Disaster event emergency aid decision-making method, device and equipment, storage medium and computer program product

Abstract

The invention relates to the technical field of disaster early warning, in particular to a disaster event emergency aid decision-making method, device and equipment, a storage medium and a computer program product. The method comprises the following steps: constructing an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and non-structured disaster professional data; based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database, determining the probability of secondary disasters and derivative disasters of the initial disaster events; constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of occurrence of secondary disasters and derivative disasters of the initial disaster event; the disaster knowledge graph is accessed to the preset digital emergency plan system, so that the accuracy of disaster event emergency aid decision making is improved.

Description

Technical Field

[0001] The present application relates to the field of disaster warning technology, and in particular to a disaster event emergency decision-making auxiliary method, device, equipment, storage medium and computer program product. Background Art

[0002] In the safety management and emergency response of modern cities, emergency decision-making assistance for disaster events has become a key link in ensuring public safety and reducing disaster losses. With the acceleration of urbanization and the frequent occurrence of extreme weather caused by climate change, various disaster events (such as earthquakes, floods, fires, etc.) pose a serious threat to urban infrastructure and residents' safety. Traditional emergency response models usually rely on static disaster plans, which make it difficult to capture secondary and derivative events that may occur in the disaster chain in real time, and thus cannot provide comprehensive emergency plan support. This limitation easily leads to delayed disaster response and affects the efficiency of overall emergency disposal. In recent years, with the development of big data and artificial intelligence technologies, intelligent emergency decision-making systems based on knowledge graphs have gradually become a research hotspot. Knowledge graphs can organically link disaster events, secondary and derivative disasters, and their causal relationships, so as to better support the modeling and analysis of complex disaster chains. However, current emergency plan systems usually lack effective integration and real-time dynamics of disaster event data, especially when calculating the probability of secondary and derivative events, the timeliness of data is not fully considered, resulting in the inability to timely predict the possibility of secondary and derivative disasters, affecting the accuracy of early warnings and the timeliness of emergency response, and resulting in inaccurate emergency decision-making assistance for disaster events. Therefore, how to improve the accuracy of emergency decision-making support for disaster events has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of this application is to provide a disaster event emergency decision-making assistance method, device, equipment, storage medium and computer program product, aiming to solve the technical problem of how to improve the accuracy of disaster event emergency decision-making assistance.

[0004] To achieve the above objectives, the present application provides a disaster emergency decision-making assistance method, the method comprising the following steps:

[0005] Construct an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data, and unstructured disaster professional data;

[0006] Based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database, determine the probability of secondary disasters and derivative disasters occurring from the initial disaster event;

[0007] Constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring from the initial disaster event;

[0008] The disaster knowledge graph is connected to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, the secondary events and derivative events corresponding to the probabilities of the secondary disasters and the derivative disasters greater than the preset secondary derivative probability threshold and the prevention strategies corresponding to the secondary events and the derivative events are pushed.

[0009] In one embodiment, before the step of constructing an emergency plan knowledge database based on structured disaster history data, semi-structured disaster field data and unstructured disaster professional data, the step further includes:

[0010] Acquiring the structured disaster historical data;

[0011] Parsing the webpage structure of the webpage where the semi-structured disaster field data is located based on a preset webpage element template matching model, and acquiring the semi-structured disaster field data in combination with a preset webpage crawler technology;

[0012] Based on the search keywords corresponding to the unstructured disaster professional data, a preset document search engine is used in combination with the preset web crawler technology to obtain the unstructured disaster professional data.

[0013] In one embodiment, the step of constructing an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data, and unstructured disaster professional data includes:

[0014] Preprocessing the structured disaster historical data, the semi-structured disaster field data and the unstructured disaster professional data to obtain preprocessed data, wherein the preprocessing includes one or more of format conversion, data cleaning and data denoising;

[0015] Verifying the preprocessed data by a preset cross-validation method;

[0016] Based on a preset classification and sorting strategy, classify and sort the pre-processed data that has passed the verification;

[0017] Based on the classification and sorting results, the emergency plan knowledge database is constructed.

[0018] In one embodiment, the step of determining the probability of secondary disasters and derivative disasters occurring from the initial disaster event based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database includes:

[0019] Based on a preset screening standard, the data in the emergency plan knowledge database is screened to obtain screening data, wherein the screening data includes a plurality of initial disaster event data;

[0020] Determining the occurrence frequency of each of the initial disaster events according to the screening data;

[0021] Based on the time when the event in the screened data occurred, assigning a timeliness weight to each piece of initial disaster event data, and marking secondary disasters and derivative disasters in each piece of initial disaster event data;

[0022] Based on the marking results, the occurrence frequency of the initial disaster event is combined with the corresponding timeliness weight to determine the probability of the secondary disaster and the derivative disaster occurring due to the initial disaster event.

[0023] In one embodiment, the step of constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event includes:

[0024] Performing entity extraction on the emergency plan knowledge database to obtain multiple disaster entities, and classifying and attribute labeling the disaster entities;

[0025] Determine the relationship type and entity causal relationship based on the classification and attribute labeling results;

[0026] An initial graph structure is constructed by taking the multiple disaster entities as nodes and the relationship types as edges;

[0027] Determine the disaster hierarchy structure based on the entity cause-effect relationship;

[0028] According to the probability of secondary disasters and derivative disasters occurring from the initial disaster event, determine the secondary derivative high probability path;

[0029] The disaster knowledge graph is constructed based on the initial graph structure, the disaster hierarchical structure and the secondary derived high probability path.

[0030] In one embodiment, after the step of connecting the disaster knowledge graph to a preset digital emergency plan system, the method further includes:

[0031] Determine the resources needed based on the prevention strategy;

[0032] Classifying the risk levels of the initial disaster event, the secondary event, and the derivative event;

[0033] Based on the risk level classification result, the required resources are allocated, and the allocated resources are tracked.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a disaster event emergency decision-making auxiliary device, the disaster event emergency decision-making auxiliary device comprising:

[0035] Database construction module, used to build emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data;

[0036] A secondary derivative evaluation module is used to determine the probability of secondary disasters and derivative disasters occurring from the initial disaster event based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database;

[0037] A graph construction module, for constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event;

[0038] The target module is used to connect the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, the secondary events and derivative events corresponding to the probabilities of the secondary disasters and the derivative disasters greater than the preset secondary derivative probability threshold and the prevention strategies corresponding to the secondary events and the derivative events are pushed.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a disaster event emergency decision-making assistance device, which includes: a memory, a processor, and a disaster event emergency decision-making assistance program stored in the memory and executable on the processor, and the disaster event emergency decision-making assistance program is configured to implement the steps of the disaster event emergency decision-making assistance method as described above.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a disaster event emergency decision-making assistance program is stored. When the disaster event emergency decision-making assistance program is executed by a processor, the steps of the disaster event emergency decision-making assistance method described above are implemented.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the disaster event emergency decision-making support method as described above.

[0042] This application constructs an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data; determines the probability of secondary disasters and derivative disasters occurring in initial disaster events based on the frequency and timeliness of each initial disaster event in the emergency plan knowledge database; constructs a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in initial disaster events; connects the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving emergency plans through the preset digital emergency plan system, based on the disaster knowledge graph, pushes secondary events and derivative events corresponding to the probability of secondary disasters and derivative disasters greater than a preset secondary derivative probability threshold, as well as prevention strategies corresponding to the secondary events and derivative events. This application comprehensively improves the coverage of disaster information by constructing an emergency plan knowledge database and integrating structured, semi-structured and unstructured multi-level data sources; determines the probability of secondary and derivative disasters based on the frequency and timeliness of initial disaster events in the database, and realizes a dynamic assessment of secondary and derivative disaster risks; constructs a disaster knowledge graph based on the results of probability analysis, clarifies the causal relationship between the initial disaster and its secondary and derivative disasters, and enhances the system's response capability to complex disaster chains; connects the disaster knowledge graph to the digital emergency plan system, pushes high-risk secondary and derivative events and their prevention strategies in real time, ensures the timeliness and predictability of emergency response, and significantly improves the accuracy of emergency auxiliary decision-making for disaster events. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flowchart of the first embodiment of the disaster emergency decision-making assistance method of the present application;

[0044] Figure 2 This is a schematic diagram of a sub-flow in the second embodiment of the disaster emergency decision-making assistance method of the present application;

[0045] Figure 3 This is a schematic diagram of a sub-flow in the third embodiment of the disaster emergency decision-making assistance method of the present application;

[0046] Figure 4 This is a schematic diagram of a disaster knowledge graph in an embodiment of a disaster event emergency decision-making assistance method of this application;

[0047] Figure 5 This is a schematic diagram of the importance of data in an embodiment of the disaster emergency decision-making assistance method of this application;

[0048] Figure 6 This is a schematic diagram of the module structure of the disaster emergency decision-making auxiliary device according to an embodiment of the present application;

[0049] Figure 7Schematic diagram of the device structure of the hardware operating environment involved in the disaster event emergency decision-making auxiliary method in the embodiment of the present application.

[0050] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] It should be noted that in the safety management and emergency response of modern cities, emergency decision-making support for disaster events has become a key link in ensuring public safety and reducing disaster losses. With the acceleration of urbanization and the frequent occurrence of extreme weather caused by climate change, various disaster events (such as earthquakes, floods, fires, etc.) pose a serious threat to urban infrastructure and residents' safety. Traditional emergency response models usually rely on static disaster plans, which makes it difficult to capture secondary and derivative events that may occur in the disaster chain in real time, and thus cannot provide comprehensive emergency plan support. This limitation easily leads to delayed disaster response and affects the efficiency of overall emergency response. In recent years, with the development of big data and artificial intelligence technologies, intelligent emergency decision-making systems based on knowledge graphs have gradually become a research hotspot. Knowledge graphs can organically link disaster events, secondary and derivative disasters, and the causal relationships between them, thereby better supporting the modeling and analysis of complex disaster chains. However, the current emergency plan system usually lacks effective integration and real-time dynamics of disaster event data, especially when calculating the probability of secondary and derivative events, the timeliness of the data is not fully considered, resulting in the inability to timely predict the possibility of secondary and derivative disasters, affecting the accuracy of early warning and the timeliness of emergency response, and resulting in inaccurate emergency auxiliary decision-making for disaster events. Therefore, how to improve the accuracy of emergency auxiliary decision-making for disaster events has become a technical problem that needs to be solved urgently.

[0054] The main solutions of this application are: to build an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data; to determine the probability of secondary disasters and derivative disasters occurring in initial disaster events based on the frequency and timeliness of each initial disaster event in the emergency plan knowledge database; to build a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in initial disaster events; to connect the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving emergency plans through the preset digital emergency plan system, based on the disaster knowledge graph, secondary events and derivative events corresponding to the probability of secondary disasters and derivative disasters greater than a preset secondary derivative probability threshold, as well as prevention strategies corresponding to secondary events and derivative events, are pushed.

[0055] This application improves the coverage of disaster information comprehensively by building an emergency plan knowledge database and integrating structured, semi-structured and unstructured multi-level data sources; determines the probability of secondary and derivative disasters based on the frequency and timeliness of initial disaster events in the database, and realizes dynamic assessment of secondary and derivative disaster risks; constructs a disaster knowledge graph based on the results of probability analysis, clarifies the causal relationship between initial disasters and their secondary and derivative disasters, and enhances the system's response capability to complex disaster chains; connects the disaster knowledge graph to the digital emergency plan system, pushes high-risk secondary and derivative events and their prevention strategies in real time, ensures the timeliness and predictability of emergency response, and significantly improves the accuracy and efficiency of emergency auxiliary decision-making for disaster events.

[0056] It should be noted that the execution subject of the method of this embodiment can be a computing service device with data processing, network communication and program running functions, or it can be the above-mentioned disaster event emergency decision-making auxiliary device with the same or similar functions. This embodiment and the following embodiments will be described by taking the disaster event emergency decision-making auxiliary device as an example.

[0057] Based on this, the first embodiment of the disaster emergency decision-making auxiliary method of the present application is proposed, please refer to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the disaster emergency decision-making assistance method of the present application.

[0058] In this embodiment, the disaster event emergency decision-making auxiliary method includes the following steps:

[0059] S1: Construct an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data, and unstructured disaster professional data;

[0060] It should be noted that structured disaster historical data refers to historical disaster information recorded in a fixed format, usually stored in the form of tables or databases, which is convenient for data screening and analysis. The sources of this type of data mainly include disaster statistical yearbooks, government disaster databases, etc., which contain basic information such as event type, time of occurrence, location, and scope of impact. Semi-structured disaster field data refers to data that is partially formatted but not fully structured, mainly from industry websites, news reports, disaster warning web pages, etc. This type of data usually contains some label information (such as title, time, and location), but the format of the text content is not uniform and needs further processing. Unstructured disaster professional data refers to data that has no fixed format and comes directly from text or multimedia, usually from professional literature, research reports, and minutes of expert meetings. This type of data is mostly free text or multimedia, lacking a unified data structure, but contains rich domain knowledge and professional opinions. The emergency plan knowledge database refers to a database that integrates and stores structured, semi-structured, and unstructured data, and is used to manage emergency plan related information. As the basis for emergency decision-making assistance, this database contains a comprehensive summary of historical disaster information, event patterns, and expert knowledge.

[0061] Specifically, data collection is first carried out. In order to ensure the comprehensiveness and accuracy of the knowledge database, structured, semi-structured and unstructured data are obtained from different sources. Structured data comes from official channels such as disaster history records or disaster statistical yearbooks to ensure data standardization and consistency; semi-structured data is obtained by parsing disaster-related websites and news reports, using crawler technology to obtain real-time or semi-real-time disaster information; unstructured data is mainly extracted from professional materials such as research literature and minutes of disaster meetings, and key information is extracted from unstructured texts using keyword retrieval and text analysis technology.

[0062] Furthermore, after completing data collection, data cleaning and processing are performed. Different types of data are converted into different formats. Structured data can be directly stored, and semi-structured and unstructured data need to be further processed, such as extracting key information such as location, time, and event type through natural language processing technology, and unifying the format. Data cleaning includes removing irrelevant data, deleting redundant information, and processing missing values ​​to ensure the accuracy and completeness of the data. The processed data is classified and sorted according to the disaster type, time, and region, and finally integrated into the emergency plan knowledge database to provide a basis for disaster event analysis and decision support.

[0063] By building an emergency plan knowledge database, structured, semi-structured and unstructured disaster data are effectively integrated to form a comprehensive information base covering historical disaster events, domain knowledge and professional insights. This integration of multi-source data not only expands the breadth of the database, but also improves the accuracy and consistency of the data through data cleaning and unified format processing, laying a solid foundation for the analysis and prediction of subsequent disaster events. In addition, the construction of the emergency plan knowledge database facilitates the rapid retrieval of information when a disaster occurs, supports disaster chain risk assessment and auxiliary decision-making, thereby improving the efficiency of emergency response and the accuracy of decision-making, and helping emergency personnel quickly formulate scientific and effective disaster response strategies.

[0064] S2: Based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database, determine the probability of secondary disasters and derivative disasters occurring in the initial disaster event;

[0065] It should be noted that the initial disaster event refers to the original disaster event that triggers secondary or derivative disasters, such as earthquakes and typhoons. Such events are often the starting point of the disaster chain and may bring about a series of secondary or derivative disasters. Secondary disasters are disasters directly caused by the initial disaster event, and the event types are basically the same or continued. For example, aftershocks caused by earthquakes, smoke spread caused by fires, etc. Derivative disasters are disasters indirectly caused by the initial disaster event, and the event types usually change. For example, fires caused by earthquakes, infectious diseases caused by floods, etc. The frequency of occurrence refers to the average number of occurrences of an initial disaster event in a specific time period, which is used to reflect the universality and historical laws of the event. Timeliness is a measure of the real-time and current relevance of data. Newer data has higher timeliness and is used for calculations first. This concept ensures the dynamic nature of disaster prediction and makes the calculation results closer to the current situation.

[0066] Specifically, firstly, based on the emergency plan knowledge database, the historical data of various initial disaster events are counted and their occurrence frequency is calculated. By analyzing the average annual occurrence of initial disaster events such as earthquakes and typhoons, the prevalence of each type of event is calculated; at the same time, combined with the occurrence records of secondary and derivative disasters, the frequency ratio of secondary and derivative disasters caused by initial events is counted, and the impact tendency of these events in the disaster chain is preliminarily evaluated.

[0067] Furthermore, considering the timeliness of the data, each data record is adjusted by assigning weights. The data of more recent disaster events are given higher weights to better reflect the current disaster situation; the data of earlier events are given lower weights, thereby reducing their impact in the current assessment. After combining the frequency of occurrence and timeliness weights, the probability of each initial disaster event triggering secondary and derivative disasters is finally calculated. This probability calculation result will be used to construct the subsequent disaster knowledge graph and provide a dynamic disaster chain risk assessment for the emergency response system.

[0068] By combining the frequency and timeliness of the initial disaster event, this process can effectively improve the accuracy of secondary and derivative disaster risk prediction. The statistics of the frequency of occurrence help the system identify high-frequency disaster chains in history, and the timeliness adjustment ensures that the prediction is more in line with the current situation, thereby improving the dynamic and real-time nature of risk assessment. In addition, the calculation of the probability of secondary and derivative disasters occurring after the initial disaster event lays a data foundation for the construction of the subsequent disaster knowledge graph, enabling the emergency plan system to better identify potential high-risk events and provide strong support for decision-making.

[0069] S3: constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event;

[0070] It should be noted that the disaster knowledge graph is a knowledge model based on a graph data structure, which represents initial disasters, secondary disasters, derivative disasters and their relationships in the form of nodes and edges. By constructing a disaster knowledge graph, it is possible to intuitively display the chain of disaster events, the probability of occurrence of events, and the causal relationship between disasters, making it easier to analyze complex disaster chains and assist in decision-making.

[0071] Specifically, the process of constructing the disaster knowledge graph first extracts disaster events and their causal relationships from the emergency plan knowledge database. For each initial disaster event, combined with the probability data of secondary and derivative disasters, the event is regarded as a node in the graph, and secondary and derivative disaster events are also added to the graph as nodes. Subsequently, edges are established for each pair of initial-secondary and initial-derivative events, and probability values ​​are marked on the edges to indicate the risk of the initial disaster event triggering secondary or derivative disasters. These relationships are marked as directed edges to indicate the causal direction of the event.

[0072] Furthermore, the structure of the graph is optimized to improve the intuitiveness and analysis effect of the graph. The system screens and prioritizes the relationships between nodes based on the probability values ​​of each edge, and marks high-risk relationship paths. This score sorting allows the graph to highlight high-risk paths when displayed, making it easier for users to focus on secondary and derivative events with potential high risks. In addition, during the graph construction process, different types of disasters are displayed in layers by category or region, making the graph hierarchy clearer and easier for emergency personnel to quickly understand event associations when the disaster chain is complex.

[0073] By constructing a disaster knowledge graph, the system can intuitively present the causal relationship between the initial disaster event and its secondary and derivative disasters in a graph structure, forming a knowledge network covering the disaster chain relationship and probability. The construction of the graph clearly displays the associated paths of each event in the disaster chain, providing a quick reference for emergency decision-making. The probabilistic annotations between events help the system give priority to high-risk events when assisting decision-making, improving the accuracy of emergency plans and the timeliness of decisions. In addition, the knowledge graph provides a multi-level and dynamic display of the disaster chain, which facilitates the rapid location of key risk nodes and paths in emergency response, thereby supporting more scientific disaster prevention and control and resource allocation.

[0074] S4: connecting the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, the secondary events and derivative events corresponding to the probabilities of the secondary disasters and the derivative disasters greater than the preset secondary derivative probability threshold and the prevention strategies corresponding to the secondary events and the derivative events are pushed;

[0075] It should be noted that the digital emergency plan system is a digital platform for managing, retrieving and executing emergency plans, supporting real-time data access and plan push. By integrating the disaster knowledge graph, this system can quickly generate emergency response recommendations when a disaster occurs, helping decision makers take appropriate response measures. The secondary derivative probability threshold is a preset value for screening high-risk events. When the probability of secondary or derivative disasters exceeds this threshold, the system will prioritize these events to help emergency personnel focus on them. Prevention strategies refer to prevention or response measures for secondary and derivative events in the disaster chain, including resource allocation, personnel arrangements, on-site disposal, etc., aimed at reducing the secondary impacts and derivative risks of disasters.

[0076] Specifically, the constructed disaster knowledge graph is first connected to the digital emergency plan system. As one of the core modules of the emergency system, the knowledge graph provides data support for the correlation analysis and risk prediction of disaster events. In the system, the graph can update and display the relationship between each event in the disaster chain and its probability of occurrence in real time, ensuring that the emergency plan is retrieved based on the latest disaster information.

[0077] Furthermore, when a disaster occurs and an emergency plan needs to be called, the system automatically checks each event node and relationship chain in the disaster knowledge graph, paying special attention to the probability of secondary and derivative events. The system screens out secondary and derivative disaster events that are higher than the preset secondary derivative probability threshold. For qualified secondary and derivative events, the system pushes corresponding prevention strategies and displays these high-risk events on the interface first. In this way, decision makers can predict possible secondary or derivative risks early in the disaster chain, facilitate the deployment of emergency resources and response measures in advance, and control the impact of disasters to the greatest extent.

[0078] By connecting the disaster knowledge graph to the digital emergency plan system and pushing the plan according to the probability of secondary and derivative events during the plan retrieval process, this method significantly improves the real-time and pertinence of the emergency plan system. The system can automatically screen out high-risk secondary and derivative disaster events, prompt decision makers to focus in advance, and provide specific prevention strategies to help decision makers effectively control risks in the early stages of the disaster chain. This process not only improves the accuracy of disaster emergency response, but also shortens the response time, ensures the rational allocation of resources and personnel, further reduces the secondary or derivative impacts of disasters, and helps to improve the overall efficiency and scientificity of disaster emergency management.

[0079] This embodiment constructs an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data; determines the probability of secondary disasters and derivative disasters occurring in the initial disaster event based on the frequency and timeliness of each initial disaster event in the emergency plan knowledge database; constructs a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event; connects the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, pushes secondary events and derivative events corresponding to the probability of secondary disasters and derivative disasters greater than a preset secondary derivative probability threshold, as well as prevention strategies corresponding to the secondary events and derivative events. This embodiment improves the coverage of disaster information comprehensively by building an emergency plan knowledge database and integrating structured, semi-structured and unstructured multi-level data sources; determines the probability of secondary and derivative disasters based on the frequency and timeliness of initial disaster events in the database, and realizes dynamic assessment of secondary and derivative disaster risks; builds a disaster knowledge graph based on the results of probability analysis, clarifies the causal relationship between the initial disaster and its secondary and derivative disasters, and enhances the system's response capability to complex disaster chains; connects the disaster knowledge graph to the digital emergency plan system, pushes high-risk secondary and derivative events and their prevention strategies in real time, ensures the timeliness and predictability of emergency response, and significantly improves the accuracy and efficiency of emergency auxiliary decision-making for disaster events.

[0080] Based on the above first embodiment, a second embodiment of the disaster event emergency decision-making auxiliary method of the present application is proposed. Figure 2 , Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the disaster emergency decision-making assistance method of the present application.

[0081] like Figure 2 As shown, in this embodiment, before step S1, the following is further included:

[0082] S1a: obtaining the structured disaster historical data;

[0083] S1b: parsing the webpage structure of the webpage where the semi-structured disaster field data is located based on a preset webpage element template matching model, and acquiring the semi-structured disaster field data in combination with a preset webpage crawler technology;

[0084] S1c: Based on the search keywords corresponding to the unstructured disaster professional data, a preset document search engine is used in combination with the preset web crawler technology to obtain the unstructured disaster professional data.

[0085] It should be noted that the web page element template matching model is a model used to parse the content structure of a web page. It matches semi-structured data by identifying key elements of the web page (such as title, time, content block, etc.), thereby accurately extracting the required information. Web crawler technology is an automated program technology used to browse, access and extract web page content. Through crawler technology, the required disaster data can be obtained in batches from web pages. The literature search engine is a tool for retrieving professional literature in a specific field. By entering the search keyword, it can automatically search and obtain qualified literature resources from the database.

[0086] Specifically, in the process of acquiring data, we first collect structured disaster history data. These data mainly come from authoritative resources such as disaster history databases and government statistical yearbooks, and are imported into the system by data download or API call. Structured data contains detailed information such as disaster type, occurrence time, and impact range, which can be directly used to build a knowledge database.

[0087] Furthermore, for semi-structured disaster field data, a preset web page element template matching model is used to parse the web page structure. The model can automatically identify key data blocks in web pages (such as time, title, location, etc.) to ensure the accuracy of information extraction. Combined with web crawler technology, the system regularly visits and crawls content from various disaster field websites (such as disaster warning, meteorological monitoring, etc.) to obtain real-time or semi-real-time semi-structured data. In the acquisition of unstructured disaster professional data, the system uses literature search engines based on search keywords in the disaster field to retrieve relevant information from research documents, disaster conference reports and other materials. Combined with web crawler technology, the system can automatically locate and download text resources that match keywords. These unstructured data will be further extracted with natural language processing technology in the future to facilitate inclusion in the knowledge database.

[0088] Through automated data acquisition and processing, structured, semi-structured, and unstructured disaster data resources are effectively integrated, providing comprehensive and real-time basic information support for the emergency plan knowledge database. Structured data provides stable historical disaster information, semi-structured data makes up for the timeliness of information through real-time updates, and unstructured data provides rich expert knowledge and domain insights. Through web element template matching and web crawler technology, the system can improve the efficiency and automation of data collection while ensuring data accuracy. Ultimately, this integration method can significantly improve the coverage and real-time nature of disaster information, and provide more accurate and comprehensive data support for emergency auxiliary decision-making for disaster events.

[0089] Based on the above first embodiment, in this embodiment, step S1 includes:

[0090] S11: preprocessing the structured disaster historical data, the semi-structured disaster field data and the unstructured disaster professional data to obtain preprocessed data, wherein the preprocessing includes one or more of format conversion, data cleaning and data denoising;

[0091] S12: verifying the preprocessed data by a preset cross-validation method;

[0092] S13: Classifying and arranging the pre-processed data that have passed the verification based on a preset classification and arrangement strategy;

[0093] S14: Based on the classification and sorting results, construct the emergency plan knowledge database.

[0094] It should be noted that format conversion refers to the process of converting data from one format to another, ensuring that data from different sources can be stored and processed in a unified manner. Format conversion is common in converting unstructured or semi-structured data into structured forms such as tables and database records. Data cleaning is a data preprocessing step used to remove invalid information, duplicate data, and incomplete records in the data to improve the accuracy and consistency of the data. Data cleaning is an important part of ensuring data quality. Data denoising refers to the removal of interference items or noise information in the data, such as irrelevant data, erroneous values, etc., to ensure the purity of the data and the reliability of the analysis. Cross-validation is a data validation method that repeatedly verifies the accuracy and consistency of the data by dividing and combining data sets multiple times to ensure the validity and integrity of the preprocessed data. Classification and sorting strategies are pre-set rules for classifying and sorting verified data, such as grouping data by disaster type, region, time, and other dimensions. Classification and sorting facilitates rapid retrieval and management of data.

[0095] Specifically, when preprocessing structured, semi-structured and unstructured disaster data, format conversion is first performed. According to the characteristics of different data types, the system converts unstructured and semi-structured data into a unified structured format, such as extracting key information from text data into tables or database entries. This conversion enables unified management and analysis of various types of data. Subsequently, data cleaning and data denoising are performed to delete invalid records, redundant information and abnormal data to improve data accuracy and consistency. Through cleaning and denoising, the quality of preprocessed data is guaranteed.

[0096] Furthermore, the preprocessed data is cross-validated to ensure the effectiveness and accuracy of data processing. The cross-validation process repeatedly confirms the integrity and consistency of the data by grouping and checking the data set multiple times, and screens out possible errors or incomplete records. The verified data is then grouped according to the preset classification and sorting strategy, for example, by disaster type (such as earthquakes, typhoons), location of the event, and time period. Through such classification and sorting, the data organization is clearer and facilitates rapid retrieval. Finally, the system integrates the preprocessed, verified and classified data into the emergency plan knowledge database to provide high-quality data support for disaster emergency decision-making.

[0097] By preprocessing, verifying, and classifying structured, semi-structured, and unstructured data, the system significantly improves the quality and consistency of data. Format conversion, data cleaning, and denoising ensure the standardization and accuracy of data; cross-validation ensures the reliability of data when used multiple times and avoids error accumulation. In addition, through classification and organization, the system can quickly retrieve and call specific types of data on demand, greatly improving the practicality and management efficiency of data. The completion of this series of steps makes the emergency plan knowledge database a core resource library for disaster information, providing a high-quality data foundation for the analysis of disaster events and auxiliary decision-making, thereby improving the scientific nature and timeliness of emergency response.

[0098] This embodiment constructs an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data; determines the probability of secondary disasters and derivative disasters occurring in the initial disaster event based on the frequency and timeliness of each initial disaster event in the emergency plan knowledge database; constructs a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event; connects the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, pushes secondary events and derivative events corresponding to the probability of secondary disasters and derivative disasters greater than a preset secondary derivative probability threshold, as well as prevention strategies corresponding to the secondary events and derivative events. This embodiment improves the coverage of disaster information comprehensively by building an emergency plan knowledge database and integrating structured, semi-structured and unstructured multi-level data sources; determines the probability of secondary and derivative disasters based on the frequency and timeliness of initial disaster events in the database, and realizes dynamic assessment of secondary and derivative disaster risks; builds a disaster knowledge graph based on the results of probability analysis, clarifies the causal relationship between the initial disaster and its secondary and derivative disasters, and enhances the system's response capability to complex disaster chains; connects the disaster knowledge graph to the digital emergency plan system, pushes high-risk secondary and derivative events and their prevention strategies in real time, ensures the timeliness and predictability of emergency response, and significantly improves the accuracy and efficiency of emergency auxiliary decision-making for disaster events.

[0099] Based on the above second embodiment, a third embodiment of the disaster emergency decision-making auxiliary method of the present application is proposed. Figure 3 , Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the disaster emergency decision-making assistance method of the present application.

[0100] In this embodiment, step S2 includes:

[0101] S21: based on a preset screening standard, screening the data in the emergency plan knowledge database to obtain screening data, wherein the screening data includes a plurality of initial disaster event data;

[0102] S22: Determine the occurrence frequency of each initial disaster event according to the screening data;

[0103] S23: assigning a timeliness weight to each piece of initial disaster event data based on the time when the event in the screened data occurred, and marking the secondary disasters and derivative disasters in each piece of initial disaster event data;

[0104] S24: Based on the marking result, the occurrence frequency of the initial disaster event is combined with the corresponding timeliness weight to determine the probability of the secondary disaster and the derivative disaster occurring due to the initial disaster event.

[0105] It should be noted that the screening criteria refer to the preset rules used to filter out qualified data from the emergency plan knowledge database. The screening criteria may include conditions such as disaster type, time range, location, etc. to ensure the relevance and applicability of the data. The initial disaster event refers to the starting event in the disaster chain, which may trigger secondary or derivative disasters, such as earthquakes, typhoons, etc. The initial disaster event usually has a greater impact and may become the cause of subsequent events. The frequency of occurrence refers to the average number of occurrences of the initial disaster event in a specific time period, which is used to reflect its historical prevalence. Frequency calculation helps analyze the regularity and trend of events. The timeliness weight is a weight value assigned according to the time characteristics of the data, which is used to indicate the current relevance of the event. The timeliness weight usually gives a higher weight to the latest data to ensure that the prediction results are close to the current situation.

[0106] Specifically, the data in the emergency plan knowledge database is screened based on preset screening criteria to extract the initial disaster event data related to the target analysis. These screening criteria may include time range, geographical restrictions or disaster types, etc., to ensure that the screened data is highly relevant and consistent. The initial disaster event data obtained after screening contains multiple historical records, which can be used to analyze the occurrence patterns of disaster events.

[0107] Furthermore, based on the screened data set, the frequency of occurrence of each initial disaster event is counted, and the average number of occurrences within a specific time range is calculated as the basis for its probability of occurrence. At the same time, the system assigns a timeliness weight to each initial disaster event based on the time information in the data record, so that recent events receive a higher weight to improve the timeliness of the prediction. According to each event record, the secondary and derivative disasters that may be caused by the event are marked. By combining the frequency of occurrence of the initial disaster event with its timeliness weight, the system ultimately calculates the probability of secondary and derivative disasters occurring for each initial disaster event. These calculation results will provide a more accurate basis for risk prediction for emergency response plans.

[0108] Through the steps of initial disaster event screening based on screening criteria, frequency statistics, timeliness weight allocation and secondary derivative disaster marking, the system can accurately assess the probability of secondary and derivative events in the disaster chain. The screening criteria ensure the relevance and applicability of the data, and the combination of frequency and timeliness weights makes the calculation results closer to the current situation. The final obtained probability of secondary and derivative disasters can not only help emergency personnel identify high-risk events in advance and provide reliable risk assessments, but also support the rational allocation of emergency resources and the formulation of response strategies, and improve the scientificity and effectiveness of the overall emergency response.

[0109] Based on the above second embodiment, in this embodiment, step S3 includes:

[0110] S31: extracting entities from the emergency plan knowledge database to obtain multiple disaster entities, and classifying and annotating the disaster entities by attributes;

[0111] S32: Determine the relationship type and entity causal relationship based on the classification and attribute labeling results;

[0112] S33: constructing an initial graph structure by taking the multiple disaster entities as nodes and the relationship types as edges;

[0113] S34: Determine a disaster hierarchical structure according to the entity causal relationship;

[0114] S35: determining a secondary derivative high probability path according to the probability of secondary disasters and derivative disasters occurring due to the initial disaster event;

[0115] S36: Construct the disaster knowledge graph based on the initial graph structure, the disaster hierarchical structure and the secondary derived high probability path.

[0116] It should be noted that entity extraction refers to identifying and extracting disaster events or objects (i.e., disaster entities) with independent significance from the emergency plan knowledge database. Entity extraction is the basis for building a knowledge graph, helping the system to identify important information such as disaster events, infrastructure, and emergency tasks. Disaster entities refer to key objects represented as nodes in the knowledge graph, including initial disasters, secondary disasters, and derivative disasters. Each disaster entity is represented as an independent node in the graph with relevant attributes. Attribute annotation refers to adding attribute information to each disaster entity, including the time of occurrence, location, scope of impact, emergency measures, etc., so as to describe the characteristics of each entity in more detail in the graph. Relationship type refers to the type of association between disaster entities, such as "trigger" and "cause", which describes the causal or correlation relationship between different disaster events. Relationship types are represented by edges in the graph, connecting related disaster entities. Entity causality is the causal relationship between disaster events, which is used to represent the causal chain between initial disasters and secondary and derivative disasters. Causal relationships help build disaster chains and clarify the mutual influence between events. The initial graph structure is the basic structure of the knowledge graph, which consists of nodes (disaster entities) and edges (relationship types) and is the most basic framework of the graph. The disaster hierarchical structure hierarchizes disaster events based on the causal relationship of entities, and displays the hierarchical relationship between the initial disaster and its secondary and derivative disaster chains. The hierarchical structure helps to clearly display the hierarchy and propagation path of the disaster chain in the graph. The secondary derivative high-probability path refers to the path with a high probability of the initial disaster event triggering secondary and derivative disasters, which is the key path in the knowledge graph. These paths usually indicate the propagation direction of high-risk events and provide key focus paths for emergency decision-making.

[0117] Specifically, in the process of constructing the disaster knowledge graph, we first extract entities from the emergency plan knowledge database, identify disaster events with independent significance, and manage them as disaster entities. Each disaster entity is annotated with detailed attributes, such as the time, location, and scope of impact of the event, so that the system can display the detailed characteristics of each event in the graph. Next, these disaster entities are classified and sorted according to the disaster type, event nature, and scope of impact, so that the graph can display the relationship between various types of events by category.

[0118] Furthermore, based on the determination of relationship types and entity causal relationships, the system constructs the initial structure of the graph by using disaster entities as nodes and relationship types as edges. The initial graph structure only contains basic nodes and relationships to build the basic framework of the graph. Subsequently, the graph is layered according to entity causal relationships to form a disaster layered structure, thereby showing the hierarchical relationship between initial disasters, secondary disasters, and derivative disasters. The system further marks high-probability paths based on the probability of initial disasters triggering secondary and derivative disasters, and uses them as key relationships, so that the knowledge graph can highlight high-risk paths and facilitate focus when making decisions.

[0119] By extracting entities, classifying and annotating attributes of the data in the emergency plan knowledge database, and gradually constructing a disaster knowledge graph containing causal relationships and high-risk paths, this method significantly improves the system's ability to display and analyze complex disaster chains. The classification and hierarchical structure of disaster entities in the graph make the hierarchical relationship of the disaster chain clearly visible, helping decision makers to quickly identify the propagation paths between events. The annotation of high-probability paths enables the system to prioritize high-risk secondary and derivative disaster chains, which helps emergency management personnel quickly lock in the disaster chains of key concern. Finally, the constructed disaster knowledge graph, as an important tool for emergency decision-making, makes the presentation of disaster information more intuitive and risk analysis more accurate, providing scientific support for real-time monitoring of disaster events and the formulation of response strategies.

[0120] Based on the above second embodiment, in this embodiment, after step S4, the following is further included:

[0121] S4a: Determine required resources based on the prevention strategy;

[0122] S4b: classifying the risk levels of the initial disaster event, the secondary event and the derivative event;

[0123] S4c: Based on the risk level classification result, the required resources are allocated, and the allocated resources are tracked.

[0124] It should be noted that prevention strategies are response and prevention measures for initial disasters and the secondary and derivative events that may be triggered, aiming to reduce the impact of disasters. Prevention strategies include measures such as resource allocation, emergency plan formulation and on-site disposal. Demand resources refer to specific resources such as personnel, materials, equipment, etc. required to implement prevention strategies, including rescue personnel, medical supplies, engineering equipment, etc. These resources provide basic support for responding to disaster events. Risk levels classify disasters into different risk levels (such as low, medium, and high) based on the potential threats and impact range of initial disaster events, secondary events, and derivative events. Risk levels help the system identify events that are prioritized. Resource allocation is to reasonably allocate demand resources based on the disaster risk level to ensure that high-risk areas and events receive adequate support. This process is based on the urgency and availability of resources. Resource tracking refers to monitoring the location, status, and usage of allocated resources to ensure that resources are used reasonably and avoid repeated scheduling or waste of resources. Resource tracking helps to monitor resource dynamics in real time and ensure the efficiency of emergency response.

[0125] Specifically, first identify and determine the resource requirements for responding to the initial disaster event and its secondary and derivative events based on the prevention strategy. These resources may include medical personnel, rescue equipment, fire trucks, etc., and the required resources are refined according to different disaster scenarios to ensure accurate matching of resources. Through the confirmation of resource requirements, the system forms a specific list of resources required to respond to each node in the disaster chain.

[0126] Furthermore, the initial disaster events, secondary events and derivative events are classified into risk levels, and disaster events are divided into different risk levels based on factors such as the scope of impact, probability of occurrence and degree of harm. According to the results of the risk level classification, the system prioritizes the allocation of resources to high-risk events and areas to ensure that key areas are fully supported. At the same time, the system tracks the allocated resources and monitors their location, usage status and consumption in real time to prevent duplicate allocation or insufficient resources. Resource tracking not only ensures the rational use of resources, but also helps the emergency team to adjust the resource allocation plan in a timely manner and improve the dynamic management capabilities of emergency response.

[0127] By determining the required resources, risk level classification, and resource allocation and tracking based on the prevention strategy, the system achieves efficient and accurate resource management. First, the identification of required resources ensures that emergency response has sufficient resource guarantees; second, risk level classification allows the system to concentrate resources to deal with high-risk events, improving the scientific nature of resource allocation. The resource tracking function ensures the transparency of the resource scheduling process, allowing decision makers to grasp the resource usage in real time, optimize resource allocation strategies, and avoid resource waste or uneven distribution. The completion of this process effectively improves the efficiency of disaster emergency response, makes resource allocation more reasonable, and provides comprehensive support for dynamic response to the disaster chain.

[0128] This embodiment constructs an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data; determines the probability of secondary disasters and derivative disasters occurring in the initial disaster event based on the frequency and timeliness of each initial disaster event in the emergency plan knowledge database; constructs a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event; connects the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, pushes secondary events and derivative events corresponding to the probability of secondary disasters and derivative disasters greater than a preset secondary derivative probability threshold, as well as prevention strategies corresponding to the secondary events and derivative events. This embodiment improves the coverage of disaster information comprehensively by building an emergency plan knowledge database and integrating structured, semi-structured and unstructured multi-level data sources; determines the probability of secondary and derivative disasters based on the frequency and timeliness of initial disaster events in the database, and realizes dynamic assessment of secondary and derivative disaster risks; builds a disaster knowledge graph based on the results of probability analysis, clarifies the causal relationship between the initial disaster and its secondary and derivative disasters, and enhances the system's response capability to complex disaster chains; connects the disaster knowledge graph to the digital emergency plan system, pushes high-risk secondary and derivative events and their prevention strategies in real time, ensures the timeliness and predictability of emergency response, and significantly improves the accuracy and efficiency of emergency auxiliary decision-making for disaster events.

[0129] For example, in order to help understand the technical concept or technical principle of the disaster event emergency decision-making auxiliary method of the above embodiment, please refer to Figure 4 , Figure 4 This is a schematic diagram of the disaster knowledge graph in one embodiment of the disaster event emergency decision support method of the present application.

[0130] In one embodiment, the specific implementation of the disaster event emergency decision-making assistance method includes the following steps.

[0131] 1. Constructing an emergency plan knowledge database

[0132] 1.1 Data Source

[0133] The data sources include structured data such as emergency plans, existing disaster case databases, disaster statistics databases, semi-structured data such as disaster public notice web pages, field industry websites and encyclopedia web pages, and unstructured data such as professional literature and text data.

[0134] 1.2 Data Acquisition

[0135] For the semi-structured data of natural disaster industry web pages such as the National Disaster Reduction Network, we parse the web page structure, design a web element template matching model, and use web crawler technology to obtain field-related data; for text-based unstructured data such as professional literature in the field, we use literature search engines, set search keywords, and use web crawlers to obtain field literature data.

[0136] 1.3 Database organization

[0137] Taking into account the differences in disaster characteristics and the secondary disasters caused by different regions, the database is first organized based on provincial administrative divisions.

[0138] 2. Building a Disaster Knowledge Graph

[0139] A disaster knowledge graph is constructed based on the data of each provincial administrative region.

[0140] 2.1 Disaster Entity and Relationship Extraction

[0141] (1) Disaster entity and relationship settings

[0142] Entities include: ① natural disasters and man-made disasters such as earthquakes, typhoons, fires, explosions, etc.; ② infrastructure involved in disasters, such as buildings, roads, bridges, etc.; ③ emergency tasks ④ model methods; ⑤ disaster data; ⑥ risk sources.

[0143] The relationships describe the causal connections between these entities, including: secondary; derived; impact; disaster-causing; disaster information; corresponding tasks; usage methods; input; output; and data association.

[0144] Among them, secondary events refer to events that are directly caused by the initial event and whose event type has not changed significantly; derivative events refer to events that are caused by the initial event and whose event type has changed significantly. Events that have changed significantly refer to natural disasters, accidental disasters, public health incidents, and social security incidents.

[0145] (2) Extraction method

[0146] The concepts defined at the ontology level for the five elements of natural disaster events, emergency tasks, disaster data, infrastructure, and risk sources have well covered the names of specific entities. Therefore, the most fine-grained classification concept of the ontology model is used as the entity name dictionary to match the entity names of the acquired multi-source data, so as to realize the entity extraction of these three elements.

[0147] For the "model method" entity, the conditional random field model (CRF) and rule matching are combined to identify the model method entity. For sentences that do not contain rule matching words, the CRF model is used for recognition, and the CRF recognition results are added to the final output results to improve the recall rate; for the names identified by rule matching, if the rule matching recognition results contain CRF recognition results, the CRF recognition method name replaces the rule-based recognition method name to improve the accuracy. The model method entity matching rules are shown in Table 1.

[0148] Table 1 Model method entity matching rules

[0149]

[0150] 2.2 Constructing a calculation method for the possibility of secondary disasters

[0151] Generate event-secondary-event and event-derivative-event paths in the disaster knowledge graph. Based on the frequency of events, consider the timeliness of data, that is, the newer the data, the better the data quality, and propose a method to calculate the possibility of secondary derivative disasters.

[0152] The smaller the time interval between the occurrence of a single event-secondary-event or event-derivative-event path and the query time interval, the greater the contribution of this data to the possibility of secondary-derivative disasters, that is, the greater the importance of the data. The importance of the data can be set in the range of (0, 1), referring to the normal distribution function. See Figure 5 , Figure 5 This is a schematic diagram of the importance of data in an embodiment of the disaster emergency decision-making assistance method of the present application.

[0153] like Figure 5 As shown in the figure, t0 represents the query time, that is, the query year; t={t1,t2,…,t N} represents the time information of a certain event-secondary-event or event-derivative-event, that is, the year of occurrence, which can be obtained by the artificial intelligence model from the historical disaster events in the database of each provincial administrative region. Taking the secondary disaster "mudslide" caused by "heavy rain" as an example, the time information of N secondary disasters "mudslide" caused by "heavy rain" is screened out in the database based on the artificial intelligence model, that is, t={t1,t2,…,t N};

[0154] The formula is as follows:

[0155]

[0156] Among them, θ represents the adjustment parameter, which adjusts the discrete degree of the importance of the data over time, which can be obtained from expert experience. Here, θ=4.3 is taken, so that when t0-t=5, f(t)≈0.5; f(t) represents the importance of the data with time information t. N The importance of the N pieces of data involved in the project is added together to obtain the possibility of the occurrence of this derivative disaster, which is represented by P. The formula is as follows.

[0157]

[0158] This importance is used as the score of each path. According to the score, the top-3 paths are selected as the screening paths and marked in the disaster knowledge graph. Please note that the numbers and letters involved in this figure are only for distinction and do not represent the actual situation.

[0159] 2.3 Dynamic Update Mechanism

[0160] When new disaster cases are added to the database, the disaster knowledge graph is updated in a timely manner.

[0161] 3. Connect to the digital emergency plan system to conduct intelligent question-and-answer decision-making

[0162] This disaster knowledge graph is connected to the digital emergency plan system based on the artificial intelligence model. Each time the emergency plan for an event is called up, the three most likely secondary derivative events caused by this event are provided based on the disaster knowledge graph, and a prevention plan is given by integrating emergency tasks. If a secondary derivative event has occurred, the corresponding emergency plan is called up again.

[0163] At the same time, users can ask questions, such as "What secondary disasters may be caused by an earthquake?" The system searches for characteristic paths related to earthquakes in the disaster knowledge graph and returns the three most likely secondary derivative events, such as "building collapse" and "fire".

[0164] The present application also provides a disaster emergency decision-making auxiliary device. Figure 6 , Figure 6 This is a schematic diagram of the module structure of a disaster event emergency decision-making auxiliary device according to an embodiment of the present application. The disaster event emergency decision-making auxiliary device includes:

[0165] A database construction module 601 is used to construct an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data;

[0166] A secondary derivative evaluation module 602 is used to determine the probability of secondary disasters and derivative disasters occurring from the initial disaster event based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database;

[0167] A graph construction module 603 is used to construct a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event;

[0168] The target module 604 is used to connect the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, the secondary events and derivative events corresponding to the probabilities of the secondary disasters and the derivative disasters greater than the preset secondary derivative probability threshold and the prevention strategies corresponding to the secondary events and the derivative events are pushed.

[0169] The disaster event emergency decision-making auxiliary device provided in the embodiment of the present application adopts the disaster event emergency decision-making auxiliary method in the above embodiment, which can solve the technical problem of how to improve the accuracy of disaster event emergency decision-making auxiliary. Compared with the prior art, the beneficial effects of the disaster event emergency decision-making auxiliary device provided in the embodiment of the present application are the same as the beneficial effects of the disaster event emergency decision-making auxiliary method provided in the above embodiment, and the other technical features in the disaster event emergency decision-making auxiliary device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0170] The present application provides a disaster event emergency decision-making assistance device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the disaster event emergency decision-making assistance method in the above-mentioned embodiment.

[0171] Reference below Figure 7 , Figure 7 The schematic diagram of the device structure of the hardware operating environment involved in the disaster event emergency decision-making assistance method in the embodiment of the present application shows a schematic diagram of the structure of the disaster event emergency decision-making assistance device suitable for implementing the embodiment of the present application. The disaster event emergency decision-making assistance device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7The disaster emergency decision support device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0172] like Figure 7 As shown, the disaster event emergency decision-making auxiliary device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the disaster event emergency decision-making auxiliary device are also stored. The processing device 1001, ROM 1002 and RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the disaster event emergency decision-making assistance device to communicate wirelessly or wired with other devices to exchange data. Although the disaster event emergency decision-making assistance device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0173] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0174] The disaster event emergency decision-making assistance device provided by the present application adopts the disaster event emergency decision-making assistance method in the above embodiment, which can solve the technical problem of how to improve the accuracy of disaster event emergency decision-making assistance. Compared with the prior art, the beneficial effects of the disaster event emergency decision-making assistance device provided by the present application are the same as the beneficial effects of the disaster event emergency decision-making assistance method provided by the above embodiment, and the other technical features in the disaster event emergency decision-making assistance device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0175] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0176] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0177] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the disaster event emergency decision-making support method in the above-mentioned embodiment.

[0178] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0179] The above-mentioned computer-readable storage medium may be included in the disaster event emergency decision-making auxiliary device; or it may exist independently without being assembled into the disaster event emergency decision-making auxiliary device.

[0180] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the disaster event emergency decision-making auxiliary device, the disaster event emergency decision-making auxiliary device: constructs an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data; determines the probability of secondary disasters and derivative disasters occurring in the initial disaster event based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database; constructs a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event; connects the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of emergency plan retrieval through the preset digital emergency plan system, based on the disaster knowledge graph, pushes secondary events and derivative events corresponding to the probability of the secondary disasters and derivative disasters being greater than a preset secondary derivative probability threshold, as well as prevention strategies corresponding to the secondary events and derivative events. Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0181] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0182] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0183] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned disaster event emergency decision-making assistance method, and can solve the technical problem of how to improve the accuracy of disaster event emergency decision-making assistance. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the disaster event emergency decision-making assistance method provided in the above-mentioned embodiment, and will not be repeated here.

[0184] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned disaster event emergency decision-making support method.

[0185] The computer program product provided in this application can solve the technical problem of how to improve the accuracy of emergency decision-making assistance for disaster events. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the emergency decision-making assistance method for disaster events provided in the above embodiment, and will not be repeated here.

[0186] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A disaster emergency decision-making assistance method, characterized in that: The method comprises: Construct an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data, and unstructured disaster professional data; Based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database, determine the probability of secondary disasters and derivative disasters occurring from the initial disaster event; Constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring from the initial disaster event; The disaster knowledge graph is connected to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, the secondary events and derivative events corresponding to the probabilities of the secondary disasters and the derivative disasters greater than the preset secondary derivative probability threshold and the prevention strategies corresponding to the secondary events and the derivative events are pushed.

2. The method according to claim 1, characterized in that Before the step of constructing an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data, the method further includes: Acquiring the structured disaster historical data; Parsing the webpage structure of the webpage where the semi-structured disaster field data is located based on a preset webpage element template matching model, and acquiring the semi-structured disaster field data in combination with a preset webpage crawler technology; Based on the search keywords corresponding to the unstructured disaster professional data, a preset document search engine is used in combination with the preset web crawler technology to obtain the unstructured disaster professional data.

3. The method according to claim 1, characterized in that The step of constructing an emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data includes: Preprocessing the structured disaster historical data, the semi-structured disaster field data and the unstructured disaster professional data to obtain preprocessed data, wherein the preprocessing includes one or more of format conversion, data cleaning and data denoising; Verifying the preprocessed data by a preset cross-validation method; Based on a preset classification and sorting strategy, classify and sort the pre-processed data that has passed the verification; Based on the classification and sorting results, the emergency plan knowledge database is constructed.

4. The method according to claim 1, characterized in that The step of determining the probability of secondary disasters and derivative disasters occurring from the initial disaster event based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database includes: Based on a preset screening standard, the data in the emergency plan knowledge database is screened to obtain screening data, wherein the screening data includes a plurality of initial disaster event data; Determining the occurrence frequency of each of the initial disaster events according to the screening data; Based on the time when the event in the screened data occurred, assigning a timeliness weight to each piece of initial disaster event data, and marking secondary disasters and derivative disasters in each piece of initial disaster event data; Based on the marking results, the occurrence frequency of the initial disaster event is combined with the corresponding timeliness weight to determine the probability of the secondary disaster and the derivative disaster occurring due to the initial disaster event.

5. The method according to claim 1, characterized in that The step of constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event includes: Performing entity extraction on the emergency plan knowledge database to obtain multiple disaster entities, and classifying and attribute labeling the disaster entities; Determine the relationship type and entity causal relationship based on the classification and attribute labeling results; An initial graph structure is constructed by taking the multiple disaster entities as nodes and the relationship types as edges; Determine the disaster hierarchy structure based on the entity cause-effect relationship; According to the probability of secondary disasters and derivative disasters occurring from the initial disaster event, determine the secondary derivative high probability path; The disaster knowledge graph is constructed based on the initial graph structure, the disaster hierarchical structure and the secondary derived high probability path.

6. The method according to any one of claims 1 to 5, characterized in that After the step of connecting the disaster knowledge graph to the preset digital emergency plan system, the method further includes: Determine the resources needed based on the prevention strategy; Classifying the risk levels of the initial disaster event, the secondary event, and the derivative event; Based on the risk level classification result, the required resources are allocated, and the allocated resources are tracked.

7. A disaster emergency decision-making auxiliary device, characterized in that: The device comprises: Database construction module, used to build emergency plan knowledge database based on structured disaster historical data, semi-structured disaster field data and unstructured disaster professional data; A secondary derivative evaluation module is used to determine the probability of secondary disasters and derivative disasters occurring from the initial disaster event based on the occurrence frequency and timeliness of each initial disaster event in the emergency plan knowledge database; A graph construction module, for constructing a disaster knowledge graph based on the emergency plan knowledge database and the probability of secondary disasters and derivative disasters occurring in the initial disaster event; The target module is used to connect the disaster knowledge graph to a preset digital emergency plan system, wherein, in the process of retrieving the emergency plan through the preset digital emergency plan system, based on the disaster knowledge graph, the secondary events and derivative events corresponding to the probabilities of the secondary disasters and the derivative disasters greater than the preset secondary derivative probability threshold and the prevention strategies corresponding to the secondary events and the derivative events are pushed.

8. A computer device, characterized in that: The device includes: a memory, a processor, and a disaster event emergency decision-making assistance program stored in the memory and executable on the processor, wherein the disaster event emergency decision-making assistance program is configured to implement the steps of the disaster event emergency decision-making assistance method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a disaster event emergency decision-making assistance program, and when the disaster event emergency decision-making assistance program is executed by the processor, the steps of the disaster event emergency decision-making assistance method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the disaster emergency decision support method according to any one of claims 1 to 6 are implemented.

Images