A method and system for large-scale modeling of emergency command and decision support

Abstract

This invention provides a method and system for a large-scale model for emergency command and decision support. It acquires safety monitoring data from the platform under monitoring, performs relevant searches on the safety monitoring data based on the large-scale model, and saves data related to the production and living conditions. This achieves comprehensive data acquisition based on the large-scale model. Real-time monitoring of the safety monitoring data is performed using the large-scale model to obtain risk and accident data. Key data correlation analysis is conducted between the risk and accident data and surrounding living data, surrounding emergency data, and relevant laws and regulations. Based on the analysis results, potential secondary accidents are determined. Based on data correlation, the implicit relationships between risk and accident events are explored in depth to reveal potential risks. This in-depth mining of data correlations provides accurate accident information for emergency command support. Based on the risk and accident data and the specific data of potential secondary accidents, an accident report document is automatically generated to provide decision support for commanders.

Description

Technical Field

[0001] This invention relates to the field of decision support technology, and in particular to a method and system for a large-scale model for emergency command decision support. Background Technology

[0002] In fields such as enterprise safety production digitalization platforms, enterprise safety production standardization management systems, emergency management comprehensive business platforms, visualized emergency rescue smart platforms, urban safety risk dynamic distribution map systems, and chemical industrial park safety risk digital twin intelligent control platforms, when risk accidents such as coal mine accidents, fire accidents, traffic accidents, gas leak accidents, hazardous chemical accidents, and industrial and commercial accidents occur, emergency command auxiliary decision-making big models are usually configured to provide auxiliary decision-making for commanders.

[0003] Existing emergency command and decision support models employ technologies such as semantic analysis, image processing, video recording, and speech recognition to clean and aggregate diverse data and model algorithms, forming intelligence services and extracting content to create text. However, they cannot delve into the implicit relationships between risks and incidents, reveal potential risk points, or independently generate reports and documents. Summary of the Invention

[0004] This invention provides a method and system for large-scale modeling of emergency command and decision support, in order to solve the problems mentioned in the background art.

[0005] A large-scale model method for emergency command and decision support includes:

[0006] S1: Obtain safety monitoring data from the platform to be monitored, and perform relevant searches on the safety monitoring data based on the large model to obtain and save surrounding living data, surrounding emergency data and relevant laws and regulations data related to the production and living data;

[0007] S2: Real-time monitoring of safety monitoring data based on a large model to obtain risk incident data;

[0008] S3: Conduct key data correlation analysis on risk incident data with surrounding life data, surrounding emergency data and relevant laws and regulations data, and determine possible secondary accidents based on the analysis results;

[0009] S4: Automatically generate accident report documents based on risk incident data and specific data on possible secondary accidents.

[0010] Preferably, in step S1, acquiring security monitoring data from the platform to be monitored includes:

[0011] Acquire sensor data and daily record data from the platform to be monitored;

[0012] The sensor-acquired data and daily recorded data are preprocessed to obtain standard data;

[0013] Based on safety monitoring standards, the standard data is processed in a specific way to obtain safety monitoring data.

[0014] Preferably, in step S1, based on a large model, relevant searches are performed on the safety monitoring data to obtain and store surrounding living data, surrounding emergency data, and relevant laws and regulations data related to the production and living data, including:

[0015] Based on the monitoring area range of the safety monitoring data, determine the relevant data acquisition area for retrieval, and extract type keywords, name keywords, and content keywords from the safety monitoring data based on data type, data name, and data content.

[0016] Semantic association is performed on the type keywords, name keywords, and content keywords. Based on the semantic association results, the type keywords, name keywords, and content keywords are integrated to obtain the target keywords.

[0017] Based on the large model, relevant data directories from the data acquisition area are obtained, and relevant searches are performed on the target data directories based on the target keywords to obtain initial search data.

[0018] The safety monitoring data is used to detect the types of safety accidents and to obtain the characteristics of the hazard sources corresponding to the types of safety accidents.

[0019] The hazard source characteristics are matched with the initial search data to obtain the feature matching results, and secondary search terms are obtained based on the feature matching results.

[0020] A horizontal search is performed on the relevant data directory based on the secondary search terms to obtain the first supplementary search data.

[0021] The secondary search terms are semantically expanded to obtain expanded search terms. The initial search data is then expanded based on the expanded search terms. Further search terms are obtained from the initial search data based on the expanded search results.

[0022] Based on the aforementioned in-depth search terms, a deeper search is performed on the relevant data directory to obtain the second supplementary search data;

[0023] The initial search data, the first supplementary search data, and the second supplementary search data are integrated, and relevant data are obtained based on the integration result.

[0024] Based on the characteristics of the data content, the relevant data is divided into surrounding life data, surrounding emergency data, and relevant laws and regulations data, which are then stored.

[0025] Preferably, obtaining secondary search terms based on feature matching results includes:

[0026] The hazard source features are retrieved from the feature matching results, and the keywords of the retrieval data are extracted. The hazard source features and keywords are then combined to obtain secondary search terms.

[0027] Preferably, the step of dividing relevant data based on data content characteristics to obtain surrounding life data, surrounding emergency data, and relevant legal and regulatory data, and then storing them, includes:

[0028] Based on specific data content related to surrounding life, Zhou Biao's emergency response, and relevant laws and regulations, establish data content characteristics;

[0029] Based on the characteristics of the data content, the relevant data is divided into surrounding life data, surrounding emergency data, and relevant laws and regulations data;

[0030] Data on surrounding living conditions, emergency response, and relevant laws and regulations will be stored and preserved.

[0031] Preferably, in step S2, real-time monitoring of safety monitoring data is performed based on a large model to obtain risk incident data, including:

[0032] Obtain the accident judgment criteria for each risk event;

[0033] Based on the large model, the safety monitoring data is compared with the accident judgment criteria, and when an anomaly occurs, a risk accident is determined to have occurred.

[0034] Abnormal safety monitoring data will be treated as risk incident data.

[0035] Preferably, in step S3, key data correlation analysis is performed on the risk accident data, surrounding living data, surrounding emergency data, and relevant legal and regulatory data. Based on the analysis results, potential secondary accidents are determined, including:

[0036] Key data about accident types and circumstances are extracted from risk and accident data, and related information features that match the key data are obtained from the information association database.

[0037] Based on the aforementioned associated data characteristics, the data is correlated with surrounding life data, surrounding emergency data, and relevant legal and regulatory data to obtain associated life data, associated emergency data, and associated legal and regulatory data.

[0038] Based on a preset correlation algorithm, the correlation between risk accident data and related life data, related emergency data, and related legal and regulatory data is calculated, and target related life data, target related emergency data, and target related legal and regulatory data with a correlation greater than a preset correlation threshold are selected.

[0039] The types of secondary accidents that may result from the risk accident data are obtained. Based on the data correlation between the secondary accident types and the risk accident types, the accident types of the risk accident data are correlated with the life types in the target associated life data to obtain the type correlation degree. The accident values ​​of the risk accident data are correlated with the life values ​​in the target associated life data to obtain the numerical correlation degree.

[0040] Based on the aforementioned type correlation, potential secondary accidents arising from risk incident data can be identified.

[0041] The probability of secondary accidents occurring is determined based on the product of the type correlation degree and the numerical correlation degree.

[0042] Preferably, after determining the secondary accidents that may arise from the risk incident data, the method further includes:

[0043] The accident characteristics of the secondary accident are correlated with the target-related emergency data to obtain relevant emergency information;

[0044] The accident characteristics of the secondary accident are correlated with the target-related legal and regulatory data to obtain relevant legal and regulatory information;

[0045] The relevant emergency information and relevant laws and regulations will be integrated and added to the specific data of secondary accidents.

[0046] Preferably, in step S4, an accident report document is automatically generated based on the risk accident data and specific data on possible secondary accidents, including:

[0047] The data on risk incidents and specific data on possible secondary incidents are integrated to obtain a dataset;

[0048] The system retrieves the user-selected document template from the large model, matches the data set with the document template, and generates an accident report document based on the matching result.

[0049] A large-scale model system for emergency command and decision support includes:

[0050] The data acquisition module is used to acquire safety monitoring data from the platform to be monitored, and to perform relevant searches on the safety monitoring data based on the big model, and to acquire and save the surrounding living data, surrounding emergency data and relevant laws and regulations data related to the production and living data.

[0051] The real-time monitoring module is used to monitor safety monitoring data in real time based on a large model to obtain risk and incident data;

[0052] The correlation analysis module is used to perform key data correlation analysis on risk incident data with surrounding life data, surrounding emergency data and relevant laws and regulations data, and to determine possible secondary accidents based on the analysis results;

[0053] The report generation module is used to automatically generate accident report documents based on risk incident data and specific data on possible secondary accidents.

[0054] Compared with the prior art, the present invention has achieved the following beneficial effects:

[0055] By acquiring safety monitoring data from the platform under monitoring and performing relevant searches on the safety monitoring data based on a large model, surrounding living data, surrounding emergency data, and relevant laws and regulations related to the production and living data are obtained and stored. This achieves comprehensive data acquisition based on the large model. Real-time monitoring of the safety monitoring data based on the large model yields risk and accident data, enabling real-time monitoring of the platform under monitoring. Key data correlation analysis is performed on the risk and accident data with surrounding living data, surrounding emergency data, and relevant laws and regulations data. Based on the analysis results, potential secondary accidents are identified. Based on data correlation, the implicit relationships between risk and accident events are explored in depth to reveal potential risks. This allows for in-depth mining of the correlations between data, providing accurate accident information to assist emergency command. Accident report documents are automatically generated based on the specific data of risk and accident events and potential secondary accidents, providing auxiliary decision-making for command personnel.

[0056] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0057] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0058] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0059] Figure 1 This is a flowchart of a large-scale model method for emergency command auxiliary decision-making in an embodiment of the present invention;

[0060] Figure 2 This is a flowchart illustrating the automatic generation of accident report documents in an embodiment of the present invention;

[0061] Figure 3 This is a structural diagram of a large-scale model system for emergency command and decision support in an embodiment of the present invention. Detailed Implementation

[0062] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0063] Example 1:

[0064] This invention provides a large-scale model method for emergency command and decision support, such as... Figure 1 As shown, it includes:

[0065] S1: Obtain safety monitoring data from the platform to be monitored, and perform relevant searches on the safety monitoring data based on the large model to obtain and save surrounding living data, surrounding emergency data and relevant laws and regulations data related to the production and living data;

[0066] S2: Real-time monitoring of safety monitoring data based on a large model to obtain risk incident data;

[0067] S3: Conduct key data correlation analysis on risk incident data with surrounding life data, surrounding emergency data and relevant laws and regulations data, and determine possible secondary accidents based on the analysis results;

[0068] S4: Automatically generate accident report documents based on risk incident data and specific data on possible secondary accidents.

[0069] In this embodiment, the platform to be monitored may be, for example, an enterprise safety production digital intelligence platform, an enterprise safety production standardization management system, an emergency management comprehensive business platform, a visualized emergency rescue smart platform, an urban safety risk dynamic distribution map system, or a chemical industrial park safety risk digital twin intelligent control platform.

[0070] In this embodiment, safety monitoring data includes temperature, pressure, air quality, production and living data, equipment data, etc.

[0071] In this embodiment, safety monitoring data is monitored in real time based on a large model to obtain risk accident data. Specifically, when the safety monitoring data is abnormal, risk accident data is obtained based on the abnormal situation. Risk accidents include, for example, coal mine accidents, fire accidents, traffic accidents, gas leak accidents, hazardous chemical accidents, industrial and commercial accidents, etc.

[0072] In this embodiment, the surrounding living data includes, for example, the activity of people and the configuration of facilities in the surrounding area.

[0073] In this embodiment, the surrounding emergency data includes, for example, the status of emergency resources such as emergency teams, emergency experts, emergency supplies, and fire stations around the accident site.

[0074] In this embodiment, a secondary accident is an accident derived from a risk accident.

[0075] The beneficial effects of the above design scheme are as follows: By acquiring safety monitoring data from the platform to be monitored and performing relevant searches on the safety monitoring data based on a large model, surrounding living data, surrounding emergency data, and relevant legal and regulatory data related to the production and living data are obtained and stored, achieving comprehensive data acquisition based on the large model. Real-time monitoring of safety monitoring data based on the large model yields risk accident data, enabling real-time monitoring of the platform to be monitored. Key data correlation analysis is performed on risk accident data and surrounding living data, surrounding emergency data, and relevant legal and regulatory data. Based on the analysis results, possible secondary accidents are determined. Based on data correlation, the implicit relationships between risk accidents are explored in depth to reveal potential risks, achieving in-depth mining of the correlation between data and providing accurate accident information for emergency command support. Accident report documents are automatically generated based on the risk accident data and the specific data of possible secondary accidents, providing auxiliary decision-making for command personnel.

[0076] Example 2:

[0077] Based on Embodiment 1, this embodiment of the invention provides a large-scale model method for emergency command auxiliary decision-making. In step S1, acquiring security monitoring data from the platform to be monitored includes:

[0078] Acquire sensor data and daily record data from the platform to be monitored;

[0079] The sensor-acquired data and daily recorded data are preprocessed to obtain standard data;

[0080] Based on safety monitoring standards, the standard data is processed in a specific way to obtain safety monitoring data.

[0081] In this embodiment, the preprocessing of sensor-acquired data and daily recorded data includes data cleaning, data conversion, and data denoising.

[0082] In this embodiment, the standard data undergoes specific processing, such as statistical analysis, machine learning, or text analysis.

[0083] The beneficial effects of the above design scheme are: by acquiring sensor data and daily record data of the platform to be monitored, preprocessing the sensor data and daily record data to obtain standard data, and based on safety monitoring standards, performing specific processing on the standard data to obtain safety monitoring data, providing high-quality data for emergency command and decision support.

[0084] Example 3:

[0085] Based on Embodiment 1, this embodiment of the invention provides a large-scale model method for emergency command auxiliary decision-making. In S1, the large-scale model is used to perform relevant searches on safety monitoring data to obtain and store surrounding living data, surrounding emergency data, and relevant laws and regulations related to the production and living data.

[0086] Based on the monitoring area range of the safety monitoring data, determine the relevant data acquisition area for retrieval, and extract type keywords, name keywords, and content keywords from the safety monitoring data based on data type, data name, and data content.

[0087] Semantic association is performed on the type keywords, name keywords, and content keywords. Based on the semantic association results, the type keywords, name keywords, and content keywords are integrated to obtain the target keywords.

[0088] Based on the large model, relevant data directories from the data acquisition area are obtained, and relevant searches are performed on the target data directories based on the target keywords to obtain initial search data.

[0089] The safety monitoring data is used to detect the types of safety accidents and to obtain the characteristics of the hazard sources corresponding to the types of safety accidents.

[0090] The hazard source characteristics are matched with the initial search data to obtain the feature matching results, and secondary search terms are obtained based on the feature matching results.

[0091] A horizontal search is performed on the relevant data directory based on the secondary search terms to obtain the first supplementary search data.

[0092] The secondary search terms are semantically expanded to obtain expanded search terms. The initial search data is then expanded based on the expanded search terms. Further search terms are obtained from the initial search data based on the expanded search results.

[0093] Based on the aforementioned in-depth search terms, a deeper search is performed on the relevant data directory to obtain the second supplementary search data;

[0094] The initial search data, the first supplementary search data, and the second supplementary search data are integrated, and relevant data are obtained based on the integration result.

[0095] Based on the characteristics of the data content, the relevant data is divided into surrounding life data, surrounding emergency data, and relevant laws and regulations data, which are then stored.

[0096] In this embodiment, for example, when the safety accident is a fire, the source of the hazard is hazardous chemicals, dangerous chemical processes, etc.

[0097] In this embodiment, the first supplementary search data is to enrich the initial search data horizontally, for example, by enriching the regional range.

[0098] In this embodiment, the second supplementary search data is to further enrich the initial search data, for example, to enrich the information within a specific region.

[0099] The beneficial effects of the above design scheme are as follows: By performing relevant searches on safety monitoring data based on a large model, and extracting type keywords, name keywords, and content keywords from the safety monitoring data based on data type, data name, and data content, semantic association is performed on the type keywords, name keywords, and content keywords. Based on the semantic association results, the type keywords, name keywords, and content keywords are integrated to obtain target keywords. Relevant data directories from the data acquisition area are obtained based on the large model. Relevant searches are performed on the target data directories based on the target keywords to obtain initial search data, ensuring the accuracy of the search. Then, based on the initial search data, further horizontal and in-depth searches are performed to obtain supplementary search data. Finally, surrounding living data, surrounding emergency data, and relevant legal and regulatory data are obtained and stored to ensure the richness of the relevant data, providing auxiliary data information for emergency command.

[0100] Example 4:

[0101] Based on Embodiment 3, this embodiment of the invention provides a method for a large-scale model for emergency command auxiliary decision-making, wherein obtaining secondary search terms based on feature matching results includes:

[0102] The hazard source features are retrieved from the feature matching results, and the keywords of the retrieval data are extracted. The hazard source features and keywords are then combined to obtain secondary search terms.

[0103] The beneficial effects of the above design scheme are: by obtaining the retrieval data corresponding to the hazard source features from the feature matching results, and extracting the keywords from the retrieval data, the hazard source features and keywords are combined to obtain secondary search terms, which provides a foundation for in-depth retrieval.

[0104] Example 5:

[0105] Based on Embodiment 3, this embodiment of the invention provides a large-scale model method for emergency command auxiliary decision-making. The method involves dividing relevant data based on data content characteristics to obtain and store surrounding living data, surrounding emergency data, and relevant legal and regulatory data, including:

[0106] Based on specific data content related to surrounding life, Zhou Biao's emergency response, and relevant laws and regulations, establish data content characteristics;

[0107] Based on the characteristics of the data content, the relevant data is divided into surrounding life data, surrounding emergency data, and relevant laws and regulations data;

[0108] Data on surrounding living conditions, emergency response, and relevant laws and regulations will be stored and preserved.

[0109] The beneficial effects of the above design scheme are as follows: by establishing data content characteristics based on specific data content related to surrounding life, emergency response, and relevant laws and regulations, the relevant data is divided into surrounding life data, surrounding emergency response data, and relevant laws and regulations data based on the data content characteristics. The surrounding life data, surrounding emergency response data, and relevant laws and regulations data are stored and saved, making it convenient to retrieve and view the relevant data.

[0110] Example 6:

[0111] Based on Embodiment 1, this embodiment of the invention provides a large-scale model method for emergency command auxiliary decision-making. In step S2, real-time monitoring of safety monitoring data is performed based on the large-scale model to obtain risk accident data, including:

[0112] Obtain the accident judgment criteria for each risk event;

[0113] Based on the large model, the safety monitoring data is compared with the accident judgment criteria, and when an anomaly occurs, a risk accident is determined to have occurred.

[0114] Abnormal safety monitoring data will be treated as risk incident data.

[0115] In this embodiment, the accident judgment criteria are pre-set based on the actual situation.

[0116] The beneficial effects of the above design scheme are: by obtaining the accident judgment criteria for each risk accident, the safety monitoring data is compared with the accident judgment criteria based on the large model. When an anomaly occurs, it is determined that a risk accident has occurred. The safety monitoring data with the anomaly is used as risk accident data, thereby realizing real-time monitoring of the monitoring platform and providing real-time accident information for emergency command assistance.

[0117] Example 7:

[0118] Based on Example 1, this embodiment of the invention provides a large-scale model method for emergency command auxiliary decision-making. In step S3, key data correlation analysis is performed on risk accident data, surrounding living data, surrounding emergency data, and relevant legal and regulatory data. Based on the analysis results, possible secondary accidents are determined, including:

[0119] Key data about accident types and circumstances are extracted from risk and accident data, and related information features that match the key data are obtained from the information association database.

[0120] Based on the aforementioned associated data characteristics, the data is correlated with surrounding life data, surrounding emergency data, and relevant legal and regulatory data to obtain associated life data, associated emergency data, and associated legal and regulatory data.

[0121] Based on a preset correlation algorithm, the correlation between risk accident data and related life data, related emergency data, and related legal and regulatory data is calculated, and target related life data, target related emergency data, and target related legal and regulatory data with a correlation greater than a preset correlation threshold are selected.

[0122] The types of secondary accidents that may result from the risk accident data are obtained. Based on the data correlation between the secondary accident types and the risk accident types, the accident types of the risk accident data are correlated with the life types in the target associated life data to obtain the type correlation degree. The accident values ​​of the risk accident data are correlated with the life values ​​in the target associated life data to obtain the numerical correlation degree.

[0123] Based on the aforementioned type correlation, potential secondary accidents arising from risk incident data can be identified.

[0124] The probability of secondary accidents occurring is determined based on the product of the type correlation degree and the numerical correlation degree.

[0125] In this embodiment, the preset association algorithm is the Apriori algorithm, which is an algorithm for mining association rules through frequent itemsets. The core idea of ​​the Apriori algorithm is to mine frequent itemsets through two stages: candidate set generation and downward closure test.

[0126] In this embodiment, if the type correlation degree is greater than a preset type threshold, the corresponding secondary accident is determined to be a possible accident.

[0127] In this embodiment, the larger the product of type correlation and numerical correlation, the greater the probability of the occurrence of the corresponding secondary accidents.

[0128] In this embodiment, the information association database is pre-designed to provide a basis for data association.

[0129] The beneficial effects of the above design scheme are as follows: Key data regarding accident types and circumstances are extracted from risk accident data; related information features matching the key data are obtained from an information association database; based on these related data features, correlation processing is performed with surrounding living data, surrounding emergency data, and relevant legal and regulatory data to obtain related living data, related emergency data, and related legal and regulatory data; the correlation between risk accident data and related living data, related emergency data, and related legal and regulatory data is calculated based on a preset correlation algorithm; target related living data, target related emergency data, and target related legal and regulatory data with a correlation greater than a preset correlation threshold are selected; and secondary risks that may arise from the risk accident data are obtained. Accident type: Based on the data correlation between secondary accident types and risk accident types, the accident type of the risk accident data is correlated with the life type in the target associated life data to obtain the type correlation degree. The accident value of the risk accident data is also correlated with the life value in the target associated life data to obtain the numerical correlation degree. Based on the type correlation degree, the possible secondary accidents that the risk accident data may generate are determined. Based on the product of the type correlation degree and the numerical correlation degree, the probability of occurrence of the possible secondary accidents is determined. This data correlation allows for in-depth exploration of the implicit relationships between risk accidents, revealing potential risks and enabling in-depth mining of data correlations to provide accurate accident information for emergency command support.

[0130] Example 8:

[0131] Based on Embodiment 7, this embodiment of the invention provides a large-scale model method for emergency command auxiliary decision-making, which further includes, after determining the secondary accidents that may be generated by risk accident data:

[0132] The accident characteristics of the secondary accident are correlated with the target-related emergency data to obtain relevant emergency information;

[0133] The accident characteristics of the secondary accident are correlated with the target-related legal and regulatory data to obtain relevant legal and regulatory information;

[0134] The relevant emergency information and relevant laws and regulations will be integrated and added to the specific data of secondary accidents.

[0135] The beneficial effects of the above design scheme are as follows: by associating the accident characteristics of the secondary accident with the target-related emergency data, relevant emergency information is obtained; by associating the accident characteristics of the secondary accident with the target-related legal and regulatory data, relevant legal and regulatory information is obtained; and by integrating the relevant emergency information and relevant legal and regulatory information, it is added to the specific data of the secondary accident, providing emergency data for the generation of subsequent accident report documents and providing auxiliary decision-making for commanders.

[0136] Example 9:

[0137] Based on Example 1, this embodiment of the invention provides a large-scale model method for emergency command auxiliary decision-making, such as... Figure 3 As shown, in step S4, an accident report document is automatically generated based on the risk accident data and specific data on possible secondary accidents, including:

[0138] The data on risk incidents and specific data on possible secondary incidents are integrated to obtain a dataset;

[0139] The system retrieves the user-selected document template from the large model, matches the data set with the document template, and generates an accident report document based on the matching result.

[0140] The beneficial effects of the above design scheme are as follows: by integrating the data on risk accidents and the specific data on possible secondary accidents, a data set is obtained; the document template selected by the user is retrieved from the large model; the data set is matched with the document template; and an accident report document is generated based on the matching result, providing auxiliary decision-making for the commanders.

[0141] Example 10:

[0142] This invention provides a large-scale model system for emergency command and decision support, used to implement the steps of the large-scale model method described in any one of embodiments 1-9, such as... Figure 3 As shown, it includes:

[0143] The data acquisition module is used to acquire safety monitoring data from the platform to be monitored, and to perform relevant searches on the safety monitoring data based on the big model, and to acquire and save the surrounding living data, surrounding emergency data and relevant laws and regulations data related to the production and living data.

[0144] The real-time monitoring module is used to monitor safety monitoring data in real time based on a large model to obtain risk and incident data;

[0145] The correlation analysis module is used to perform key data correlation analysis on risk incident data with surrounding life data, surrounding emergency data and relevant laws and regulations data, and to determine possible secondary accidents based on the analysis results;

[0146] The report generation module is used to automatically generate accident report documents based on risk incident data and specific data on possible secondary accidents.

[0147] In this embodiment, the platform to be monitored may be, for example, an enterprise safety production digital intelligence platform, an enterprise safety production standardization management system, an emergency management comprehensive business platform, a visualized emergency rescue smart platform, an urban safety risk dynamic distribution map system, or a chemical industrial park safety risk digital twin intelligent control platform.

[0148] In this embodiment, safety monitoring data includes temperature, pressure, air quality, production and living data, equipment data, etc.

[0149] In this embodiment, safety monitoring data is monitored in real time based on a large model to obtain risk accident data. Specifically, when the safety monitoring data is abnormal, risk accident data is obtained based on the abnormal situation. Risk accidents include, for example, coal mine accidents, fire accidents, traffic accidents, gas leak accidents, hazardous chemical accidents, industrial and commercial accidents, etc.

[0150] In this embodiment, the surrounding living data includes, for example, the activity of people and the configuration of facilities in the surrounding area.

[0151] In this embodiment, the surrounding emergency data includes, for example, the status of emergency resources such as emergency teams, emergency experts, emergency supplies, and fire stations around the accident site.

[0152] In this embodiment, a secondary accident is an accident derived from a risk accident.

[0153] The beneficial effects of the above design scheme are as follows: By acquiring safety monitoring data from the platform to be monitored and performing relevant searches on the safety monitoring data based on a large model, surrounding living data, surrounding emergency data, and relevant legal and regulatory data related to the production and living data are obtained and stored, achieving comprehensive data acquisition based on the large model. Real-time monitoring of safety monitoring data based on the large model yields risk accident data, enabling real-time monitoring of the platform to be monitored. Key data correlation analysis is performed on risk accident data and surrounding living data, surrounding emergency data, and relevant legal and regulatory data. Based on the analysis results, possible secondary accidents are determined. Based on data correlation, the implicit relationships between risk accidents are explored in depth to reveal potential risks, achieving in-depth mining of the correlation between data and providing accurate accident information for emergency command support. Accident report documents are automatically generated based on the risk accident data and the specific data of possible secondary accidents, providing auxiliary decision-making for command personnel.

[0154] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this application and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A large-scale model method for emergency command and decision support, characterized in that, include: S1: Acquire safety monitoring data from the platform to be monitored, and perform relevant searches on the safety monitoring data based on the large model. Retrieve and save surrounding living data, surrounding emergency data, and relevant laws and regulations related to production and daily life, including: Based on the monitoring area range of the safety monitoring data, determine the relevant data acquisition area for retrieval, and extract type keywords, name keywords, and content keywords from the safety monitoring data based on data type, data name, and data content. Semantic association is performed on the type keywords, name keywords, and content keywords. Based on the semantic association results, the type keywords, name keywords, and content keywords are integrated to obtain the target keywords. Based on the large model, relevant data directories from the data acquisition area are obtained, and relevant searches are performed on the target data directories based on the target keywords to obtain initial search data. The safety monitoring data is used to detect the types of safety accidents and to obtain the characteristics of the hazard sources corresponding to the types of safety accidents. The hazard source characteristics are matched with the initial search data to obtain the feature matching results, and secondary search terms are obtained based on the feature matching results. A horizontal search is performed on the relevant data directory based on the secondary search terms to obtain the first supplementary search data. The secondary search terms are semantically expanded to obtain expanded search terms. The initial search data is then expanded based on the expanded search terms. Further search terms are obtained from the initial search data based on the expanded search results. Based on the aforementioned in-depth search terms, a deeper search is performed on the relevant data directory to obtain the second supplementary search data; The initial search data, the first supplementary search data, and the second supplementary search data are integrated, and relevant data are obtained based on the integration result. Based on the characteristics of the data content, the relevant data is divided into surrounding life data, surrounding emergency data, and relevant laws and regulations data, and then stored. S2: Real-time monitoring of safety monitoring data based on a large model to obtain risk incident data, including: Obtain the accident judgment criteria for each risk event; Based on the large model, the safety monitoring data is compared with the accident judgment criteria, and when an anomaly occurs, a risk accident is determined to have occurred. Abnormal safety monitoring data will be treated as risk incident data. S3: Conduct key data correlation analysis on risk incident data with surrounding living data, surrounding emergency data and relevant laws and regulations data, and determine possible secondary accidents based on the analysis results; S4: Automatically generate accident report documents based on risk incident data and specific data on possible secondary accidents.

2. The method for a large-scale model for emergency command and decision support according to claim 1, characterized in that, In step S1, security monitoring data is acquired from the platform to be monitored, including: Acquire sensor data and daily record data from the platform to be monitored; The sensor-collected data and daily recorded data are preprocessed to obtain standard data; Based on safety monitoring standards, the standard data is processed in a specific way to obtain safety monitoring data.

3. The method for a large-scale model for emergency command and decision support according to claim 1, characterized in that, The process of obtaining secondary search terms based on feature matching results includes: The hazard source features are retrieved from the feature matching results, and the keywords of the retrieval data are extracted. The hazard source features and keywords are then combined to obtain secondary search terms.

4. The method for a large-scale model for emergency command and decision support according to claim 1, characterized in that, Based on data content characteristics, relevant data is divided into surrounding life data, surrounding emergency data, and relevant legal and regulatory data, which are then stored. Establish data content characteristics based on data content related to surrounding life, surrounding emergencies, and relevant laws and regulations; Based on the characteristics of the data content, the relevant data is divided into surrounding life data, surrounding emergency data, and relevant laws and regulations data; Store and preserve data on surrounding living conditions, surrounding emergency situations, and relevant laws and regulations.

5. The method for a large-scale model for emergency command and decision support according to claim 1, characterized in that, In step S3, key data correlation analysis is performed on risk incident data with surrounding living data, surrounding emergency data, and relevant legal and regulatory data. Based on the analysis results, potential secondary incidents are determined, including: Key data about accident types and circumstances are extracted from risk and accident data, and related information features that match the key data are obtained from the information association database. Based on the aforementioned associated information features, the data is correlated with surrounding living data, surrounding emergency data, and relevant legal and regulatory data to obtain associated living data, associated emergency data, and associated legal and regulatory data. Based on a preset correlation algorithm, the correlation between risk accident data and related life data, related emergency data, and related legal and regulatory data is calculated, and target related life data, target related emergency data, and target related legal and regulatory data with a correlation greater than a preset correlation threshold are selected. The types of secondary accidents that may result from the risk accident data are obtained. Based on the data correlation between the secondary accident types and the risk accident types, the accident types of the risk accident data are correlated with the life types in the target associated life data to obtain the type correlation degree. The accident values ​​of the risk accident data are correlated with the life values ​​in the target associated life data to obtain the numerical correlation degree. Based on the aforementioned type correlation, potential secondary accidents arising from risk incident data can be identified. The probability of secondary accidents occurring is determined based on the product of the type correlation degree and the numerical correlation degree.

6. The method for a large-scale model for emergency command and decision support according to claim 5, characterized in that, After identifying potential secondary incidents arising from risk incident data, the following is also included: The accident characteristics of the secondary accident are correlated with the target-related emergency data to obtain relevant emergency information; The accident characteristics of the secondary accident are correlated with the target-related legal and regulatory data to obtain relevant legal and regulatory information; The relevant emergency information and relevant laws and regulations will be integrated and added to the specific data of secondary accidents.

7. The method for a large-scale model for emergency command and decision support according to claim 1, characterized in that, In step S4, an accident report document is automatically generated based on the risk accident data and specific data on possible secondary accidents, including: The data on risk incidents and specific data on possible secondary incidents are integrated to obtain a dataset; The system retrieves the user-selected document template from the large model, matches the data set with the document template, and generates an accident report document based on the matching result.

8. A large-scale model system for emergency command and decision support, used to implement the steps of the large-scale model method according to any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire safety monitoring data from the platform to be monitored, and to perform relevant searches on the safety monitoring data based on the big model, and to acquire and save the surrounding living data, surrounding emergency data and relevant laws and regulations data related to the production and living data. The real-time monitoring module is used to monitor safety monitoring data in real time based on a large model to obtain risk and incident data; The correlation analysis module is used to perform key data correlation analysis on risk incident data with surrounding life data, surrounding emergency data and relevant laws and regulations data, and to determine possible secondary accidents based on the analysis results; The report generation module is used to automatically generate accident report documents based on risk incident data and specific data on possible secondary accidents.

Images