Oil and gas field station risk prediction method and device

Abstract

The application discloses an oil and gas field station risk prediction method and device, wherein the method comprises the following steps: based on the historical accident database of the oil and gas field station, risk factors and the correlation between the risk factors are extracted to form risk factors; the risk factors are abstracted as network nodes, the evolution path of the risk factors is abstracted as the directed edge between the nodes, a directed and weightless network is constructed, the topological structure of the directed and weightless network is generated as the risk prediction network model of the oil and gas field station; the risk prediction network model of the oil and gas field station is subjected to multidimensional analysis to determine the topological structure characteristics of the risk prediction network model of the oil and gas field station; based on the topological structure characteristics of the risk prediction network model, the risk prediction network model outputs the risk factors of the to-be-tested oil and gas field station event according to the input characteristic data, and generates an early warning prompt. The application can improve the accuracy of the oil and gas field station accident prediction and improve the effectiveness of the oil and gas field station safety warning.

Description

Technical Field

[0001] This invention relates to the field of oil and gas field station accident prediction technology, and in particular to oil and gas field station risk prediction methods and devices. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] In the management of oil and gas field stations, accidents often occur due to a variety of factors. Past accidents have resulted in multifaceted losses due to the inability to prevent impending incidents. Currently, relying solely on experience to analyze accident factors cannot meet the accuracy requirements of actual accident prediction. The overly simplistic analysis of factors in existing technologies leads to inaccurate accident predictions at oil and gas field stations, hindering effective safety early warning systems. Summary of the Invention

[0004] This invention provides a risk prediction method for oil and gas field stations to improve the accuracy of accident prediction and the effectiveness of safety early warning for oil and gas field stations. The method includes:

[0005] Based on the historical accident database of oil and gas field stations, risk factors and the correlation between risk factors are extracted to form risk factors; risk factors include people, materials, technology, management, and environment;

[0006] Risk factors are abstracted as network nodes, and the evolution path of risk factors is abstracted as directed edges between nodes, thus constructing a directed unweighted network.

[0007] Based on the constructed directed unweighted network, the topology of the directed unweighted network is generated as a risk prediction network model for oil and gas field stations.

[0008] A multi-dimensional analysis was conducted on the risk prediction network model of oil and gas field stations: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topological characteristics of the risk prediction network model of oil and gas field stations.

[0009] The characteristic data of the oil and gas field station event to be tested is input into the risk prediction network model of the oil and gas field station. Based on the topological characteristics of the risk prediction network model, the risk prediction network model outputs the risk factors of the oil and gas field station event to be tested according to the input characteristic data, determines whether the output risk factors exceed the preset threshold, and generates an early warning prompt.

[0010] This invention also provides an oil and gas field station risk prediction device to improve the accuracy of oil and gas field station accident prediction and the effectiveness of oil and gas field station safety early warning. The device includes:

[0011] The risk factor formation module is used to extract risk factors and the relationships between them based on the historical accident database of oil and gas field stations, and form risk factors; risk factors include people, materials, technology, management, and environment;

[0012] The directed unweighted network construction module is used to abstract risk factors into network nodes and the evolution path of risk factors into directed edges between nodes to construct a directed unweighted network.

[0013] The risk prediction network model construction module for oil and gas field stations is used to generate the topology of the directed unweighted network as the risk prediction network model for oil and gas field stations based on the constructed directed unweighted network.

[0014] The topology characteristic analysis module is used to perform multi-dimensional analysis on the risk prediction network model of oil and gas field stations: network index analysis, cohesive subgroup analysis, and core node and edge node analysis, to determine the topology characteristics of the risk prediction network model of oil and gas field stations.

[0015] The early warning module is used to input the characteristic data of the oil and gas field station event to be tested into the risk prediction network model of the oil and gas field station. Based on the topological characteristics of the risk prediction network model, the risk prediction network model outputs the risk factors of the oil and gas field station event to be tested according to the input characteristic data, determines whether the output risk factors exceed the preset threshold, and generates an early warning.

[0016] This invention also provides a computer device, 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 above-described oil and gas field station risk prediction method.

[0017] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described oil and gas field station risk prediction method.

[0018] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described oil and gas field station risk prediction method.

[0019] In this embodiment of the invention, risk factors and their interrelationships are extracted from the historical accident database of oil and gas field stations to form risk factors. Risk factors include people, materials, technology, management, and environment. Risk factors are abstracted as network nodes, and their evolution paths are abstracted as directed edges between nodes, constructing a directed unweighted network. Based on the constructed directed unweighted network, its topology is generated as a risk prediction network model for the oil and gas field station. The risk prediction network model is subjected to multi-dimensional analysis: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topological characteristics of the risk prediction network model. Feature data of the oil and gas field station event to be measured is input into the risk prediction network model. Based on the topological characteristics of the risk prediction network model, the model outputs the risk factors of the oil and gas field station event according to the input feature data, determines whether the output risk factors exceed a preset threshold, and generates an early warning. In the above process, the embodiments of the present invention construct a risk prediction network model for oil and gas field stations by studying the evolution path of risk factors. By analyzing the model in multiple dimensions, the topological characteristics of the model are determined, which solves the problems of overly singular analysis factors and inaccurate analysis of topological characteristics in the prior art. This improves the accuracy of accident prediction for oil and gas field stations and enhances the effectiveness of safety early warning for oil and gas field stations. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0021] Figure 1 This is a flowchart of the oil and gas field station risk prediction method in an embodiment of the present invention;

[0022] Figure 2 This is the topology of the risk prediction network model for oil and gas field stations in this embodiment of the invention;

[0023] Figure 3 This is a diagram showing the results of agglomerative subgroup analysis in an embodiment of the present invention;

[0024] Figure 4 This is a diagram showing the results of the analysis of core nodes and edge nodes in an embodiment of the present invention;

[0025] Figure 5 This is a flowchart illustrating the generation of early warning prompts in an embodiment of the present invention;

[0026] Figure 6 This is a specific early warning flowchart in an embodiment of the present invention;

[0027] Figure 7 This is a schematic diagram of the oil and gas field station risk prediction device in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0029] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0030] Figure 1 This is a flowchart of an oil and gas field station risk prediction method according to an embodiment of the present invention. The method includes:

[0031] Step 101: Based on the historical accident database of oil and gas field stations, extract risk factors and the correlation between risk factors to form risk factors; risk factors include people, materials, technology, management, and environment;

[0032] Step 102: Abstract the risk factors into network nodes, and the evolution path of the risk factors into directed edges between nodes to construct a directed unweighted network.

[0033] Step 103: Based on the constructed directed unweighted network, generate the topology of the directed unweighted network as a risk prediction network model for oil and gas field stations.

[0034] Step 104: Conduct multi-dimensional analysis of the risk prediction network model of oil and gas field stations: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis to determine the topological characteristics of the risk prediction network model of oil and gas field stations.

[0035] Step 105: Input the feature data of the oil and gas field station event to be tested into the risk prediction network model of the oil and gas field station. Based on the topological characteristics of the risk prediction network model, the risk prediction network model outputs the risk factors of the oil and gas field station event to be tested according to the input feature data, determines whether the output risk factors exceed the preset threshold, and generates an early warning prompt.

[0036] Each step is explained in detail below.

[0037] In step 101, risk factors and their relationships are extracted from the historical accident database of oil and gas field stations to form risk factors; risk factors include people, materials, technology, management, and environment.

[0038] In a specific embodiment, the historical accident database of oil and gas field stations includes historical accidents from other chemical plants, refineries, and petrochemical plants. The collected accidents were categorized and summarized, and commonalities among the accident cases were compared and identified. Cause analysis was performed on the collected accidents, analyzing and organizing the factors leading to the accidents from four aspects: personnel, machinery, environment, and management. Based on the accident occurrence process in each case, various risk factors were identified. On this basis, the chronological order of the occurrence of each hazard point was determined, and these hazard points were linked together to form an accident chain, thereby demonstrating the risk evolution process.

[0039] In step 102, risk factors are abstracted as network nodes, and the evolution path of risk factors is abstracted as directed edges between nodes to construct a directed unweighted network. In step 103, based on the constructed directed unweighted network, the topology of the directed unweighted network is generated as a risk prediction network model for oil and gas field stations.

[0040] Figure 2 This invention presents the topology of a risk prediction network model for oil and gas field stations in an embodiment of the invention. Specifically, the model is established based on complex network theory. Oil and gas field station operations are complex; therefore, complex network methods are used to visualize the intricate risk network structure and analyze the characteristics of this complex system to provide practical safety management recommendations. Since complex networks are composed of multiple nodes and intricate edge relationships, and the evolution of risk accidents at oil and gas field stations exhibits significant complex network characteristics, network nodes represent disaster-causing crisis events / elements in the oil and gas field station, and edges represent the evolutionary relationships of dangerous events, thus constructing a risk prediction network model for the oil and gas field station. Risk factors are abstracted as network nodes, and the evolution paths of risk factors are abstracted as directed edges between nodes, integrating all accident chains into a single network.

[0041] After the incident chain fusion is completed, the compiled incident chains are statistically analyzed to form an initial data matrix, which statistically identifies the relationships between 76 risk factors. The initial data is then binarized in Ucinet software, and the processed data packets are used in Netdraw software to construct and visualize a complex network graph. Finally, a directed unweighted network consisting of 76 network nodes and 456 network edges is output. Figure 2 As shown, A6, H2, H5, H10, MC2, M18, and E2-E9 are block nodes, encompassing risk events and risk factors. Table 1 shows the accident risk system for oil and gas field stations.

[0042] Table 1. Accident Risk System for Oil and Gas Field Stations

[0043]

[0044] Continued from Table 1: Accident Risk System of Oil and Gas Field Stations

[0045]

[0046]

[0047] Continued from Table 1: Accident Risk System of Oil and Gas Field Stations

[0048]

[0049]

[0050] In step 104, a multi-dimensional analysis is performed on the risk prediction network model of the oil and gas field station: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topological characteristics of the risk prediction network model of the oil and gas field station.

[0051] In one embodiment, a multi-dimensional analysis is performed on the risk prediction network model of the oil and gas field station: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topological characteristics of the risk prediction network model of the oil and gas field station, including:

[0052] Network metrics analysis is used to analyze the following network metrics: overall network density, network correlation, reciprocity, and the average shortest evolution path of risk factors, in order to determine the network performance of the risk prediction network model.

[0053] Agglomeration subgroup analysis is used to analyze agglomeration subgroups involving risk events and determine the risk clustering characteristics of the risk prediction network model.

[0054] Core node and edge node analysis is used to analyze the connection relationships between core nodes and edge nodes, and between edge nodes and core nodes, to determine the causes of risk factor evolution in the risk prediction network model.

[0055] In a specific embodiment, during the network indicator analysis process, the network indicators obtained after removing the risk factor H8 caused by insufficient professional competence and operational errors of the operators are compared with the network indicators before removing H8, as shown in Table 2 below.

[0056] Table 2 Comparison of Network Indicators

[0057]

[0058] In a specific embodiment, during agglomerative subgroup analysis, when a complex network contains an agglomerative subgroup with relatively high network density, it indicates that the connections between these nodes are very close, and information is frequently exchanged. That is, an agglomerative subgroup refers to a subset of members with direct, close, and frequent connections. In a complex network structure, it manifests as a small spatial set of several closely connected and geographically proximate groups. It can reveal the state and characteristics of the internal structure of a complex network, thereby allowing for the exploration of the network's evolutionary features, the formation mechanism of these small sets, and the influencing factors of the interactions between these small sets. Figure 3 This is a diagram showing the results of the condensation subgroup analysis in an embodiment of the present invention.

[0059] In a specific embodiment, during the analysis of core nodes and edge nodes, edge nodes are only closely connected to some core nodes, while their connections with other nodes are loose and diffusely distributed. The entire network can be divided into core and edge regions to determine the impact of each node on the overall network. Figure 4 This is a diagram showing the results of the analysis of core nodes and edge nodes in an embodiment of the present invention. Information corresponding to each node number is shown in Table 1.

[0060] In step 105, the feature data of the oil and gas field station event to be tested is input into the risk prediction network model of the oil and gas field station. Based on the topological characteristics of the risk prediction network model, the risk prediction network model outputs the risk factor of the oil and gas field station event to be tested according to the input feature data, determines whether the output risk factor exceeds the preset threshold, and generates an early warning prompt.

[0061] In one embodiment, the risk factors of the oil and gas field site event to be tested are output, and it is determined whether the output risk factors exceed a preset threshold, including:

[0062] When the risk value corresponding to a risk factor exceeds the preset risk threshold range, the corresponding risk factor is identified as an abnormal risk factor, and an early warning is generated.

[0063] Figure 5 This is a flowchart illustrating the generation of early warning prompts in an embodiment of the present invention. In one embodiment, the corresponding risk factor is identified as an abnormal risk factor, and an early warning prompt is generated, including:

[0064] Step 501: Identify the nodes corresponding to the abnormal risk factors and monitor the nodes;

[0065] Step 502: Generate corresponding early warning prompts based on the monitoring results of the nodes.

[0066] Figure 6The following is a specific early warning flowchart in this embodiment of the invention. In this specific embodiment, the early warning process can be subdivided into the following parts: identifying the alarm situation, which means identifying the research object, namely the early warning elements of oil and gas field station accidents; finding the alarm source, which means the cause of the early warning elements, namely the risk factors; analyzing the warning signs, which means analyzing and studying the various risk factors collected to determine whether the risk value meets the early warning conditions; early warning level, which means determining the risk level after the risk value meets the early warning requirements; and eliminating hidden dangers, which means carrying out handling and adjustment for accidents of different risk levels to eliminate the warning hazards.

[0067] This invention also provides an oil and gas field station risk prediction device, as described in the following embodiments. Since the principle behind this device is similar to the oil and gas field station risk prediction method, its implementation can be referenced from the implementation of the oil and gas field station risk prediction method; repeated details will not be elaborated further.

[0068] Figure 7 This is a schematic diagram of an oil and gas field station risk prediction device according to an embodiment of the present invention. The device includes:

[0069] The risk factor formation module 701 is used to extract risk factors and the relationships between risk factors based on the historical accident database of oil and gas field stations, and form risk factors; risk factors include people, materials, technology, management, and environment;

[0070] The directed unweighted network construction module 702 is used to abstract risk factors into network nodes and the evolution path of risk factors into directed edges between nodes to construct a directed unweighted network.

[0071] The risk prediction network model construction module 703 for oil and gas field stations is used to generate the topology of the directed unweighted network as the risk prediction network model for oil and gas field stations based on the constructed directed unweighted network.

[0072] The topology characteristic analysis module 704 is used to perform multi-dimensional analysis on the risk prediction network model of oil and gas field stations: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topology characteristics of the risk prediction network model of oil and gas field stations.

[0073] The early warning module 705 is used to input the feature data of the oil and gas field station event to be tested into the risk prediction network model of the oil and gas field station. Based on the topological characteristics of the risk prediction network model, the risk prediction network model outputs the risk factor of the oil and gas field station event to be tested according to the input feature data, determines whether the output risk factor exceeds the preset threshold, and generates an early warning.

[0074] In one embodiment, the topology characteristic analysis module 704 is specifically used for:

[0075] Network metrics analysis is used to analyze the following network metrics: overall network density, network correlation, reciprocity, and the average shortest evolution path of risk factors, in order to determine the network performance of the risk prediction network model.

[0076] Agglomeration subgroup analysis is used to analyze agglomeration subgroups involving risk events and determine the risk clustering characteristics of the risk prediction network model.

[0077] Core node and edge node analysis is used to analyze the connection relationships between core nodes and edge nodes, and between edge nodes and core nodes, to determine the causes of risk factor evolution in the risk prediction network model.

[0078] In one embodiment, the early warning module 705 is specifically used for:

[0079] When the risk value corresponding to a risk factor exceeds the preset risk threshold range, the corresponding risk factor is identified as an abnormal risk factor, and an early warning is generated.

[0080] In one embodiment, the early warning module 705 is specifically used for:

[0081] Identify the nodes corresponding to abnormal risk factors and monitor these nodes;

[0082] Based on the monitoring results of the nodes, corresponding early warning prompts are generated.

[0083] This invention also provides a computer device, 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 above-described oil and gas field station risk prediction method.

[0084] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described oil and gas field station risk prediction method.

[0085] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described oil and gas field station risk prediction method.

[0086] In this embodiment of the invention, risk factors and their interrelationships are extracted from the historical accident database of oil and gas field stations to form risk factors. Risk factors include people, materials, technology, management, and environment. Risk factors are abstracted as network nodes, and their evolution paths are abstracted as directed edges between nodes, constructing a directed unweighted network. Based on the constructed directed unweighted network, its topology is generated as a risk prediction network model for the oil and gas field station. The risk prediction network model is subjected to multi-dimensional analysis: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topological characteristics of the risk prediction network model. Feature data of the oil and gas field station event to be measured is input into the risk prediction network model. Based on the topological characteristics of the risk prediction network model, the model outputs the risk factors of the oil and gas field station event according to the input feature data, determines whether the output risk factors exceed a preset threshold, and generates an early warning. In the above process, the embodiments of the present invention construct a risk prediction network model for oil and gas field stations by studying the evolution path of risk factors. By analyzing the model in multiple dimensions, the topological characteristics of the model are determined, which solves the problems of overly singular analysis factors and inaccurate analysis of topological characteristics in the prior art. This improves the accuracy of accident prediction for oil and gas field stations and enhances the effectiveness of safety early warning for oil and gas field stations.

[0087] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0091] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting risks at oil and gas field stations, characterized in that, include: Based on the historical accident database of oil and gas field stations, risk factors and the correlation between risk factors are extracted to form risk factors. Risk factors include people, materials, technology, management, and environment; Risk factors are abstracted as network nodes, and the evolution path of risk factors is abstracted as directed edges between nodes, thus constructing a directed unweighted network. Based on the constructed directed unweighted network, the topology of the directed unweighted network is generated as a risk prediction network model for oil and gas field stations. A multi-dimensional analysis was conducted on the risk prediction network model of oil and gas field stations: network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topological characteristics of the risk prediction network model of oil and gas field stations. The characteristic data of the oil and gas field station event to be tested is input into the risk prediction network model of the oil and gas field station. Based on the topological characteristics of the risk prediction network model, the risk prediction network model outputs the risk factors of the oil and gas field station event to be tested according to the input characteristic data, determines whether the output risk factors exceed the preset threshold, and generates an early warning prompt.

2. The method as described in claim 1, characterized in that, A multi-dimensional analysis was conducted on the risk prediction network model of oil and gas field stations, including network index analysis, agglomeration subgroup analysis, and core node and edge node analysis, to determine the topological characteristics of the risk prediction network model of oil and gas field stations, including: Network metrics analysis is used to analyze the following network metrics: overall network density, network correlation, reciprocity, and the average shortest evolution path of risk factors, in order to determine the network performance of the risk prediction network model. Agglomeration subgroup analysis is used to analyze agglomeration subgroups involving risk events and determine the risk clustering characteristics of the risk prediction network model. Core node and edge node analysis is used to analyze the connection relationships between core nodes and edge nodes, and between edge nodes and core nodes, to determine the causes of risk factor evolution in the risk prediction network model.

3. The method as described in claim 1, characterized in that, Output the risk factors for the oil and gas field site events to be tested, and determine whether the output risk factors exceed the preset thresholds, including: When the risk value corresponding to a risk factor exceeds the preset risk threshold range, the corresponding risk factor is identified as an abnormal risk factor, and an early warning is generated.

4. The method as described in claim 3, characterized in that, The corresponding risk factors are identified as abnormal risk factors, and early warning alerts are generated, including: Identify the nodes corresponding to abnormal risk factors and monitor these nodes; Based on the monitoring results of the nodes, corresponding early warning prompts are generated.

5. A risk prediction device for oil and gas field stations, characterized in that, include: The risk factor formation module is used to extract risk factors and the relationships between risk factors based on the historical accident database of oil and gas field stations, and form risk factors. Risk factors include people, materials, technology, management, and environment; The directed unweighted network construction module is used to abstract risk factors into network nodes and the evolution path of risk factors into directed edges between nodes to construct a directed unweighted network. The risk prediction network model construction module for oil and gas field stations is used to generate the topology of the directed unweighted network as the risk prediction network model for oil and gas field stations based on the constructed directed unweighted network. The topology characteristic analysis module is used to perform multi-dimensional analysis on the risk prediction network model of oil and gas field stations: network index analysis, cohesive subgroup analysis, and core node and edge node analysis, to determine the topology characteristics of the risk prediction network model of oil and gas field stations. The early warning module is used to input the characteristic data of the oil and gas field station event to be tested into the risk prediction network model of the oil and gas field station. Based on the topological characteristics of the risk prediction network model, the risk prediction network model outputs the risk factors of the oil and gas field station event to be tested according to the input characteristic data, determines whether the output risk factors exceed the preset threshold, and generates an early warning.

6. The apparatus as claimed in claim 5, characterized in that, The topology characteristic analysis module is specifically used for: Network metrics analysis is used to analyze the following network metrics: overall network density, network correlation, reciprocity, and the average shortest evolution path of risk factors, in order to determine the network performance of the risk prediction network model. Agglomeration subgroup analysis is used to analyze agglomeration subgroups involving risk events and determine the risk clustering characteristics of the risk prediction network model. Core node and edge node analysis is used to analyze the connection relationships between core nodes and edge nodes, and between edge nodes and core nodes, to determine the causes of risk factor evolution in the risk prediction network model.

7. The apparatus as claimed in claim 5, characterized in that, The early warning module is specifically used for: When the risk value corresponding to a risk factor exceeds the preset risk threshold range, the corresponding risk factor is identified as an abnormal risk factor, and an early warning is generated.

8. The apparatus as claimed in claim 7, characterized in that, The early warning module is specifically used for: Identify the nodes corresponding to abnormal risk factors and monitor these nodes; Based on the monitoring results of the nodes, corresponding early warning prompts are generated.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

Images