On-site emergency decision support method and system based on zero-time response mechanism, and medium

Abstract

The invention discloses an on-site emergency decision support method based on a zero-time response mechanism, and belongs to the technical field of emergency management, and the method comprises the following steps: S1, obtaining the information of an on-site emergency event in real time; s2, on the basis of a preset zero-time priority evaluation model, performing instant priority evaluation on the emergency event, outputting a priority score, and configuring the evaluation model to complete the instant priority evaluation within one second; s3, generating a decision support scheme according to the priority score and the event information; s4, instantly issuing the decision support scheme to a field execution unit through a communication network, and starting an emergency response action; and S5, monitoring an emergency response execution condition in real time, collecting feedback data, and dynamically adjusting the zero-time priority evaluation model and the decision support scheme based on a machine learning algorithm. According to the method, the dependence on artificial experience in the decision making process is greatly reduced, the risk caused by personnel tension and misjudgment is reduced, and the objectivity and consistency of response are improved.

Description

Technical Field

[0001] This invention belongs to the field of emergency management technology, specifically relating to a method and system for on-site emergency decision support based on a zero-time response mechanism. Background Technology

[0002] Currently, with the acceleration of urbanization and the frequent occurrence of extreme weather events, emergency management systems face challenges in integrating multi-source heterogeneous data, conducting dynamic risk assessments, and optimizing resource allocation. Traditional emergency decision-making methods are often based on static rules or single indicators, lacking dynamic assessment of event priorities, leading to uneven resource allocation, response delays, and increased risks of secondary disasters. For example, in rainstorm disasters, existing technologies struggle to assess the evolution risk of disaster chains in real time, making precise resource allocation impossible. While some existing technologies employ priority assessment, they typically rely on simple rules or historical data, failing to consider the dynamic evolution of disaster chains and the fusion of multi-source data, resulting in low assessment accuracy and insufficient scheduling efficiency. Furthermore, existing systems often have response times exceeding several seconds or even minutes, failing to meet the demands of immediate response under extreme weather conditions. Therefore, there is an urgent need for an intelligent decision support method that integrates disaster chain analysis, dynamic trust assessment, and data fusion to achieve "zero-time" response and improve the accuracy and timeliness of emergency responses. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a field emergency decision support method and system based on a zero-time response mechanism. Through dynamic priority evaluation and multi-objective optimization, it achieves efficient scheduling of emergency resources and solves the technical problems mentioned in the background.

[0004] The objective of this invention is achieved as follows: a field emergency decision support method based on a zero-time response mechanism, comprising the following steps: S1, acquiring real-time information on field emergency events, the information including at least one of event type, event location, event severity, and environmental parameters; S2, performing an immediate priority assessment on the emergency event based on a preset zero-time priority assessment model, outputting a priority score, the assessment model being configured to complete the immediate priority assessment within 1 second; S3, generating a decision support scheme based on the priority score and event information; S4, immediately distributing the decision support scheme to the field execution unit via a communication network to initiate emergency response actions; S5, monitoring the emergency response execution status in real time, collecting feedback data, and dynamically adjusting the zero-time priority assessment model and decision support scheme based on machine learning algorithms.

[0005] By constructing a "zero-time response" method, the lengthy process of "information collection, manual analysis, hierarchical reporting, and instruction issuance" in traditional emergency decision-making is broken. Through a highly integrated and automated data processing and decision-making chain, a rapid closed loop from event occurrence to response initiation is achieved, laying the foundation for subsequent rapid decision-making and action. During implementation, raw information about emergency events is continuously and automatically collected through a network of sensors (such as IoT devices and cameras), system reporting interfaces, and external data APIs, ensuring the real-time and direct nature of the information source. The collected information is immediately input into a pre-set "zero-time priority assessment model." This model automatically calculates the urgency and importance of the event within a one-second time window, outputting a quantitative priority score, replacing traditional manual judgment. Based on this priority score and specific event information (such as type and location), the system automatically generates a decision support plan containing specific action instructions using a built-in rule base or optimization algorithm. The generated plan is immediately distributed to the front-end execution unit (such as drones or rescue personnel's handheld terminals) via a high-speed communication network (such as 5G) to directly initiate emergency response actions. Considering the dynamic evolution of the disaster chain and the fusion of multi-source data, the system has high assessment accuracy and high scheduling efficiency, reducing the initial response time for emergency decision-making from the traditional several minutes to seconds. This meets the needs of immediate response under extreme weather conditions, buys valuable time for saving lives and property, greatly reduces the reliance on human experience in the decision-making process, reduces the risk caused by personnel shortages and judgment errors, and improves the objectivity and consistency of the response.

[0006] Further, in step S2, the zero-time-priority assessment model is constructed based on the disaster chain risk evolution law, which is obtained through complex network analysis, including calculating at least one network parameter among node degree, clustering coefficient, and betweenness centrality. The complex network analysis includes a dynamic trust assessment component, which performs real-time comprehensive scoring based on at least one of device status data, environmental factor data, and user behavior data, and is implemented through trusted computing. The zero-time-priority assessment model employs a data fusion strategy, which is DS evidence theory fusion, used to integrate multi-source data, including at least two of meteorological data, geographic information data, real-time sensor data, and historical disaster data. The fusion process integrates privacy computing, including at least one of homomorphic encryption, secure multi-party computation, or a Trusted Execution Environment (TEE). During the data acquisition phase, the system acquires information from different sources according to a preset schema. For example, it acquires environmental parameters (such as wind speed and rainfall) from sensors, extracts event types (such as fire and pipeline leaks) and severity from reported information, and locates event positions from GPS signals. The system clarifies that emergency incident information should include at least four key dimensions: "event type, event location, event severity, and environmental parameters," ensuring the completeness of input information and the accuracy of assessment. This provides precise input for generating targeted decision support plans (such as which resources to deploy and where to deploy them).

[0007] Further, in step S3, the decision support scheme includes at least one of resource scheduling strategies, risk control measures, and early warning instructions; the decision support scheme includes multi-objective optimization using optimization algorithms, wherein the optimization algorithm is at least one of genetic algorithms, particle swarm optimization, or linear programming, and the optimization objectives include minimizing response time, minimizing resource costs, and maximizing coverage. The optimization process is combined with simulation verification, including at least one of discrete event simulation or Monte Carlo simulation. During model construction, a disaster network diagram is constructed using historical data. During evaluation, the centrality index (such as betweenness centrality) of the current event in the network is calculated; a higher value indicates greater criticality. The health status of data source devices (such as sensors), the stability of communication links, and even operator behavior logs are monitored in real time to comprehensively calculate a trust score. The weight of low-trust data sources is reduced. Disaster chain analysis enables the model to have "predictive" capabilities, not only looking at the present but also assessing the potential chain reactions of an event, thereby prioritizing the handling of "pivotal" events. Dynamic trust assessment equips the model with a "firewall," ensuring that the data sources it relies on are trustworthy and preventing misjudgments due to data tampering or equipment failure.

[0008] Furthermore, in step S4, the communication network supports collaboration between edge computing nodes and the cloud platform. The edge computing nodes deploy lightweight cryptographic modules to achieve secure communication. The execution unit includes at least one of drones, robots, mobile terminals, or emergency vehicles. During implementation, meteorological bureau data, on-site sensor readings, and historical database records are input into the system. Before fusion, homomorphic encryption is used for encryption. Subsequently, DS evidence theory is used for reasoning in the encrypted data or secure computing environment to derive a comprehensive and more reliable situation assessment result. The fusion result is more accurate and reliable than any single data source, improving the quality of decision-making information. While protecting the data privacy of all parties, it promotes cross-departmental and cross-system data collaboration and sharing, releasing data value and breaking down data silos.

[0009] An on-site emergency decision support system based on a zero-time response mechanism is provided to implement the above method. The system includes: a data acquisition module for acquiring emergency event information in real time; a priority evaluation module for running a zero-time priority evaluation model and outputting a priority score; a decision generation module for generating decision support schemes; and a communication execution module for distributing the schemes to the execution units.

[0010] An electronic device includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the method described above.

[0011] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0012] The beneficial effects of this invention are as follows: By constructing a "zero-time response" method, it breaks the lengthy process of "information collection, manual analysis, hierarchical reporting, and instruction issuance" in traditional emergency decision-making. Through a highly integrated and automated data processing and decision-making chain, it achieves a rapid closed loop from event occurrence to response initiation, laying the foundation for subsequent rapid decision-making and action. In implementation, raw information about emergency events is continuously and automatically collected through a sensor network distributed across the site, system reporting interfaces, and external data APIs, ensuring the real-time and direct nature of the information source. The collected information is immediately input into a pre-set "zero-time priority assessment model." This model automatically calculates the urgency and importance of the event within a 1-second time window, outputting a quantitative priority score, replacing traditional manual judgment. Based on this priority score and specific event information, the system automatically generates a decision support plan containing specific action instructions using a built-in rule base or optimization algorithm. The generated plan is immediately distributed to the front-end execution unit via a high-speed communication network, directly initiating emergency response actions. Considering the dynamic evolution of the disaster chain and the fusion of multi-source data, the system has high assessment accuracy and high scheduling efficiency, reducing the initial response time for emergency decisions from the traditional several minutes to seconds. This meets the needs of immediate response under extreme weather conditions, buying precious time to save lives and property, greatly reducing reliance on human experience in the decision-making process, reducing the risks caused by personnel shortages and judgment errors, and improving the objectivity and consistency of the response. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system modules of the present invention. Detailed Implementation

[0014] The present invention will now be described in further detail with reference to the accompanying drawings. It should be noted that this is only for the purpose of more clearly illustrating and explaining the present invention. Example 1

[0015] like Figure 1 and 2As shown, this embodiment discloses an on-site emergency decision support method based on a zero-time response mechanism, including the following steps: S1, acquiring on-site emergency event information in real time, the information including at least one of event type, event location, event severity, and environmental parameters; S2, performing an immediate priority assessment of the emergency event based on a preset zero-time priority assessment model, outputting a priority score, the assessment model being configured to complete the immediate priority assessment within 1 second; S3, generating a decision support scheme based on the priority score and event information; S4, immediately distributing the decision support scheme to the on-site execution unit through a communication network to initiate emergency response actions; S5, monitoring the emergency response execution status in real time, collecting feedback data, and dynamically adjusting the zero-time priority assessment model and decision support scheme based on machine learning algorithms.

[0016] By constructing a "zero-time response" method, the lengthy process of "information collection, manual analysis, hierarchical reporting, and instruction issuance" in traditional emergency decision-making is broken. Through a highly integrated and automated data processing and decision-making chain, a rapid closed loop from event occurrence to response initiation is achieved, laying the foundation for subsequent rapid decision-making and action. During implementation, raw information about emergency events is continuously and automatically collected through a network of sensors (such as IoT devices and cameras), system reporting interfaces, and external data APIs, ensuring the real-time and direct nature of the information source. The collected information is immediately input into a pre-set "zero-time priority assessment model." This model automatically calculates the urgency and importance of the event within a one-second time window, outputting a quantitative priority score, replacing traditional manual judgment. Based on this priority score and specific event information (such as type and location), the system automatically generates a decision support plan containing specific action instructions using a built-in rule base or optimization algorithm. The generated plan is immediately distributed to the front-end execution unit (such as drones or rescue personnel's handheld terminals) via a high-speed communication network (such as 5G) to directly initiate emergency response actions. Considering the dynamic evolution of the disaster chain and the fusion of multi-source data, the system has high assessment accuracy and high scheduling efficiency, reducing the initial response time for emergency decision-making from the traditional several minutes to seconds. This meets the needs of immediate response under extreme weather conditions, buys valuable time for saving lives and property, greatly reduces the reliance on human experience in the decision-making process, reduces the risk caused by personnel shortages and judgment errors, and improves the objectivity and consistency of the response. Example 2

[0017] like Figure 1 and 2As shown, this embodiment discloses an on-site emergency decision support method based on a zero-time response mechanism, including the following steps: S1, acquiring on-site emergency event information in real time, the information including at least one of event type, event location, event severity, and environmental parameters; S2, performing an immediate priority assessment of the emergency event based on a preset zero-time priority assessment model, outputting a priority score, the assessment model being configured to complete the immediate priority assessment within 1 second; S3, generating a decision support scheme based on the priority score and event information; S4, immediately distributing the decision support scheme to the on-site execution unit through a communication network to initiate emergency response actions; S5, monitoring the emergency response execution status in real time, collecting feedback data, and dynamically adjusting the zero-time priority assessment model and decision support scheme based on machine learning algorithms.

[0018] For better results, in step S2, the zero-time-priority assessment model is constructed based on the disaster chain risk evolution law. This law is obtained through complex network analysis, including calculating at least one network parameter among node degree, clustering coefficient, and betweenness centrality. The complex network analysis includes a dynamic trust assessment component, which performs real-time comprehensive scoring based on at least one of device status data, environmental factor data, and user behavior data, and is implemented through trusted computing. The zero-time-priority assessment model employs a data fusion strategy, specifically DS evidence theory fusion, used to integrate multi-source data, including at least two of meteorological data, geographic information data, real-time sensor data, and historical disaster data. The fusion process integrates privacy computing, including at least one of homomorphic encryption, secure multi-party computation, or a Trusted Execution Environment (TEE). During the data acquisition phase, the system acquires information from different sources according to a preset schema. For example, it acquires environmental parameters (such as wind speed and rainfall) from sensors, extracts event types (such as fires and pipeline leaks) and severity from reported information, and locates event positions from GPS signals. The system clarifies that emergency incident information should include at least four key dimensions: "event type, event location, event severity, and environmental parameters," ensuring the completeness of input information and the accuracy of assessment. This provides precise input for generating targeted decision support plans (such as which resources to deploy and where to deploy them).

[0019] For better results, in step S3, the decision support scheme includes at least one of resource scheduling strategies, risk management measures, and early warning instructions. The decision support scheme includes multi-objective optimization using optimization algorithms, such as genetic algorithms, particle swarm optimization, or linear programming. The optimization objectives include minimizing response time, minimizing resource costs, and maximizing coverage. The optimization process is combined with simulation verification, including at least one of discrete event simulation or Monte Carlo simulation. During model construction, a disaster network diagram is built using historical data. During evaluation, the centrality index (such as betweenness centrality) of the current event in the network is calculated; a higher value indicates greater criticality. The health status of data source devices (such as sensors), the stability of communication links, and even operator behavior logs are monitored in real time to calculate a comprehensive trust score. The weight of low-trust data sources is reduced. Disaster chain analysis enables the model to be "predictive," not only looking at the present but also assessing the potential chain reactions of events, thus prioritizing the handling of "pivotal" events. Dynamic trust assessment provides a "firewall" for the model, ensuring that the data sources it relies on are trustworthy and preventing misjudgments due to data tampering or equipment failure.

[0020] For better results, in step S4, the communication network supports collaboration between edge computing nodes and the cloud platform. The edge computing nodes deploy lightweight cryptographic modules to achieve secure communication. The execution unit includes at least one of drones, robots, mobile terminals, or emergency vehicles. During implementation, meteorological bureau data, on-site sensor readings, and historical database records are input into the system. Before fusion, homomorphic encryption is used for encryption. Subsequently, DS evidence theory is used for reasoning in the encrypted data or secure computing environment to derive a comprehensive and more reliable situation assessment result. The fusion result is more accurate and reliable than any single data source, improving the quality of decision-making information. While protecting the data privacy of all parties, it promotes cross-departmental and cross-system data collaboration and sharing, unlocking data value and breaking down data silos.

[0021] An on-site emergency decision support system based on a zero-time response mechanism is provided to implement the above method. The system includes: a data acquisition module for acquiring emergency event information in real time; a priority evaluation module for running a zero-time priority evaluation model and outputting a priority score; a decision generation module for generating decision support schemes; and a communication execution module for distributing the schemes to the execution units.

[0022] An electronic device includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the method described above.

[0023] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0024] Taking the urban water supply system of a certain city during an extreme rainfall event in July 2024 as an example: Real-time information acquisition: Data such as rainfall, pipeline pressure, and geographical location are collected in real time through IoT sensors and API interfaces. When rainfall exceeds 50 mm / h, the system automatically triggers event collection, with data updates occurring once per second to ensure real-time performance.

[0025] Real-time Priority Assessment: Utilizing a zero-time priority assessment model based on disaster chain analysis, a disaster chain network for the water supply system is constructed to identify key nodes (such as pipe ruptures and pump station damage). Complex network analysis is used to calculate parameters such as node degree, clustering coefficient, and betweenness centrality to determine critical evolution paths. Dynamic Trust Assessment: Data on equipment status (such as pump station operating status), environmental factors (such as water depth), and user behavior are collected. A trustworthy report is generated through a Trusted Computing Module (TPM), and a comprehensive priority score (range 0-1) is output. The model response time is controlled within 1 second to ensure "zero-time" response.

[0026] Generate decision support solutions: Based on priority scoring, analyze the required resources (such as water pumps and rescue teams), and use a genetic algorithm for multi-objective optimization. The optimization objectives include minimizing response time, minimizing cost, and maximizing coverage. The optimization process is combined with Monte Carlo simulation to verify the robustness of the solution.

[0027] Real-time deployment and execution: The solution is deployed to drones and mobile terminals via the 5G network. Edge computing nodes process local data, reducing latency. Execution units immediately initiate a response, such as dispatching water pumps to flooded areas.

[0028] Data acquisition module: Deployed on the front-end server, using the Vue.js framework, integrating IoT sensors (such as water level sensors and cameras) and meteorological APIs to collect data in real time.

[0029] Priority assessment module: Deployed on the backend server, using the Spring Boot framework, running Python algorithms (such as the NetworkX library for complex network analysis), and integrating a TPM chip for trusted computing.

[0030] Decision generation module: Deployed on edge nodes, it uses C++ to implement optimization algorithms (such as genetic algorithms) and supports discrete event simulation (using AnyLogic software).

[0031] The execution communication module communicates with the execution unit via a RESTful API and the MQTT protocol, supporting drones, robots, and mobile terminals. Lightweight cryptographic modules (such as the SM4 algorithm) are deployed on edge nodes to ensure secure communication.

[0032] Deployment architecture: It adopts a front-end and back-end separation deployment. The front-end server handles the user interface, the back-end server handles the business logic, the database uses MySQL, and the cache uses Redis.

[0033] This invention constructs a "zero-time response" method, breaking away from the lengthy process of "information collection, manual analysis, hierarchical reporting, and instruction issuance" in traditional emergency decision-making. Through a highly integrated and automated data processing and decision-making chain, it achieves a rapid closed loop from event occurrence to response initiation, laying the foundation for subsequent rapid decision-making and action. In implementation, raw information about the emergency event is continuously and automatically collected through a network of sensors (such as IoT devices and cameras), system reporting interfaces, and external data APIs, ensuring the real-time and direct nature of the information source. The collected information is immediately input into a pre-set "zero-time priority assessment model." This model automatically calculates the urgency and importance of the event within a one-second time window, outputting a quantitative priority score, replacing traditional manual judgment. Based on this priority score and specific event information (such as type and location), the system automatically generates a decision support plan containing specific action instructions using a built-in rule base or optimization algorithm. The generated plan is immediately distributed to the front-end execution unit (such as drones or rescue personnel's handheld terminals) via a high-speed communication network (such as 5G) to directly initiate emergency response actions. Considering the dynamic evolution of the disaster chain and the fusion of multi-source data, the system has high assessment accuracy and high scheduling efficiency, reducing the initial response time for emergency decision-making from the traditional several minutes to seconds. This meets the needs of immediate response under extreme weather conditions, buys valuable time for saving lives and property, greatly reduces the reliance on human experience in the decision-making process, reduces the risk caused by personnel shortages and judgment errors, and improves the objectivity and consistency of the response.

[0034] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A field emergency decision support method based on a zero-time response mechanism, characterized in that, Includes the following steps: S1. Obtain real-time information on on-site emergency events; S2. Based on the preset zero-time priority assessment model, the emergency event is assessed in real time, and a priority score is output. The assessment model is configured to complete the real-time priority assessment within 1 second. S3. Generate a decision support scheme based on the priority score and event information; S4. The decision support plan is immediately distributed to the field execution unit through the communication network to initiate emergency response actions.

2. The on-site emergency decision support method based on a zero-time response mechanism according to claim 1, characterized in that, In step S1, the information includes at least one of the following: event type, event location, event severity, and environmental parameters.

3. The on-site emergency decision support method based on a zero-time response mechanism according to claim 1, characterized in that, In step S2, the zero-time-priority assessment model is constructed based on the disaster chain risk evolution law, which is obtained through complex network analysis, including calculating at least one network parameter among node degree, clustering coefficient, and betweenness centrality; the complex network analysis includes a dynamic trust assessment component, which performs real-time comprehensive scoring based on at least one of equipment status data, environmental factor data, and user behavior data, and is implemented through trusted computing.

4. The on-site emergency decision support method based on a zero-time response mechanism according to claim 3, characterized in that, The zero-time-priority evaluation model adopts a data fusion strategy, which is DS evidence theory fusion, used to integrate multi-source data, including at least two of meteorological data, geographic information data, real-time sensor data and historical disaster data. The fusion process integrates privacy computing, including at least one of homomorphic encryption, secure multi-party computation or trusted execution environment (TEE).

5. The on-site emergency decision support method based on a zero-time response mechanism according to claim 1, characterized in that, In step S3, the decision support scheme includes at least one of resource scheduling strategy, risk control measures, and early warning instructions; the decision support scheme includes multi-objective optimization using an optimization algorithm, wherein the optimization algorithm is at least one of genetic algorithm, particle swarm optimization, or linear programming, and the optimization objectives include minimizing response time, minimizing resource cost, and maximizing coverage, and the optimization process is combined with simulation verification, including at least one of discrete event simulation or Monte Carlo simulation.

6. The on-site emergency decision support method based on a zero-time response mechanism according to claim 1, characterized in that, In step S4, the communication network supports collaboration between edge computing nodes and cloud platforms. The edge computing nodes deploy lightweight cryptographic modules to achieve secure communication. The execution unit includes at least one of drones, robots, mobile terminals, or emergency vehicles.

7. The on-site emergency decision support method based on a zero-time response mechanism according to claim 1, characterized in that, It also includes step S5, which involves real-time monitoring of the emergency response execution, collecting feedback data, and dynamically adjusting the zero-time-priority assessment model and decision support scheme based on machine learning algorithms.

8. A field emergency decision support system based on a zero-time response mechanism, used to implement the method as described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire emergency event information in real time. The priority assessment module is used to run a zero-time priority assessment model and output a priority score. The decision generation module is used to generate decision support solutions; The communication execution module is used to send the plan to the execution unit.

9. An electronic device comprising a processor and a memory, characterized in that, The memory stores a computer program that, when executed by the processor, implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images