Climate risk prevention and control method and device based on graph theory and knowledge graph

Abstract

The invention discloses a climate risk prevention and control method and device based on a graph theory and a knowledge graph. The method comprises the following steps: collecting climate data, traffic facility data and geographic topology data from multi-source heterogeneous data; constructing a knowledge graph by utilizing the entities extracted from the data and the relationship between the entities, representing knowledge by adopting triads in the knowledge graph, and updating by adopting a dynamic updating mechanism; a multi-temporal-spatial dynamic network is constructed based on a graph theory technology, a time dimension is introduced into the multi-temporal-spatial dynamic network, and a dynamic propagation process of climate risks is described by using a nonlinear dynamic model; describing a dynamic propagation process of climate risks in the multiple spatial-temporal dynamic networks by using a nonlinear dynamic model; by analyzing the multiple time-space dynamic networks, key nodes and risk propagation paths are identified and optimized. The technical problem that in the prior art, key risk nodes and propagation paths are difficult to accurately recognize, and consequently corresponding optimization strategies are lacked is solved.

Description

Technical Field

[0001] This application relates to the field of climate risk prevention and control. Specifically, it relates to a method and device for climate risk prevention and control based on graph theory and knowledge graph. Background Art

[0002] This section aims to provide background or context for the content stated in the claims or the specification. The content described here is not admitted to be prior art merely because it is included in this section.

[0003] With the intensification of global climate change, extreme climate events such as sea - level rise, typhoons, and storm surges are becoming more and more frequent, causing complex and non - linear impacts on waterway transportation infrastructure. These climate factors are dynamic in time and space, resulting in the possibility that facilities such as ports and waterways may face partial or systemic failures, affecting the stability of regional economies and the global supply chain.

[0004] For the above reasons, it is difficult for the prior art to accurately identify key risk nodes and propagation paths, lacking corresponding optimization strategies. For this problem, no effective solution has been proposed yet. Summary of the Invention

[0005] The embodiments of this application provide a method and device for climate risk prevention and control based on graph theory and knowledge graph. By integrating graph theory and knowledge graph technologies, the impact of climate change on waterway transportation infrastructure is analyzed. Through multi - spatio - temporal dynamic network modeling and semantic reasoning, accurate identification of climate risk propagation paths, optimization of key nodes, and generation of dynamic prevention and control strategies are realized, providing intelligent support for the planning and management of waterway transportation systems, so as to at least solve the technical problem in the prior art of lacking corresponding optimization strategies due to the difficulty in accurately identifying key risk nodes and propagation paths.

[0006] According to one aspect of the embodiments of this application, a method for climate risk prevention and control based on graph theory and knowledge graph is provided, including: collecting climate data, transportation facility data, and geographical topology data from multi - source heterogeneous data; constructing a knowledge graph by using entities and relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data, where the knowledge graph represents knowledge in triples and uses a dynamic update mechanism for updating; constructing a multi - spatio - temporal dynamic network based on graph theory technology, where the multi - spatio - temporal dynamic network introduces a time dimension and uses a non - linear dynamics model to describe the dynamic propagation process of climate risk; using the non - linear dynamics model to describe the dynamic propagation process of climate risk in the multi - spatio - temporal dynamic network; and by analyzing the multi - spatio - temporal dynamic network, identifying key nodes and risk propagation paths and optimizing them.

[0007] According to another aspect of the embodiments of the present application, there is also provided a climate risk prevention and control device based on graph theory and knowledge graph, including: a data collection unit for collecting climate data, transportation facility data, and geographical topology data from multi-source heterogeneous data; a knowledge graph construction unit for constructing a knowledge graph by using entities and relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data, wherein the knowledge graph represents knowledge in triples and adopts a dynamic update mechanism for updating; a multi-temporal and spatial network construction unit for constructing a multi-temporal and spatial dynamic network based on graph theory technology, wherein the multi-temporal and spatial dynamic network introduces a time dimension and uses a nonlinear dynamics model to describe the dynamic propagation process of climate risk; a risk propagation modeling unit for using a nonlinear dynamics model to describe the dynamic propagation process of climate risk in the multi-temporal and spatial dynamic network; a risk optimization unit for identifying key nodes and risk propagation paths by analyzing the multi-temporal and spatial dynamic network and performing optimization.

[0008] According to another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, which includes a stored program, and when the program runs, it executes the above method.

[0009] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the above method through the computer program.

[0010] According to one aspect of the present application, there is provided a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps of any one of the above methods.

[0011] In the embodiments of the present application, climate data, transportation facility data, and geographical topology data are collected from multi-source heterogeneous data; an entity and the relationship between entities extracted from the climate data, the transportation facility data, and the geographical topology data are used to construct a knowledge graph, wherein the knowledge graph represents knowledge using triples and adopts a dynamic update mechanism for updating; a multi-temporal and dynamic network is constructed based on graph theory technology, wherein the multi-temporal and dynamic network introduces a time dimension and uses a non-linear dynamics model to describe the dynamic propagation process of climate risks; the non-linear dynamics model is used to describe the dynamic propagation process of climate risks in the multi-temporal and dynamic network; by analyzing the multi-temporal and dynamic network, key nodes and risk propagation paths are identified and optimized, thereby solving the technical problem in the prior art of lacking corresponding optimization strategies due to the difficulty in accurately identifying key risk nodes and propagation paths. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings: Figure 1 is a flowchart of an optional climate risk prevention and control method based on graph theory and knowledge graph according to an embodiment of the present application; Figure 2 is a schematic diagram of an optional climate risk prevention and control solution based on graph theory and knowledge graph according to an embodiment of the present application; Figure 3 is a schematic diagram of an optional climate risk prevention and control device based on graph theory and knowledge graph according to an embodiment of the present application; Figure 4 is a structural block diagram of a terminal according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0014] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0015] First, some nouns or terms that appear in the process of describing the embodiments of this application are applicable to the following explanations: Climate factors are dynamic in time and space, which may cause facilities such as ports and waterways to face partial or systemic failures, affecting the stability of the regional economy and the global supply chain. The existing technologies have the following deficiencies in dealing with the above problems: 1) Lack of dynamic modeling ability: It is unable to comprehensively capture the complex interactions between climate factors and transportation facilities and their dynamic evolution process, and it is difficult to cope with the problem of multi-temporal and multi-spatial risk conduction.

[0016] 2) Insufficient semantic association: The existing methods lack effective integration of multi-source heterogeneous data (such as climate data, traffic data, geographical data, etc.), and it is difficult to deeply understand the semantic relationship between climate factors and facilities.

[0017] 3) Limited optimization ability: It is difficult to accurately identify key risk nodes and propagation paths, and lacks an optimization strategy based on dynamic update and intelligent reasoning.

[0018] To solve the above problems, according to one aspect of the embodiments of this application, a method embodiment of a climate risk prevention and control method based on graph theory and knowledge graph is provided. Figure 1 It is a flowchart of an optional climate risk prevention and control method based on graph theory and knowledge graph according to the embodiments of this application. By introducing graph theory and knowledge graph technologies, this application constructs a multi-temporal and multi-spatial dynamic network and a semantic analysis framework, making up for the deficiencies of the existing technologies and having significant innovation and practical value. As Figure 2 shown, the method may include the following steps: Step S102, collect climate data, transportation facility data, and geographical topology data from multi-source heterogeneous data.

[0019] Step S104: Construct a knowledge graph using entities and relationships between entities extracted from climate data, transportation facility data, and geographical topology data. The knowledge graph represents knowledge using triples and adopts a dynamic update mechanism for updating.

[0020] Define the following entities: climate factors, transportation facilities, and events; define the relationships between entities; represent knowledge using triples (entity, relationship, entity) to construct a knowledge graph; dynamically adjust the entity attributes of the knowledge graph and the relationship weights of the triples through real-time data flow.

[0021] Step S106: Construct a multi-temporal and multi-spatial dynamic network based on graph theory techniques. The multi-temporal and multi-spatial dynamic network introduces the time dimension and uses a non-linear dynamics model to describe the dynamic propagation process of climate risks.

[0022] Define the following nodes for the network: ports, waterways, climate factors, and dynamic states; define the network edges, which are used to represent the risk propagation paths or functional dependency relationships between nodes; calculate the weights of the edges based on the causal relationship strength and physical distance between nodes: , where, represents the weight of the edge between node i and node j , represents the causal relationship strength between node i and node j , represents the physical distance between node i and node j , and λ is a tuning parameter.

[0023] Step S108: Use a non-linear dynamics model in the multi-temporal and multi-spatial dynamic network to describe the dynamic propagation process of climate risks.

[0024] Adopt a non-linear dynamics model described by the following non-linear dynamics equation to describe the dynamic propagation process of climate risks in the multi-temporal and multi-spatial dynamic network: , where, represents the risk state of node i , N(i) represents the set of neighbor nodes of node i , F(t) represents the external driving factor, α represents the self-risk growth coefficient of the node, β represents the risk propagation coefficient, γ represents the external driving influence coefficient.

[0025] Step S110: By analyzing the multi-temporal and multi-spatial dynamic network, identify key nodes and risk propagation paths, and optimize them.

[0026] Identify the lowest-risk propagation path from the multi-temporal and multi-spatial dynamic network through the shortest path algorithm and path optimization algorithm: Use the shortest path algorithm to calculate the lowest-risk path with the lowest risk from the starting point to the ending point; where the risk of the path R(P) is calculated by the following formula: ; Introduce a risk cost function in path search through the path optimization algorithm f(n) to optimize the path: , g(n) is the risk cost from the starting point to the current node, h(n) is the estimated risk cost from the current node to the target node.

[0027] After that, use centrality metrics to identify key nodes from the multi-temporal and multi-spatial dynamic network, and combine risk zoning, path optimization, and protection strategies to optimize key nodes and high-risk propagation paths in the multi-temporal and multi-spatial dynamic network: Identify high-risk areas from the multi-temporal and multi-spatial dynamic network through the community detection algorithm; optimize high-risk propagation paths through the maximum flow-minimum cut algorithm; generate protection strategies by adding redundant paths or dynamically adjusting node states.

[0028] Through the above steps, collect climate data, traffic facility data, and geographical topology data from multi-source heterogeneous data; use the entities and relationships between entities extracted from climate data, traffic facility data, and geographical topology data to construct a knowledge graph, where the knowledge graph represents knowledge using triples and uses a dynamic update mechanism for updating; construct a multi-temporal and multi-spatial dynamic network based on graph theory technology, where the multi-temporal and multi-spatial dynamic network introduces a time dimension and uses a nonlinear dynamics model to describe the dynamic propagation process of climate risk; use the nonlinear dynamics model to describe the dynamic propagation process of climate risk in the multi-temporal and multi-spatial dynamic network; by analyzing the multi-temporal and multi-spatial dynamic network, identify key nodes and risk propagation paths, and optimize them, which can solve the technical problem in the prior art of the lack of corresponding optimization strategies due to the difficulty in accurately identifying key risk nodes and propagation paths.

[0029] As an optional embodiment, the technical solution of the present application is further described in detail below in combination with specific implementation manners: This application aims to solve the problem of multi - spatio - temporal non - linear risk conduction of climate change to waterway traffic infrastructure, and proposes a multi - spatio - temporal network - chain generation scheme based on graph theory and knowledge graph to achieve: 1) Dynamic network modeling: Combining graph theory techniques to construct a multi - spatio - temporal dynamic network to capture the complex interaction relationships between climate factors and traffic facilities. 2) Semantic risk analysis: Through knowledge graph technology, endow the network with semantic information to realize intelligent logical reasoning and dynamic update among climate factors, facilities and events. 3) Key node optimization: Identify key nodes and risk propagation chains in the network, and provide dynamic optimization strategies based on semantic reasoning to improve the risk resistance and adaptability of the system. The specific implementation technical solutions are as follows: 1) Data collection and knowledge graph construction Data collection: Climate data, including long - term trends (such as sea - level rise), medium - term changes (such as precipitation patterns), short - term extreme events (such as typhoons, storm surges); Traffic facility data: Port operation status (throughput, outage probability), waterway navigation capacity (siltation risk, water - level changes) and ship scheduling information, etc.; Geographical topology data: The spatial distribution of the waterway traffic network, the connection relationships between nodes and facility attributes.

[0030] Knowledge graph construction: Entity definition: Climate factor entities, such as "storm surge", "typhoon", "sea - level rise"; facility entities, such as "Port A", "Waterway B", "Ship scheduling system"; event entities: such as "Typhoon Event X", "Storm Surge Event Y"; Relationship definition: Influence, the direct influence relationship of climate factors on facilities; Dependency: The functional coupling relationship between facilities; Transmission: The relationship of risk propagation from one node to another node; Triple representation and semantic extension: Use triples (entity - relationship - entity) to represent knowledge, for example: (storm surge, influence, Port A), (Port A, dependency, Waterway B), (change in precipitation pattern, influence, Waterway C); Expand the semantic expression ability of the knowledge graph through hyponymy and nesting relationships, for example: "typhoon" is a subclass of "extreme weather"; "Port A" is a subclass of "port facilities".

[0031] Dynamic update mechanism: Real - time data streams (such as meteorological warnings, facility status data) trigger the update of the knowledge graph; Automatically adjust the triple relationship weights, update the risk propagation paths and optimization strategies.

[0032] Storage and query: Use a graph database (such as Neo4j) to store the knowledge graph and support SPARQL queries for semantic reasoning.

[0033] 2) Graph Theory Modeling of Multi - spatio - temporal Networks Network Structure Definition: Nodes, including ports, waterways, climate factors and their dynamic states; Edges: representing the risk propagation paths or functional dependence relationships between nodes; Weights: calculated based on the following formula:

[0034] Where: C ij Represents the strength of the causal relationship between nodes i and j; D ij Represents the physical or topological distance between nodes; λ is a tuning parameter, optimized and determined through historical data.

[0035] Introduction of the Time Dimension: Construct a dynamic graph sequence G(t) , representing the network state at different times; Different time scales are connected by cross - layer edges to capture the multi - spatio - temporal influence characteristics of climate factors.

[0036] Risk Propagation Modeling: Use non - linear dynamics equations to describe risk propagation:

[0037] Where: x i Represents the risk state of node i; N(i) Is the set of neighbor nodes of node i ; F(t) Represents the external driving factor (such as the change of climate factor intensity over time).

[0038] 3) Risk Propagation Path Analysis Shortest Path Identification: Use the Dijkstra algorithm to calculate the lowest - risk path from the starting point to the ending point:

[0039] Optimized Path Search: Combine the A* algorithm and introduce a heuristic function h(n) in path search:

[0040] Where: g(n) Is the risk cost from the starting point to the current node n ; h(n) Is the estimated risk cost from the current node n to the target node.

[0041] 4) Identification and Optimization of Key Nodes Calculation of Centrality Metrics: Methods such as degree centrality, betweenness centrality, and eigenvector centrality are used to identify key nodes in the network.

[0042] Optimization steps: Risk zoning: Identify high-risk areas through community detection algorithms; Path optimization: Optimize high-risk paths through the maximum flow - minimum cut algorithm; Protection strategy: Add redundant paths or dynamically adjust node states.

[0043] Combined with Figure 2 , this application also provides a more specific implementation plan. The case background of this implementation plan: In recent years, the main port clusters and waterway transportation networks in a coastal country have been frequently affected by climate change, especially extreme climate events such as storm surges, typhoons, and sea-level rise. These events have led to a decline in port throughput and blocked waterways, seriously affecting the stability of the regional economy and the global supply chain. In order to enhance the risk resistance ability of the waterway transportation system, this country plans to introduce a climate risk multi-temporal and multi-spatial network chain generation method based on graph theory and knowledge graphs to model, analyze, and optimize the risk propagation mechanism of its port clusters and surrounding waterway transportation.

[0044] Case objectives: Dynamic modeling, construct a multi-temporal and multi-spatial dynamic network for port clusters and waterways to capture the complex interaction relationships between climate factors and facilities; Risk identification, identify the propagation paths and key nodes of climate risks through semantic analysis; Optimization decision-making: Generate dynamic prevention and control strategies to enhance the adaptability and risk resistance ability of the waterway transportation system.

[0045] Case implementation steps: 1) Data collection and knowledge graph construction Data collection: Climate data: Long-term trend: The sea-level rise rate is 3 mm / year; Medium-term changes: The frequency and intensity of typhoons increase year by year; Short-term events: Historical typhoon records show that storm surges cause an average of 3 - 4 port closures per year.

[0046] Transportation facility data: Port throughput data: Port A bears 80% of the cargo throughput, and the outage probability is 5%; Waterway navigation capacity: Waterway B is affected by siltation risk, and its annual traffic capacity decreases by 10%; Geographical topology data: The spatial distribution of ports and waterways: Ports A, B, and C are connected by waterways B and C, forming a core shipping network.

[0047] Knowledge graph construction: Entity definition: Climate factors: Typhoon, storm surge, sea-level rise; Facilities: Port A, Waterway B, Ship scheduling system; Events: Storm surge event X, Typhoon event Y.

[0048] Relationship definition: (Typhoon, affects, Waterway B); (Storm surge, affects, Port A); (Port A, depends on, Waterway B).

[0049] Dynamic update: Real-time meteorological data triggers the update of the knowledge graph. For example, when a storm surge warning is issued, the knowledge graph automatically adjusts the weight of "(storm surge, impact, Port A)".

[0050] 2) Graph theory modeling of multi-temporal and multi-spatial network Definition of network structure: Nodes: Port A, Port B, Waterway C, typhoon factor, storm surge factor.

[0051] Edges: (Port A, Waterway C): Represents a dependency relationship with a weight of 0.8; (typhoon, Waterway B): Represents a risk propagation path with a weight of 0.9.

[0052] Weight calculation: Combine the intensity of causal relationship and physical distance. For example: Cij = the impact intensity of the storm surge on Port A = 0.7; Dij = the distance between the storm surge center and Port A = 50 km; Weight = Cij / Dij = 0.7 / 50 = 0.014.

[0053] Introduction of time dimension: Construct a dynamic graph sequence G(t), and update the network status once an hour.

[0054] Connect different time scales through cross-layer edges. For example: (typhoon factor t1, storm surge factor t2): Capture the multi-temporal and multi-spatial impact of typhoons causing storm surges.

[0055] 3) Risk propagation path analysis Use the Dijkstra algorithm to calculate the lowest-risk path: For example, when storm surge event X occurs, the lowest-risk path from Port A to Port B is: Path 1: Port A -> Waterway C -> Port B, risk value = 0.25; Path 2: Port A -> Waterway B -> Port B, risk value = 0.4; Select Path 1 as the recommended path.

[0056] Use the A* algorithm to further optimize the path: Introduce a heuristic estimation function h(n) in path search: h(n) = the remaining rate of the current navigable capacity of the waterway. Select the path with the minimum risk cost for recommendation.

[0057] 4) Identification and optimization of key nodes Calculation of centrality indicators: Degree centrality: The degree centrality of Port A is the highest, indicating that it is the core node in the network; Betweenness centrality: The betweenness centrality of Waterway B is relatively high, indicating that it plays a key role in risk propagation.

[0058] Optimization steps: Risk zoning: By using community detection algorithms, Port A and Waterway B are divided into high-risk areas for key prevention and control. Route optimization: By using the maximum flow-minimum cut algorithm, the transportation route from Port A to Port B is optimized. Protection strategy: Add redundant routes, such as building a new waterway D to share the transportation pressure of Waterway B; when a storm surge warning is issued, dynamically adjust the scheduling strategy of Port A to preferentially transfer vulnerable goods.

[0059] Case results: By implementing the climate risk multi-temporal and spatial network chain generation method based on graph theory and knowledge graph, the waterway transportation system of this country has achieved the following goals: Risk identification: Accurately identified the key impact paths of storm surges on Port A and Waterway B; determined that Port A and Waterway B are high-risk key nodes. Optimization strategy: Dynamically generated the lowest-risk paths to ensure transportation efficiency; proposed protection strategies of adding redundant waterway paths and dynamic scheduling to reduce the risk of systemic failure caused by storm surges. System improvement: Improved the risk resistance and adaptability of the waterway transportation network; provided intelligent support for the planning and management of the national port cluster.

[0060] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequences, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0061] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present application.

[0062] According to another aspect of the embodiments of the present application, there is also provided a climate risk prevention and control device based on graph theory and knowledge graph for implementing the above-mentioned climate risk prevention and control method based on graph theory and knowledge graph. Figure 3 It is a schematic diagram of an optional climate risk prevention and control device based on graph theory and knowledge graph according to the embodiments of the present application, as Figure 3 shown. The device may include: A data acquisition unit 31 for collecting climate data, traffic facility data, and geographical topology data from multi-source heterogeneous data.

[0063] A knowledge graph construction unit 33 for constructing a knowledge graph by using entities and relationships between entities extracted from the climate data, the traffic facility data, and the geographical topology data, where the knowledge graph represents knowledge in triples and adopts a dynamic update mechanism for updating.

[0064] Define the following entities: climate factors, traffic facilities, and events; define the relationships between entities; represent knowledge in triples (entity, relationship, entity) to construct the knowledge graph; dynamically adjust the entity attributes of the knowledge graph and the relationship weights of the triples through real-time data flow.

[0065] A multi-temporal and spatial network construction unit 35 for constructing a multi-temporal and spatial dynamic network based on graph theory technology, where the multi-temporal and spatial dynamic network introduces a time dimension and uses a non-linear dynamics model to describe the dynamic propagation process of climate risks.

[0066] Define the following network nodes: ports, waterways, climate factors, and dynamic states; define network edges, where the network edges are used to represent the risk propagation paths or functional dependency relationships between nodes; calculate the weights of the edges according to the causal relationship strength and physical distance between nodes: , where represents the weight of the edge between node i and node j , represents the causal relationship strength between node i and node j , represents the physical distance between node i and node j , and λ is a regulation parameter.

[0067] A risk propagation modeling unit 37 for using a non-linear dynamics model to describe the dynamic propagation process of climate risks in the multi-temporal and spatial dynamic network.

[0068] Use a non-linear dynamics model described by the following non-linear dynamics equation to describe the dynamic propagation process of climate risks in the multi-temporal and spatial dynamic network: , where represents the risk state of node i , N(i) represents the set of neighbor nodes of node i , F(t)Denote an external driving factor, α Denote the risk growth coefficient of the node itself, β Denote the risk propagation coefficient, γ Denote the external driving influence coefficient.

[0069] The risk optimization unit 39 is used to identify key nodes and risk propagation paths by analyzing the multi - spatio - temporal dynamic network, and perform optimization.

[0070] Identify the lowest - risk propagation path from the multi - spatio - temporal dynamic network through the shortest - path algorithm and the path - optimization algorithm: Calculate the lowest - risk path with the lowest risk from the starting point to the end point using the shortest - path algorithm; where the risk of the path R(P) Is calculated by the following formula: ; Introduce a risk cost function in path search through the path - optimization algorithm f(n) To optimize the path: , g(n) Is the risk cost from the starting point to the current node, h(n) Is the estimated risk cost from the current node to the target node.

[0071] Then use centrality metrics to identify key nodes from the multi - spatio - temporal dynamic network, and optimize the key nodes and high - risk propagation paths in the network by combining risk partitioning, path optimization, and protection strategies: Identify high - risk regions from the multi - spatio - temporal dynamic network through the community detection algorithm; Optimize high - risk propagation paths through the maximum - flow minimum - cut algorithm; Generate protection strategies by adding redundant paths or dynamically adjusting node states.

[0072] Through the above modules, collect climate data, transportation facility data, and geographical topology data from multi - source heterogeneous data; Use the entities and relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data to construct a knowledge graph, where the knowledge graph represents knowledge using triples and uses a dynamic update mechanism for updating; Construct a multi - spatio - temporal dynamic network based on graph - theory techniques, where the multi - spatio - temporal dynamic network introduces a time dimension and uses a non - linear dynamics model to describe the dynamic propagation process of climate risk; Use the non - linear dynamics model to describe the dynamic propagation process of climate risk in the multi - spatio - temporal dynamic network; By analyzing the multi - spatio - temporal dynamic network, identify key nodes and risk propagation paths, and perform optimization, which can solve the technical problem in the prior art of the lack of corresponding optimization strategies due to the difficulty in accurately identifying key risk nodes and propagation paths.

[0073] It should be noted here that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in the corresponding hardware environment, can be implemented by software, or can be implemented by hardware, where the hardware environment includes a network environment.

[0074] According to another aspect of the embodiments of the present application, there is also provided a server or a terminal for implementing the above-mentioned climate risk prevention and control method based on graph theory and knowledge graph.

[0075] Figure 4 is a structural block diagram of a terminal according to an embodiment of the present application, as Figure 4 shown, the terminal may include: one or more (only one is shown in the figure) processors 401, a memory 403, and a transmission device 405, as Figure 4 shown, the terminal may further include an input / output device 407.

[0076] Among them, the memory 403 can be used to store software programs and modules, such as program instructions / modules corresponding to the climate risk prevention and control method and device based on graph theory and knowledge graph in the embodiments of the present application. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 403, that is, implements the above-mentioned climate risk prevention and control method based on graph theory and knowledge graph. The memory 403 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 403 may further include a memory remotely disposed relative to the processor 401, and these remote memories can be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof.

[0077] The above-mentioned transmission device 405 is used to receive or send data via a network, and can also be used for data transmission between the processor and the memory. Specific examples of the above network may include a wired network and a wireless network. In one instance, the transmission device 405 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through a network cable, so as to communicate with the Internet or a local area network. In one instance, the transmission device 405 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0078] Specifically, the memory 403 is used to store application programs.

[0079] The processor 401 can call the application program stored in the memory 403 through the transmission device 405 to execute the following steps: Collect climate data, transportation facility data, and geographical topology data from multi-source heterogeneous data; use the entities and the relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data to construct a knowledge graph, where the knowledge graph represents knowledge using triples and adopts a dynamic update mechanism for updating; construct a multi-temporal and dynamic network based on graph theory technology, where the multi-temporal and dynamic network introduces a time dimension and uses a nonlinear dynamics model to describe the dynamic propagation process of climate risks; use the nonlinear dynamics model to describe the dynamic propagation process of climate risks in the multi-temporal and dynamic network; analyze the multi-temporal and dynamic network to identify key nodes and risk propagation paths and optimize them.

[0080] Adopting the embodiments of the present application, collect climate data, transportation facility data, and geographical topology data from multi-source heterogeneous data; use the entities and the relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data to construct a knowledge graph, where the knowledge graph represents knowledge using triples and adopts a dynamic update mechanism for updating; construct a multi-temporal and dynamic network based on graph theory technology, where the multi-temporal and dynamic network introduces a time dimension and uses a nonlinear dynamics model to describe the dynamic propagation process of climate risks; use the nonlinear dynamics model to describe the dynamic propagation process of climate risks in the multi-temporal and dynamic network; analyze the multi-temporal and dynamic network to identify key nodes and risk propagation paths and optimize them, thereby solving the technical problem in the prior art of lacking corresponding optimization strategies due to the difficulty in accurately identifying key risk nodes and propagation paths.

[0081] Optionally, the specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0082] Those of ordinary skill in the art can understand that Figure 4 The structure shown is only schematic. The terminal can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a mobile Internet device (Mobile Internet Devices, MID), a PAD and other terminal devices. Figure 4 It does not limit the structure of the above electronic device. For example, the terminal may further include more or fewer components (such as a network interface, a display device, etc.) than those shown Figure 4 in, or have a different configuration from that shown Figure 4 in.

[0083] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware of the terminal device through a program, and the program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, an optical disc, etc.

[0084] An embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the above storage medium may be used to execute the program code of the climate risk prevention and control method based on graph theory and knowledge graph.

[0085] Optionally, in this embodiment, the above storage medium may be located on at least one of the multiple network devices in the network shown in the above embodiment.

[0086] Optionally, in this embodiment, the storage medium is set to store program code for performing the following steps: Collect climate data, transportation facility data, and geographical topology data from multi-source heterogeneous data; use the entities and relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data to construct a knowledge graph, where the knowledge graph represents knowledge using triples and uses a dynamic update mechanism for updating; construct a multi-temporal and dynamic network based on graph theory technology, where the multi-temporal and dynamic network introduces a time dimension and uses a non-linear dynamics model to describe the dynamic propagation process of climate risk; use the non-linear dynamics model to describe the dynamic propagation process of climate risk in the multi-temporal and dynamic network; identify key nodes and risk propagation paths by analyzing the multi-temporal and dynamic network, and optimize them.

[0087] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and will not be elaborated here.

[0088] Optionally, in this embodiment, the above storage medium may include but is not limited to: various media such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disc that can store program code.

[0089] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0090] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage media. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.

[0091] In the above embodiments of this application, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] In the several embodiments provided by this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in electrical or other forms.

[0093] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] In addition, the functional units in the various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0095] The above are only the preferred embodiments of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A climate risk prevention and control method based on graph theory and knowledge graph, characterized in that Including: Collect climate data, transportation facility data, and geographical topology data from multi-source heterogeneous data; Utilize the entities and relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data to construct a knowledge graph, where the knowledge graph represents knowledge using triples and uses a dynamic update mechanism for updating; Construct a multi-temporal and dynamic network based on graph theory techniques, where the multi-temporal and dynamic network introduces a time dimension and uses a non-linear dynamics model to describe the dynamic propagation process of climate risks; Use a non-linear dynamics model in the multi-temporal and dynamic network to describe the dynamic propagation process of climate risks; Through analyzing the multi-temporal and dynamic network, identify key nodes and risk propagation paths and optimize them.

2. The method according to claim 1, wherein Utilize the entities and relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data to construct a knowledge graph, including: Define the following entities: climate factors, transportation facilities, and events; Define the relationships between entities; Use triples (entity, relationship, entity) to represent knowledge and construct the knowledge graph; Dynamically adjust the entity attributes of the knowledge graph and the relationship weights of the triples through real-time data flow.

3. The method according to claim 1, wherein Construct a multi-temporal and dynamic network based on graph theory techniques, including: Define the following nodes of the network: ports, waterways, climate factors, and dynamic states; Define network edges, where the network edges are used to represent the risk propagation paths or functional dependency relationships between nodes; Calculate the weights of the edges according to the causal relationship strength and physical distance between nodes: ， Among them, represents the weight of the edge between node i and node j ; represents the strength of the causal relationship between node i and node j ; represents the physical distance between node i and node j , and λ is a tuning parameter.

4. The method according to claim 1, characterized in that Use a non-linear dynamics model in the multi-temporal and dynamic network to describe the dynamic propagation process of climate risks, including: Use a non-linear dynamics model described by the following non-linear dynamics equation to describe the dynamic propagation process of climate risks in the multi-temporal and dynamic network: ， Among them, represents the risk status of the node i , N(i) represents the set of neighbor nodes of the node i , F(t) represents the external driving factor α represents the self-risk growth coefficient of the node β represents the risk propagation coefficient γ represents the external driving influence coefficient 5. The method according to any one of claims 1 to 4, characterized in that, Through analyzing the multi-temporal and dynamic network, identify key nodes and risk propagation paths and optimize them, including: Identify the lowest risk propagation path from the multi-temporal and dynamic network through the shortest path algorithm and path optimization algorithm, and identify key nodes from the multi-temporal and dynamic network using centrality indicators; Combine risk zoning, path optimization, and protection strategies to optimize the key nodes and high-risk propagation paths in the multi-temporal and dynamic network.

6. The method according to claim 5, characterized in that, Identify the lowest risk propagation path from the multi-temporal and dynamic network through the shortest path algorithm and path optimization algorithm, including: Use the shortest path algorithm to calculate the lowest risk path with the lowest risk from the starting point to the ending point; Among them, the risk of the path R(P) is calculated by the following formula: ； Introduce a risk cost function in path search through the path optimization algorithm f(n) Optimized path: g(n) is the risk cost from the starting point to the current node, h(n) is the estimated risk cost from the current node to the target node.

7. The method according to claim 5, characterized in that, Combine risk zoning, path optimization, and protection strategies to optimize the key nodes and high-risk propagation paths in the multi-temporal and dynamic network, including: Identify high-risk areas from the multi-temporal and dynamic network through the community detection algorithm; Optimize high-risk propagation paths through the maximum flow - minimum cut algorithm; Generate protection strategies by adding redundant paths or dynamically adjusting node states.

8. A climate risk prevention and control device based on graph theory and knowledge graph, characterized in that, Including: A data acquisition unit for collecting climate data, transportation facility data, and geographical topology data from multi-source heterogeneous data; A knowledge graph construction unit, configured to construct a knowledge graph by using entities and relationships between entities extracted from the climate data, the transportation facility data, and the geographical topology data, wherein the knowledge graph represents knowledge in triples and adopts a dynamic update mechanism for updating; A multi-temporal and spatial network construction unit, configured to construct a multi-temporal and spatial dynamic network based on graph theory techniques, wherein the multi-temporal and spatial dynamic network introduces a time dimension and uses a non-linear dynamics model to describe the dynamic propagation process of climate risks; A risk propagation modeling unit, configured to use a non-linear dynamics model to describe the dynamic propagation process of climate risks in the multi-temporal and spatial dynamic network; A risk optimization unit, configured to identify key nodes and risk propagation paths by analyzing the multi-temporal and spatial dynamic network and perform optimization.

9. A computer-readable storage medium, characterized in that, The storage medium includes a stored program, wherein the program, when running, executes the method described in any one of claims 1 to 7 above.

10. An electronic device, 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 method described in any one of claims 1 to 7 above through the computer program.

Images