Marine storm surge emergency response scheme recommendation method and device

Abstract

The invention provides an ocean storm surge emergency response scheme recommendation method and device, and the method comprises the steps: constructing a scene-response disaster disposal system fusing an event chain and an emergency plan, and a scene-response visual knowledge graph, through a constructed ocean storm surge scene-coping disaster disposal system, a scene-coping knowledge graph and a knowledge reasoning model, scene-coping matching of historical disaster events can be completed, pre-disaster rehearsal and post-disaster analysis are realized, and coping knowledge base text matching can be performed according to a disaster scene text generated in real time. And an emergency response scheme is generated and a map recommendation result is visually displayed, so that in-disaster response is realized, the whole-process disaster prevention and reduction chain of the ocean storm surge disaster event is perfected, the generalization ability of a knowledge reasoning method is improved, and important support is provided for further improving the intelligent disposal ability of the ocean storm surge disaster.

Description

Technical Field

[0001] The present invention relates to the field of intelligent disaster disposal technology, and in particular to a method for recommending an ocean storm surge emergency response plan, a device for recommending an ocean storm surge emergency response plan, an electronic device, and a computer-readable medium. Background Art

[0002] At present, the research methods in the field of intelligent disaster disposal are mainly carried out from two aspects: disaster event chain and emergency plan. The research on disaster event chain includes two parts: event chain knowledge construction method and disaster scenario deduction method. Wang Ke et al. constructed 6 marine disaster chains, summarized the impact characteristics of marine disasters, established a comprehensive marine disaster chain, and provided technical support for marine disaster prevention and control. Chen Xuelong et al. used Bayesian network to analyze the attribute relationship between events to deal with the modeling problem of concurrent disaster event chains, and used prior probability to analyze event evolution. In terms of storm surge disaster scenario construction and deduction methods, Rao Wenli et al. constructed a typhoon storm surge disaster scenario through the dynamic Bayesian network method, calculated the scenario state probability using prior probability and conditional probability, and realized the key scenario deduction of typhoon storm surge. Zhang Chao et al. conducted scenario construction method research in the field of urban public safety, established complete risk event information through scenario construction, and laid a foundation for subsequent risk analysis, risk assessment, and risk disposal. Wang Jiadong constructed a typhoon storm surge event chain, and based on this, conducted scenario deduction, and conducted a chain-breaking disaster reduction analysis from the perspective of protecting the disaster-bearing body, and proposed a disaster reduction strategy. Zhu Haiming et al. constructed a typhoon disaster chain knowledge map based on the disaster risk census knowledge base, providing a new method and perspective for the study of disaster chains.

[0003] The "scenario-response" model is to store and rehearse the disaster scenarios and disposal plans that have already occurred, so as to deal with the current disasters and possible secondary derivative disasters. In recent years, many scholars have used the "scenario-response" model to quickly deal with emergencies. Gong Qiansheng took the recognition of emergency scenarios as the research object and studied the key technologies such as the elements of emergency scenario information, the generation of scenario information needs, the extraction and expression of objects in scenario elements, and scenario deduction in the "scenario-response" type emergency decision-making. Zhang Gongxiao and others established a hazardous chemical leakage emergency decision-making system based on the "scenario-response" model, and applied it to the emergency rescue of chlorine gas leakage accidents, which improved the efficiency of emergency decision-making. Zhou Lin and others deduced mountain torrent disasters based on the "scenario-response" model. Tang Zhaoping and others adopted the "scenario-response" model through the analysis and calculation of the accident scenario set, considering the uncertainty of emergency resource demand after the emergency, and improving the emergency response level of high-speed railways.

[0004] In summary, although there have been many studies in the field of "scenario-response" intelligent disaster management, the existing research on the construction method of the "scenario-response" model for marine storm surges rarely combines the event chain with emergency plan knowledge, and most of them are based on historical disaster scenarios and the disposal measures at the time. The generalization ability is insufficient, and the generated emergency response plans are coarse-grained. Summary of the invention

[0005] In view of the above problems, the present invention is proposed to provide a method for recommending an ocean storm surge emergency response plan and a corresponding ocean storm surge emergency response plan recommendation device, an electronic device and a computer-readable medium that overcome the above problems or at least partially solve the above problems.

[0006] The present invention discloses a method for recommending an emergency response plan for an ocean storm surge, the method comprising: Constructing a marine storm surge disaster disposal system; the marine storm surge disaster disposal system includes an event chain structure, a secondary derivative relationship table of typical marine storm surge disaster events, a concept system of emergency plan knowledge elements, and an emergency plan entity relationship expression model; According to the marine storm surge disaster disposal system, a visual knowledge graph ontology for marine storm surge disaster disposal is generated. Based on the visual knowledge graph ontology for marine storm surge disaster disposal, entities and relationships are jointly extracted from a large number of historical marine storm surge events and emergency plans to generate a visual knowledge graph for marine storm surge disaster disposal. According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the current event is matched and deduced to obtain the event chain of the current event; the event chain of the current event includes the disaster situation that has occurred in the current event and the secondary derivative disasters that may occur in the future; The event chain of the current event is matched with the visual knowledge graph of ocean storm surge disaster disposal to obtain the ocean storm surge emergency response plan of the current event, and the ocean storm surge emergency response plan of the current event is visualized in the form of a knowledge graph and recommended to emergency decision makers.

[0007] Optionally, a marine storm surge disaster management system is constructed, including: The event chain structure is obtained by analyzing the structural characteristics of a large number of historical ocean storm surge events, and the storm surge propagation mechanism and secondary derivative law of a large number of historical ocean storm surge events are analyzed by using the time-space constraint analysis method to obtain the secondary derivative relationship table of typical ocean storm surge disaster events; A structured analysis of the ocean storm surge emergency plan was conducted to obtain the conceptual system of emergency plan knowledge elements, and the relationship between different types of elements was analyzed to obtain the emergency plan entity relationship expression model; the emergency plan knowledge element conceptual system includes emergency plan categories, emergency plan handling procedures, and emergency plan basic contents.

[0008] Optionally, according to the marine storm surge disaster disposal system, a marine storm surge disaster disposal visualization knowledge graph ontology is generated, and based on the marine storm surge disaster disposal visualization knowledge graph ontology, a large number of historical marine storm surge events and emergency plans are jointly extracted in terms of entities and relationships to generate a marine storm surge disaster disposal visualization knowledge graph, including: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the conceptual hierarchical relationship, attribute relationship and association relationship in the disaster scenario are sorted out to generate the disaster scenario ontology semantic expression formula. According to the emergency plan knowledge element concept system and the emergency plan entity relationship expression model, the conceptual hierarchical relationship, attribute relationship and association relationship of the emergency plan are sorted out to generate the emergency response subject ontology semantic expression formula. The disaster scenario ontology semantic expression formula and the emergency response subject ontology semantic expression formula are integrated to generate the marine storm surge disaster disposal visualization knowledge graph ontology. Based on the visual knowledge graph ontology of marine storm surge disaster disposal, the OSS-CasRel model is used to jointly extract entities and relationships from a large number of historical marine storm surge events and emergency plans, and generate a visual knowledge graph for marine storm surge disaster disposal. The OSS-CasRel model is an improved CasRel model, which uses a self-built entity relationship corpus in the field of marine storm surge to replace the word segmentation dictionary of the original CasRel model, and uses the marine storm surge emergency plan for parameter training.

[0009] Optionally, the event chain of the current event is matched with the ocean storm surge disaster disposal visualization knowledge graph to obtain the ocean storm surge emergency response plan of the current event, including: The text representation of the event chain and the text representation of the emergency response plan in the visual knowledge graph of marine storm surge disaster disposal are spliced ​​together, and the BERT-Base-Chinese model is used for text knowledge embedding and text vector feature extraction to obtain the event chain-emergency response plan text embedding vector; The BERT-Base-Chinese model is used to perform text knowledge embedding and text vector feature extraction on the text representation of the event chain of the current event, and the event chain text embedding vector of the current event is obtained; The matching degree of each event chain-emergency response plan text embedding vector with the event chain text embedding vector of the current event is calculated, and the event chain-emergency response plan text embedding vector with the highest matching degree is split according to different attributes to obtain the ocean storm surge emergency response plan for the current event.

[0010] Optionally, according to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the current event is matched and deduced to obtain the event chain of the current event, including: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the structural characteristics, storm surge propagation mechanism and secondary derivative law of the current event are analyzed to obtain the event chain of the current event.

[0011] The present invention also discloses a device for recommending an emergency response plan for an ocean storm surge, the device comprising: A disaster disposal system construction module is used to construct an ocean storm surge disaster disposal system; the ocean storm surge disaster disposal system includes an event chain structure, a secondary derivative relationship table of typical ocean storm surge disaster events, an emergency plan knowledge element concept system, and an emergency plan entity relationship expression model; The disaster disposal visualization knowledge graph generation module is used to generate a visualization knowledge graph ontology for marine storm surge disaster disposal based on the marine storm surge disaster disposal system, and to jointly extract entities and relationships of a large number of historical marine storm surge events and emergency plans based on the visualization knowledge graph ontology for marine storm surge disaster disposal, so as to generate a visualization knowledge graph for marine storm surge disaster disposal; The real-time event chain matching and deduction module is used to match and deduce the current event according to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events to obtain the event chain of the current event; the event chain of the current event includes the disaster situation that has occurred in the current event and the secondary derivative disasters that may occur in the future; The emergency response plan generation module is used to match the event chain of the current event with the visual knowledge graph of ocean storm surge disaster disposal, obtain the ocean storm surge emergency response plan of the current event, and visualize the ocean storm surge emergency response plan of the current event in the form of a knowledge graph and recommend it to emergency decision makers.

[0012] Optionally, the disaster handling system construction module is also used to: The event chain structure is obtained by analyzing the structural characteristics of a large number of historical ocean storm surge events, and the storm surge propagation mechanism and secondary derivative law of a large number of historical ocean storm surge events are analyzed by using the time-space constraint analysis method to obtain the secondary derivative relationship table of typical ocean storm surge disaster events; A structured analysis of the ocean storm surge emergency plan was conducted to obtain the conceptual system of emergency plan knowledge elements, and the relationship between different types of elements was analyzed to obtain the emergency plan entity relationship expression model; the emergency plan knowledge element conceptual system includes emergency plan categories, emergency plan handling procedures, and emergency plan basic contents.

[0013] Optionally, the disaster disposal visualization knowledge graph generation module is further used to: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the conceptual hierarchical relationship, attribute relationship and association relationship in the disaster scenario are sorted out to generate the disaster scenario ontology semantic expression formula. According to the emergency plan knowledge element concept system and the emergency plan entity relationship expression model, the conceptual hierarchical relationship, attribute relationship and association relationship of the emergency plan are sorted out to generate the emergency response subject ontology semantic expression formula. The disaster scenario ontology semantic expression formula and the emergency response subject ontology semantic expression formula are integrated to generate the marine storm surge disaster disposal visualization knowledge graph ontology. Based on the visual knowledge graph ontology of marine storm surge disaster disposal, the OSS-CasRel model is used to jointly extract entities and relationships from a large number of historical marine storm surge events and emergency plans, and generate a visual knowledge graph for marine storm surge disaster disposal. The OSS-CasRel model is an improved CasRel model, which uses a self-built entity relationship corpus in the field of marine storm surge to replace the word segmentation dictionary of the original CasRel model, and uses the marine storm surge emergency plan for parameter training.

[0014] Optionally, the emergency response plan generation module is further used to: The text representation of the event chain and the text representation of the emergency response plan in the visual knowledge graph of marine storm surge disaster disposal are spliced ​​together, and the BERT-Base-Chinese model is used for text knowledge embedding and text vector feature extraction to obtain the event chain-emergency response plan text embedding vector; The BERT-Base-Chinese model is used to perform text knowledge embedding and text vector feature extraction on the text representation of the event chain of the current event, and the event chain text embedding vector of the current event is obtained; The matching degree of each event chain-emergency response plan text embedding vector with the event chain text embedding vector of the current event is calculated, and the event chain-emergency response plan text embedding vector with the highest matching degree is split according to different attributes to obtain the ocean storm surge emergency response plan for the current event.

[0015] Optionally, the real-time event chain matching and deduction module is further used to: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the structural characteristics, storm surge propagation mechanism and secondary derivative law of the current event are analyzed to obtain the event chain of the current event.

[0016] The present invention also discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is used to implement the method for recommending an emergency response plan for marine storm surges as described in the present invention when executing the program stored in the memory.

[0017] The present invention also discloses one or more computer-readable media on which instructions are stored. When executed by one or more processors, the processors execute the method for recommending an emergency response plan for ocean storm surges as described in the present invention.

[0018] The present invention includes the following advantages: The method for recommending emergency response plans for marine storm surges of the present invention constructs a "scenario-response" disaster disposal system and a "scenario-response" visualized knowledge graph that integrate event chains and emergency plans. The constructed marine storm surge "scenario-response" disaster disposal system and the "scenario-response" knowledge graph and knowledge reasoning model can not only complete the "scenario-response" matching of historical disaster events, realize pre-disaster rehearsals and post-disaster analysis, but also can match the "response" knowledge base text according to the real-time generated disaster "scenario" text, generate emergency response plans and visualize the graph recommendation results to achieve response during the disaster, improve the full-process disaster prevention and mitigation chain of marine storm surge disaster events, improve the generalization ability of knowledge reasoning methods, and provide important support for further improving the intelligent disposal capabilities of marine storm surge disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of the steps of a method for recommending an ocean storm surge emergency response plan provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of an entity relationship expression model of an emergency plan provided by an embodiment of the present invention; Figure 3 It is a design diagram of the ocean storm surge "scenario-response" spatiotemporal knowledge graph ontology provided by an embodiment of the present invention; Figure 4 It is a diagram of the OSS-CasRel model architecture provided by an embodiment of the present invention; Figure 5 It is an overall flow chart of ocean storm surge "scenario-response" knowledge embedding and knowledge reasoning provided by an embodiment of the present invention; Figure 6 It is a schematic diagram of a marine storm surge disaster event handling system provided by an embodiment of the present invention; Figure 7 It is a schematic diagram of some nodes of the ocean storm surge "scenario-response" knowledge graph provided by an embodiment of the present invention; Figure 8 It is a schematic diagram showing an example of a seawall breach disaster event and the Longgang District Meteorological Disaster Emergency Plan in the “Scenario-Response” knowledge graph provided by an embodiment of the present invention; Fig. 9It is a structural block diagram of a device for recommending an ocean storm surge emergency response plan provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Reference Figure 1 , shows a flow chart of the steps of a method for recommending an ocean storm surge emergency response plan provided in an embodiment of the present invention, which may specifically include the following steps: Step 101, constructing a marine storm surge disaster disposal system; the marine storm surge disaster disposal system includes an event chain structure, a secondary derivative relationship table of typical marine storm surge disaster events, a concept system of emergency plan knowledge elements, and an emergency plan entity relationship expression model; Step 102, generating a visual knowledge graph ontology for handling marine storm surge disasters based on the marine storm surge disaster management system, and extracting entities and relationships from a large number of historical marine storm surge events and emergency plans based on the visual knowledge graph ontology for handling marine storm surge disasters, to generate a visual knowledge graph for handling marine storm surge disasters; Step 103, according to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the current event is matched and deduced to obtain the event chain of the current event; the event chain of the current event includes the disaster situation that has occurred in the current event and the secondary derivative disasters that may occur in the future; Step 104, matching the event chain of the current event with the visual knowledge graph of ocean storm surge disaster disposal, obtaining the ocean storm surge emergency response plan of the current event, and visually displaying the ocean storm surge emergency response plan of the current event in the form of a knowledge graph and recommending it to emergency decision makers.

[0022] In a first embodiment of the present invention, a marine storm surge disaster management system is constructed, including: The event chain structure is obtained by analyzing the structural characteristics of a large number of historical ocean storm surge events, and the storm surge propagation mechanism and secondary derivative law of a large number of historical ocean storm surge events are analyzed by using the time-space constraint analysis method to obtain the secondary derivative relationship table of typical ocean storm surge disaster events; A structured analysis of the ocean storm surge emergency plan was conducted to obtain the conceptual system of emergency plan knowledge elements, and the relationship between different types of elements was analyzed to obtain the emergency plan entity relationship expression model; the emergency plan knowledge element conceptual system includes emergency plan categories, emergency plan handling procedures, and emergency plan basic contents.

[0023] In the first embodiment of the present invention, according to the marine storm surge disaster disposal system, a marine storm surge disaster disposal visualization knowledge graph ontology is generated, and based on the marine storm surge disaster disposal visualization knowledge graph ontology, a large number of historical marine storm surge events and emergency plans are jointly extracted with entities and relationships to generate a marine storm surge disaster disposal visualization knowledge graph, including: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the conceptual hierarchical relationship, attribute relationship and association relationship in the disaster scenario are sorted out to generate the disaster scenario ontology semantic expression formula. According to the emergency plan knowledge element concept system and the emergency plan entity relationship expression model, the conceptual hierarchical relationship, attribute relationship and association relationship of the emergency plan are sorted out to generate the emergency response subject ontology semantic expression formula. The disaster scenario ontology semantic expression formula and the emergency response subject ontology semantic expression formula are integrated to generate the marine storm surge disaster disposal visualization knowledge graph ontology. Based on the visual knowledge graph ontology of marine storm surge disaster disposal, the OSS-CasRel model is used to jointly extract entities and relationships from a large number of historical marine storm surge events and emergency plans, and generate a visual knowledge graph for marine storm surge disaster disposal. The OSS-CasRel model is an improved CasRel model, which uses a self-built entity relationship corpus in the field of marine storm surge to replace the word segmentation dictionary of the original CasRel model, and uses the marine storm surge emergency plan for parameter training.

[0024] In the first embodiment of the present invention, the event chain of the current event is matched with the ocean storm surge disaster disposal visualization knowledge map to obtain the ocean storm surge emergency response plan of the current event, including: The text representation of the event chain and the text representation of the emergency response plan in the visual knowledge graph of marine storm surge disaster disposal are spliced ​​together, and the BERT-Base-Chinese model is used for text knowledge embedding and text vector feature extraction to obtain the event chain-emergency response plan text embedding vector; The BERT-Base-Chinese model is used to perform text knowledge embedding and text vector feature extraction on the text representation of the event chain of the current event, and the event chain text embedding vector of the current event is obtained; The matching degree of each event chain-emergency response plan text embedding vector with the event chain text embedding vector of the current event is calculated, and the event chain-emergency response plan text embedding vector with the highest matching degree is split according to different attributes to obtain the ocean storm surge emergency response plan for the current event.

[0025] In the first embodiment of the present invention, according to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the current event is matched and deduced to obtain the event chain of the current event, including: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the structural characteristics, storm surge propagation mechanism and secondary derivative law of the current event are analyzed to obtain the event chain of the current event.

[0026] 1. Methods The knowledge reasoning technology based on knowledge graph can establish the connection between different entities in the "scenario-response" visualization process, integrating the knowledge expression requirements of the event chain and the visual expression form of the emergency plan. The implementation process of the "scenario-response" reasoning method that integrates the event chain and the event chain is as follows: ① Construction of the "scenario-response" disaster disposal system that integrates the event chain and the emergency plan. Combine historical disaster data to analyze the construction and deduction process of the event chain; conduct a structural analysis of the emergency plan related to the ocean storm surge; and build a "scenario-response" disaster disposal system. ② Construction of the "scenario-response" visualization knowledge graph. Define the ontology layer of the "scenario-response" visualization knowledge graph, use the entity and relationship joint extraction technology to obtain the corresponding knowledge triples in the ontology layer, and construct the "scenario-response" visualization knowledge graph. ③ "Scenario-response" knowledge embedding. Knowledge embedding is performed on the data features of the knowledge graph, the disaster scenario input data, and the visualization dimension information of the emergency plan, and the high-dimensional corpus information is converted into a low-dimensional feature vector; ④ "Scenario-response" matching degree calculation. After obtaining the eigenvector matrix, calculate the matching degree between the eigenvector of the disaster scenario input data and the eigenvector composed of the nodes related to the emergency plan in the knowledge graph; ⑤ Visual emergency response plan recommendation. The emergency plan and related content with a high matching degree with the input data are visualized in the form of a knowledge graph and recommended to emergency decision makers.

[0027] 1.1 Method for constructing a “scenario-response” disaster management system integrating event chains and emergency plans As a way to describe the evolution of a disaster event, the event chain can clearly express the process of the disaster event deriving and generating other disasters in time and space. Emergency decision-makers can match and deduce current events based on the event chain, and can also discover possible secondary disasters in the future based on the event chain, and make emergency warnings in advance. In the construction of the event chain, events are generally extracted through a large number of historical case analyses, and common event chain structures are classified and sorted from different perspectives such as the cause of the event chain and the area where the emergency occurred. The structural characteristics of the event chain are analyzed, and the event nodes are organized in the form of a graph to reveal the evolutionary laws between events.

[0028] In the structured analysis of emergency plans, the analysis can be conducted from three levels: emergency plan categories, emergency plan handling processes, and basic contents of emergency plans, as shown in Table 1. The plan categories can be divided into provincial, municipal, district, street, unit, and grassroots organization levels according to the level; according to the type, they can be divided into general emergency plans, special emergency plans, and departmental emergency plans. By sorting out relevant documents such as the "National Natural Disaster Relief Emergency Plan", "Disaster Relief Emergency Work Regulations", and "Guangdong Meteorological Disaster Emergency Plan" issued by national and provincial departments, combined with disaster risk management and emergency management theories, according to the process of disaster occurrence, the emergency plan handling process is divided into daily support stage, monitoring and early warning stage, emergency response stage, and post-handling stage according to the execution order of different stages. In terms of the knowledge expression method of the emergency plan, the ontology theory is used to establish a conceptual system of emergency knowledge elements, and the relationship between different types of elements is analyzed to obtain the entity relationship expression model of the emergency plan, such as Figure 2 shown.

[0029] Table 1. Categories and contents of emergency plans

[0030] 1.2 “Scenario-Response” Visual Knowledge Graph Construction and Knowledge Embedding Method In the design of the marine storm surge "scenario-response" knowledge graph ontology, the "scenario" part is a unified description of the conceptual hierarchical relationship, attribute relationship, and association relationship of the disaster event chain and the disaster scenario itself. The present invention semantically represents a disaster scenario ontology as follows: DisasterScene={Scene_Concept, Scene_Property, Scene_Relation, Scene_Restriction, Scene_Instance} Among them, Scene_Concept represents the set of all disaster scenario concepts, including the definition of disaster scenario concepts and the conceptual hierarchy classification; Scene_Property represents the definition of the attributes of the disaster scenario itself, such as disaster name, occurrence time, occurrence location, etc.; Scene_Relation represents the definition of the semantic association relationship between disaster scenarios, such as secondary derivation, concurrency, and group transmission, etc.; Scene_Restriction represents axioms, which describe the constraint relationship between natural disaster scenarios. For example, seawater backflow will cause floods, and seawater backflow is part of the "rainstorm-flood" disaster chain; Scene_Instance represents a specific instance of a natural disaster scenario, such as the storm surge disaster in Shenzhen City, Guangdong Province.

[0031] The "response" part of the ocean storm surge "scenario-response" knowledge graph is a unified description of the conceptual hierarchical relationship, attribute relationship, and association relationship of emergency plan data such as emergency forces, disposal content, and emergency command. The semantic representation of an emergency response subject ontology is: ResponseSubject={Subject_Concept, Subject_Property, Subject_Relation, Subject_Restriction, Subject_Instance} Among them, Subject_Concept represents the set of all emergency response data concepts, including the definition of emergency response subject concepts and conceptual hierarchy classification; Subject_Property represents the definition of the attributes of the emergency response subject itself, such as the name of the emergency response subject, the type of response subject, etc.; Subject_Relation represents the definition of the semantic association relationship between emergency response subjects, such as the inclusion relationship between subjects, etc.; Subject_Restriction represents the axiom, which describes the constraint relationship between subjects; Subject_Instance represents a specific instance of the emergency response subject, such as the disaster emergency command center.

[0032] Combining the semantic expression formulas of "scenario" and "response" ontology, the design of the ocean storm surge "scenario-response" spatiotemporal knowledge graph ontology is obtained as follows: Figure 3 As shown, the double arrows represent mapping rules and the single arrows represent inclusion relationships.

[0033] In previous studies involving knowledge graph construction, the most tedious and time-consuming work is entity and relationship extraction. In recent years, there are many methods used to complete entity and relationship extraction. From the simplest but tedious manual extraction to rule-based extraction methods to deep learning model-based extraction methods, the construction of knowledge graphs has become more and more efficient. Among them, the extraction method based on deep learning models is relatively efficient and has become a hot method in recent years.

[0034] The entity-relationship joint extraction model can extract entities and relationships at the same time, reducing the workload of entity-relationship alignment and greatly improving the efficiency of graph construction. Among them, the CasRel model is relatively well-known in the field of entity-relationship joint extraction models and has high extraction accuracy. In particular, it solves the biggest difficulty in entity-relationship joint extraction - the problem of relationship overlap.

[0035] This technical solution proposes an improved model OSS-CasRel based on the CasRel model. OSS is the abbreviation of the English name of ocean storm surge, indicating that the model is an entity relationship extraction model improved for the field of ocean storm surge. OSS-CasRel replaces the original word segmentation dictionary of the CasRel model and adopts a self-built entity relationship corpus in the field of ocean storm surge. The default word segmentation dictionary divides sentences according to characters, that is, each character in a sentence is a word. This word segmentation method loses the semantics of specific Chinese words. The self-built ocean storm surge corpus contains most of the common geographical vocabulary, which can improve the model's extraction accuracy of entity relationships in the field of ocean storm surges, and also improves the interpretability of the model. The improved model is as follows Figure 4 Secondly, the OSS-CasRel model conducts targeted parameter training for specific texts such as emergency plans, which have a distinct structure, making it more sensitive to the entity relationships in emergency plan texts.

[0036] Knowledge embedding is a widely used knowledge representation method, and its main idea is to embed entities and relationships in the knowledge graph into continuous space vectors. With the development of artificial intelligence technology, deep learning models have shined in the field of natural language processing, such as the BERT pre-trained deep language model, which has achieved significant performance improvements in multiple NLP tasks. BERT-Base-Chinese is a version of the BERT model for Chinese text. It has pre-trained Chinese text and can learn the semantic and grammatical information of Chinese text. Therefore, the present invention performs text knowledge embedding and text vector feature extraction based on the BERT-Base-Chinese model.

[0037] 1.3 “Scenario-Response” Matching Calculation and Knowledge Reasoning The present invention defines the "scenario-response" knowledge reasoning task as a matching task from "scenario" text to "response" text. That is, given a "scenario" text, find the "response" text that best matches it from the knowledge graph as an emergency response plan. The "scenario" text is represented as ,in Represents the overall text of a disaster scenario, Represents the disaster event itself and the collection of related attribute nodes in the graph, Represents the set of event category nodes in the graph that are connected to the disaster event itself. Represents the set of event scale nodes in the graph connected to the disaster event itself, Represents the set of event spatiotemporal attribute nodes in the graph that are connected to the disaster event itself. The “response” text is represented by ,in Represents the overall text of the response strategy under a disaster situation, Represents the emergency plan itself and the set of related attribute nodes in the graph, Represents the set of treatment category nodes in the graph that are connected to the emergency plan itself. Represents the set of treatment level nodes in the graph that are connected to the emergency plan itself. It represents the collection of spatiotemporal attribute nodes in the graph that are connected to the emergency plan itself. Both the "scenario" text and the "response" text are composed of the associated nodes in the constructed ocean storm surge "scenario-response" knowledge graph. This matching method based on the associated node information in the knowledge graph is more scientific and explainable.

[0038] The overall process of ocean storm surge "scenario-response" knowledge embedding and knowledge reasoning is as follows: Figure 5 As shown, first and Use semicolons to separate them into one text The model uses the tokenizer as input, and the token sequence is output after the tokenizer of the BERT-Base-Chinese model performs word segmentation and text vectorization. input_ids and used to determine the valid position in the token attention_mask ;The second step is to extract text features. First, load the pre-trained model, and then input_ids and attention_mask The vector features of the text are calculated as the parameters of the pre-trained model last_hidden_state ;The third step is to calculate the text matching degree. First, define the downstream text matching task model, and then use the model to calculate the matching score between the "scenario" text and the "response" text. out ; Finally, an emergency response plan is generated. First, the "response" text with the highest score after matching calculation under the current "scenario" is taken as the final result, and then the "response" text with the highest score is split according to different attributes to generate the final emergency decision-making plan. Finally, the "response" reasoning results are visualized based on the constructed ocean storm surge "scenario-response" knowledge graph.

[0039] 2 Experiments 2.1 Construction of a “scenario-response” disaster management system integrating event chains and emergency plans In the present invention, the disaster event data is obtained from news reports, marine disaster bulletins, journals, etc. in the past ten years by combining crawlers and manual selection. Then, according to the event chain construction and deduction analysis theory in Section 1.1, typical storm surge disaster events are sorted out, and the storm surge propagation mechanism and secondary derivative law are analyzed using the time-space constraint analysis method. Finally, the secondary derivative relationship table of typical marine storm surge disaster events is obtained as shown in Table 2: The disaster event level is divided into four levels according to the secondary derivative law.

[0040] Table 2 Secondary derivative relationships of typical marine storm surge disaster events

[0041] The plans studied in this technical solution are mainly from the emergency plans published on the government portal websites at all levels in Guangdong Province, cities, districts, and streets. After being obtained by combining crawlers and manual selection, the plans related to marine storm surge disasters were further collected and sorted, such as the "Guangdong Meteorological Disaster Plan", "Shenzhen Flood Control Plan", "Longgang District Meteorological Disaster Emergency Plan", "Henggang Street Natural Disaster Emergency Plan", etc., totaling 1,043. Combined with the structured analysis results of marine storm surge disaster events and emergency plans in the above text, the storm surge disaster disposal chain was analyzed and the marine storm surge disaster event disposal system was obtained. Figure 6 shown.

[0042] 2.2 Construction of “Scenario-Response” Visual Knowledge Graph In order to give full play to the response speed advantage of the "scenario-response" mode and meet the response plan needs of emergency personnel in different disaster scenarios, the present invention proposes to recommend reasonable response plans for emergency personnel by integrating the "scenario-response" visual knowledge graph of event chain and emergency plan. The present invention first takes the disaster event caused by Typhoon "Pearl" No. 1 in Shenzhen City, Guangdong Province in 2006 and the "Shenzhen City Typhoon Emergency Plan" as an example, and extracts knowledge from the disaster event and emergency plan according to the ontology layer of the "scenario-response" visual knowledge graph of ocean storm surge defined in Section 1.2. The data of the knowledge extraction experiment comes from the storm surge disaster events and emergency plans collected above, and the entities and relationships therein are organized into JSON format to form the training set and validation set of the model. The attribute names, attribute meanings and samples in the JSON data are shown in Table 3. There are 13414 data in the training set and 5312 data in the validation set. After multiple experiments, the accuracy of the CasRel model on the validation set is 65%, and the accuracy of the OSS-CasRel model on the validation set reaches 80%. The experimental results show that the improved OSS-CasRel model can more accurately extract entities and relationships in marine storm surge disaster events and emergency plan texts. Finally, the entity and relationship triples extracted by the OSS-CasRel model are saved in the neo4j database to complete the construction of the marine storm surge "scenario-response" knowledge graph. In this case, a total of 18,525 entities and 68 relationships were extracted. Figure 7 Some nodes in the knowledge graph are displayed, among which the green node represents a specific event in the event chain; the blue node represents the emergency plan; the purple node represents the command entity; the red node represents the response level; and the gray node represents the disposal entity.

[0043] Table 3 OSS-CasRel model input data name, meaning and example

[0044] 2.3 Experimental Methods and Case Analysis In order to verify the accuracy of the marine storm surge "scenario-response" knowledge reasoning method, the present invention conducts experiments through the disaster events caused by Typhoon "Pearl" in Shenzhen City and the "Shenzhen Typhoon Emergency Plan" and "Longgang District Meteorological Disaster Emergency Plan" and other data. The reasoning results of emergency information such as plan name, disposal subject, disposal content, command subject, plan category, plan level, response level, geographical location, disposal stage, land use type and the coincidence rate of the original control experimental data are selected as evaluation indicators to measure the accuracy of the recommended results from a macro perspective. This section conducts a "scenario-response" knowledge reasoning experiment based on the marine storm surge "scenario-response" knowledge graph constructed in Section 1.2 and the "scenario-response" matching degree calculation and knowledge reasoning overall process introduced in Section 1.3. The experimental data of the "scenario-response" matching degree calculation model comes from the node information in the marine storm surge "scenario-response" knowledge graph, and the node information in the graph is merged according to the expression formula of the "scenario" text and the "response" text. Taking the Xichong Coastal Seawall Breach Incident in Dapeng Street, Longgang District, Shenzhen’s Eastern Coast and the Longgang District Meteorological Disaster Emergency Plan as examples, the entities and relationships involved in the “Scenario-Response” model are expressed in the knowledge graph in the following diagram: Figure 8 The left half is shown. Among them, green nodes represent disaster events; blue nodes represent emergency plans; purple nodes represent attribute categories of disaster events and emergency plans; and red nodes represent specific attribute values. The spliced ​​"scenario" text , "Response" text The information of the knowledge graph nodes involved is shown in Table 4, where the classification of land use types is based on the national standard "Land Use Status Classification" (GB / T21010-2017) revised by national departments. The current "scenario" text is spliced ​​with each "response" text input as Figure 5 The input of the process shown in the figure is used to calculate the recommended "response" text with the highest score under the current "scenario", and the emergency information such as the name of the emergency plan, disposal subject, disposal content, command subject, plan category, plan level, response level, geographical location, disposal stage, land use type, etc. is extracted, and the "response" node information of the original "response" text in the marine storm surge "scenario-response" knowledge graph is visualized, as shown in Figure 1. Figure 8As shown in the right half: blue nodes represent the names of the plans; purple nodes represent the attribute categories of disaster events and emergency plans; red nodes represent specific attribute values; brown nodes represent specific names of disposal entities; and gray nodes represent specific disposal contents. Finally, the "response" recommendation text output by the model is compared with the "response" node information of the original "response" text in the "scenario-response" knowledge graph of the ocean storm surge (as shown in the example shown in Table 4), and the overlap rate between the inference result and the original data is calculated and used as the accuracy of the model.

[0045] Table 4 “Scenario” and “Response” texts and their node information in the knowledge graph

[0046] 2.4 Overall Results and Analysis The training set of the ocean storm surge "scenario-response" knowledge reasoning model has a total of 1044 data, and the validation set has a total of 642 data. The "scenario" and "response" text data in the validation set are reasoned according to the knowledge embedding and knowledge reasoning process, and the coincidence rate of different node information in the original visualization form of the "response" text reasoning results and the experimental data is recorded. The experimental results are shown in Table 5.

[0047] Table 5 Overall experimental results

[0048] Among them, the overlap rates of plan name, disposal subject and plan level are 96%, 95% and 95% respectively, which are higher than the overlap rates of other node attributes, indicating that the model is better in extracting plan name features, disposal subject and plan level features. The possible reason is that the plan name, disposal subject and plan level texts contain more distinct feature information, such as disaster-stricken areas, disaster categories, department names, province, city and district names, etc.; while other node attributes such as command subject, plan category, response level, geographical location, disposal stage, land use, etc. have less distinguishable feature information; the disposal content text is often long and has poor relationship It is more complex and difficult to extract, so the matching effect is not ideal; however, in the process of emergency personnel actually using the marine storm surge "scenario-response" knowledge map, they only need to construct the current "scenario" text and input it into the model to obtain the "response" recommended text. According to the plan name information in the "response" recommended text, the emergency plan and the associated disposal subject, disposal content, command subject, plan category, plan level, response level, geographical location, disposal stage, land use type and other node information visualization map results can be queried in the marine storm surge "scenario-response" knowledge map and used. From the perspective of practical application, the generation of the visualization map recommendation results mainly depends on the overlap rate of the plan name, so overall, the "scenario-response" reasoning model proposed in the present invention has a higher recommendation accuracy.

[0049] The present invention has the following advantages: The present invention integrates event chains and emergency plans to construct a marine storm surge "scenario-response" knowledge graph. Through the "scenario-response" knowledge reasoning method, a rapid response to complex and changeable disaster "scenarios" is achieved. The event chain can clearly display the secondary derivative relationship between disaster events, thereby assisting emergency personnel to prevent possible secondary derivative disasters in advance; the event itself, event category, event scale, and spatiotemporal attributes contained in the event chain constitute the "scenario" of the disaster event. In the knowledge graph, the attribute information of each disaster event is stored in the form of a triple node, which is convenient for decision-makers to quickly form disaster "scenario" information based on the information of each node associated with the current disaster event, and these "scenarios" are linked through the event chain to form a "scenario" chain. As a guiding document for emergency response work, the importance of emergency plans in the process of disaster prevention and mitigation is self-evident. Through the analysis of the content and structure of the emergency plan, the present invention completes the design of the emergency plan ontology and splits the content in the emergency plan into triple nodes according to the ontology design and saves it in the knowledge graph, thereby improving the efficiency of the use of the emergency plan. In the process of constructing the knowledge graph, the present invention uses a joint entity and relationship extraction model to complete the extraction work, and uses a self-built marine storm surge field corpus to further improve the model extraction effect. Experimental results show that this method can greatly improve the efficiency of graph construction and reduce labor costs.

[0050] In order to further improve the speed of generating emergency response plans for different disaster scenarios, the present invention proposes a "scenario-response" knowledge reasoning method that integrates event chains and emergency plans. The rapid matching of "scenario" text to "response" text is achieved through a text matching deep learning model. Experiments show that this method not only has high accuracy but also has better interpretability based on the matching of associated node information in the knowledge graph. In practical applications, the disaster "scenario" can be constructed through the disaster event "scenario" ontology design proposed in the technical solution, and then the disaster "scenario" and each "response" text are input into the model to calculate the matching degree. Finally, the "response" text with the highest matching degree is reverse parsed according to the attribute information of the emergency plan and combined with the associated nodes in the knowledge graph to obtain a visualized emergency response plan.

[0051] Compared with the previous technologies related to the emergency response methods for marine storm surge disasters, firstly, the technical solution of the present invention closely combines the event chain with the emergency plan knowledge, and realizes the visual expression of the knowledge association relationship through the knowledge graph; secondly, the efficiency and accuracy of knowledge reasoning are improved by using deep learning models and self-built marine storm surge field dictionaries; in addition, the input of the model comes from the associated node information in the knowledge graph, which also improves the interpretability of the model to a certain extent; finally, the marine storm surge "scenario-response" knowledge graph and knowledge reasoning model constructed by the technical solution of the present invention can not only complete the "scenario-response" matching of historical disaster events, realize pre-disaster rehearsal and post-disaster analysis, but also can match the "response" knowledge base text according to the real-time generated disaster "scenario" text, generate emergency response plans and visualize the graph recommendation results to achieve response during the disaster, improve the whole process of marine storm surge disaster prevention and mitigation chain, improve the generalization ability of knowledge reasoning methods, and provide important support for further improving the intelligent disposal capabilities of marine storm surge disasters.

[0052] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0053] Reference Fig. 9 , shows a structural block diagram of a marine storm surge emergency response plan recommendation device provided in an embodiment of the present invention, which may specifically include the following modules: The disaster handling system construction module 901 is used to construct an ocean storm surge disaster handling system; the ocean storm surge disaster handling system includes an event chain structure, a secondary derivative relationship table of typical ocean storm surge disaster events, an emergency plan knowledge element concept system, and an emergency plan entity relationship expression model; The disaster disposal visualization knowledge graph generation module 902 is used to generate a marine storm surge disaster disposal visualization knowledge graph ontology according to the marine storm surge disaster disposal system, and based on the marine storm surge disaster disposal visualization knowledge graph ontology, jointly extract entities and relationships of a large number of historical marine storm surge events and emergency plans to generate a marine storm surge disaster disposal visualization knowledge graph; The real-time event chain matching and deduction module 903 is used to match and deduce the current event according to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events to obtain the event chain of the current event; the event chain of the current event includes the disaster situation that has occurred in the current event and the secondary derivative disasters that may occur in the future; The emergency response plan generation module 904 is used to match the event chain of the current event with the visual knowledge graph of ocean storm surge disaster disposal, obtain the ocean storm surge emergency response plan of the current event, and visualize the ocean storm surge emergency response plan of the current event in the form of a knowledge graph and recommend it to emergency decision makers.

[0054] Optionally, the disaster handling system construction module is also used to: The event chain structure is obtained by analyzing the structural characteristics of a large number of historical ocean storm surge events, and the storm surge propagation mechanism and secondary derivative law of a large number of historical ocean storm surge events are analyzed by using the time-space constraint analysis method to obtain the secondary derivative relationship table of typical ocean storm surge disaster events; A structured analysis of the ocean storm surge emergency plan was conducted to obtain the conceptual system of emergency plan knowledge elements, and the relationship between different types of elements was analyzed to obtain the emergency plan entity relationship expression model; the emergency plan knowledge element conceptual system includes emergency plan categories, emergency plan handling procedures, and emergency plan basic contents.

[0055] Optionally, the disaster disposal visualization knowledge graph generation module is further used to: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the conceptual hierarchical relationship, attribute relationship and association relationship in the disaster scenario are sorted out to generate the disaster scenario ontology semantic expression formula. According to the emergency plan knowledge element concept system and the emergency plan entity relationship expression model, the conceptual hierarchical relationship, attribute relationship and association relationship of the emergency plan are sorted out to generate the emergency response subject ontology semantic expression formula. The disaster scenario ontology semantic expression formula and the emergency response subject ontology semantic expression formula are integrated to generate the marine storm surge disaster disposal visualization knowledge graph ontology. Based on the visual knowledge graph ontology of marine storm surge disaster disposal, the OSS-CasRel model is used to jointly extract entities and relationships from a large number of historical marine storm surge events and emergency plans, and generate a visual knowledge graph for marine storm surge disaster disposal. The OSS-CasRel model is an improved CasRel model, which uses a self-built entity relationship corpus in the field of marine storm surge to replace the word segmentation dictionary of the original CasRel model, and uses the marine storm surge emergency plan for parameter training.

[0056] Optionally, the emergency response plan generation module is further used to: The text representation of the event chain and the text representation of the emergency response plan in the visual knowledge graph of marine storm surge disaster disposal are spliced ​​together, and the BERT-Base-Chinese model is used for text knowledge embedding and text vector feature extraction to obtain the event chain-emergency response plan text embedding vector; The BERT-Base-Chinese model is used to perform text knowledge embedding and text vector feature extraction on the text representation of the event chain of the current event, and the event chain text embedding vector of the current event is obtained; The matching degree of each event chain-emergency response plan text embedding vector with the event chain text embedding vector of the current event is calculated, and the event chain-emergency response plan text embedding vector with the highest matching degree is split according to different attributes to obtain the ocean storm surge emergency response plan for the current event.

[0057] Optionally, the real-time event chain matching and deduction module is further used to: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the structural characteristics, storm surge propagation mechanism and secondary derivative law of the current event are analyzed to obtain the event chain of the current event.

[0058] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0059] In addition, an embodiment of the present invention further provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus. Memory, used to store computer programs; The processor is used to implement the method for recommending an emergency response plan for ocean storm surges as described in the above embodiment when executing the program stored in the memory.

[0060] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0061] The communication interface is used for communication between the above terminal and other devices.

[0062] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0063] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0064] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, which stores instructions. When the computer-readable storage medium is executed on a computer, the computer executes the method for recommending an emergency response plan for ocean storm surges described in the above embodiment.

[0065] In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the method for recommending an emergency response plan for ocean storm surges described in the above embodiment.

[0066] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0067] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0068] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0069] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for recommending an emergency response plan for an ocean storm surge, characterized in that: The method comprises: Constructing a marine storm surge disaster disposal system; the marine storm surge disaster disposal system includes an event chain structure, a secondary derivative relationship table of typical marine storm surge disaster events, a concept system of emergency plan knowledge elements, and an emergency plan entity relationship expression model; According to the marine storm surge disaster disposal system, a visual knowledge graph ontology for marine storm surge disaster disposal is generated. Based on the visual knowledge graph ontology for marine storm surge disaster disposal, entities and relationships are jointly extracted from a large number of historical marine storm surge events and emergency plans to generate a visual knowledge graph for marine storm surge disaster disposal. According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the current event is matched and deduced to obtain the event chain of the current event; the event chain of the current event includes the disaster situation that has occurred in the current event and the secondary derivative disasters that may occur in the future; The event chain of the current event is matched with the visual knowledge graph of ocean storm surge disaster disposal to obtain the ocean storm surge emergency response plan of the current event, and the ocean storm surge emergency response plan of the current event is visualized in the form of a knowledge graph and recommended to emergency decision makers.

2. The method according to claim 1, characterized in that Construct a marine storm surge disaster management system, including: The event chain structure is obtained by analyzing the structural characteristics of a large number of historical ocean storm surge events, and the storm surge propagation mechanism and secondary derivative law of a large number of historical ocean storm surge events are analyzed by using the time-space constraint analysis method to obtain the secondary derivative relationship table of typical ocean storm surge disaster events; A structured analysis of the ocean storm surge emergency plan was conducted to obtain the conceptual system of emergency plan knowledge elements, and the relationship between different types of elements was analyzed to obtain the emergency plan entity relationship expression model; the emergency plan knowledge element conceptual system includes emergency plan categories, emergency plan handling procedures, and emergency plan basic contents.

3. The method according to claim 1, characterized in that According to the marine storm surge disaster disposal system, a visual knowledge graph ontology for marine storm surge disaster disposal is generated. Based on the visual knowledge graph ontology for marine storm surge disaster disposal, entities and relationships are jointly extracted for a large number of historical marine storm surge events and emergency plans to generate a visual knowledge graph for marine storm surge disaster disposal, including: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the conceptual hierarchical relationship, attribute relationship and association relationship in the disaster scenario are sorted out to generate the disaster scenario ontology semantic expression formula. According to the emergency plan knowledge element concept system and the emergency plan entity relationship expression model, the conceptual hierarchical relationship, attribute relationship and association relationship of the emergency plan are sorted out to generate the emergency response subject ontology semantic expression formula. The disaster scenario ontology semantic expression formula and the emergency response subject ontology semantic expression formula are integrated to generate the marine storm surge disaster disposal visualization knowledge graph ontology. Based on the visual knowledge graph ontology of marine storm surge disaster disposal, the OSS-CasRel model is used to jointly extract entities and relationships from a large number of historical marine storm surge events and emergency plans, and generate a visual knowledge graph for marine storm surge disaster disposal. The OSS-CasRel model is an improved CasRel model, which uses a self-built entity relationship corpus in the field of marine storm surge to replace the word segmentation dictionary of the original CasRel model, and uses the marine storm surge emergency plan for parameter training.

4. The method according to claim 1, characterized in that Match the event chain of the current event with the visual knowledge graph of marine storm surge disaster disposal to obtain the marine storm surge emergency response plan for the current event, including: The text representation of the event chain and the text representation of the emergency response plan in the visual knowledge graph of marine storm surge disaster disposal are spliced ​​together, and the BERT-Base-Chinese model is used for text knowledge embedding and text vector feature extraction to obtain the event chain-emergency response plan text embedding vector; The BERT-Base-Chinese model is used to embed text knowledge and extract text vector features from the text representation of the event chain of the current event, and the event chain text embedding vector of the current event is obtained; The matching degree of each event chain-emergency response plan text embedding vector with the event chain text embedding vector of the current event is calculated, and the event chain-emergency response plan text embedding vector with the highest matching degree is split according to different attributes to obtain the ocean storm surge emergency response plan for the current event.

5. The method according to claim 1, characterized in that According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the current event is matched and deduced to obtain the event chain of the current event, including: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the structural characteristics, storm surge propagation mechanism and secondary derivative law of the current event are analyzed to obtain the event chain of the current event.

6. A device for recommending marine storm surge emergency response plans, characterized in that: The device comprises: A disaster disposal system construction module is used to construct an ocean storm surge disaster disposal system; the ocean storm surge disaster disposal system includes an event chain structure, a secondary derivative relationship table of typical ocean storm surge disaster events, an emergency plan knowledge element concept system, and an emergency plan entity relationship expression model; The disaster disposal visualization knowledge graph generation module is used to generate a visualization knowledge graph ontology for marine storm surge disaster disposal based on the marine storm surge disaster disposal system, and to jointly extract entities and relationships of a large number of historical marine storm surge events and emergency plans based on the visualization knowledge graph ontology for marine storm surge disaster disposal, so as to generate a visualization knowledge graph for marine storm surge disaster disposal; The real-time event chain matching and deduction module is used to match and deduce the current event according to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events to obtain the event chain of the current event; the event chain of the current event includes the disaster situation that has occurred in the current event and the secondary derivative disasters that may occur in the future; The emergency response plan generation module is used to match the event chain of the current event with the visual knowledge graph of ocean storm surge disaster disposal, obtain the ocean storm surge emergency response plan of the current event, and visualize the ocean storm surge emergency response plan of the current event in the form of a knowledge graph and recommend it to emergency decision makers.

7. The device according to claim 6, characterized in that The disaster management system building module is also used for: The event chain structure is obtained by analyzing the structural characteristics of a large number of historical ocean storm surge events, and the storm surge propagation mechanism and secondary derivative law of a large number of historical ocean storm surge events are analyzed by using the time-space constraint analysis method to obtain the secondary derivative relationship table of typical ocean storm surge disaster events; A structured analysis of the ocean storm surge emergency plan was conducted to obtain the conceptual system of emergency plan knowledge elements, and the relationship between different types of elements was analyzed to obtain the emergency plan entity relationship expression model; the emergency plan knowledge element conceptual system includes emergency plan categories, emergency plan handling procedures, and emergency plan basic contents.

8. The device according to claim 6, characterized in that The disaster disposal visualization knowledge graph generation module is also used for: According to the event chain structure and the secondary derivative relationship table of typical marine storm surge disaster events, the conceptual hierarchical relationship, attribute relationship and association relationship in the disaster scenario are sorted out to generate the disaster scenario ontology semantic expression formula. According to the emergency plan knowledge element concept system and the emergency plan entity relationship expression model, the conceptual hierarchical relationship, attribute relationship and association relationship of the emergency plan are sorted out to generate the emergency response subject ontology semantic expression formula. The disaster scenario ontology semantic expression formula and the emergency response subject ontology semantic expression formula are integrated to generate the marine storm surge disaster disposal visualization knowledge graph ontology. Based on the visual knowledge graph ontology of marine storm surge disaster disposal, the OSS-CasRel model is used to jointly extract entities and relationships from a large number of historical marine storm surge events and emergency plans, and generate a visual knowledge graph for marine storm surge disaster disposal. The OSS-CasRel model is an improved CasRel model, which uses a self-built entity relationship corpus in the field of marine storm surge to replace the word segmentation dictionary of the original CasRel model, and uses the marine storm surge emergency plan for parameter training.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the method for recommending an ocean storm surge emergency response plan as described in any one of claims 1 to 5 when executing the program stored in the memory.

10. One or more computer-readable media having instructions stored thereon, which, when executed by one or more processors, enable the processors to execute the method for recommending marine storm surge emergency response plans as described in any one of claims 1-5.

Images