An emergency resource scheduling and route planning method

Abstract

This invention relates to the field of emergency response technology, specifically to an emergency resource scheduling and path planning method, comprising the following steps: constructing a dynamic weight evaluation system based on emergency resource scheduling factors, wherein the weight evaluation system can dynamically calculate and adjust the factor weights to determine the most critical resources to be scheduled to the most needed locations in an emergency; constructing a deep reinforcement learning model, using historical emergency response data as a training set, enabling the agent to learn and optimize its strategy for selecting the optimal path under different conditions in simulated or historical emergency scenarios. Highly efficient emergency response: Through the combined application of the dynamic weight evaluation system and the deep reinforcement learning model, the system can quickly identify and prioritize the scheduling of the most critical resources to the most needed locations, while simultaneously planning the optimal path, significantly improving the speed and efficiency of emergency response.

Description

Technical Field

[0001] This invention relates to the field of emergency response technology, specifically to an emergency resource scheduling and route planning method. Background Technology

[0002] In the field of emergency response, rapid and accurate resource allocation and route planning are crucial for reducing disaster losses and protecting people's lives and property. Traditional emergency resource allocation and route planning methods often rely on manual decision-making or fixed algorithm models. These methods often struggle to achieve efficient, flexible, and precise allocation when faced with complex and ever-changing emergency scenarios.

[0003] First, the allocation of emergency resources is influenced by a variety of factors, including time urgency, urgency of resource demand, traffic congestion, weather conditions, disaster severity, the number of affected people, and road capacity. These factors are dynamic and change dynamically during emergency response, and the weights of different factors also adjust as the situation develops. Traditional fixed-weight evaluation systems struggle to accurately reflect these dynamic changes, thus limiting the optimization of resource allocation strategies.

[0004] Secondly, in terms of route planning, traditional algorithm models are often based on static road networks and fixed traffic conditions, making it difficult to cope with unexpected situations such as traffic congestion and road closures that may occur in actual emergency responses. This can lead to suboptimal planned routes, or even routes that may fail to reach the target location, thus affecting rescue efficiency.

[0005] Therefore, there is a need for an emergency resource scheduling and path planning method that can dynamically evaluate factor weights, intelligently plan optimal paths, effectively integrate multi-source heterogeneous data, provide real-time feedback on scheduling effects, and continuously optimize scheduling strategies, as well as the system required to implement this method. Summary of the Invention

[0006] This invention addresses the technical problems existing in the prior art by providing an emergency resource scheduling and path planning method. This method solves the problem that traditional emergency resource scheduling and path planning methods often fail to achieve efficient, flexible, and accurate scheduling when faced with complex and ever-changing emergency scenarios.

[0007] The technical solution of this invention to solve the above-mentioned technical problems is as follows: An emergency resource scheduling and path planning method, comprising the following steps:

[0008] A dynamic weight evaluation system is constructed based on emergency resource allocation factors. The weight evaluation system can dynamically calculate and adjust the factor weights to determine the most critical resources to be allocated to the most needed locations in emergency situations.

[0009] Construct a deep reinforcement learning model and use historical emergency response data as a training set to enable the agent to learn and optimize the strategy of selecting the optimal path under different conditions in simulated or historical emergency scenarios.

[0010] A data preprocessing module is constructed to integrate multi-source heterogeneous data, extract key information, and provide real-time and accurate input for dynamic weight evaluation and reinforcement learning models;

[0011] An adaptive scheduling algorithm is designed by combining the output results of a dynamic weight evaluation system and a reinforcement learning model. This algorithm is used to quickly adjust resource allocation strategies based on the current situation.

[0012] Based on the above technical solution, the present invention can be further improved as follows.

[0013] Furthermore, the emergency resource allocation factors include time urgency, resource demand urgency, traffic congestion, weather impact, disaster severity, number of affected people, and road capacity.

[0014] Furthermore, the dynamic weight evaluation system includes a weight adaptive adjustment mechanism, which is used to automatically adjust the weights of emergency resource scheduling factors according to the real-time changes of emergency events, so as to dynamically optimize resource scheduling strategies.

[0015] Furthermore, the construction of the dynamic weight evaluation system includes the following steps:

[0016] Define the set of key factors for emergency resource allocation;

[0017] Assign an initial weight to each key factor and obtain the latest data on the key factors in real time;

[0018] Based on real-time data, the weights of each factor are dynamically adjusted using specific algorithms;

[0019] Based on the adjusted weights and real-time data, a score is calculated for each scheduling scheme, and the scheme with the highest score is selected for execution.

[0020] Furthermore, the basic weights are calculated using the entropy weight method, including the following process:

[0021] For each factor, its real-time data is standardized to the [0,1] interval and denoted as X'. i (i = 1, 2, ..., 7);

[0022] For each factor, calculate its information entropy E. i The formula is:

[0023]

[0024] Where n is the number of scheduling schemes, p ij This represents the proportion of the standardized value of the i-th factor in the j-th scheme to the total sum of that factor.

[0025] Redundancy d i =1-E i , representing the information utility value of a factor;

[0026] Calculate the basic weight W' of each factor based on redundancy. i The formula is:

[0027]

[0028] Based on the actual situation of the emergency response, define the feedback indicator F;

[0029] Based on the comparison between the feedback indicator F and the preset target value, the weight adjustment coefficient α is calculated using the following formula:

[0030]

[0031] Among them, F min and F max These are the minimum and maximum values ​​of the feedback indicator, respectively.

[0032] Based on the weight adjustment factor α and the basic weight W' i Calculate the adjusted weight W” i The formula is

[0033] W” i =αW' i +(1-α)W i ;

[0034] Among them, W i These are the initial weights;

[0035] According to the adjusted weight W” i and real-time data X' i Calculate the score S for each scheduling scheme. i The formula is:

[0036]

[0037] The solution with the highest score is selected as the final scheduling decision;

[0038] T represents time urgency, indicating the time pressure required to respond as quickly as possible after an emergency occurs;

[0039] R represents the urgency of resource demand, indicating the degree of urgency of resource demand in the event of an emergency.

[0040] C represents traffic congestion, indicating potential traffic obstacles during emergency response;

[0041] W represents weather impact, indicating the potential impact of weather conditions on emergency response;

[0042] D represents the severity of the disaster, indicating the destructive power and scope of impact of the emergency event;

[0043] P represents the number of people directly affected by the emergency.

[0044] H represents road capacity, indicating the efficiency and reliability of road traffic during emergency response.

[0045] Furthermore, the deep reinforcement learning model uses historical emergency response data as a training set, enabling the agent to learn and optimize the selection of the optimal path under different conditions in simulated or historical emergency scenarios.

[0046] The deep reinforcement learning model selects the optimal path by including the following steps:

[0047] Identify the various states during the emergency response process, as well as all possible actions that can be taken;

[0048] Construct a reward function to evaluate the immediate reward of an agent after taking an action in a given state;

[0049] Construct a deep neural network as the policy network of the agent to predict the best action based on the current state;

[0050] In simulated or historical emergency scenarios, a pre-trained deep neural network is used for path planning;

[0051] The efficiency and effectiveness of the emergency response are calculated based on the path and resource allocation scheme selected by the agent.

[0052] Based on the simulation results, the deep neural network was fine-tuned to further optimize the path selection strategy;

[0053] In actual emergency response, the current state is input into a deep neural network to obtain the optimal path and resource allocation scheme;

[0054] Execute the selected path and resource allocation plan to carry out an emergency response.

[0055] Furthermore, the data preprocessing module also includes a data fusion and verification unit, which is used to integrate data from different sources.

[0056] Furthermore, the adaptive scheduling algorithm includes:

[0057] Based on the output of the dynamic weight evaluation system, initialize the resource scheduling strategy and determine the initial resource allocation and path planning;

[0058] Real-time monitoring of key data during the emergency response process, and dynamic updating of relevant parameters in the resource scheduling strategy based on real-time data;

[0059] An adaptive adjustment mechanism is adopted to dynamically adjust resource scheduling strategies based on real-time data and historical experience;

[0060] Define scheduling performance evaluation metrics, and calculate the performance score of the current scheduling strategy based on the evaluation metrics;

[0061] If the performance score of the current scheduling strategy is lower than the preset threshold, then strategy iteration and optimization will be performed;

[0062] Output the final optimized resource scheduling strategy, which includes resource allocation and path planning;

[0063] The formula for adjusting resource allocation is:

[0064] R alloc (t)=R base +ΔR(t);

[0065] Among them, R alloc (t) represents the amount of resources allocated at time t;

[0066] R base Indicates the amount of basic resources allocated;

[0067] ΔR(t) represents the incremental resource allocation adjusted based on real-time data;

[0068] The path planning adjustment formula is:

[0069]

[0070] Where, Path opt (t) represents the optimal path at time t;

[0071] PathSct represents the set of all possible paths;

[0072] Time(P,t) represents the rescue time required along path P at time t;

[0073] Cost(P) represents the cost of path P;

[0074] λ is the weighting coefficient.

[0075] Furthermore, it also includes an emergency response effectiveness evaluation and feedback mechanism, which is used to compare the actual scheduling results with the expected goals, to evaluate the effectiveness of resource scheduling and path planning, and to feed the evaluation results back to the dynamic weight evaluation system and reinforcement learning model.

[0076] Furthermore, the emergency response effectiveness evaluation and feedback mechanism also includes a user feedback interface, which allows emergency responders or decision-makers to provide direct feedback on the dispatch results.

[0077] Furthermore, it also includes a visualization report generation module, which is used to automatically generate visualization reports containing one or more key information such as scheduling strategy, resource allocation, path planning, response time, and rescue effect.

[0078] The beneficial effects of this invention are:

[0079] Highly efficient emergency response: Through the combined application of a dynamic weight evaluation system and a deep reinforcement learning model, the system can quickly identify and prioritize the dispatch of the most critical resources to the locations where they are most needed, while also planning the optimal path, which significantly improves the speed and efficiency of emergency response.

[0080] Flexibility and Targetedness: The dynamic weighting evaluation system can automatically adjust factor weights according to changes in the actual emergency situation, ensuring the flexibility and targetedness of resource allocation. This dynamism enables the system to cope with various complex and ever-changing emergency environments and achieve effective resource allocation.

[0081] Data-driven decision-making: The data preprocessing module integrates multi-source heterogeneous data and ensures data accuracy and consistency through data fusion and verification units, providing high-quality input for dynamic weight evaluation and reinforcement learning models. This makes the system's decisions more data-driven and more scientific and reliable.

[0082] Adaptive scheduling capability: Adaptive scheduling algorithms can dynamically adjust resource scheduling strategies based on real-time data and historical experience, ensuring that resources are scheduled to where they are most needed in the most efficient way. This adaptability enhances the system's robustness and adaptability, enabling it to flexibly respond to various unforeseen circumstances.

[0083] Continuous optimization and evolution: The emergency response effectiveness evaluation and feedback mechanism comprehensively assesses the effectiveness of resource scheduling and path planning by comparing actual scheduling results with expected goals. The evaluation results are then fed back to the dynamic weight evaluation system and reinforcement learning model to continuously optimize the scheduling strategy. This continuous feedback and optimization cycle drives the continuous evolution of the entire system, enhancing its ability to respond to various emergency situations. Attached Figure Description

[0084] Figure 1 This is a schematic diagram illustrating the principle of the emergency resource scheduling and route planning method of the present invention. Detailed Implementation

[0085] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0086] like Figure 1 As shown, an emergency resource scheduling and route planning method includes the following steps:

[0087] A dynamic weight evaluation system is constructed based on emergency resource allocation factors. The weight evaluation system can dynamically calculate and adjust the factor weights to determine the most critical resources to be allocated to the most needed locations in emergency situations.

[0088] Construct a deep reinforcement learning model and use historical emergency response data as a training set to enable the agent to learn and optimize the strategy of selecting the optimal path under different conditions in simulated or historical emergency scenarios.

[0089] A data preprocessing module is constructed to integrate multi-source heterogeneous data, extract key information, and provide real-time and accurate input for dynamic weight evaluation and reinforcement learning models;

[0090] An adaptive scheduling algorithm is designed by combining the output results of a dynamic weight evaluation system and a reinforcement learning model. This algorithm is used to quickly adjust resource allocation strategies based on the current situation.

[0091] This method integrates a dynamic weight evaluation system, a deep reinforcement learning model, a data preprocessing module, and an adaptive scheduling algorithm. Its core principles can be summarized as follows:

[0092] Dynamic Weighted Evaluation System: This method first establishes an evaluation system capable of dynamically calculating and adjusting factor weights. This system can identify and evaluate which resources are most critical at a specific time and place based on the specific needs of an emergency. This dynamism ensures the flexibility and targeting of resource allocation, enabling resources to be most effectively allocated to where they are most needed.

[0093] Deep Reinforcement Learning Model: Utilizing historical emergency response data as a training set, this method constructs a deep reinforcement learning model. This model allows the agent to learn and optimize its strategy for selecting the optimal path under different conditions by simulating or reviewing historical emergency scenarios. In this way, the model gradually acquires the ability to make optimal decisions in complex and ever-changing emergency environments.

[0094] Data Preprocessing Module: To support the effective operation of dynamic weight evaluation and reinforcement learning models, this method also includes a data preprocessing module. This module is responsible for integrating heterogeneous data from multiple different sources and extracting key information. This provides real-time, accurate input data for the two core components, ensuring they can make decisions based on the latest and most comprehensive information.

[0095] Adaptive Scheduling Algorithm: Finally, this method combines the output of a dynamic weight evaluation system and a reinforcement learning model to design an adaptive scheduling algorithm. This algorithm can quickly adjust resource allocation strategies according to the current situation, ensuring that resources are scheduled to where they are most needed in the most efficient way. This adaptability allows the method to flexibly respond to various emergencies, ensuring the timeliness and effectiveness of emergency response.

[0096] As one implementation method, the emergency resource allocation factors include time urgency, resource demand urgency, traffic congestion, weather impact, disaster severity, number of affected people, and road capacity.

[0097] As one implementation method, the dynamic weight evaluation system includes a weight adaptive adjustment mechanism, which is used to automatically adjust the weights of emergency resource scheduling factors according to the real-time changes of emergency events (specifically, the speed of disaster spread, newly affected areas, etc.) in order to dynamically optimize resource scheduling strategies.

[0098] Specifically, the construction of the dynamic weight evaluation system includes the following steps:

[0099] Define the set of key factors for emergency resource allocation (including time urgency (T), resource demand urgency (R), traffic congestion (C), weather impact (W), disaster severity (D), affected population (P), and road capacity (H)).

[0100] Assign an initial weight to each key factor and obtain the latest data on the key factors in real time;

[0101] Based on real-time data, the weights of each factor are dynamically adjusted using specific algorithms;

[0102] Based on the adjusted weights and real-time data, calculate the score for each scheduling scheme and select the scheme with the highest score for execution;

[0103] Furthermore, the basic weights are calculated using the entropy weight method, including the following process:

[0104] For each factor, its real-time data is standardized to the [0,1] interval and denoted as X'. i (i = 1, 2, ..., 7);

[0105] For each factor, calculate its information entropy E. i The formula is:

[0106]

[0107] Where n is the number of scheduling schemes, p ijThis represents the proportion of the standardized value of the i-th factor in the j-th scheme to the total sum of that factor.

[0108] Redundancy d i =1-E i , representing the information utility value of a factor;

[0109] Calculate the basic weight W' of each factor based on redundancy. i The formula is:

[0110]

[0111] Define feedback indicators F based on the actual situation of the emergency response; (such as rescue efficiency, the percentage reduction in the affected population, etc.);

[0112] Based on the comparison between the feedback indicator F and the preset target value, the weight adjustment coefficient α is calculated using the following formula:

[0113]

[0114] Among them, F min and F max These are the minimum and maximum values ​​of the feedback indicator, respectively.

[0115] Based on the weight adjustment factor α and the basic weight W' i Calculate the adjusted weight W” i The formula is

[0116] W” i =αW' i +(1-α)W i ;

[0117] Among them, W i These are the initial weights;

[0118] According to the adjusted weight W” i and real-time data X' i Calculate the score S for each scheduling scheme. i The formula is:

[0119]

[0120] The solution with the highest score is selected as the final scheduling decision;

[0121] T represents time urgency, indicating the time pressure required to respond as quickly as possible after an emergency occurs;

[0122] R represents the urgency of resource demand, indicating the degree of urgency of resource demand in the event of an emergency.

[0123] C represents traffic congestion, indicating potential traffic obstacles during emergency response;

[0124] W represents weather impact, indicating the potential impact of weather conditions on emergency response;

[0125] D represents the severity of the disaster, indicating the destructive power and scope of impact of the emergency event;

[0126] P represents the number of people directly affected by the emergency.

[0127] H represents road capacity, indicating the efficiency and reliability of road traffic during emergency response.

[0128] As one implementation method, the deep reinforcement learning model uses historical emergency response data as a training set, enabling the agent to learn and optimize the selection of the optimal path under different conditions in simulated or historical emergency scenarios.

[0129] Specifically, the deep reinforcement learning model selects the optimal path by including the following steps:

[0130] Identify the various states during the emergency response process and all possible actions that can be taken (i.e., select different paths or resource allocation plans).

[0131] Construct a reward function to evaluate the immediate reward of an agent after taking an action in a given state;

[0132] The reward function should consider factors such as the efficiency of emergency response (e.g., rescue time, resource utilization efficiency), the rationality of resource use (e.g., avoiding resource waste, ensuring resource sufficiency), and the degree of reduction in the affected population (e.g., the number of rescuers, the reduction in casualties).

[0133] Construct a deep neural network as the policy network of the agent to predict the best action based on the current state;

[0134] Using historical emergency response data as a training set, a neural network is trained using deep reinforcement learning algorithms (such as Actor-Critic, PPO, etc.) to learn and optimize strategies for selecting the optimal path under different conditions.

[0135] In simulated or historical emergency scenarios, a pre-trained deep neural network is used for path planning;

[0136] The efficiency and effectiveness of the emergency response are calculated based on the path and resource allocation scheme selected by the agent.

[0137] Based on the simulation results, the deep neural network was fine-tuned to further optimize the path selection strategy;

[0138] In actual emergency response, the current state is input into a deep neural network to obtain the optimal path and resource allocation scheme;

[0139] Execute the selected path and resource allocation plan to carry out an emergency response.

[0140] The following is an example:

[0141] To further describe in detail the actual operation process of a deep reinforcement learning model selecting the optimal path, the present invention also includes the following embodiments:

[0142] This embodiment uses a deep reinforcement learning model, combined with historical emergency response data, to optimize the strategy of selecting the optimal path under different conditions.

[0143] Specific implementation steps

[0144] State definition and feature extraction

[0145] During emergency response, the following state variables are defined:

[0146] Current location: The current coordinates of the emergency vehicle or resources.

[0147] Target location: The coordinates of the location where rescue or resource allocation is needed.

[0148] Time urgency (T): Remaining rescue time window, in hours.

[0149] Resource Requirement Urgency (R): The urgency of resource requirements at the target location, ranging from [0,1].

[0150] Traffic congestion status (C): The current level of road congestion, range: [0,1], where 0 indicates unobstructed traffic and 1 indicates severe congestion.

[0151] Weather Impact (W): The degree of impact of the current weather on the emergency response, range: [0,1], where 0 indicates no impact and 1 indicates severe impact.

[0152] Disaster Severity (D): The extent of damage caused by the disaster, ranging from [0,1].

[0153] Number of people affected (P): The number of people affected at the target location.

[0154] Road capacity (H): The current capacity of the road, in vehicles per hour.

[0155] For non-numerical data (such as weather impacts and disaster severity), one-hot encoding or normalization is used to convert them into numerical features.

[0156] Action space construction

[0157] The action space is defined as all possible paths and resource allocation schemes that an agent can take. Each action is represented by a path selection and a resource allocation, i.e.:

[0158] Path: The path taken by emergency vehicles or resources from their current location to the target location.

[0159] Resource: The quantity or type of resources allocated to the target location.

[0160] Reward function design

[0161] The reward function, taking into account the efficiency of emergency response, the rationality of resource use, and the degree of reduction in the affected population, is defined as follows:

[0162]

[0163] T Rescue Time: The time required for an agent to reach the target location and complete the rescue after taking action a from its current state s.

[0164] R usage: The amount of resources allocated by the agent in action a.

[0165] R_total_requirement: The total resource requirements for the target location.

[0166] P_rescue: The number of people successfully rescued by the agent in action a.

[0167] P affected: The total population affected by the target location.

[0168] α, β, γ: weight coefficients for time, resources, and population factors, respectively, and α, β, γ > 0.

[0169] Deep Neural Network Construction and Training

[0170] Construct a deep neural network as the policy network for the agent. The input layer receives state variables, and the output layer predicts the optimal action. Use historical emergency response data as the training set and train the neural network using deep reinforcement learning algorithms (such as Actor-Critic, PPO, etc.).

[0171] During training, the agent continuously tries different paths and resource allocation schemes in simulated or historical emergency scenarios, and evaluates their effectiveness based on the reward function. The weights of the neural network are adjusted using the backpropagation algorithm, enabling it to gradually learn strategies for selecting the optimal path under different conditions.

[0172] Simulation and Optimization

[0173] In simulated or historical emergency scenarios, a pre-trained deep neural network is used for path planning. Based on the path chosen by the agent and the resource allocation scheme, the efficiency and effectiveness of the emergency response are calculated, such as rescue time, resource utilization efficiency, and the number of people rescued.

[0174] Based on the simulation results, the deep neural network is fine-tuned to further optimize the path selection strategy. During fine-tuning, hyperparameters such as the neural network architecture, learning rate, and batch size can be adjusted to improve the model's generalization ability and accuracy.

[0175] Actual emergency response

[0176] In actual emergency response, the current state is input into a deep neural network to obtain the optimal path and resource allocation plan. The selected path and resource allocation plan are then executed to carry out the emergency response. Simultaneously, data from the emergency response process is collected in real time for subsequent model updates and optimizations.

[0177] As one implementation, the data preprocessing module further includes a data fusion and verification unit, which is used to integrate data from different sources (such as satellite images, social media feedback, sensor data, etc.) and ensure the accuracy and consistency of the data through data verification algorithms, providing high-quality input for dynamic weight evaluation and reinforcement learning models.

[0178] As a key component of the data preprocessing module, the data fusion and verification unit's core function is to integrate data resources from different sources, such as satellite imagery, social media feedback, and sensor data. These data sources each possess unique value and perspectives, but may also exhibit issues such as format differences, redundancy, or inconsistencies. Therefore, the data fusion and verification unit must first effectively integrate these data to ensure they form a unified and comprehensive dataset.

[0179] During data integration, the data fusion and verification unit employs a series of data verification algorithms. These algorithms aim to verify the accuracy and consistency of the data, eliminating erroneous or invalid information, thereby ensuring that the data provided to the dynamic weight evaluation and reinforcement learning models is of high quality and reliability. Through this process, the data preprocessing module can provide a solid foundation for subsequent decision support, improving the effectiveness and accuracy of emergency resource scheduling and route planning.

[0180] As one implementation method, the adaptive scheduling algorithm includes:

[0181] Based on the output of the dynamic weight evaluation system, initialize the resource scheduling strategy and determine the initial resource allocation and path planning;

[0182] Real-time monitoring of key data during the emergency response process, including time urgency, resource demand urgency, traffic congestion, weather impact, disaster severity, number of affected people, and road capacity, and dynamic updating of relevant parameters in resource scheduling strategies based on real-time data;

[0183] An adaptive adjustment mechanism is adopted to dynamically adjust resource scheduling strategies based on real-time data and historical experience;

[0184] Specific adjustment strategies include: prioritizing the allocation of resources closest to the target location when time urgency increases; increasing the amount of resources allocated to the target location when resource demand urgency increases; and selecting detour routes when traffic congestion worsens.

[0185] Define scheduling effectiveness evaluation indicators, such as rescue time, resource utilization efficiency, and number of people rescued; calculate the effectiveness score of the current scheduling strategy based on the evaluation indicators;

[0186] If the performance score of the current scheduling strategy is lower than the preset threshold, then strategy iteration and optimization will be performed;

[0187] A reinforcement learning algorithm is used to fine-tune the scheduling strategy based on historical data and real-time feedback to improve its adaptability and accuracy.

[0188] Output the final optimized resource scheduling strategy, which includes resource allocation and path planning;

[0189] The formula for adjusting resource allocation is:

[0190] R alloc (t)=R base +ΔR(t);

[0191] Among them, R alloc (t) represents the amount of resources allocated at time t;

[0192] R base Indicates the amount of basic resources allocated;

[0193] ΔR(t) represents the incremental resource allocation adjusted based on real-time data;

[0194] The path planning adjustment formula is:

[0195]

[0196] Where, Path opt (t) represents the optimal path at time t;

[0197] PathSct represents the set of all possible paths;

[0198] Time(P,t) represents the rescue time required along path P at time t;

[0199] Cost(P) represents the cost of path P;

[0200] λ is the weighting coefficient.

[0201] The present invention also includes the following embodiments:

[0202] This embodiment describes in detail the specific operation process of the adaptive scheduling algorithm.

[0203] Step a: Scheduling policy initialization

[0204] Based on the output of the dynamic weighted evaluation system, preliminary resource allocation and path planning are determined. For example, if time is of high urgency, resources closest to the target location are prioritized for scheduling; if resource demand is of high urgency, the amount of resources allocated to the target location is increased.

[0205] Step b: Real-time data monitoring and updating

[0206] Real-time monitoring of key data during the emergency response process, such as time urgency and resource demand urgency, and dynamic updates to relevant parameters in the resource scheduling strategy based on real-time data. For example, when time urgency increases, the resource scheduling strategy is adjusted promptly, prioritizing the scheduling of resources closer to the target location.

[0207] Step c: Strategy Adjustment and Optimization

[0208] An adaptive adjustment mechanism is adopted to dynamically adjust resource scheduling strategies based on real-time data and historical experience. For example, when traffic congestion worsens, detour routes are selected to shorten rescue time; when the urgency of resource demand increases, the amount of resources allocated to the target location is increased to ensure the effectiveness of rescue efforts.

[0209] Step d: Evaluation of scheduling effectiveness

[0210] Define evaluation metrics for scheduling effectiveness, such as rescue time, resource utilization efficiency, and number of people rescued, and calculate the effectiveness score of the current scheduling strategy based on these metrics. For example, if the rescue time is short and resource utilization efficiency is high, the current scheduling strategy will receive a higher effectiveness score.

[0211] Step e: Strategy iteration and optimization

[0212] If the performance score of the current scheduling strategy falls below a preset threshold, strategy iteration and optimization are performed. A reinforcement learning algorithm is used to fine-tune the scheduling strategy based on historical data and real-time feedback to improve its adaptability and accuracy. For example, the resource allocation and path planning strategies are optimized by adjusting the parameters in the resource allocation and path planning adjustment formulas.

[0213] Step f: Scheduling decision output

[0214] The final optimized resource scheduling strategy, including resource allocation and path planning, is output. This optimized strategy is then sent to emergency responders or decision-makers to enable rapid response and optimization of resource scheduling and path planning. Simultaneously, data from the emergency response process is collected in real time for subsequent model updates and optimizations.

[0215] As one implementation method, it also includes an emergency response effect evaluation and feedback mechanism. The emergency response effect evaluation and feedback mechanism is used to compare the actual scheduling results with the expected goals, to evaluate the effectiveness of resource scheduling and path planning, and to feed the evaluation results back to the dynamic weight evaluation system and reinforcement learning model to continuously optimize the scheduling strategy.

[0216] This mechanism aims to comprehensively evaluate the effectiveness of resource scheduling and path planning by comparing actual scheduling results with expected goals. This evaluation process not only focuses on whether the scheduling results achieved the expected emergency response effect, but also delves into the performance of the scheduling strategy in actual execution.

[0217] After the evaluation is completed, the mechanism provides detailed feedback to the dynamic weight evaluation system and the reinforcement learning model. For the dynamic weight evaluation system, the feedback helps it adjust the weights of each factor based on the actual scheduling results, ensuring that the most critical resources can be more accurately identified and prioritized in subsequent scheduling. For the reinforcement learning model, the feedback serves as an important basis for its learning and optimization, helping it learn from actual scheduling experience and continuously revise and improve its strategy for selecting the optimal path under different conditions.

[0218] Through this continuous feedback and optimization cycle, the emergency response effectiveness evaluation and feedback mechanism can drive the continuous evolution of the entire resource scheduling and route planning system, improve its ability to cope with various emergencies, and ensure that resources can be efficiently and accurately dispatched to the places where they are most needed in the shortest possible time.

[0219] As a supplement, the emergency response effectiveness evaluation and feedback mechanism also includes a user feedback interface, which allows emergency responders or decision-makers to provide direct feedback on the dispatch results in order to further refine the optimization direction of the dispatch strategy.

[0220] As one implementation, a visualization report generation module is also included, which is used to automatically generate a visualization report containing one or more key information such as scheduling strategy, resource allocation, path planning, response time, and rescue effect.

[0221] The present invention also relates to an emergency resource scheduling and route planning system, which includes the aforementioned emergency resource scheduling and route planning method, as well as computing devices, data storage devices and communication interfaces required to implement the method, for rapid response and optimization of resource scheduling and route planning in emergency situations.

[0222] This system is a comprehensive solution designed to address emergencies and ensure that resources can be rapidly and effectively deployed to where they are needed. At its core is its integrated emergency resource scheduling and routing method, which is meticulously designed to quickly analyze, evaluate, and formulate optimal resource scheduling and routing strategies in emergency situations.

[0223] To implement this approach, the system is equipped with the necessary hardware and software resources. The computing devices are responsible for performing complex computational tasks, such as dynamic weight evaluation, training and inference of deep reinforcement learning models, ensuring the method's efficient operation. The data storage devices are used to store large amounts of historical emergency response data, real-time data, and intermediate and result data generated during the method's operation, providing data support for continuous optimization and decision-making.

[0224] Furthermore, the communication interface is a crucial component of the system, responsible for communicating with other systems, devices, or personnel to ensure real-time information transmission and sharing. In emergencies, the communication interface can rapidly receive and process requests and information from various parties, providing timely and accurate data support for resource scheduling and route planning.

[0225] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An emergency resource scheduling and path planning method, characterized in that, The method comprises the following steps: A dynamic weight evaluation system is constructed based on emergency resource scheduling factors, which can dynamically calculate and adjust factor weights to determine the most critical resources to be dispatched to the most needed locations in an emergency situation; A deep reinforcement learning model is constructed, and historical emergency response data is used as a training set to enable the agent to learn and optimize the strategy for selecting the optimal path under different conditions in simulated or historical emergency scenarios; A data preprocessing module is constructed to integrate multi-source heterogeneous data, extract key information, and provide real-time and accurate inputs for the dynamic weight evaluation and reinforcement learning model; An adaptive scheduling algorithm is designed based on the output results of the dynamic weight evaluation system and the reinforcement learning model, which is used to quickly adjust the resource allocation strategy according to the current situation; The adaptive scheduling algorithm comprises: According to the output results of the dynamic weight evaluation system, the resource scheduling strategy is initialized to determine the preliminary resource allocation and path planning; Real-time monitoring of key data during the emergency response process, dynamic updating of related parameters in the resource scheduling strategy based on real-time data; Adaptive adjustment mechanism is adopted to dynamically adjust the resource scheduling strategy based on real-time data and historical experience; Define the scheduling effect evaluation index, and calculate the effect score of the current scheduling strategy according to the evaluation index; If the effect score of the current scheduling strategy is lower than the preset threshold, the strategy iteration and optimization are performed; Output the final optimized resource scheduling strategy, which includes resource allocation and path planning; The resource allocation adjustment formula is: R alloc (t) = R base + ΔR(t); wherein R alloc (t) denotes the resource allocation at time t; R base represents the basic resource allocation amount; ΔR(t) represents the resource allocation increment adjusted according to real-time data; The path planning adjustment formula is: wherein, Path opt (t) denotes the optimal path at time t; PathSct represents the set of all possible paths; Time(P,t) represents the rescue time required along path P at time t; Cost(P) represents the cost of path P; λ is the weight coefficient.

2. The emergency resource scheduling and path planning method according to claim 1, wherein The emergency resource scheduling factors include time urgency, resource demand urgency, traffic congestion, weather influence, disaster severity, affected population, and road capacity.

3. The emergency resource scheduling and path planning method according to claim 2, wherein The dynamic weight evaluation system includes a weight adaptive adjustment mechanism for automatically adjusting the weights of emergency resource scheduling factors based on real-time changes of emergency events to dynamically optimize the resource scheduling strategy.

4. The emergency resource scheduling and path planning method according to claim 3, wherein The dynamic weight evaluation system construction comprises the following steps: Define a set of key factors for emergency resource scheduling; Set an initial weight for each key factor and obtain the latest data of the key factors in real time; Based on real-time data, dynamically adjust the weights of each factor using a specific algorithm; According to the adjusted weights and real-time data, calculate the score of each scheduling scheme, and select the scheme with the highest score for execution.

5. The emergency resource scheduling and path planning method according to claim 4, wherein The entropy weight method is used to calculate the basic weight, including the following processes: For each factor, its real-time data is standardized to the interval [0, 1], denoted as X ' i (i = 1, 2,..., 7); For each factor, its information entropy E is calculated i , the formula is: wherein n is the number of scheduling schemes, p ij is the proportion of the standardized value of the i-th factor in the j-th scheme to the total sum of the factor. Redundancy d i = 1 - E i , represents the information utility value of the factor; The basic weight W' of each factor is calculated according to the redundancy i The formula is: According to the actual situation of emergency response, define the feedback index F; According to the comparison of feedback index F and preset target value, calculate the weight adjustment coefficient α, the formula is: where F min and F max are the minimum and maximum values of the feedback metric, respectively. According to the weight adjustment coefficient a and the basic weight W i , the adjusted weight W i , the formula is W i = aW i + (1 - a)W i ; wherein W i is the initial weight; According to the adjusted weight W i and real-time data X i , the score S i of each scheduling scheme is calculated, and the formula is: Select the scheme with the highest score as the final scheduling decision; T is the time urgency, representing the time pressure that needs to be responded as soon as possible after the emergency event occurs; R is the resource demand urgency, representing the emergency degree of resource demand of the emergency event; C is the traffic congestion condition, representing the traffic obstacles that may be encountered in the emergency response process; W is the weather influence, representing the potential influence of weather conditions on emergency response; D is the disaster severity, representing the destructive power and influence range of the emergency event; P is the number of affected population, representing the number of population directly affected by the emergency event; H is the road traffic capacity, representing the traffic efficiency and reliability of the road in the emergency response process.

6. The emergency resource scheduling and path planning method according to claim 1, characterized in that, The deep reinforcement learning model uses historical emergency response data as the training set, so that the agent learns and optimizes the selection of the optimal path under different conditions in the simulation or historical emergency scene; The deep reinforcement learning model selecting the optimal path includes the following steps: Determine various states in the emergency response process and all possible actions that can be taken; Construct a reward function to evaluate the immediate reward of the agent after taking actions in a given state; Construct a deep neural network as the agent's policy network to predict the best action based on the current state; In the simulation or historical emergency scene, use the trained deep neural network for path planning; According to the path and resource allocation scheme selected by the agent, calculate the efficiency and effect of emergency response; According to the simulation results, fine-tune the deep neural network to further optimize the path selection strategy; In actual emergency response, input the deep neural network according to the current state to obtain the optimal path and resource allocation scheme; Execute the selected path and resource allocation scheme to respond to the emergency.

7. The method of claim 1, wherein, The data preprocessing module also includes a data fusion and verification unit for integrating data from different sources.

8. The method of claim 1, wherein, It also includes an emergency response effect evaluation and feedback mechanism for comparing actual scheduling results with expected targets, evaluating the effectiveness of resource scheduling and path planning, and feeding back the evaluation results to the dynamic weight evaluation system and reinforcement learning model.

9. The method of claim 8, wherein, The emergency response effect evaluation and feedback mechanism also includes a user feedback interface that allows emergency response personnel or decision-makers to provide direct feedback on the scheduling results.

10. The method of claim 1, wherein, It also includes a visual report generation module for automatically generating visual reports containing one or more key information such as scheduling strategy, resource allocation, path planning, response time, and rescue effect.

Images