Resource allocation system based on disaster influence range and first-aid repair personnel position

Abstract

The invention discloses a resource allocation system based on a disaster influence range and a first-aid repair personnel position, which comprises a personnel positioning module, an equipment information management module, a real-time disaster data integration module, a central data processing module and an intelligent allocation module, the data of the personnel positioning module, the equipment information management module and the real-time disaster data integration module are uploaded to the central data processing module, the resource allocation system closely pays attention to the emergency repair condition of a disaster-affected area, the central data processing module fuses personnel, equipment and disaster data to generate a unified view, the field awareness is enhanced, and the resource allocation efficiency is improved. And the intelligent allocation module establishes a resource allocation model, outputs a resource allocation scheme, clarifies equipment and personnel to be allocated in each time period, and ensures timely response to faults and demands, and the resource allocation system not only can improve the rescue efficiency, but also can effectively reduce the rescue cost and reduce life and property loss.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster emergency response, and in particular to a resource allocation system based on the disaster impact range and the positions of emergency repair personnel. Background Art

[0002] Against the backdrop of global climate change and accelerated urbanization, the frequency and severity of natural disasters are increasing, posing a huge challenge to emergency management. At present, when a natural disaster occurs, the fault is mainly judged by the data of the monitoring devices installed on the distribution network equipment, and the emergency management department makes corresponding decisions based on the actual situation on site. The allocation of relevant emergency resources mainly relies on the description of the disaster situation on site and the previous historical data. There are certain limitations. When the disaster-stricken area is large and resources are unevenly distributed, it is impossible to achieve maximum efficiency in resource allocation. At the same time, the rescue efficiency cannot be guaranteed, resulting in loss of life and property in the disaster area.

[0003] With the development of big data technology and intelligent algorithms, intelligent algorithms have great advantages in data calculation, analysis, decision-making, etc., which can improve efficiency and make optimal decisions. In the distribution network demonstration area, the integration of intelligent algorithms and personnel positioning technology has played an important role in improving operational efficiency, response time and resource management, especially in emergency situations such as natural disasters. It can make the best adjustments according to the actual situation and minimize the impact of the disaster. Summary of the invention

[0004] In order to overcome the above problems, the purpose of the present invention is to provide a resource allocation system based on the disaster impact range and the location of the repair personnel. The resource allocation system closely monitors the repair situation in the disaster-stricken area through three parts: personnel positioning module, equipment information management module, and real-time disaster data integration module. The central data processing module integrates personnel, equipment and disaster data to generate a unified view, enhances on-site awareness, and uses time analysis methods for analysis. The intelligent allocation module establishes a resource allocation model, outputs a resource allocation plan, and clarifies the equipment and personnel to be allocated in each time period to ensure timely response to faults and needs. The resource allocation system can not only improve rescue efficiency, but also effectively reduce rescue costs, reduce loss of life and property, and provide a practical solution for emergency management.

[0005] The technical solution adopted by the present invention is:

[0006] The resource allocation system based on the disaster impact range and the location of the repair personnel includes a personnel positioning module, an equipment information management module, a real-time disaster data integration module, a central data processing module, and an intelligent allocation module.

[0007] The data of the personnel positioning module, equipment information management module, and real-time disaster data integration module are uploaded to the central data processing module, which processes the data and transmits it to the intelligent deployment module, which generates an emergency repair plan.

[0008] The personnel positioning module tracks the location of the repair personnel in real time through GPS or RFID technology.

[0009] The equipment information management module includes a database management unit, a real-time monitoring unit, and an alarm unit.

[0010] The real-time disaster data integration module aggregates information from weather stations and government databases, uses machine learning algorithms to analyze input data, and calculates disaster-affected areas and areas that require immediate attention.

[0011] The central data processing module integrates personnel, equipment and disaster data into a unified view, enhances on-site awareness, and uses time analysis methods to analyze.

[0012] The intelligent allocation module establishes a resource allocation model, outputs a resource allocation plan, clarifies the equipment and personnel to be allocated in each time period, and ensures timely response to faults and needs.

[0013] As a further description of the present invention, the database management unit of the device information management module establishes a centralized database, including data records of maintaining device type, status, and location,

[0014] The real-time monitoring unit installs sensors and IoT devices on the maintenance equipment to perform continuous monitoring and data transmission.

[0015] The alarm unit automatically issues an alarm of equipment failure or maintenance requirement based on the operation data.

[0016] As a further description of the present invention, the specific steps of fusing the data in the central data processing module into a unified view are as follows:

[0017] Fusion S1: Data abstraction and normalization, cleaning and formatting the data of the personnel positioning module, equipment information management module, and real-time disaster data integration module to ensure data consistency.

[0018] Fusion S2: Data model selection: Use graph database or relational database to store the integrated data.

[0019] Fusion S3: Data connection and integration: Create primary key and foreign key relationships in the data model to connect data from different sources through association relationships, which is implemented through nodes and edges in graph databases and foreign keys in relational databases.

[0020] Fusion S4: Establish a unified query interface: Use API or SQL interface to achieve unified access to integrated data;

[0021] The steps of the time analysis are as follows:

[0022] Analysis S1: Establish a time series database and use it to store data with timestamps. Each data point contains a timestamp field to record the changes of events in chronological order.

[0023] Analysis S2: Data collection and segmentation, storing historical data in time segments,

[0024] Analysis S3: Trend analysis and modeling, using machine learning algorithms to perform trend analysis and predictive modeling, reading historical data from the time series database, and training corresponding prediction models to predict the changing trends of personnel, equipment, or disaster events in the future.

[0025] Analysis S4: Real-time data update, update data in the time series database in real time to ensure that the model's predictions are based on the latest situation.

[0026] As a further description of the present invention, the steps for establishing the resource allocation model of the intelligent allocation module are as follows:

[0027] Step 1: Determine the objective function, which includes minimizing the repair time minT, maximizing the resource utilization maxU, and minimizing the total safety risk minS.

[0028] Step 2: Algorithm selection: select genetic algorithm, search for the optimal solution through selection, crossover and mutation operations, select particle swarm optimization algorithm, dynamically adjust resource allocation through swarm intelligence simulation, and quickly adapt to on-site changes.

[0029] As a further description of the present invention, the construction process of the objective function is:

[0030] The minimized repair time minT is:

[0031] Assume t i is the estimated completion time of the i-th task, and the total repair time can be expressed as:

[0032]

[0033] Where n is the total number of tasks;

[0034] The maximum resource utilization masU is:

[0035] Suppose there are m kinds of resources, let u j is the utilization rate of the jth resource, measured by the average resource utilization rate:

[0036]

[0037] The utilization rate of the resource u j It is expressed as the ratio of resource usage time to total available time;

[0038] The minimized security risk sum minS is:

[0039] Assume i The goal of ensuring personnel safety is achieved by minimizing the sum of safety risks for the i safety risk factor of the task being performed:

[0040]

[0041] As a further description of the present invention, the constraints of the objective function include the number of available personnel, equipment status, task priority, and geographical location restrictions:

[0042] The number of available personnel, let x i The number of people assigned to task i satisfies:

[0043] x i ≤X max

[0044] Where X max is the maximum number of available personnel.

[0045] The device state, let e i represents the status of the i-th device, where 1 means available and 0 means unavailable. The allocation of each task should satisfy:

[0046] e i =1

[0047] The task priority, let p i is the priority coefficient of task i, and introduces task priority constraints to prioritize high-priority tasks to meet the following requirements:

[0048] p i x i ≥θ

[0049] Where θ is the minimum priority requirement of task i;

[0050] The geographical location restriction is that the task needs to be performed within a certain geographical location range, which is expressed by setting a distance constraint. Let d ij is the distance from task i to resource location j, satisfying:

[0051] d ij ≤D max

[0052] Where D max is the maximum allowed distance.

[0053] As a further description of the present invention, the genetic algorithm in the algorithm selection adds three parts: adaptive parameter adjustment, priority-based selection strategy, and multi-stage evolution on the basis of the traditional one.

[0054] The adaptive parameter adjustment adaptively adjusts the parameters according to the resource demand and task urgency during the resource allocation process, increases the mutation probability and expands the search range when the resource demand changes greatly, and reduces the mutation probability and improves the stability of the solution when the demand is stable;

[0055] The priority-based selection strategy designs a priority-weighted selection method in the selection stage, takes the task priority as the weight, guides the algorithm to allocate resources to high-priority tasks, and ensures that high-priority tasks are allocated first;

[0056] The multi-stage evolution divides the algorithm into different stages, encourages large solution space exploration in the early exploration stage to ensure global search, and accelerates the convergence speed in the later stage to find the optimal solution within a limited time, effectively improving the efficiency of the algorithm.

[0057] As a further description of the present invention, the particle swarm optimization algorithm in the algorithm selection adds three parts: multi-group dynamic scheduling, target guidance factor, and adaptive neighborhood update.

[0058] The multi-group dynamic scheduling divides the particle group into multiple sub-groups, each of which focuses on a specific objective function and regularly exchanges information to achieve multi-objective collaborative optimization;

[0059] The target guidance factor adds a target guidance factor to the particle position update to guide the particles to concentrate on the task area with higher priority, dynamically adjust the position of the particles, and make the algorithm quickly converge to the solution with the highest task demand;

[0060] The adaptive neighborhood update dynamically adjusts the neighborhood structure of particles when the task and resource conditions change dynamically. Particles that are closer to the task resource position can form a close neighborhood, ensuring that resources are preferentially allocated to the most urgent tasks.

[0061] Beneficial effects of the present invention:

[0062] The resource allocation system of the present invention is based on the disaster impact range and the location of the emergency repair personnel, including a personnel positioning module, an equipment information management module, a real-time disaster data integration module, a central data processing module, and an intelligent allocation module. The resource allocation system closely monitors the emergency repair situation in the disaster-stricken area through the personnel positioning module, the equipment information management module, and the real-time disaster data integration module. The central data processing module integrates personnel, equipment and disaster data to generate a unified view, enhances on-site awareness, and adopts a time analysis method for analysis. The intelligent allocation module establishes a resource allocation model, outputs a resource allocation plan, clarifies the equipment and personnel to be allocated in each time period, and ensures timely response to faults and needs. The resource allocation system can not only improve rescue efficiency, but also effectively reduce rescue costs, reduce loss of life and property, and provide a practical solution for emergency management. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a structural diagram of the resource allocation system proposed by the present invention based on the disaster impact range and the location of the repair personnel;

[0064] Figure 2 This is a flow chart of the data integration of the resource allocation system based on the disaster impact range and the location of the repair personnel proposed by the present invention;

[0065] Figure 3 This is a time analysis flow chart of the resource allocation system based on the disaster impact range and the location of the repair personnel proposed by the present invention. DETAILED DESCRIPTION

[0066] The specific implementation of the present invention is described below in conjunction with the accompanying drawings and embodiments:

[0067] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which the present invention can be implemented. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0068] At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" cited in this specification are only for the convenience of description and are not used to limit the scope of implementation of the present invention. Changes or adjustments to their relative relationships should be regarded as the scope of implementation of the present invention without substantially changing the technical content.

[0069] like Figure 1-3 As shown, it shows a specific embodiment of the present invention:

[0070] Embodiment 1

[0071] The resource allocation system based on the disaster impact range and the location of the repair personnel includes a personnel positioning module, an equipment information management module, a real-time disaster data integration module, a central data processing module, and an intelligent allocation module.

[0072] The data of the personnel positioning module, equipment information management module, and real-time disaster data integration module are uploaded to the central data processing module, which processes the data and transmits it to the intelligent deployment module, which generates an emergency repair plan.

[0073] The personnel positioning module tracks the location of the repair personnel in real time through GPS or RFID technology.

[0074] The equipment information management module includes a database management unit, a real-time monitoring unit, and an alarm unit.

[0075] The real-time disaster data integration module aggregates information from weather stations and government databases, uses machine learning algorithms to analyze input data, and calculates disaster-affected areas and areas that require immediate attention.

[0076] The central data processing module integrates personnel, equipment and disaster data into a unified view, enhances on-site awareness, and uses time analysis methods to analyze.

[0077] The intelligent allocation module establishes a resource allocation model, outputs a resource allocation plan, clarifies the equipment and personnel to be allocated in each time period, and ensures timely response to faults and needs.

[0078] As a further description of the present invention, the database management unit of the device information management module establishes a centralized database, including data records of maintaining device type, status, and location,

[0079] The real-time monitoring unit installs sensors and IoT devices on the maintenance equipment to perform continuous monitoring and data transmission.

[0080] The alarm unit automatically issues an alarm of equipment failure or maintenance requirement based on the operation data.

[0081] In this embodiment, if Figure 1As shown, the resource allocation system closely monitors the emergency repair situation in the disaster-stricken area through three parts: personnel positioning module, equipment information management module, and real-time disaster data integration module. The central data processing module integrates personnel, equipment and disaster data to generate a unified view, enhances on-site awareness, and uses time analysis method for analysis. The intelligent allocation module establishes a resource allocation model, outputs a resource allocation plan, and clarifies the equipment and personnel to be allocated in each time period to ensure timely response to faults and needs. The resource allocation system can not only improve rescue efficiency, but also effectively reduce rescue costs, reduce loss of life and property, and provide a practical solution for emergency management.

[0082] As a further description of the present invention, the specific steps of fusing the data in the central data processing module into a unified view are as follows:

[0083] Fusion S1: Data abstraction and normalization, cleaning and formatting the data of the personnel positioning module, equipment information management module, and real-time disaster data integration module to ensure data consistency.

[0084] Fusion S2: Data model selection: Use graph database or relational database to store the integrated data.

[0085] Fusion S3: Data connection and integration: Create primary key and foreign key relationships in the data model to connect data from different sources through association relationships, which is implemented through nodes and edges in graph databases and foreign keys in relational databases.

[0086] Fusion S4: Establish a unified query interface: Use API or SQL interface to achieve unified access to integrated data;

[0087] In this embodiment, Figure 2 As shown, the purpose of the central data processing module to fuse the data into a unified view is to display all information on one picture to improve on-site awareness.

[0088] The purpose of data abstraction and normalization in the fusion S1 step is to ensure data consistency. Data from different sources may have different formats or units and need to be converted into a unified structure.

[0089] In the fusion S2 step, the data model is selected to use a graph database, such as Neo4j, or a relational database, such as MySQL, to store the integrated data. The graph database is particularly suitable for contextual data with complex relationships. Nodes can be used to represent entities such as personnel, equipment, and disasters, and edges can be used to represent the relationships between them, thereby forming a coherent network view.

[0090] Integrate the data connection and integration in the S3 step, create primary key and foreign key relationships in the data model, connect data from different sources through association relationships, and in practical applications, associate a disaster event with the data of related personnel and equipment so that all information related to the event can be directly obtained during query.

[0091] In step S4, a unified query interface is established, and unified access to the integrated data is achieved using an API or SQL interface. Users can obtain all contextual information of a disaster event, including relevant personnel and equipment data, through a single query statement.

[0092] The steps of the time analysis are as follows:

[0093] Analysis S1: Establish a time series database and use it to store data with timestamps. Each data point contains a timestamp field to record the changes of events in chronological order.

[0094] Analysis S2: Data collection and segmentation, storing historical data in time segments,

[0095] Analysis S3: Trend analysis and modeling, using machine learning algorithms to perform trend analysis and predictive modeling, reading historical data from the time series database, and training corresponding prediction models to predict the changing trends of personnel, equipment, or disaster events in the future.

[0096] Analysis S4: Real-time data update, update data in the time series database in real time to ensure that the model's predictions are based on the latest situation.

[0097] In this embodiment, Figure 3 As shown, the time analysis is used to track changes in data over time, facilitating trend analysis and predictive modeling.

[0098] As a further description of the present invention, the steps for establishing the resource allocation model of the intelligent allocation module are as follows:

[0099] Step 1: Determine the objective function, which includes minimizing the repair time minT, maximizing the resource utilization maxU, and minimizing the total safety risk minS.

[0100] Step 2: Algorithm selection: select genetic algorithm, search for the optimal solution through selection, crossover and mutation operations, select particle swarm optimization algorithm, dynamically adjust resource allocation through swarm intelligence simulation, and quickly adapt to on-site changes.

[0101] In this embodiment, the disaster handling requires the corresponding optimization model calculation implementation, the corresponding objective function is selected and the corresponding algorithm is selected based on the objective function to achieve the optimal resource allocation plan and improve the repair efficiency.

[0102] As a further description of the present invention, the construction process of the objective function is:

[0103] The minimized repair time minT is:

[0104] Assume t i is the estimated completion time of the i-th task, and the total repair time can be expressed as:

[0105]

[0106] Where n is the total number of tasks;

[0107] The maximum resource utilization maxU is:

[0108] Suppose there are m kinds of resources, let u j is the utilization rate of the jth resource, measured by the average resource utilization rate:

[0109]

[0110] The utilization rate of the resource u j It is expressed as the ratio of resource usage time to total available time;

[0111] The minimized security risk sum minS is:

[0112] Assume i The goal of ensuring personnel safety is achieved by minimizing the sum of safety risks for the i safety risk factor of the task being performed:

[0113]

[0114] As a further description of the present invention, the constraints of the objective function include the number of available personnel, equipment status, task priority, and geographical location restrictions:

[0115] The number of available personnel, let x i The number of people assigned to task i satisfies:

[0116] x i ≤X max

[0117] Where X max is the maximum number of available personnel.

[0118] The device state, let e i represents the status of the i-th device, where 1 means available and 0 means unavailable. The allocation of each task should satisfy:

[0119] e i =1

[0120] The task priority, let p i is the priority coefficient of task i, and introduces task priority constraints to prioritize high-priority tasks to meet the following requirements:

[0121] p i x i ≥θ

[0122] Where θ is the minimum priority requirement of task i;

[0123] The geographical location restriction is that the task needs to be performed within a certain geographical location range, which is expressed by setting a distance constraint. Let d ij is the distance from task i to resource location j, satisfying:

[0124] d ij ≤D max

[0125] Where D max is the maximum allowed distance.

[0126] In this embodiment, a corresponding objective function is constructed according to the resource allocation parameters that affect disaster rescue, and constraint conditions are correspondingly considered in the process of resource allocation to ensure reasonable and effective allocation of resources.

[0127] Embodiment 2

[0128] On the basis of the above-mentioned first embodiment, a genetic algorithm is selected to solve the resource allocation model to achieve maximum utilization of resources.

[0129] As a further description of the present invention, the genetic algorithm in the algorithm selection adds three parts: adaptive parameter adjustment, priority-based selection strategy, and multi-stage evolution on the basis of the traditional one.

[0130] The adaptive parameter adjustment adaptively adjusts the parameters according to the resource demand and task urgency during the resource allocation process, increases the mutation probability and expands the search range when the resource demand changes greatly, and reduces the mutation probability and improves the stability of the solution when the demand is stable;

[0131] The priority-based selection strategy designs a priority-weighted selection method in the selection stage, takes the task priority as the weight, guides the algorithm to allocate resources to high-priority tasks, and ensures that high-priority tasks are allocated first;

[0132] The multi-stage evolution divides the algorithm into different stages, encourages large solution space exploration in the early exploration stage to ensure global search, and accelerates the convergence speed in the later stage to find the optimal solution within a limited time, effectively improving the efficiency of the algorithm.

[0133] Embodiment 3

[0134] On the basis of the above-mentioned embodiment 1, a particle swarm optimization algorithm is selected to solve the resource allocation model to achieve maximum utilization of resources.

[0135] As a further description of the present invention, the particle swarm optimization algorithm in the algorithm selection adds three parts: multi-group dynamic scheduling, target guidance factor, and adaptive neighborhood update.

[0136] The multi-group dynamic scheduling divides the particle group into multiple sub-groups, each of which focuses on a specific objective function and regularly exchanges information to achieve multi-objective collaborative optimization;

[0137] The target guidance factor adds a target guidance factor to the particle position update to guide the particles to concentrate on the task area with higher priority, dynamically adjust the position of the particles, and make the algorithm quickly converge to the solution with the highest task demand;

[0138] The adaptive neighborhood update dynamically adjusts the neighborhood structure of particles when the task and resource conditions change dynamically. Particles that are closer to the task resource position can form a close neighborhood, ensuring that resources are preferentially allocated to the most urgent tasks.

[0139] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention.

[0140] Many other changes and modifications may be made without departing from the concept and scope of the present invention.It should be understood that the present invention is not limited to the specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. A resource allocation system based on the disaster impact area and the location of emergency repair personnel, characterized by: It includes personnel positioning module, equipment information management module, real-time disaster data integration module, central data processing module, and intelligent deployment module. The data of the personnel positioning module, equipment information management module, and real-time disaster data integration module are uploaded to the central data processing module, which processes the data and transmits it to the intelligent deployment module, which generates an emergency repair plan. The personnel positioning module tracks the location of the repair personnel in real time through GPS or RFID technology. The equipment information management module includes a database management unit, a real-time monitoring unit, and an alarm unit. The real-time disaster data integration module aggregates information from weather stations and government databases, uses machine learning algorithms to analyze input data, and calculates disaster-affected areas and areas that require immediate attention. The central data processing module integrates personnel, equipment and disaster data into a unified view, enhances on-site awareness, and uses time analysis methods to analyze. The intelligent allocation module establishes a resource allocation model, outputs a resource allocation plan, clarifies the equipment and personnel to be allocated in each time period, and ensures timely response to faults and needs.

2. The resource allocation system based on the disaster impact range and the location of the repair personnel according to claim 1 is characterized in that: The database management unit of the device information management module establishes a centralized database, which contains data records of device type, status, and location. The real-time monitoring unit installs sensors and IoT devices on the maintenance equipment to perform continuous monitoring and data transmission. The alarm unit automatically issues an alarm of equipment failure or maintenance requirement based on the operation data.

3. The resource allocation system based on the disaster impact range and the location of the repair personnel according to claim 1 is characterized in that: The specific steps of fusing the data in the central data processing module into a unified view are as follows: Fusion S1: Data abstraction and normalization, cleaning and formatting the data of the personnel positioning module, equipment information management module, and real-time disaster data integration module to ensure data consistency. Fusion S2: Data model selection: Use graph database or relational database to store the integrated data. Fusion S3: Data connection and integration: Create primary key and foreign key relationships in the data model to connect data from different sources through association relationships, which is implemented through nodes and edges in graph databases and foreign keys in relational databases. Fusion S4: Establish a unified query interface: Use API or SQL interface to achieve unified access to integrated data; The steps of the time analysis are as follows: Analysis S1: Establish a time series database and use it to store data with timestamps. Each data point contains a timestamp field to record the changes of events in chronological order. Analysis S2: Data collection and segmentation, storing historical data in time segments, Analysis S3: Trend analysis and modeling, using machine learning algorithms to perform trend analysis and predictive modeling, reading historical data from the time series database, and training corresponding prediction models to predict the changing trends of personnel, equipment, or disaster events in the future. Analysis S4: Real-time data update, update data in the time series database in real time to ensure that the model's predictions are based on the latest situation.

4. The resource allocation system based on the disaster impact range and the location of the repair personnel according to claim 1 is characterized in that: The steps for establishing the resource allocation model of the intelligent allocation module are as follows: Step 1: Determine the objective function, which includes minimizing the repair time minT, maximizing the resource utilization maxU, and minimizing the total safety risk mminS. Step 2: Algorithm selection: select genetic algorithm, search for the optimal solution through selection, crossover and mutation operations, select particle swarm optimization algorithm, dynamically adjust resource allocation through swarm intelligence simulation, and quickly adapt to on-site changes.

5. The resource allocation system based on the disaster impact range and the location of the repair personnel according to claim 4 is characterized in that: The construction process of the objective function is: The minimized repair time minT is: Assume t i is the estimated completion time of the i-th task, and the total repair time can be expressed as: Where n is the total number of tasks; The maximum resource utilization maxU is: Suppose there are m kinds of resources, let u j is the utilization rate of the jth resource, measured by the average resource utilization rate: The utilization rate of the resource u j It is expressed as the ratio of resource usage time to total available time; The minimized security risk sum minS is: Assume i The goal of ensuring personnel safety is achieved by minimizing the sum of safety risks for the i safety risk factor of the task being performed:

6. The resource allocation system based on the disaster impact range and the location of the repair personnel according to claim 5 is characterized in that: The constraints of the objective function include the number of available personnel, equipment status, task priority, and geographical location restrictions: The number of available personnel, let x i The number of people assigned to task i satisfies: x i ≤X max Where X max is the maximum number of available personnel. The device state, let e i represents the status of the i-th device, where 1 means available and 0 means unavailable. The allocation of each task should satisfy: e i ＝1 The task priority, let p i is the priority coefficient of task i, and introduces task priority constraints to prioritize high-priority tasks to meet the following requirements: pix i ≥θ Where θ is the minimum priority requirement of task i; The geographical location restriction is that the task needs to be performed within a certain geographical location range, which is expressed by setting a distance constraint. Let d ij is the distance from task i to resource location j, satisfying: d ij ≤D max Where D max is the maximum allowed distance.

7. The resource allocation system based on the disaster impact range and the location of the repair personnel according to claim 4 is characterized in that: The genetic algorithm in the algorithm selection adds three parts: adaptive parameter adjustment, priority-based selection strategy, and multi-stage evolution on the basis of the traditional one. The adaptive parameter adjustment adaptively adjusts the parameters according to the resource demand and task urgency during the resource allocation process, increases the mutation probability and expands the search range when the resource demand changes greatly, and reduces the mutation probability and improves the stability of the solution when the demand is stable; The priority-based selection strategy designs a priority-weighted selection method in the selection stage, takes the task priority as the weight, guides the algorithm to allocate resources to high-priority tasks, and ensures that high-priority tasks are allocated first; The multi-stage evolution divides the algorithm into different stages, encourages exploration of a large solution space in the early exploration stage to ensure global search, and accelerates the convergence speed in the later stage to find the optimal solution within a limited time.

8. The resource allocation system based on the disaster impact range and the location of the repair personnel according to claim 4 is characterized in that: The particle swarm optimization algorithm in the algorithm selection adds three parts: multi-group dynamic scheduling, target guidance factor, and adaptive neighborhood update. The multi-group dynamic scheduling divides the particle group into multiple sub-groups, each of which focuses on a specific objective function and regularly exchanges information to achieve multi-objective collaborative optimization; The target guidance factor adds a target guidance factor to the particle position update to guide the particles to concentrate on the task area with higher priority, dynamically adjust the position of the particles, and make the algorithm quickly converge to the solution with the highest task demand; The adaptive neighborhood update dynamically adjusts the neighborhood structure of particles when the task and resource conditions change dynamically. Particles that are closer to the task resource position can form a close neighborhood, ensuring that resources are preferentially allocated to the most urgent tasks.

Images