Emergency path planning method and system based on big data analysis

Abstract

The invention provides an emergency path planning method and system based on big data analysis. The method comprises the following steps: collecting dynamic and static information flows from multiple channels, and performing identification and prediction processing on various complex situation factors to obtain first-aid resource allocation suggestions; according to the first-aid resource allocation suggestion, carrying out fine evaluation processing on emergency occurrence rates of different geographic areas in a specific time period, and generating a risk distribution map; based on the risk distribution map, performing optimization processing on the path according to a shortest time principle and avoiding an expected congestion road section to obtain an optimal response path; and by utilizing the optimal response path, continuously receiving field feedback by setting a two-way communication mechanism, and synchronizing the information to all mobile terminals participating in first-aid actions to generate an efficient collaborative response network. According to the technical scheme provided by the invention, the first-aid response speed and efficiency are improved, the resource configuration and deployment are optimized, and the flexibility and reliability of path planning are enhanced.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of emergency route planning, and in particular, to an emergency route planning method and system based on big data analysis. Background Art

[0002] In modern emergency systems, it is crucial to respond to emergencies quickly and accurately. With the acceleration of urbanization and the increase in population density, the frequency and complexity of emergency incidents are also increasing. In order to effectively meet these challenges, emergency services not only need to rely on efficient resource scheduling and route planning, but also need to be able to process information from multiple heterogeneous data sources in real time, such as traffic flow, weather forecasts, social media hot spots, and historical emergency case databases. This multi-dimensional data integration and analysis capability is the key to ensuring the speed and efficiency of emergency response, and also provides a solid foundation for optimizing resource allocation.

[0003] At present, most emergency systems rely mainly on traditional static resource allocation and experience-based path planning methods. These systems usually allocate emergency resources through a preset emergency site distribution map and select rescue paths based on fixed rules or manual judgment. Although some advanced systems have begun to introduce GPS positioning technology and simple traffic information update functions, they still seem to be powerless in the face of complex dynamic environments. In addition, existing emergency path planning often lacks forward-looking predictions for high-risk areas and time periods, making it difficult to achieve optimal allocation and efficient use of resources.

[0004] Traditional methods are unable to identify potential high-risk areas and time periods in advance, resulting in untimely and inaccurate resource allocation when emergencies occur; route planning based on fixed rules or simple update mechanisms has limited adjustment capabilities when faced with emergencies (such as temporary traffic control, emergencies), which can easily cause delays; it fails to fully utilize multi-source heterogeneous data for comprehensive analysis, ignoring the risk patterns and demand trends hidden behind the data, affecting the scientific nature and accuracy of decision-making. Summary of the invention

[0005] The embodiments of the present application provide an emergency path planning method and system based on big data analysis, so as to solve the problem of limited adjustment capability of path planning in the prior art when facing emergencies.

[0006] In a first aspect, an embodiment of the present application provides an emergency path planning method based on big data analysis, including:

[0007] Collect dynamic and static information flows from multiple channels, identify and predict various complex situational factors, and obtain emergency resource allocation recommendations;

[0008] Based on the emergency resource allocation recommendations, Bayesian networks are used to model risk probability, and combined with the knowledge base technology of the expert system, the incidence of emergencies in different geographical areas within a specific time period is carefully evaluated and processed to generate a risk distribution map;

[0009] Based on the risk distribution map, an ant colony optimization algorithm is introduced to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination. At the same time, combined with the real-time road condition update provided by the intelligent transportation system, the path is optimized based on the shortest time principle and avoiding expected congested sections to obtain the optimal response path;

[0010] By utilizing the optimal response path and establishing a two-way communication mechanism to continuously receive on-site feedback, this information is synchronized to all mobile terminals participating in the emergency operation, thereby generating an efficient collaborative response network.

[0011] Optionally, the risk probability modeling is performed using a Bayesian network based on the emergency resource allocation suggestion, and combined with the knowledge base technology of the expert system, the incidence of emergency situations in different geographical areas within a specific time period is finely evaluated and processed to generate a risk distribution map, including:

[0012] Using the emergency resource allocation recommendations of forward-looking guidance, we integrate and analyze multi-source heterogeneous data to generate basic data sets;

[0013] Based on the basic data set, a risk probability model is constructed using a Bayesian network to quantify the probability of emergency occurrence in each geographical area and generate a risk probability estimate;

[0014] Based on the risk probability estimation, combined with the knowledge base technology of the expert system, the model parameters are adjusted and optimized to ensure that the risk assessment results are closer to the actual situation and generate an optimized risk probability estimation;

[0015] The optimized risk probability estimation is used to perform a detailed assessment of the incidence of emergency situations in different geographical areas within a specific time period to generate a risk distribution map.

[0016] Optionally, the emergency resource allocation recommendations using forward-looking guidance integrate and analyze multi-source heterogeneous data to generate a basic data set, including:

[0017] Using the emergency resource allocation recommendations of forward-looking guidance, determine the scope and focus of multi-source heterogeneous data collection and generate data collection strategies;

[0018] According to the data collection strategy, real-time and historical data related to first aid are collected from different data sources to generate a raw data set;

[0019] Based on the original data set, perform data cleaning, formatting and standardization processing to eliminate noise and inconsistency in the data and generate a purified data set;

[0020] Utilizing the purified data set, combining time and space attributes to perform data association analysis, mining potential connections between different data, and generating an association data model;

[0021] Extracting meaningful information features according to the associated data model, encoding and indexing the information features to ensure effective retrieval and rapid access to information, and generating feature encoding data;

[0022] Based on the feature coded data, information from various data sources is integrated to generate a basic data set.

[0023] Optionally, the optimized risk probability estimation is used to perform a detailed assessment of the emergency rate in different geographical areas within a specific time period to generate a risk distribution map, including:

[0024] Using the optimized risk probability estimates, combined with spatiotemporal analysis methods, a comprehensive assessment of the frequency and severity of emergencies in each geographic area is conducted to generate a preliminary risk score;

[0025] Based on the preliminary risk scores, spatial interpolation techniques are used to fill in the risk information in data-sparse areas to ensure that all geographic areas have corresponding risk assessment results and generate a complete risk coverage map;

[0026] Based on the complete risk coverage map, clustering algorithms are applied to identify high-risk hotspot areas, and the time series characteristics of these areas are deeply analyzed to generate information on hotspot areas and high-risk periods;

[0027] Utilizing the information of the hot spots and high-risk periods, combined with real-time traffic flow and weather conditions, the risk assessment results are adjusted and refined to generate a risk distribution map.

[0028] Optionally, based on the risk distribution map, an ant colony optimization algorithm is introduced to simulate the path selection process of the rescue vehicle from multiple potential starting points to the destination, and at the same time, combined with the real-time road condition update provided by the intelligent transportation system, the path is optimized based on the shortest time principle and avoiding expected congested sections to obtain the optimal response path, including:

[0029] Using the risk distribution map, determine the high-incidence area of ​​emergency as the destination, and identify all available emergency unit locations as potential departure points to generate a set of paths;

[0030] Initializing the parameters of the ant colony optimization algorithm according to the path set, and setting an initial path matrix to guide path selection during the simulation process and generate an initial path configuration;

[0031] Based on the initial path configuration, an ant colony optimization algorithm is applied to simulate the travel process from each potential starting point to the destination, each possible path is evaluated, and a preliminary optimized path list is generated;

[0032] Using the real-time traffic update data provided by the intelligent transportation system, dynamically adjusting each path in the preliminary optimized path list to generate a dynamically adjusted path list;

[0033] According to the dynamically adjusted path list, all factors are comprehensively considered, and a path that meets the optimal response conditions is selected as a reference for the actual rescue operation to generate the optimal response path.

[0034] Optionally, the initializing ant colony optimization algorithm parameters according to the path set and setting an initial path matrix for guiding path selection in the simulation process and generating an initial path configuration includes:

[0035] Analyze all possible connections between the starting point and the destination using the path set to generate a connection relationship table;

[0036] According to the connection relationship table, key parameters of the ant colony optimization algorithm are determined, and initial values ​​of these parameters are set to generate algorithm parameter configuration;

[0037] Based on the algorithm parameter configuration, an initial path matrix including all nodes and their connections is constructed to guide path selection in subsequent simulation processes and generate an initial path matrix;

[0038] Using the initial path matrix, combined with the algorithm parameter configuration, a preliminary path exploration simulation is performed to ensure that at least one feasible path between the paths is found, and an initial path configuration is generated.

[0039] Optionally, the optimal response path is used to continuously receive on-site feedback by establishing a two-way communication mechanism, and the information is synchronized to all mobile terminals participating in the emergency operation to generate an efficient collaborative response network, including:

[0040] Using the optimal response path, a safe and reliable two-way communication channel is established to generate a two-way communication mechanism;

[0041] According to the two-way communication mechanism, a field feedback collection system is deployed to capture and transmit first-hand information from emergency personnel and generate a field feedback data stream;

[0042] Based on the on-site feedback data stream, a synchronization update algorithm is developed to enable the latest situation to be instantly reflected on the mobile terminals of all relevant emergency personnel and generate an information synchronization plan;

[0043] By utilizing the information synchronization solution, multiple resources are integrated to form an efficient collaborative response system and generate an efficient collaborative response network.

[0044] In a second aspect, an embodiment of the present application provides an emergency path planning system based on big data analysis, including:

[0045] The collection module is used to collect dynamic and static information flows from multiple channels, identify and predict various complex situational factors, and obtain emergency resource allocation suggestions;

[0046] An evaluation module is used to use the Bayesian network to perform risk probability modeling based on the emergency resource allocation suggestion, and combine the knowledge base technology of the expert system to perform a detailed evaluation of the emergency incidence rate in different geographical areas within a specific time period to generate a risk distribution map;

[0047] An optimization module is used to introduce an ant colony optimization algorithm to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination based on the risk distribution map, and at the same time, combined with the real-time road condition update provided by the intelligent transportation system, optimize the path based on the shortest time principle and avoid expected congested sections to obtain the optimal response path;

[0048] The synchronization module is used to utilize the optimal response path, continuously receive on-site feedback by establishing a two-way communication mechanism, synchronize this information to all mobile terminals participating in the emergency operation, and generate an efficient collaborative response network.

[0049] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a first aid path planning method based on big data analysis as described in the first aspect.

[0050] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a method for emergency route planning based on big data analysis as described in the first aspect.

[0051] In the embodiment of the present application, dynamic and static information flows from multiple channels are collected, various complex situational factors are identified and predicted, and emergency resource allocation suggestions are obtained; based on the emergency resource allocation suggestions, risk probability modeling is performed using a Bayesian network, and combined with the knowledge base technology of the expert system, the incidence of emergencies in different geographical areas within a specific time period is finely evaluated and processed to generate a risk distribution map; based on the risk distribution map, an ant colony optimization algorithm is introduced to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination, and at the same time, combined with the real-time road condition updates provided by the intelligent transportation system, the path is optimized based on the shortest time principle and avoiding expected congested sections to obtain the optimal response path; using the optimal response path, a two-way communication mechanism is established to continuously receive on-site feedback, and this information is synchronized to all mobile terminals participating in the emergency operation to generate an efficient collaborative response network.

[0052] The technical solution of this application has the following beneficial effects:

[0053] By collecting and integrating multi-source heterogeneous data and combining spatiotemporal association rule mining technology, potential high-risk areas and time periods can be identified in advance. This makes the allocation of emergency resources more forward-looking, ensuring that resources can be quickly mobilized when an emergency occurs, greatly shortening the response time and improving the efficiency of emergency rescue. The risk probability model constructed by the Bayesian network and the knowledge base technology of the expert system are used to achieve a detailed assessment of the incidence of emergencies in different geographical areas. The generated risk distribution map guides the pre-deployment of emergency resources, ensuring that resource allocation is more scientific and reasonable, and avoiding the problem of resource waste and imbalance. The ant colony optimization algorithm is introduced to simulate the travel process of rescue vehicles from multiple potential starting points to the destination, and is dynamically adjusted in combination with the real-time road condition updates provided by the intelligent transportation system. This method not only takes into account the shortest time principle, but also effectively avoids expected congested sections, enhancing the flexibility and reliability of path planning; through the two-way communication mechanism, on-site feedback is continuously received, and the latest information is synchronized to the mobile terminals of all relevant personnel involved in the emergency operation, forming an efficient collaborative response network. This mechanism ensures that all parties can obtain the latest information in a timely manner and quickly adjust the action strategy, thereby improving the accuracy and practicality of decision support and providing a solid guarantee for the effective implementation of emergency measures.

[0054] Furthermore, the forward-looking guidance of emergency resource allocation recommendations is used to integrate and analyze multi-source heterogeneous data, generate basic data sets, and use Bayesian networks to build risk probability models, quantify the probability of emergency situations in various geographical areas, generate risk probability estimates, and then adjust and optimize model parameters in combination with the knowledge base technology of the expert system to ensure that the evaluation results are close to the actual situation. Finally, the optimized risk probability estimates are generated and the emergency rates in different geographical areas within a specific time period are finely evaluated to generate risk distribution maps. This process significantly improves the accuracy and scientificity of risk assessment, makes resource pre-deployment more reasonable and effective, and avoids resource waste and imbalance. At the same time, through forward-looking risk prediction and dynamic adjustment mechanisms, the system's ability to respond to emergencies is enhanced, the speed and efficiency of emergency response are improved, and solid data support and reliable basis are provided for emergency decision-making.

[0055] Furthermore, the ant colony optimization algorithm is introduced to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination, and the path is optimized according to the shortest time principle and avoiding expected congested sections in combination with the real-time traffic update provided by the intelligent transportation system, and finally the optimal response path is obtained. This method first uses the risk distribution map to determine the high-incidence area of ​​emergency as the destination, and identifies all available emergency units as potential starting points to generate a path set; then initializes the ant colony optimization algorithm parameters and sets the initial path matrix to guide path selection and generate an initial path configuration; then applies the ant colony optimization algorithm to simulate the travel process and evaluate each possible path to generate a preliminary optimized path list; then uses the real-time traffic update data of the intelligent transportation system to dynamically adjust the path and generate a dynamically adjusted path list; finally, comprehensively considers and selects the path that meets the optimal response conditions as a reference for the actual rescue operation. This method significantly improves the speed and efficiency of rescue response, ensures that rescue vehicles can arrive at the scene quickly and accurately, and minimizes rescue time and uncertainty. At the same time, through the application of intelligent path planning and real-time traffic information, traffic congestion is effectively avoided, the success rate of rescue operations is further guaranteed, and the overall efficiency and service quality of the public safety emergency system are improved.

[0056] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 A flowchart of an emergency path planning method based on big data analysis provided in an embodiment of the present application;

[0059] Figure 2 A schematic diagram of the structure of an emergency path planning system based on big data analysis provided in an embodiment of the present application;

[0060] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0062] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0064] Figure 1 A flowchart of an emergency path planning method based on big data analysis is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0065] 101. Collect dynamic and static information flows from multiple channels, identify and predict various complex situational factors, and obtain emergency resource allocation suggestions;

[0066] This step involves collecting dynamic (such as real-time traffic conditions, weather forecasts) and static (such as geographic information, fixed emergency facility locations) data from multiple sources to build a comprehensive database. These data are processed through advanced analytical algorithms to identify potential complex situational factors and predict the possibility of emergency situations, thereby providing a scientific basis for the allocation of emergency resources.

[0067] In the embodiment of the present application, by integrating information from different channels, data analysis technology is used to identify and predict various factors that affect emergency response, and then optimize configuration suggestions are made. In this process, the use of machine learning models can better understand historical patterns and predict future trends, ensuring more accurate and efficient resource allocation.

[0068] For example, in an urban environment, the system collects data on all traffic accidents in the past year, current road construction information, and weather forecasts. After analysis, it finds that the probability of accidents in specific areas of the city center is higher on weekend afternoons, so it recommends increasing the deployment of ambulances in the area.

[0069] 102. Based on the emergency resource allocation recommendations, use Bayesian networks to model risk probability, and combine with the knowledge base technology of the expert system to conduct a detailed assessment of the incidence of emergencies in different geographical areas within a specific time period to generate a risk distribution map;

[0070] In this step, based on the configuration recommendations obtained in the previous step, a Bayesian network is used to simulate the probability of different events, and combined with the knowledge base of the expert system, the incidence of emergencies in various geographical areas within a specific time period is evaluated. The Bayesian network is a probabilistic graphical model that can express the dependencies between variables, while the expert system contains the knowledge of domain experts. The combination of the two can generate an accurate risk distribution map.

[0071] In the embodiment of the present application, a Bayesian network is first used to calculate the probability of occurrence of various emergency situations based on known conditions, and then these estimates are further refined with the help of rules and experience in the expert system, ultimately forming a detailed risk map to guide subsequent path planning and other decision support activities.

[0072] Suppose an area in a city is marked as a high-risk area during specific holidays. Because the Bayesian network shows that the probability of traffic accidents increases significantly during this period, and the expert system confirms that the locations of local hospitals and fire stations are not sufficient to cover all needs, it is decided to temporarily add mobile medical points and service vehicles.

[0073] Optionally, in step 102, based on the emergency resource allocation suggestion, a Bayesian network is used to perform risk probability modeling, and combined with the knowledge base technology of the expert system, a detailed evaluation process is performed on the emergency incidence rate in different geographical areas within a specific time period to generate a risk distribution map, including:

[0074] Using the forward-looking guidance on emergency resource allocation recommendations, multi-source heterogeneous data are integrated and analyzed to generate a basic data set; based on the basic data set, a risk probability model is constructed using a Bayesian network to quantify the probability of emergency situations in each geographical area and generate a risk probability estimate; based on the risk probability estimate, combined with the knowledge base technology of the expert system, the model parameters are adjusted and optimized to ensure that the risk assessment results are closer to the actual situation and to generate an optimized risk probability estimate; using the optimized risk probability estimate, the incidence of emergencies in different geographical areas within a specific time period is carefully evaluated and processed to generate a risk distribution map.

[0075] In this step, the first step involves forward-looking guidance of emergency resource allocation recommendations, which include historical data, prediction model outputs, and expert opinions, to develop a more scientific and reasonable resource allocation strategy. This is followed by the integration and analysis of multi-source heterogeneous data, which covers data from different sources (such as sensor networks, social media, and government databases) to generate a comprehensive basic data set. Then, a Bayesian network is used to construct a risk probability model, which provides a mathematical framework for estimating risks by quantifying the probability of emergency situations in each geographic area. Finally, the model parameters are adjusted and optimized in combination with the knowledge base technology of the expert system to ensure that the evaluation results are as close to the actual situation as possible, thereby generating a more accurate risk distribution map.

[0076] In the embodiments of the present application, firstly, based on the forward-looking emergency resource allocation recommendations, the system will collect and process data from multiple sources to form a comprehensive basic data set; secondly, using this basic data set, through the Bayesian network modeling technology, the probability of emergency situations in various geographical areas is calculated to obtain a preliminary risk probability estimate; thirdly, the knowledge base technology of the expert system is introduced to fine-tune the parameters in the Bayesian network model so that the results of the risk assessment are more in line with the actual situation; finally, based on the optimized risk probability estimate, the incidence of emergency situations in different geographical areas within a specific time period is evaluated in detail to produce an accurate risk distribution map.

[0077] In order to cope with the problem of increased urban traffic accidents during the peak summer tourist season, first, the city's emergency management team formulated recommendations for emergency resource allocation for the summer based on previous accident statistics, weather forecasts, and local hospital emergency records. Secondly, they integrated various types of data, such as traffic flow monitoring points, travel plan discussions on social media, and tourist number estimates provided by the Municipal Tourism Bureau, to form a detailed basic data set. Thirdly, they used the Bayesian network analysis method to conduct in-depth mining of these data and derived the initial value of the probability of traffic accidents occurring in various tourist hotspots every weekend in July. Finally, experts in the fields of traffic engineering and public safety were invited to participate in the review. Based on their experience and field research, some key parameters in the model were adjusted, and finally a city-wide risk distribution map was generated, which clearly shows which areas need to strengthen police patrols or add temporary medical stations.

[0078] Through the above steps, city managers can deploy more resources to high-risk areas in advance, effectively reducing potential dangers and improving the efficiency of emergency response.

[0079] Optionally, the emergency resource allocation recommendations using forward-looking guidance integrate and analyze multi-source heterogeneous data to generate a basic data set, including:

[0080] Utilize forward-looking guidance on emergency resource allocation recommendations to determine the scope and focus of multi-source heterogeneous data collection and generate a data collection strategy; based on the data collection strategy, collect emergency-related real-time and historical data from different data sources to generate an original data set; based on the original data set, perform data cleaning, formatting, and standardization to eliminate noise and inconsistencies in the data and generate a purified data set; utilize the purified data set to perform data association analysis in combination with time and space attributes, explore potential connections between different data, and generate an associated data model; based on the associated data model, extract meaningful information features, encode and index the information features to ensure effective retrieval and rapid access to information, and generate feature-coded data; based on the feature-coded data, integrate information from various data sources to generate a basic data set.

[0081] Optionally, the optimized risk probability estimation is used to perform a detailed assessment of the emergency rate in different geographical areas within a specific time period to generate a risk distribution map, including:

[0082] Using the optimized risk probability estimation, combined with the spatiotemporal analysis method, a comprehensive assessment is made on the frequency and severity of emergencies in each geographical area to generate a preliminary risk score; based on the preliminary risk score, spatial interpolation technology is used to fill in the risk information of data-sparse areas to ensure that all geographical areas have corresponding risk assessment results and generate a complete risk coverage map; based on the complete risk coverage map, a clustering algorithm is applied to identify high-risk hot spots, and the time series characteristics of these areas are deeply analyzed to generate information on hot spots and high-risk time periods; using the information on hot spots and high-risk time periods, combined with real-time traffic flow and weather conditions, the risk assessment results are adjusted and refined to generate a risk distribution map.

[0083] In this step, the first step is to use forward-looking guidance to recommend emergency resource allocation, which is based on historical data, forecasting model outputs, expert opinions and other information to formulate a more scientific and reasonable resource allocation strategy. Multi-source heterogeneous data includes data from different channels (such as sensor networks, social media, and government databases). These data are integrated and analyzed to generate basic data sets to provide support for subsequent risk assessment. The optimized risk probability estimate is combined with spatiotemporal analysis methods to comprehensively evaluate the frequency and severity of emergencies in various geographic areas, and finally generate a detailed risk distribution map to guide the optimal allocation of emergency resources.

[0084] In the embodiment of the present application, first, according to the forward-looking emergency resource allocation suggestions, the scope and focus of data collection are determined, and an effective data collection strategy is formulated; secondly, according to this strategy, real-time and historical emergency-related data are collected from multiple data sources to form an original data set; thirdly, the original data set is cleaned, formatted and standardized to eliminate noise and inconsistency, ensure data quality, and generate a purified data set; finally, the purified data set is used to perform association analysis in combination with time and space attributes, explore potential connections, and encode and index meaningful information features, integrate information from various data sources, and finally generate a basic data set. For the generation of risk distribution maps, first, the optimized risk probability estimation is used, combined with the spatiotemporal analysis method, to evaluate the frequency and severity of emergencies in each geographical area, and generate a preliminary risk score; secondly, spatial interpolation technology is used to fill the risk information in the data sparse area, ensure that all geographical areas have corresponding assessment results, and generate a complete risk coverage map; thirdly, clustering algorithm is applied to identify high-risk hotspot areas, and the time series characteristics of these areas are deeply analyzed to generate information about hotspot areas and high-risk periods; finally, combined with real-time traffic flow and weather conditions, the risk assessment results are adjusted and refined to generate the final risk distribution map.

[0085] In order to improve the city's safety management level during the peak summer tourist season, first, the city's emergency management team formulated recommendations for emergency resource allocation for the summer vacation based on previous accident statistics, weather forecasts, and local hospital emergency records, and clarified the types of data and sources that need to be focused on; second, they followed these recommendations and collected real-time and historical data on traffic accidents, tourist flows, weather changes, etc. from multiple channels such as traffic monitoring systems, social media platforms, and tourism bureau databases to form a huge set of raw data; third, the team carried out meticulous data cleaning, formatting, and standardization on this raw data set, removed duplicates and outliers, ensured data consistency and accuracy, and thus generated a purified data set; finally, through data association analysis combining time and space attributes, the potential connections between different data were discovered, key information features were extracted, coded and indexed for rapid retrieval and access, and an integrated basic data set was successfully constructed.

[0086] Through the above steps, city managers can deploy more resources to high-risk areas in advance, effectively reducing potential dangers and improving the efficiency of emergency response.

[0087] The present application takes into account that in the prior art, due to the problem that static resource configuration and experience-based path planning methods cannot adapt to complex dynamic environments, emergency response efficiency is low and resource allocation is unreasonable. In addition, the lack of forward-looking predictions for high-risk areas and time periods leads to insufficient timeliness and accuracy in resource allocation when emergencies occur. Therefore, the embodiment of the present invention proposes this optional solution, which introduces Bayesian networks for risk probability modeling, combines the knowledge base technology of expert systems, and ant colony optimization algorithms and other advanced methods to solve the above technical problems and improve the speed, accuracy and efficiency of emergency response.

[0088] Optionally, the method of constructing a risk probability model using a Bayesian network based on the basic data set, quantitatively calculating the probability of emergency occurrence in each geographical area, and generating a risk probability estimate includes:

[0089] In calculating the emergency event E i The conditional probability P(E i |C) Before that, it is necessary to integrate and clean multi-source heterogeneous data, identify high-risk areas and time periods through spatiotemporal association rule mining technology, and establish a comprehensive situational awareness platform based on historical emergency cases to lay the foundation for subsequent probability calculations;

[0090]

[0091] E i Indicates the occurrence of emergency events in the i-th geographical area; E kIndicates the occurrence of the kth emergency, used to represent different types of emergency F j represents the jth state of the influencing factors, including traffic flow, weather conditions, etc.; w j (t) represents the weight coefficient of the jth influencing factor at time t, which is dynamically adjusted according to historical data and real-time situations; P(E i ∣F j ,H) represents the conditional probability of an emergency occurring under a given influencing factor state and considering historical data H; P(F j |C) represents the probability that the influencing factor is in a specific state under the current situation C; δ represents the environmental change coefficient, which measures the degree of influence of external environmental changes on the influencing factor; I j (t) represents the instantaneous change of the jth influencing factor at time t, including emergencies or temporary control measures; M represents the total number of all considered emergency types; ∈ represents the visualization coefficient, which is used to adjust the visualization data B k (t) Impact on risk assessment, where V k (t) represents the public feedback or social media popularity about the kth emergency at time t;

[0092] Complete the probability of emergency occurrence in each geographical area P(E i After the quantitative calculation of |C), enter the risk probability estimate RPE i (t+1) transition phase; this phase integrates the probability results, considers temporal changes and spatial interaction effects, introduces a learning rate adjustment mechanism and an evaluation of the interaction intensity between adjacent geographical regions, and ensures that the final estimate reflects the latest situation in a timely manner;

[0093] RPE i (t+1) = RPE i (t)+α·[P(E i |C)-RPE i (t)]+β·∑ k∈N(i) γ ik (t)·[RPE k (t)-RPE i (t)]+ζ·Δ i (t)

[0094] RPE i (t) represents the risk probability estimate of the i-th geographical area at time t; α represents the learning rate, which controls the influence of new information on the existing estimate; β represents the neighbor influence coefficient, which measures the interaction strength between adjacent geographical areas; N(i) represents the neighbor set of the i-th geographical area; γ ik(t) represents the strength of association between the i-th geographical area and the k-th neighboring geographical area at time t, and this value is dynamically adjusted with time and actual conditions; ζ represents the dynamic adjustment coefficient, which is used to adjust the impact of additional factors on risk estimation; Δ i (t) represents the change of pheromone in the i-th geographical area at time t; RPE k (t) represents the risk probability estimate of the kth neighboring geographic area at time t, which is used to measure the risk difference between neighboring areas and help adjust the risk estimate of the current area;

[0095] Calculate the risk probability estimate RPE i After (t+1), the latest information is synchronized to the mobile terminals of all relevant personnel through a two-way communication mechanism, and scenario analysis technology is used to simulate the impact of emergencies on path selection. At the same time, sensitivity analysis is performed to verify the stability and robustness of the solution, ensuring that the generated risk probability estimate is scientific and practical, providing decision support for emergency resource allocation.

[0096] This formula aims to overcome the defects in the existing emergency rescue system, such as uneven resource allocation, slow response, lack of foresight and flexibility. This application further provides an optional solution, which aims to integrate and clean multi-source heterogeneous data, mine spatiotemporal association rules, build risk probability models through Bayesian networks, select paths using ant colony optimization algorithms, and update real-time traffic conditions in intelligent transportation systems.

[0097] A series of steps are used to conduct a detailed assessment of the incidence of emergencies in different geographical areas within a specific time period, generate risk distribution maps and optimal response paths, and ultimately form an efficient collaborative response network. These measures work together to ensure that emergency resources are allocated more scientifically and rationally, and improve the speed and effectiveness of emergency response.

[0098] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0099]

[0100] The sum of the weights of each influencing factor: Reflects the importance of different factors; conditional probability product: w j (t)·P(E i ∣F j ,H); measure the probability of an emergency occurring under a given influencing factor state and considering historical data; immediate change adjustment: P(F j |C)+δ·I j (t); Consider the impact of changes in the external environment on influencing factors; The sum of different types of emergencies: Home

[0101] Unified processing to ensure the rationality of probability values; public feedback Or social media heat adjustment: P(E k ∣C)+∈·

[0102] V k (t); reflect the impact of public opinion on risk assessment;

[0103] The following is a brief introduction to how to obtain the parameters of the formula:

[0104] for The importance of each influencing factor is obtained from historical data analysis and dynamically adjusted according to the real-time situation; for P(E i ∣F j ,H), establish a comprehensive situational awareness platform based on the historical emergency case database; for P(F j |C), according to the actual situation in the current situation; for δ, a reasonable environmental change coefficient is set through experiments; for I j (t) Extract emergency or temporary control measures information from real-time data streams; Covering the total number of emergency types considered;

[0105] For ∈, it is set according to the impact of the visualized data on risk assessment; for V k (t), obtained from public feedback or social media popularity.

[0106] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0107] RPE i (t+1) = RPE i (t)+α·[P(E i |C)-RPE i (t)]+β·∑ k∈N(i) γ ik (t)·[RPE k (t)-Δ i (t)

[0108] Adjustment of existing estimates: RPE i (t); as the base value; the impact of new information: α·[P(E i |C)-RPE i (t)]; control the impact of new information on existing estimates; neighbor influence: β·∑ k∈N(i) γ ik (t)·[RPE k (t)-RPE i (t)]; considering the interaction strength between adjacent geographical areas; additional factor adjustment: ζ·Δ i(t); Adjust for the effects of other factors on risk estimates;

[0109] The following is a brief introduction to how to obtain the parameters of the formula:

[0110] For RPE i (t), based on the risk probability estimate at the previous moment; for α, it is set according to the learning rate, usually determined by experiments; for P(E i |C), calculated by Formula 1; for β, it is set according to the neighbor influence coefficient, reflecting the interaction intensity between adjacent geographical areas; for N(i), it defines the neighbor set of the i-th geographical area; for γ ik (t), dynamically adjusted according to the actual correlation strength at time t; for RPE k (t), based on the risk probability estimate of the neighboring geographical areas at the same time point; for ζ, it is set according to the dynamic adjustment coefficient; for Δ i (t), obtain the pheromone change amount from the real-time data stream.

[0111] Suppose in a large city, in order to prepare for the upcoming typhoon season, the emergency management department plans to optimize the response routes of emergency vehicles from multiple fire stations to potential disaster areas. First, the team collected and integrated the location data of all fire stations in the city, the locations of communities expected to be severely affected, traffic flow, weather forecasts and other multi-source heterogeneous data, and cleaned and analyzed them; secondly, they used spatiotemporal association rule mining technology to identify high-risk areas and time periods, and established a comprehensive situational awareness platform based on historical emergency cases, laying the foundation for subsequent probability calculations; then, they used the Bayesian network to build a risk probability model to calculate the probability of emergency occurrence P(E) in each geographical area. i ∣C), for example, a community E 1 The probability of flooding during a typhoon is P(E 1 |C) = 0.85; then, enter the generation of risk probability estimate RPE i In the transition phase (t+1), the above probability results are integrated, and the time variation and spatial interaction effects are considered. The formula RPE is applied i (t+1) = RPE i (t)+0.7·[0.85-RPE i (t)]+0.3·∑ k∈V(i) γ ik (t)·[RPE k (t)-RPE i (t)]+0.1·Δ i (t), assuming the initial estimated RPE i (0) = 0.5, after several iterations, the latest risk probability estimate RPE is obtained i(5) = 0.8; Finally, the latest information is synchronized to the mobile terminals of all relevant personnel through a two-way communication mechanism, and scenario analysis technology is used to simulate the impact of emergencies on path selection. At the same time, sensitivity analysis is performed to verify the stability and robustness of the solution, ensuring that the generated risk probability estimate is scientific and practical, providing decision support for emergency resource allocation. Through the above steps, the entire emergency operation becomes more orderly and efficient, greatly improving the speed and effect of emergency response, and ensuring that the safety of life and property of citizens is protected to the greatest extent.

[0112] In summary, through the application of the above series of steps and technical means, not only the accuracy and timeliness of emergency resource allocation are improved, but also the rescue response time is greatly shortened through intelligent path planning and real-time information update, and the delay caused by traffic obstructions is reduced. In addition, by establishing an efficient collaborative response network, the communication and coordination capabilities between departments are enhanced, making the entire emergency system more flexible, fast and effective, ultimately improving the level of public safety services and saving more lives.

[0113] 103. Based on the risk distribution map, an ant colony optimization algorithm is introduced to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination. At the same time, combined with the real-time road condition update provided by the intelligent transportation system, the path is optimized based on the shortest time principle and avoiding expected congested sections to obtain the optimal response path;

[0114] In this step, the risk distribution map is used as a basis to simulate the optimal path selection for rescue vehicles by introducing the ant colony optimization algorithm, and the real-time road condition update of the intelligent transportation system is coordinated to achieve the shortest path time principle and the goal of avoiding congested sections. The ant colony optimization algorithm imitates the foraging behavior of ants in nature to find the optimal solution from the starting point to the destination.

[0115] In the embodiment of the present application, based on the risk distribution map generated in the previous step, all possible starting points and target locations are defined, and then the ant colony optimization algorithm is used to simulate different path options. At the same time, the path is adjusted considering the real-time data of the intelligent transportation system to ensure that the selected path is fast and avoids traffic jams, thereby improving rescue efficiency.

[0116] For example, after a major accident occurs, the system quickly determines the nearest emergency unit with smooth traffic as the starting point, and selects the fastest route to the scene based on the traffic flow at the time, ensuring that the rescue team can arrive in the shortest time.

[0117] Optionally, in step 103, based on the risk distribution map, an ant colony optimization algorithm is introduced to simulate the path selection process of the rescue vehicle from multiple potential starting points to the destination, and at the same time, combined with the real-time road condition update provided by the intelligent transportation system, the path is optimized based on the shortest time principle and avoiding expected congested sections to obtain the optimal response path, including:

[0118] Using the risk distribution map, emergency high-incidence areas are determined as destinations, and all available emergency unit locations are identified as potential starting points to generate a path set; based on the path set, the ant colony optimization algorithm parameters are initialized, and an initial path matrix is ​​set to guide path selection in the simulation process and generate an initial path configuration; based on the initial path configuration, the ant colony optimization algorithm is applied to simulate the travel process from each potential starting point to the destination, each possible path is evaluated, and a preliminary optimized path list is generated; using the real-time traffic update data provided by the intelligent transportation system, each path in the preliminary optimized path list is dynamically adjusted to generate a dynamically adjusted path list; based on the dynamically adjusted path list, all factors are comprehensively considered to select a path that meets the optimal response conditions as a reference for actual rescue operations to generate an optimal response path.

[0119] In this step, the risk distribution map includes map data generated through data analysis to show the probability of emergency situations in various regions. These data are used to guide the allocation of emergency resources. The ant colony optimization algorithm is a heuristic search algorithm that simulates the foraging behavior of ants and is used to find paths close to the optimal solution in complex path selection problems. The real-time traffic update data provided by the intelligent transportation system contains information on current road conditions, such as traffic flow, accident reports, etc., which is used to dynamically adjust the routes of rescue vehicles.

[0120] In the embodiment of the present application, first, based on the risk distribution map, the high-incidence area of ​​emergency is set as the destination, and all available emergency units are found as potential starting points, and a series of possible paths are constructed on this basis; secondly, the parameters of the ant colony optimization algorithm are initialized according to the above path set, and the initial path matrix is ​​set to guide the selection of paths during the simulation process; thirdly, the ant colony optimization algorithm is used to simulate the movement process from each potential starting point to the destination, and the quality of each possible path is evaluated to form a preliminary optimized path list; finally, combined with the real-time traffic update information of the intelligent transportation system, the preliminary optimized path is dynamically adjusted, and after comprehensively considering all factors, the best path that meets the shortest time principle and avoids the expected congested road section conditions is selected as a reference for actual rescue operations.

[0121] Assume that in a large city, frequent thunderstorms in summer cause power outages and tree falls in some areas, resulting in frequent emergencies. First, the city emergency management department uses a pre-prepared risk distribution map to identify several areas with high incidence of power outages and tree falls as destinations that require rapid response; second, they identify all available emergency unit locations in the city, including fire stations, ambulance stops, etc. as potential starting points, forming a comprehensive set of paths; third, based on this set of paths, the team initialized the relevant parameters of the ant colony optimization algorithm, such as the number of ants, pheromone evaporation rate, etc., and set the initial path matrix to guide the subsequent simulation process and generate the initial path configuration; then, by applying the ant colony optimization algorithm, the travel process of each emergency unit to the target area was simulated, the efficiency of different paths was evaluated, and a preliminary optimized path list was generated; finally, using the latest road condition information provided by the intelligent transportation system, such as traffic light status, traffic accident reports, etc., the preliminary optimized path was adjusted in real time to ensure that the selected path can reach the target as quickly as possible and avoid possible traffic congestion, and finally the optimal response path was determined, providing accurate navigation guidance for on-site rescue.

[0122] Through the above steps, the rescue team can reach the accident site in the shortest time, improve rescue efficiency and ensure public safety.

[0123] Optionally, the initializing ant colony optimization algorithm parameters according to the path set and setting an initial path matrix for guiding path selection in the simulation process and generating an initial path configuration includes:

[0124] Using the path set, the connections between all possible starting points and destinations are analyzed to generate a connection relationship table; based on the connection relationship table, the key parameters of the ant colony optimization algorithm are determined, and the initial values ​​of these parameters are set to generate an algorithm parameter configuration; based on the algorithm parameter configuration, an initial path matrix including all nodes and their mutual connections is constructed to guide path selection in subsequent simulation processes to generate an initial path matrix; using the initial path matrix, combined with the algorithm parameter configuration, a preliminary path exploration simulation is performed to ensure that at least one feasible path between each path is found, and an initial path configuration is generated.

[0125] In this step, the path set includes the connection information between all possible starting points and destinations, which is used to generate a connection relationship table. The key parameters of the ant colony optimization algorithm, such as the number of ants and the pheromone evaporation rate, need to be initialized according to the actual situation to ensure the effectiveness of the algorithm. The initial path matrix is ​​a data structure containing all nodes and their connections, which is used to guide path selection in subsequent simulations. By performing preliminary path exploration simulations, it can be verified that at least one feasible path between each path is found, thereby generating an initial path configuration.

[0126] In an embodiment of the present application, first, based on the path set, a detailed analysis is performed on the connections between all possible starting points and destinations to generate a clear connection relationship table; secondly, based on this connection relationship table, the key parameters required for the ant colony optimization algorithm are determined, and the initial values ​​of these parameters are set to form an algorithm parameter configuration; thirdly, using the generated algorithm parameter configuration, a complete initial path matrix is ​​constructed, which includes all nodes and their connections to each other, providing guidance for subsequent simulations; finally, combining the initial path matrix and the algorithm parameter configuration, a preliminary path exploration simulation is performed to ensure that there is at least one feasible path between each pair of starting points and destinations, and finally an initial path configuration is generated.

[0127] Suppose in a large city, in order to prepare for the upcoming typhoon season, the emergency management department plans to optimize the response routes of emergency vehicles from multiple fire stations to potential disaster areas. First, the team collected the location data of all fire stations in the city and the communities expected to be severely affected as destinations, and generated a comprehensive set of routes; second, they conducted a detailed analysis of the connections between all possible departure points and destinations, taking into account factors such as road types and traffic flow, and generated a detailed connection relationship table; third, based on this connection relationship table, the team set the key parameters of the ant colony optimization algorithm, such as the number of ants, pheromone intensity, evaporation rate, etc., and set the initial values ​​of these parameters to form a reasonable algorithm parameter configuration; then, using the above algorithm parameter configuration, an initial path matrix containing all nodes and their connections was constructed to ensure that each node can be effectively connected to other nodes; finally, combined with the initial path matrix and algorithm parameter configuration, the team performed a preliminary path exploration simulation to ensure that there is at least one feasible path between each pair of departure points and destinations, and finally generated an initial path configuration.

[0128] Through the above steps, the rescue team can plan the optimal response path in advance before the typhoon arrives, ensuring that they can arrive at the scene quickly and effectively when a disaster occurs, thereby improving the speed and efficiency of emergency response.

[0129] The present application takes into account that in the prior art, due to the problem that static resource configuration and experience-based path planning methods cannot adapt to complex dynamic environments, emergency response efficiency is low and resource allocation is unreasonable. In addition, the lack of forward-looking predictions for high-risk areas and time periods leads to insufficient timeliness and accuracy in resource allocation when an emergency occurs. Therefore, the embodiment of the present invention proposes this optional solution, which introduces an ant colony optimization algorithm to simulate the travel process from each potential starting point to the destination, and combines the real-time traffic condition updates provided by the intelligent transportation system to perform the shortest time principle and optimize the avoidance of expected congested sections to solve the above-mentioned technical problems and improve the speed, accuracy and efficiency of emergency response.

[0130] Optionally, based on the initial path configuration, an ant colony optimization algorithm is applied to simulate the travel process from each potential starting point to the destination, each possible path is evaluated, and a preliminary optimized path list is generated, including:

[0131] When calculating the probability P of the ant choosing a path ij (t) Before, a network diagram containing all potential departure points and destinations is constructed, and the historical traffic efficiency and current traffic conditions of the road sections are evaluated to identify high congestion risk areas, providing a basis for subsequent probability calculations;

[0132]

[0133] P ij (t) represents the probability that the ant chooses node j from node j at time t; t ij (t) represents the pheromone concentration between node i and node j at time t; α represents the pheromone importance factor, which measures the influence of pheromone concentration; η ij (t) represents the heuristic value between nodes at time t, including the inverse of the distance or the estimated travel time; β represents the importance of the heuristic factor, which measures the influence of the heuristic value; N i represents the set of all adjacent nodes of a node; γ represents the dynamic adjustment coefficient, which is used to adjust the impact of real-time traffic conditions on path selection; D ij (t) represents the dynamic traffic congestion index between node i and node j at time t, reflecting the congestion situation of the current road section;

[0134] Completion probability P ij (t) After calculation, simulate the ant's marching process and record the path and time consumed. Combine the pheromone volatilization mechanism and external feedback to adjust the pheromone increment to ensure that the generated pheromone concentration truly reflects the actual passage conditions of the path and prepare for pheromone renewal.

[0135]

[0136] τ ij(t+1) represents the new pheromone concentration between node j at time t+1; τ ij (t) represents the new pheromone concentration between node i and node j at time t; (1-ρ) represents the pheromone volatility rate, which indicates the ratio of the natural decrease of pheromone over time; ρ represents the volatility coefficient, which controls the speed of pheromone reduction; Δτ ij (t) represents the pheromone increment between nodes at time t, which is contributed by all ants passing through the path; in is the pheromone increment of the kth ant on the path at time t. If ant k passes through path (i, j), then Otherwise, it is 0; Q is a constant, representing the total amount of pheromones released by ants; L k represents the total length or time taken by the kth ant to complete the path; θ represents the feedback coefficient, which is used to adjust the effect of external feedback on the pheromone concentration; F ij (t) represents the external feedback value between node t and node j at time t, including real-time traffic updates from the intelligent transportation system or public feedback, reflecting the actual traffic efficiency of the path and the impact of emergencies; λ represents the average speed influence coefficient, which measures the impact of average speed changes on pheromone concentration; L ij Represents the set of all segments on the node-to-node path; V l (t) represents the time t -10 Average speed on the segment; |L ij | represents the road segment set L ij The number of intermediate sections; μ represents the preset benchmark average speed, which is used to compare the change of the actual average speed;

[0137] After calculating the new pheromone concentration τ ij After (t+1), the path selection probability is re-evaluated, and the paths with high pheromone concentration and in line with the shortest time principle are screened out through multiple rounds of iterations. The scenario analysis technology is used to optimize the candidate paths to ensure that the generated preliminary optimized path list is scientific, reasonable and practical.

[0138] The formula aims to generate a preliminary list of optimized paths by building a network diagram containing all potential departure points and destinations, evaluating the historical efficiency and current traffic conditions of road sections, and identifying high congestion risk areas, etc. These measures work together to ensure that emergency resources are allocated more scientifically and rationally, and improve the speed and effectiveness of emergency response.

[0139] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0140]

[0141] Effect of pheromone concentration: [τij (t)] α ; Measures the influence of pheromone concentration; Heuristic value influence: [η ij (t)] β ; Measures the influence of heuristic values ​​(such as the inverse of distance or estimated travel time); Dynamic adjustment coefficient: [1+γ·D ij (t)]; adjust the impact of real-time traffic conditions on path selection; sum the adjacent node set: Ensure probabilities are normalized;

[0142] The following is a brief introduction to how to obtain the parameters of the formula:

[0143] For [τ ij (t)] α , obtained from the previous pheromone concentration records, and α is set according to the experiment; for [η ij (t)] β , calculated based on the distance between nodes or the estimated travel time, and β is set according to the experiment; for N i , directly determined from the network diagram; for γ, a reasonable dynamic adjustment coefficient is set according to the real-time traffic conditions; for D ij (t), extract the congestion situation of the current road section from the real-time traffic data stream.

[0144] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0145]

[0146] Natural reduction of pheromones: (1-ρ)·τ ij (t); represents the ratio of pheromone naturally decreasing over time; ant contribution increment: Δτ ij (t); reflects the contribution of ants passing through the path to its pheromone concentration; external feedback adjustment: θ·F ij (t); the effect of regulating external feedback on pheromone concentration; the effect of average speed: Measure the effect of changes in average speed on pheromone concentration;

[0147] The following is a brief introduction to how to obtain the parameters of the formula:

[0148] For (1-ρ)·τ ij (t), according to the set volatility coefficient ρ and the pheromone concentration τ at the previous moment ij (t) calculation; for in is the pheromone increment of the kth ant on the path at time t. If ant k passes through path (i, j), then Otherwise, it is 0; for θ, it is set according to the importance of external feedback; for F ij (t) is obtained from the real-time traffic updates of the intelligent transportation system or public feedback; λ is set according to the impact of the average speed change on the pheromone concentration; Get the average vehicle speed on each road segment from real-time traffic data; for |L ij |, statistical road segment set L ij For μ, a benchmark average speed is preset to compare the change of the actual average speed.

[0149] Suppose in a large city, in order to prepare for the upcoming typhoon season, the emergency management department plans to optimize the response routes of emergency vehicles from multiple fire stations to potential disaster areas. First, the team constructed a network diagram containing the locations of all fire stations in the city and the communities expected to be severely affected as destinations, and evaluated the historical traffic efficiency and current traffic conditions of each road section to identify high congestion risk areas, laying the foundation for subsequent probability calculations; secondly, they used the ant colony optimization algorithm to calculate the probability P of ants choosing a path ij (t), for example, the probability of a certain road section i to j The final probability value is 0.9. Then, simulate the ant's marching process and record the path and time. Combine the pheromone volatilization mechanism and external anti-expensive to adjust the pheromone increment to ensure that the generated pheromone concentration truly reflects the actual passage conditions of the path. Next, update the pheromone concentration. Assuming the initial pheromone concentration is 0.7, the new pheromone concentration τ is obtained after calculation ij (t+1)=0.85; Finally, re-evaluate the path selection probability, screen out paths with high pheromone concentration and in line with the shortest time principle through multiple rounds of iteration, and use scenario analysis technology to optimize candidate paths to ensure that the generated preliminary optimized path list is scientific, reasonable and practical. Through the above steps, the entire emergency operation becomes more orderly and efficient, greatly improving the speed and effect of emergency response, and ensuring the safety of life and property of citizens to the greatest extent.

[0150] In summary, through the application of the above series of steps and technical means, not only the accuracy and timeliness of emergency resource allocation are improved, but also the rescue response time is greatly shortened through intelligent path planning and real-time information update, and the delay caused by traffic obstructions is reduced. In addition, by establishing an efficient collaborative response network, the communication and coordination capabilities between departments are enhanced, making the entire emergency system more flexible, fast and effective, and ultimately improving the level of public safety services and saving more lives. Assuming that the threshold is set to 0.8, since the result is greater than the set threshold, it shows that the selected path has high reliability and effectiveness, thereby verifying the stability and robustness of the scheme.

[0151] 104. Utilize the optimal response path, establish a two-way communication mechanism to continuously receive on-site feedback, synchronize this information to all mobile terminals participating in the emergency operation, and generate an efficient collaborative response network.

[0152] In this step, a two-way communication platform is established to enable rescuers to continuously receive the latest on-site feedback and synchronize this information to all mobile terminals involved in the operation, thereby creating an efficient collaborative response network. This helps ensure timely sharing of information between all parties and improves the overall level of collaboration.

[0153] In the embodiment of the present application, by establishing a two-way communication mechanism, the rescue team can continuously obtain the latest environmental change information while performing the mission, and disseminate it to all relevant parties so as to adjust the strategy or path in time and enhance the speed and accuracy of the emergency response.

[0154] When the rescue vehicle was rushing to the accident site, the command center received the news of the road closure ahead through the two-way communication platform, and immediately notified all the emergency units involved to change the route, and sent the latest instructions to the emergency personnel on the scene to ensure that they can reach the designated location as quickly as possible.

[0155] Optionally, the optimal response path in step 104 is used to continuously receive on-site feedback by establishing a two-way communication mechanism, and the information is synchronized to all mobile terminals participating in the emergency operation to generate an efficient collaborative response network, including:

[0156] Utilize the optimal response path to establish a safe and reliable two-way communication channel and generate a two-way communication mechanism; deploy a field feedback collection system based on the two-way communication mechanism to capture and transmit first-hand information from emergency personnel and generate a field feedback data stream; develop a synchronous update algorithm based on the field feedback data stream so that the latest situation can be immediately reflected on the mobile terminals of all relevant emergency personnel and generate an information synchronization solution; utilize the information synchronization solution to integrate multiple resources to form an efficient and collaborative response system and generate an efficient collaborative response network.

[0157] In this step, the optimal response path refers to the best rescue route determined by the ant colony optimization algorithm and the intelligent transportation system. The two-way communication mechanism includes the establishment of a safe and reliable communication channel to ensure the real-time exchange of information between emergency personnel and the command center. The on-site feedback data stream covers the first-hand information collected by emergency personnel during the operation, such as road conditions, weather changes, and the severity of the accident. This information is used to update and adjust the rescue strategy. The synchronous update algorithm is a technology that can quickly process and disseminate the latest situation, ensuring that all personnel involved in the emergency can obtain the latest information in real time. The efficient collaborative response network integrates multiple resources to form a closely coordinated emergency response system.

[0158] In the embodiments of the present application, first, a secure and reliable two-way communication channel is constructed based on the optimal response path to ensure that information can be seamlessly transmitted between emergency personnel and the command center; second, an on-site feedback collection system is deployed to capture the various conditions encountered by emergency personnel on the scene, and transmit this information back to the command center in real time to form a continuous data stream; third, a synchronous update algorithm is developed so that the latest situation can be quickly reflected on the mobile terminals of all relevant emergency personnel, ensuring that everyone can keep abreast of the latest developments; finally, using this synchronously updated information, resources from different departments and units are integrated to form an efficient and collaborative response system to ensure that all parties can respond to emergencies in a coordinated manner.

[0159] In a large city, in order to improve the efficiency of responding to public emergencies, the emergency management department decided to implement an advanced two-way communication mechanism. First, based on the pre-calculated optimal response path, the team established a safe and reliable two-way communication channel to ensure that the information exchange between emergency personnel and the command center would not be interrupted, whether in the city center or remote areas; second, they deployed a set of on-site feedback collection system. Emergency personnel were equipped with smart devices to upload videos, pictures and text descriptions of the scene in real time. These first-hand information was quickly transmitted to the command center, generating a continuous on-site feedback data stream; third, based on these data streams, the team developed a synchronous update algorithm that can process new information within a few seconds and push it to each emergency personnel's mobile terminal to ensure that everyone has the latest on-site situation; finally, through these synchronously updated information, the emergency management department integrated the resources of multiple departments such as fire, medical, and police to form an efficient and collaborative response system, enabling all parties to share information and work together on the same platform.

[0160] Through the above steps, the entire emergency operation has become more orderly and efficient, greatly improving the speed and effectiveness of emergency response and ensuring that the safety of life and property of citizens is protected to the greatest extent.

[0161] In general, steps 101 to 104 not only improve the accuracy and timeliness of emergency resource allocation, but also significantly shorten the rescue response time and reduce delays caused by traffic obstructions through intelligent route planning and real-time information updates. In addition, by establishing an efficient collaborative response network, the communication and coordination capabilities between departments are enhanced, making the entire emergency system more flexible, fast, and effective, ultimately improving the level of public safety services and saving more lives.

[0162] Figure 2 A schematic diagram of the structure of an emergency path planning system based on big data analysis is provided for an embodiment of the present application. Figure 2 As shown, the device comprises:

[0163] The collection module 21 is used to collect dynamic and static information flows from multiple channels, identify and predict various complex situational factors, and obtain emergency resource allocation suggestions;

[0164] An evaluation module 22 is used to perform risk probability modeling using a Bayesian network based on the emergency resource allocation suggestion, and in combination with the knowledge base technology of the expert system, to perform a detailed evaluation process on the emergency incidence rate in different geographical areas within a specific time period, and generate a risk distribution map;

[0165] The optimization module 23 is used to introduce an ant colony optimization algorithm to simulate the path selection process of the rescue vehicle from multiple potential starting points to the destination based on the risk distribution map, and at the same time, in combination with the real-time road condition update provided by the intelligent transportation system, optimize the path based on the shortest time principle and avoid expected congested sections to obtain the optimal response path;

[0166] The synchronization module 24 is used to utilize the optimal response path to continuously receive on-site feedback by establishing a two-way communication mechanism, synchronize this information to all mobile terminals participating in the emergency operation, and generate an efficient collaborative response network.

[0167] Figure 2 The emergency path planning system based on big data analysis can be executed Figure 1 The implementation principle and technical effect of the emergency path planning method based on big data analysis described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the emergency path planning system based on big data analysis in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0168] In one possible design, Figure 2 The emergency path planning system based on big data analysis of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0169] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0170] The processing component 32 is used to: collect dynamic and static information flows from multiple channels, identify and predict various complex situational factors, and obtain emergency resource allocation recommendations; based on the emergency resource allocation recommendations, use Bayesian networks to model risk probabilities, and combine the knowledge base technology of the expert system to conduct detailed assessments of the incidence of emergencies in different geographical areas within a specific time period to generate a risk distribution map; based on the risk distribution map, introduce an ant colony optimization algorithm to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination, and at the same time combine the real-time road condition updates provided by the intelligent transportation system to optimize the path based on the shortest time principle and avoid expected congested sections to obtain the optimal response path; use the optimal response path to continuously receive on-site feedback by establishing a two-way communication mechanism, synchronize this information to all mobile terminals participating in the emergency operation, and generate an efficient collaborative response network.

[0171] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0172] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0173] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0174] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0175] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0176] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0177] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a method for emergency route planning based on big data analysis.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0179] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0180] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for emergency path planning based on big data analysis, characterized in that: include: Collect dynamic and static information flows from multiple channels, identify and predict various complex situational factors, and obtain emergency resource allocation recommendations; Based on the emergency resource allocation recommendations, Bayesian networks are used to model risk probability, and combined with the knowledge base technology of the expert system, the incidence of emergencies in different geographical areas within a specific time period is carefully evaluated and processed to generate a risk distribution map; Based on the risk distribution map, an ant colony optimization algorithm is introduced to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination. At the same time, combined with the real-time road condition update provided by the intelligent transportation system, the path is optimized based on the shortest time principle and avoiding expected congested sections to obtain the optimal response path; By utilizing the optimal response path and establishing a two-way communication mechanism to continuously receive on-site feedback, this information is synchronized to all mobile terminals participating in the emergency operation, thereby generating an efficient collaborative response network.

2. The method according to claim 1, characterized in that According to the emergency resource allocation suggestion, the Bayesian network is used to model the risk probability, and combined with the knowledge base technology of the expert system, the emergency incidence rate in different geographical areas within a specific time period is finely evaluated and processed to generate a risk distribution map, including: Using the emergency resource allocation recommendations of forward-looking guidance, we integrate and analyze multi-source heterogeneous data to generate basic data sets; Based on the basic data set, a risk probability model is constructed using a Bayesian network to quantify the probability of emergency occurrence in each geographical area and generate a risk probability estimate; Based on the risk probability estimation, combined with the knowledge base technology of the expert system, the model parameters are adjusted and optimized to ensure that the risk assessment results are closer to the actual situation and generate an optimized risk probability estimation; The optimized risk probability estimation is used to perform a detailed assessment of the incidence of emergency situations in different geographical areas within a specific time period to generate a risk distribution map.

3. The method according to claim 2, characterized in that The emergency resource allocation recommendations based on forward-looking guidance are used to integrate and analyze multi-source heterogeneous data to generate basic data sets, including: Using the emergency resource allocation recommendations of forward-looking guidance, determine the scope and focus of multi-source heterogeneous data collection and generate data collection strategies; According to the data collection strategy, real-time and historical data related to first aid are collected from different data sources to generate a raw data set; Based on the original data set, perform data cleaning, formatting and standardization processing to eliminate noise and inconsistency in the data and generate a purified data set; Utilizing the purified data set, combining time and space attributes to perform data association analysis, mining potential connections between different data, and generating an association data model; Extracting meaningful information features according to the associated data model, encoding and indexing the information features to ensure effective retrieval and rapid access to information, and generating feature encoding data; Based on the feature coded data, information from various data sources is integrated to generate a basic data set.

4. The method according to claim 2, characterized in that: The optimized risk probability estimation is used to perform a detailed assessment of the emergency rate in different geographical areas within a specific time period to generate a risk distribution map, including: Using the optimized risk probability estimates, combined with spatiotemporal analysis methods, a comprehensive assessment of the frequency and severity of emergencies in each geographic area is conducted to generate a preliminary risk score; Based on the preliminary risk scores, spatial interpolation techniques are used to fill in the risk information in data-sparse areas to ensure that all geographic areas have corresponding risk assessment results and generate a complete risk coverage map; Based on the complete risk coverage map, clustering algorithms are applied to identify high-risk hotspot areas, and the time series characteristics of these areas are deeply analyzed to generate information on hotspot areas and high-risk periods; Utilizing the information of the hot spots and high-risk periods, combined with real-time traffic flow and weather conditions, the risk assessment results are adjusted and refined to generate a risk distribution map.

5. The method according to claim 1, characterized in that: Based on the risk distribution map, the ant colony optimization algorithm is introduced to simulate the path selection process of the rescue vehicle from multiple potential starting points to the destination. At the same time, combined with the real-time road condition update provided by the intelligent transportation system, the path is optimized according to the shortest time principle and avoiding expected congested sections to obtain the optimal response path, including: Using the risk distribution map, determine the emergency high-incidence area as the destination, and identify all available emergency unit locations as potential departure points to generate a set of paths; Initializing the parameters of the ant colony optimization algorithm according to the path set, and setting an initial path matrix to guide path selection during the simulation process and generate an initial path configuration; Based on the initial path configuration, an ant colony optimization algorithm is applied to simulate the travel process from each potential starting point to the destination, each possible path is evaluated, and a preliminary optimized path list is generated; Using the real-time traffic update data provided by the intelligent transportation system, dynamically adjusting each path in the preliminary optimized path list to generate a dynamically adjusted path list; According to the dynamically adjusted path list, all factors are comprehensively considered, and a path that meets the optimal response conditions is selected as a reference for the actual rescue operation to generate the optimal response path.

6. The method according to claim 5, characterized in that Initializing the ant colony optimization algorithm parameters according to the path set and setting the initial path matrix to guide the path selection in the simulation process and generate the initial path configuration includes: Analyze all possible connections between the starting point and the destination using the path set to generate a connection relationship table; According to the connection relationship table, key parameters of the ant colony optimization algorithm are determined, and initial values ​​of these parameters are set to generate algorithm parameter configuration; Based on the algorithm parameter configuration, an initial path matrix including all nodes and their connections is constructed to guide path selection in subsequent simulation processes and generate an initial path matrix; Using the initial path matrix, combined with the algorithm parameter configuration, a preliminary path exploration simulation is performed to ensure that at least one feasible path between the paths is found, and an initial path configuration is generated.

7. The method according to claim 1, characterized in that The optimal response path is used to continuously receive on-site feedback by establishing a two-way communication mechanism, and the information is synchronized to all mobile terminals participating in the emergency operation to generate an efficient collaborative response network, including: Using the optimal response path, a safe and reliable two-way communication channel is established to generate a two-way communication mechanism; According to the two-way communication mechanism, a field feedback collection system is deployed to capture and transmit first-hand information from emergency personnel and generate a field feedback data stream; Based on the on-site feedback data stream, a synchronization update algorithm is developed to enable the latest situation to be instantly reflected on the mobile terminals of all relevant emergency personnel and generate an information synchronization plan; By utilizing the information synchronization solution, multiple resources are integrated to form an efficient collaborative response system and generate an efficient collaborative response network.

8. An emergency path planning system based on big data analysis, characterized in that: include: The collection module is used to collect dynamic and static information flows from multiple channels, identify and predict various complex situational factors, and obtain emergency resource allocation suggestions; An evaluation module is used to use the Bayesian network to perform risk probability modeling based on the emergency resource allocation suggestion, and combine the knowledge base technology of the expert system to perform a detailed evaluation of the emergency incidence rate in different geographical areas within a specific time period to generate a risk distribution map; An optimization module is used to introduce an ant colony optimization algorithm to simulate the path selection process of rescue vehicles from multiple potential starting points to the destination based on the risk distribution map, and at the same time, combined with the real-time road condition update provided by the intelligent transportation system, optimize the path based on the shortest time principle and avoid expected congested sections to obtain the optimal response path; The synchronization module is used to utilize the optimal response path, continuously receive on-site feedback by establishing a two-way communication mechanism, synchronize this information to all mobile terminals participating in the emergency operation, and generate an efficient collaborative response network.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an emergency path planning method based on big data analysis as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an emergency path planning method based on big data analysis as described in any one of claims 1 to 7 is implemented.

Images