as follows: ； In the formula: represents the production risk correlation value, represents the node number of the target outdoor production feature node, represents the correlation value weight parameter.

8. The standardized management method for hydraulic works according to claim 1, characterized in that, The indoor production operation data comprises indoor production area drawing data and indoor image data of the indoor production area, the indoor dangerous area is pre-labeled in the indoor production area drawing data, and the indoor safety risk level of the indoor production area is determined based on the indoor production operation data by combining the BIM technology and the image recognition technology. An indoor engineering BIM model of the indoor production area is generated based on the indoor production area drawing data and by using the BIM technology. A corresponding model dangerous area is generated in the indoor engineering BIM model according to the indoor dangerous area pre-labeled in the indoor production area drawing data. The area proportion of the model dangerous area in the indoor engineering BIM model is counted. An indoor risk point in the indoor image data is recognized by using the image recognition technology, and the number of dangerous sources of the indoor risk point is counted. The indoor safety risk level of the indoor production area is determined by combining the area proportion and the number of dangerous sources.

9. A standardized management system applied to water conservancy projects, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the standardized management method applied to the water conservancy project as claimed in any one of claims 1 to 8.

Images