A path optimization and resource intelligent scheduling method and system based on digital twinning

Abstract

The application discloses a path optimization and resource intelligent scheduling method and system based on digital twinning, and the method comprises the following steps: constructing a digital twinning three-dimensional model of disaster area infrastructure to realize three-dimensional scene reconstruction; constructing a rescue path optimization model based on a multi-objective function to optimize the paths between various places in the digital twinning three-dimensional model; establishing a job resource multi-objective scheduling model to realize intelligent scheduling of resources of the digital twinning three-dimensional model; setting constraint conditions for scheduling and execution; adopting a model predictive control thought to update the multi-objective path optimization model and the job resource multi-objective scheduling model once every other scheduling period; and the application can realize collaborative optimization of rescue path and resource scheduling, generate an optimal scheme in combination with a terrain and risk constraint, and improve rescue operation efficiency.

Description

Technical Field

[0001] This invention relates to the field of infrastructure repair and emergency dispatch technology, specifically to a method and system for path optimization and intelligent resource scheduling based on digital twins. Background Technology

[0002] Currently, in the wake of natural disasters, infrastructure is often damaged to varying degrees. Traditional manual inspection and route planning methods are slow to react, lack global awareness and dynamic decision-making capabilities, and cannot quickly respond and adjust route planning in real time in the post-disaster environment. These methods typically rely on static data, lacking dynamic awareness of real-time changes after a disaster, and are ill-equipped to cope with constantly evolving disaster situations. Furthermore, traditional systems lack precise modeling and 3D visualization capabilities for post-disaster infrastructure, making it difficult to accurately perceive the extent of damage and resource status in disaster areas, affecting the optimization of repair routes and the rational allocation of resources. Although some systems have introduced information technology for task management, these systems typically cannot update the post-disaster scenario in real time, lack sufficient intelligent optimization capabilities, and cannot tightly integrate route planning with resource scheduling, resulting in low scheduling efficiency and an inability to make rapid decisions and adjustments as the disaster situation changes.

[0003] Digital twin technology possesses the capability of physical-virtual mapping, enabling the construction of accurate digital models of post-disaster infrastructure. Furthermore, the combination of path planning algorithms and resource scheduling strategies can improve repair efficiency and the scientific nature of scheduling. Therefore, developing a comprehensive solution integrating "digital twin + path optimization + resource scheduling" has become an urgent need for technological development. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a path optimization and intelligent resource scheduling method and system based on digital twins, aiming to solve the problems in the background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a path optimization and intelligent resource scheduling method based on digital twins, comprising the following steps:

[0006] Step S1: Construct a digital twin 3D model of the disaster area's infrastructure to reconstruct the 3D scene;

[0007] Step S2: Based on a multi-objective function, construct an emergency repair path optimization model to optimize the paths between various locations in the digital twin 3D model;

[0008] Step S3: Establish a multi-objective scheduling model for job resources to achieve intelligent resource scheduling in the digital twin 3D model;

[0009] Step S4: Set constraints for scheduling and execution, including personnel / equipment attendance constraints, path accessibility constraints, task completion time constraints, personnel capability matching constraints, and dynamic post-disaster obstacle constraints;

[0010] Step S5: Using the model predictive control concept, update the multi-objective path optimization model and the job resource multi-objective scheduling model once every scheduling cycle.

[0011] Furthermore, the specific process of step S2 is as follows:

[0012] Step S2.1: Based on the graph model, treat the disaster area roads / scenes in the digital twin 3D model as a weighted directed graph. ,in, This represents the vertex set, which represents locations in the digital twin 3D model. The edge set represents the paths between various locations in the digital twin 3D model. The weight function represents the original cost of the path.

[0013] Step S2.2: Use the improved Dijkstra's algorithm to find the starting point. The path with minimum cost to all vertices is the shortest path; for any vertex... , defined from the starting point arrive The total cost of the minimum cost path for:

[0014] ;

[0015] In the formula, Indicates all starting from the origin arrive The path; Representing a path A certain edge in; express The weights;

[0016] The shortest path satisfies the Bellman optimality principle:

[0017] ;

[0018] In the formula, Indicates from vertex arrive The directed edges; Indicates from arrive The total cost of the minimum cost path; Representing an edge The weights;

[0019] Step S2.3: Determine the multi-objective attributes of path optimization, including length, time, resource handling / transportation cost, and path risk indicators; quantify each edge in the weighted directed graph. Multi-objective attributes, setting weighting coefficients, constructing edges Multi-dimensional comprehensive cost :

[0020] ;

[0021] In the formula, Representing an edge The actual length; Representing an edge The estimated time; Representing an edge The cost of resource handling / transportation; Representing an edge Risk indicators; , , , These represent the weighting coefficients for length, time consumption, resources, and risk, respectively.

[0022] Step S2.4: Construct the objective function for path optimization with the goal of minimizing the overall path cost:

[0023] ;

[0024] In the formula, Representing a path The multi-dimensional comprehensive cost; Representing a path The total cost of the path's length is calculated from the cost of all edges on the path. The summation is obtained; Representing a path The total time cost is calculated from the sum of the costs of all edges on the path. The summation is obtained; Representing a path The total cost of resource handling / transportation is calculated from all edges along the path. The summation is obtained; Representing a path The total risk and cost is calculated from all edges on the path. The sum is obtained by accumulation;

[0025] By minimizing We obtained the path with the optimal overall cost in the disaster area scenario.

[0026] Furthermore, feasible paths are optimized based on genetic algorithms; using the multi-dimensional comprehensive cost constructed in step S2.3 as the fitness function, the following process is executed:

[0027] Initial feasible path generation: Run steps S2.2 and S2.3 to obtain an initial feasible path. ;

[0028] by For each individual, initiate a genetic algorithm to optimize feasible paths:

[0029] exist Within the neighborhood of , an initial population is generated by k-shortest perturbation;

[0030] Perform crossover, mutation, and selection operations sequentially on the initial population;

[0031] When the preset maximum number of generations is reached or the fitness value of two consecutive generations is less than the preset threshold, the process stops, and the best individual in the current population is selected as the optimized feasible path.

[0032] Furthermore, when the digital twin model detects a new obstacle or a new emergency repair task, it executes:

[0033] Temporary adjustment of edge weights: In the affected road segments, the risk cost of the corresponding edge is set to the maximum value;

[0034] Local path repair: Rerun the improved Dijkstra algorithm only on the affected subgraphs in the weighted directed graph to obtain locally repaired paths;

[0035] Population update and re-evolution: The local repair path is injected into the population of the genetic algorithm and, as a new individual, the optimization process is restarted.

[0036] Furthermore, the specific process of step S3 is as follows:

[0037] Step S3.1: Transform resource scheduling optimization into a "task-resource" matching problem; Definition:

[0038] Resource Collection: , Indicates the first Class resources, Indicates the total quantity of resources;

[0039] Task Collection: , Indicates the first Task Indicates the total number of tasks;

[0040] Decision variables: When it is 0, the first Class resources Not assigned to the first Task When the value is 1, Assigned to , , ;

[0041] Step S3.2: Define the individual costs of resource and task matching from multiple core dimensions:

[0042] Response cost: , indicating resources To the mission Response time / arrival time;

[0043] Distance Cost: , indicating resources With the task Spatial distance between them;

[0044] Skill compatibility penalty: , indicating resources Abilities and Tasks The required "degree of mismatch" express The set of skills possessed express The required skill set Indicates the penalty coefficient;

[0045] Resource operating cost item: This represents the operating cost of resources performing tasks;

[0046] Step S3.3: The multi-dimensional costs of resource and task matching in Step S3.2 are fused together using weighting coefficients to form the objective function for optimizing the total cost:

[0047] ;

[0048] In the formula, in the formula, , , All represent scheduling preference weights.

[0049] Furthermore, in step S4, the personnel / equipment attendance constraints are represented as follows: , Represents a resource availability function. Represents time; path accessibility constraints are expressed as: , Describes the path accessibility function. All represent nodes on the path; the task completion time constraint is represented as: , The task time limit function and personnel capability matching constraint are represented as follows: Dynamic post-disaster obstacle constraints are represented as follows: , Represents the edge obstacle function.

[0050] Furthermore, in step S5, the specific update process is as follows: input the latest on-site images, equipment status, and traffic information, re-optimize, and generate scheduling instructions:

[0051] Path planning update: Adjust the path planning to take into account newly emerging obstacles or new tasks;

[0052] Dynamic resource rescheduling: Update the real-time location and job progress of resources, and perform dynamic rescheduling accordingly;

[0053] Instruction and work order issuance: Generate new path instructions and work orders, and issue them to mobile terminals;

[0054] Human interaction support: Allows manual intervention in the scheduling process and supports task merging or splitting operations.

[0055] A path optimization and intelligent resource scheduling system based on digital twins includes:

[0056] The scene modeling and reconstruction module is used to build a digital twin 3D model of the disaster area's infrastructure to achieve 3D scene reconstruction.

[0057] The path optimization module is used to construct an emergency repair path optimization model based on a multi-objective function to optimize the paths between various locations in the digital twin 3D model;

[0058] The resource scheduling module is used to establish a multi-objective scheduling model for job resources and realize intelligent resource scheduling in the digital twin 3D model.

[0059] The constraint module is used to set constraints for scheduling and execution, including personnel / equipment attendance constraints, path accessibility constraints, task completion time constraints, personnel capability matching constraints, and dynamic post-disaster obstacle constraints.

[0060] The real-time update module is used to update the multi-objective path optimization model and the multi-objective scheduling model of job resources once every scheduling cycle, using the model predictive control concept.

[0061] An electronic device includes a processor, a memory, and a bus, wherein the processor and the memory are connected via the bus, the memory is used to store a set of program code, and the processor is used to call the program code stored in the memory to execute a path optimization and intelligent resource scheduling method based on digital twins.

[0062] A non-volatile computer storage medium storing computer-executable instructions that execute a path optimization and resource intelligent scheduling method based on digital twins.

[0063] Compared with existing technologies, the present invention has the following advantages:

[0064] (1) In the post-disaster environment where the disaster situation is dynamically changing, the status of infrastructure can be mapped in real time through digital twin models, so as to achieve accurate fault location and global disaster awareness. Compared with traditional technologies, this innovation can reflect the actual situation of post-disaster infrastructure in real time, while traditional methods usually rely on static data or manual inspection, which are slow to respond and difficult to respond quickly to sudden changes.

[0065] (2) Achieve coordinated optimization of emergency repair routes and resource scheduling, and generate the optimal solution by combining terrain and risk constraints to improve the efficiency of emergency repair operations. Existing technologies often process route planning and resource scheduling separately, lacking systematicness and real-time optimization. This invention organically combines route planning and resource scheduling to ensure dynamic optimization of routes and resources in complex post-disaster environments, thereby greatly improving emergency repair efficiency.

[0066] (3) While considering terrain limitations and resource availability, the system enables automatic dispatching of emergency repair tasks and dynamic allocation of resources to ensure the safety and efficiency of the emergency repair process. Traditional resource scheduling relies heavily on human experience and lacks precise matching and real-time performance. However, this invention uses intelligent scheduling to intelligently match and allocate tasks and resources based on real-time data, avoiding resource waste and scheduling delays, and improving overall efficiency and safety.

[0067] (4) Through dynamic updating and rolling optimization mechanisms, the scheduling plan can be continuously adjusted according to changes on site, and can quickly adapt to changes in the disaster situation. This function greatly improves the adaptability and robustness of the system in complex and dynamic environments. Compared with existing static optimization methods, the present invention has strong adaptive capabilities and can make timely adjustments based on the latest post-disaster images, equipment status and traffic information, avoiding the lag of traditional solutions in changing environments.

[0068] (5) Based on a multi-dimensional cost optimization objective function, compared with traditional single-objective path planning, this invention can comprehensively consider multiple factors such as path length, time consumption, resource consumption, and safety, and achieve a comprehensive balance between path optimization and resource scheduling. This multi-objective optimization method can simultaneously meet the needs of efficiency, safety, and cost in the post-disaster repair process, far exceeding the limitations of traditional path planning methods that rely on only a single objective. Attached Figure Description

[0069] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0070] like Figure 1 As shown, the present invention provides a technical solution: a path optimization and intelligent resource scheduling method based on digital twins, comprising the following steps:

[0071] Step S1: Construct a digital twin 3D model of the disaster area's infrastructure to reconstruct the 3D scene;

[0072] In the post-disaster environment, multiple data sources such as drone inspection images and GIS geographic information data are collected and utilized. Point cloud reconstruction and image recognition technologies are applied and integrated with BIM models to generate digital twin 3D models of infrastructure in the disaster area.

[0073] This digital twin 3D model provides an accurate virtual mapping, enabling real-time understanding of the specific status of post-disaster infrastructure, such as broken poles, disconnected wires, and foundation displacement, ensuring accurate data support for subsequent route optimization and resource scheduling. This step, through point cloud reconstruction, image recognition, and integration with the BIM model, generates a digital model that provides the foundation for subsequent route planning, task scheduling, and resource allocation. The real-time updating capability of the digital twin model ensures that the model remains consistent with the actual on-site conditions.

[0074] Step S2: Construct an emergency repair path optimization model based on a multi-objective function to optimize the paths between various locations in the digital twin 3D model.

[0075] Step S2.1: Based on the graph model, abstract the disaster area roads / scenes in the digital twin 3D model into a weighted directed graph. ,in, This represents a vertex set, symbolizing locations such as emergency repair task points and resource warehouses in the digital twin 3D model. The edge set represents the paths between various locations in the digital twin 3D model. The weight function represents the original cost of the path (such as time, distance, and risk).

[0076] Step S2.2: Use the improved Dijkstra's algorithm to find the starting point. The path with minimum cost to all vertices is the shortest path; for any vertex... , defined from the starting point arrive The total cost of the minimum cost path for:

[0077] ;

[0078] In the formula, Indicates all starting from the origin arrive The path; Representing a path A certain edge in; express The weights.

[0079] The shortest path satisfies the Bellman Optimality principle:

[0080] ;

[0081] In the formula, Indicates from vertex arrive The directed edges; Indicates from arrive The total cost of the minimum cost path; Representing an edge The weights.

[0082] Step S2.3: Determine the multi-objective attributes of path optimization, including length, time, resource handling / transportation cost, and path risk indicators;

[0083] Each edge in a quantized weighted directed graph Multi-objective attributes, setting weighting coefficients, constructing edges Multi-dimensional comprehensive cost :

[0084] ;

[0085] In the formula, Representing an edge The actual length; Representing an edge Estimated travel time (taking into account traffic, flooding, etc.); Representing an edge The cost of resource handling / transportation; Representing an edge Risk indicators (such as passing through landslide areas); , , , These represent the weighting coefficients for length, time consumption, resources, and risk, respectively.

[0086] Step S2.4: Construct the objective function for path optimization with the goal of minimizing the overall path cost:

[0087] ;

[0088] In the formula, Representing a path The multi-dimensional comprehensive cost; Representing a path The total cost of the path's length is calculated from the cost of all edges on the path. The sum is obtained by accumulation; Representing a path The total time cost is calculated from the sum of the costs of all edges on the path. The sum is obtained by accumulation; Representing a path The total cost of resource handling / transportation is calculated from all edges along the path. The sum is obtained by accumulation; Representing a path The total risk and cost is calculated from all edges on the path. The sum is obtained by accumulation.

[0089] By minimizing This allows us to obtain the optimal path in disaster-stricken areas in terms of overall cost (while balancing multiple requirements such as length, time, resources, and risks).

[0090] Regarding the objective function for optimizing disaster relief infrastructure repair routes based on digital twins, it should be noted that this function is constructed around the core requirements of "efficiency, safety, and cost" in disaster relief. The expression can be simplified to the total path cost being the weighted sum of distance cost, time cost, resource cost, and safety penalty cost. The length cost is determined by... and The purpose of product quantization is to reduce unnecessary detours while ensuring feasibility, avoiding the "short but inaccessible" problem caused by traditional methods that only consider distance as the sole objective; time cost is considered... and The product constitutes, During emergency repairs in critical load areas, the weighting can be increased to ensure the fastest possible arrival at the fault point, overcoming the drawback of traditional static paths that "only calculate distance and not actual time"; resource costs are reduced by... and The product is composed of, When resources are scarce, the weight can be increased, prioritizing low-cost routes to reduce post-disaster resource waste; the penalty for safety is... and The product of In high-risk scenarios such as earthquakes and floods, this function significantly improves performance by forcibly avoiding dangerous areas and preventing traditional path planning from neglecting safety risks. Compared to traditional manual experience-based planning or single-objective algorithms, this function, through multi-dimensional weighting and dynamic weight adjustment, combined with real-time data updates from a digital twin model, can adjust path strategies in each scheduling cycle based on changes in the disaster situation (such as new obstacles or expansion of risk areas). This solves the problem that traditional methods cannot cope with dynamic post-disaster scenarios, achieving "efficient, safe, and economical" collaborative optimization of repair paths and improving the response speed and operational safety of post-disaster infrastructure repair.

[0091] Among them, feasible paths are optimized based on genetic algorithms (path planning combines the improved Dijkstra algorithm with genetic algorithms, taking into account both global optimality and local feasibility, and supporting path replanning and obstacle avoidance for sudden tasks).

[0092] Using the multi-dimensional comprehensive cost constructed in step S2.3 as the fitness function, the following process is executed:

[0093] 1. Initial feasible path generation: Run steps S2.2 and S2.3 to obtain an initial feasible path. .

[0094] 2. With For each individual, initiate a genetic algorithm to optimize feasible paths:

[0095] exist Within the neighborhood of , the initial population is generated by k-shortest perturbation.

[0096] The initial population is subjected to crossover, mutation, and selection operations in sequence. The crossover operation uses PMX crossover (partial matching crossover) to ensure the validity of the vertex order after crossover. The mutation operation adopts a combination of single-point mutation and local rerouting. The selection operation combines tournament selection and elite retention strategies to avoid losing the optimal solution.

[0097] In genetic algorithms, the fitness value is usually required to be "the larger the better". The optimization objective here is "minimizing the comprehensive cost across multiple dimensions", and the fitness value is a numerical measure of the "quality of the path"; the larger the value, the better the path.

[0098] When the preset maximum number of generations is reached or the fitness value of individuals in two consecutive generations is less than the preset threshold, the process stops, and the best individual in the current population is selected as the optimized feasible path.

[0099] Specifically, when the digital twin model detects a new obstacle (triggered by dynamic post-disaster obstacle constraints) or a new emergency repair task:

[0100] 1. Temporary adjustment of edge weights: In the affected road segments, the risk cost of the corresponding edge is set to the maximum value (the path selection of this road segment is prohibited).

[0101] 2. Local path repair: The improved Dijkstra algorithm is re-run only on the affected subgraphs in the weighted directed graph to quickly obtain the locally repaired path.

[0102] 3. Population update and re-evolution: Local repair paths are injected into the population of the genetic algorithm and treated as new individuals to restart the optimization process, ensuring that global optimality is not compromised.

[0103] Step S3: Establish a multi-objective scheduling model for job resources to achieve intelligent resource scheduling in the digital twin 3D model.

[0104] Step S3.1: Transform resource scheduling optimization into a "task-resource" matching problem; Definition:

[0105] Resource Collection: (Including various resources such as people, vehicles, and equipment). Indicates the first Class resources, This indicates the total quantity of resources.

[0106] Task Collection: (emergency repairs, work tasks, etc. that need to be performed). Indicates the first Task This indicates the total number of tasks.

[0107] Decision variables: When it is 0, the first Class resources Not assigned to the first Task When the value is 1, Assigned to , , .

[0108] Step S3.2: Define the individual costs of resource and task matching from multiple core dimensions (time, space, skill matching, and operational cost) to provide a foundation for subsequent total cost fusion, as follows:

[0109] Response cost (time dimension) , indicating resources To the mission Response time / arrival time (reflecting scheduling response efficiency).

[0110] Distance cost (spatial dimension) , indicating resources With the task The spatial distance between them (reflecting the cost of spatial transfer).

[0111] Skill compatibility penalty (ability matching dimension) , indicating resources Abilities and Tasks The required "degree of mismatch" express The set of skills possessed express The required skill set This represents the penalty coefficient.

[0112] Resource operating costs (economic cost dimension) This represents the operating cost of resources performing tasks (such as vehicle fuel costs, labor costs, etc.), and the calculation formula is "unit usage cost × estimated task time".

[0113] Step S3.3: The multi-dimensional costs of resource and task matching in Step S3.2 are fused together using weighting coefficients to form the objective function for optimizing the total cost:

[0114] ;

[0115] In the formula, , , All represent scheduling preference weights, used to balance the relative importance of the three types of costs: spatial distance, response time, and skill matching.

[0116] Regarding the resource scheduling optimization objective function mentioned above, it should be noted that this function is constructed around the core requirement of precise "task-resource" matching. The expression can be simplified to the total scheduling cost equaling the weighted sum of spatial distance cost, response time cost, and capability matching penalty cost. Among these, and The purpose of product quantization is to prioritize scheduling nearby resources, reduce round-trip time, and avoid the inefficiency caused by the traditional scheduling method of "choosing the far one over the near one"; the response time cost is reduced by... and The product constitutes, In critical tasks such as hospitals and communication base stations, the weight of capability matching can be increased to ensure rapid response and solve the problem of delayed response in traditional manual dispatching; the penalty for capability matching is... and The product of This technology significantly improves performance in specialized tasks such as high-voltage operations and equipment replacement, forcibly matching resources with the corresponding qualifications to avoid rework or safety accidents caused by "resource mismatch" in traditional scheduling. Compared to traditional resource allocation methods that rely on human experience, this function, through multi-factor quantification and dynamic weight adjustment, combined with real-time updates of resource status from a digital twin model, can adjust the allocation strategy based on resource location and skill changes in each scheduling cycle. This solves the problems of low resource utilization and poor matching accuracy in traditional methods, achieving "fast, adaptable, and efficient" collaborative scheduling of emergency repair resources, and improving resource utilization efficiency and task completion quality in post-disaster infrastructure emergency repair.

[0117] The objective function comprehensively considers response speed, path cost, and resource suitability. It uses a genetic algorithm to solve for the resource allocation sequence, thereby achieving optimal resource matching and automatic generation of scheduling work orders.

[0118] Step S4: Set constraints for scheduling and execution, including personnel / equipment attendance constraints, path accessibility constraints, task completion time constraints, personnel capability matching constraints, and dynamic post-disaster obstacle constraints.

[0119] Personnel / equipment attendance constraints are represented as follows: , Represents a resource availability function. Indicates time; the constraint means that only personnel or equipment that are "available at the current moment" can be scheduled (ensuring that resources are actually available for use).

[0120] Path accessibility constraints are expressed as: , Describes the path accessibility function. All of these represent nodes on the path; the constraint means that the nodes (or points) on the path must be located within the "post-disaster marked accessible area" (to ensure the physical path is feasible).

[0121] The task completion time limit constraint is represented as: , This represents a task time limit function; the constraint means that critical emergency repair tasks must be completed within a specified time window (deadline). Complete within the specified timeframe (to ensure timely completion of the task).

[0122] Personnel capability matching constraints are expressed as follows: This constraint means that the allocated resources (such as personnel) must have "all the capabilities required to complete the task" (ensuring that the task can be executed effectively).

[0123] Dynamic post-disaster obstacle constraints are represented as follows: , This represents the obstacle function; the constraint means that in a post-disaster environment, obstacles may appear at any time (such as landslides, collapsed buildings, flooding, etc.). In path planning, traditional methods often only consider static obstacle data and cannot cope with the rapidly changing post-disaster environment. Dynamic post-disaster obstacle constraints require the system to be able to identify and update obstacle information in real time, ensuring that path planning avoids the newly appearing obstacles.

[0124] Regarding the constraints in the aforementioned digital twin-based post-disaster infrastructure repair route and resource scheduling system, it should be noted that these constraints are key limitations ensuring the feasibility, safety, and efficiency of the repair plan. These constraints mainly include personnel / equipment attendance constraints, route accessibility constraints, task completion time constraints, personnel capability matching constraints, and dynamic post-disaster obstacle constraints. Attendance constraints ensure that only available resources are scheduled, avoiding duplicate assignments; accessibility constraints, based on real-time terrain data from the digital twin, guarantee physically passable routes, preventing situations where "feasible on paper, but blocked on-site"; time constraints set time windows for critical tasks, prioritizing the restoration of core loads; capability matching constraints require resources to have corresponding qualifications, avoiding accidents caused by "mismatch between personnel and positions"; and dynamic post-disaster obstacle constraints ensure that route planning always avoids newly emerging risk areas by identifying and updating sudden obstacles such as landslides, water accumulation, and collapsed buildings in real time. Compared to the traditional problems of missing or singular constraints, these multi-dimensional constraints are integrated into the objective function's penalty term and take effect simultaneously. This not only safeguards the bottom line of safety and feasibility but also retains the flexibility of dynamic adjustment, resolving the contradiction of traditional "rigid constraints or uncontrolled situations without constraints".

[0125] Step S5: Using the Model Predictive Control (MPC) approach, update the multi-objective path optimization model and the job resource multi-objective scheduling model every scheduling cycle.

[0126] The specific update process is as follows: input the latest on-site images, equipment status, and traffic information, re-optimize, and generate dispatch instructions:

[0127] Path planning update: Adjust the path planning to take into account newly emerging obstacles or new tasks.

[0128] Dynamic resource rescheduling: Update the real-time location and job progress of resources, and perform dynamic rescheduling accordingly.

[0129] Instruction and work order issuance: Generate new path instructions and work orders and issue them to mobile terminals (such as the terminals of repair personnel and equipment).

[0130] Human interaction support: Allows manual intervention in the scheduling process and supports task merging or splitting operations.

[0131] This rolling optimization strategy enables adaptive evolution of scheduling schemes, improving the system's resilience and adaptability in dynamic post-disaster environments.

[0132] A path optimization and intelligent resource scheduling system based on digital twins includes:

[0133] The scene modeling and reconstruction module is used to build a digital twin 3D model of the disaster area's infrastructure to achieve 3D scene reconstruction.

[0134] The path optimization module is used to construct an emergency repair path optimization model based on a multi-objective function to optimize the paths between various locations in the digital twin 3D model;

[0135] The resource scheduling module is used to establish a multi-objective scheduling model for job resources and realize intelligent resource scheduling in the digital twin 3D model.

[0136] The constraint module is used to set constraints for scheduling and execution, including personnel / equipment attendance constraints, path accessibility constraints, task completion time constraints, personnel capability matching constraints, and dynamic post-disaster obstacle constraints.

[0137] The real-time update module is used to update the multi-objective path optimization model and the multi-objective scheduling model of job resources once every scheduling cycle, using the model predictive control concept.

[0138] An electronic device includes a processor, a memory, and a bus, wherein the processor and the memory are connected via the bus, the memory is used to store a set of program code, and the processor is used to call the program code stored in the memory to execute a path optimization and intelligent resource scheduling method based on digital twins.

[0139] A non-volatile computer storage medium storing computer-executable instructions that execute a path optimization and resource intelligent scheduling method based on digital twins.

[0140] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A path optimization and intelligent resource scheduling method based on digital twins, characterized in that, Includes the following steps: Step S1: Construct a digital twin 3D model of the disaster area's infrastructure to reconstruct the 3D scene; Step S2: Based on a multi-objective function, construct an emergency repair path optimization model to optimize the paths between various locations in the digital twin 3D model; Step S3: Establish a multi-objective scheduling model for job resources to achieve intelligent resource scheduling in the digital twin 3D model; Step S4: Set constraints for scheduling and execution, including personnel / equipment attendance constraints, path accessibility constraints, task completion time constraints, personnel capability matching constraints, and dynamic post-disaster obstacle constraints; Step S5: Using the model predictive control approach, update the multi-objective path optimization model and the job resource multi-objective scheduling model every scheduling cycle; The specific process of step S2 is as follows: Step S2.1: Based on the graph model, treat the disaster area roads / scenes in the digital twin 3D model as a weighted directed graph. ,in, This represents the vertex set, which represents locations in the digital twin 3D model. The edge set represents the paths between various locations in the digital twin 3D model. The weight function represents the original cost of the path. Step S2.2: Use the improved Dijkstra's algorithm to find the starting point. The path with minimum cost to all vertices is the shortest path; for any vertex... , defined from the starting point arrive The total cost of the minimum cost path for: ； In the formula, Indicates all starting from the origin arrive The path; Representing a path A certain edge in; express The weights; The shortest path satisfies the Bellman optimality principle: ； In the formula, Indicates from vertex arrive The directed edges; Indicates from arrive The total cost of the minimum cost path; Representing an edge The weights; Step S2.3: Determine the multi-objective attributes of path optimization, including length, time, resource handling / transportation cost, and path risk indicators; quantify each edge in the weighted directed graph. Multi-objective attributes, setting weighting coefficients, constructing edges Multi-dimensional comprehensive cost : ； In the formula, Representing an edge The actual length; Representing an edge The estimated time; Representing an edge The cost of resource handling / transportation; Representing an edge Risk indicators; , , , These represent the weighting coefficients for length, time consumption, resources, and risk, respectively. Step S2.4: Construct the objective function for path optimization with the goal of minimizing the overall path cost: ； In the formula, Representing a path The multi-dimensional comprehensive cost; Representing a path The total cost of the path's length is calculated from the cost of all edges on the path. The sum is obtained by accumulation; Representing a path The total time cost is calculated from the sum of the costs of all edges on the path. The sum is obtained by accumulation; Representing a path The total cost of resource handling / transportation is calculated from all edges along the path. The sum is obtained by accumulation; Representing a path The total risk and cost is calculated from all edges on the path. The sum is obtained by accumulation; By minimizing We obtained the path with the optimal overall cost in the disaster area scenario.

2. The path optimization and intelligent resource scheduling method based on digital twins according to claim 1, characterized in that: Feasible paths are optimized based on genetic algorithms; using the multi-dimensional comprehensive cost constructed in step S2.3 as the fitness function, the following process is executed: Initial feasible path generation: Run steps S2.2 and S2.3 to obtain an initial feasible path. ; by For each individual, initiate a genetic algorithm to optimize feasible paths: exist Within the neighborhood of , an initial population is generated by k-shortest perturbation; Perform crossover, mutation, and selection operations sequentially on the initial population; When the preset maximum number of generations is reached or the fitness value of two consecutive generations is less than the preset threshold, the process stops, and the best individual in the current population is selected as the optimized feasible path.

3. The path optimization and intelligent resource scheduling method based on digital twins according to claim 2, characterized in that: When the digital twin model detects a new obstacle or a new emergency repair task, it executes: Temporary adjustment of edge weights: In the affected road segments, the risk cost of the corresponding edge is set to the maximum value; Local path repair: Rerun the improved Dijkstra algorithm only on the affected subgraphs in the weighted directed graph to obtain locally repaired paths; Population update and re-evolution: The local repair path is injected into the population of the genetic algorithm and, as a new individual, the optimization process is restarted.

4. The path optimization and intelligent resource scheduling method based on digital twins according to claim 3, characterized in that: The specific process of step S3 is as follows: Step S3.1: Transform resource scheduling optimization into a "task-resource" matching problem; definition: Resource Collection: , Indicates the first Class resources, Indicates the total quantity of resources; Task Collection: , Indicates the first Task Indicates the total number of tasks; Decision variables: When it is 0, the first Class resources Not assigned to the first Task When the value is 1, Assigned to , , ; Step S3.2: Define the individual costs of resource and task matching from multiple core dimensions: Response cost: , indicating resources To the mission Response time / arrival time; Distance Cost: , indicating resources With the task Spatial distance between them; Skill compatibility penalty: , indicating resources Abilities and Tasks The required "degree of mismatch" express The set of skills possessed express The required skill set Indicates the penalty coefficient; Resource operating cost item: This represents the operating cost of resources performing tasks; Step S3.3: The multi-dimensional costs of resource and task matching in Step S3.2 are fused together using weighting coefficients to form the objective function for optimizing the total cost: ； In the formula, , , All represent scheduling preference weights.

5. The path optimization and intelligent resource scheduling method based on digital twins according to claim 4, characterized in that: In step S4, the personnel / equipment attendance constraints are represented as follows: , Represents a resource availability function. Represents time; path accessibility constraints are expressed as: , Describes the path accessibility function. All represent nodes on the path; the task completion time constraint is represented as: , Represents the task time limit function; Personnel capability matching constraints are expressed as follows: Dynamic post-disaster obstacle constraints are represented as follows: , Represents the edge obstacle function.

6. The path optimization and intelligent resource scheduling method based on digital twins according to claim 5, characterized in that: In step S5, the specific update process is as follows: input the latest on-site images, equipment status, and traffic information, re-optimize, and generate dispatch instructions: Path planning update: Adjust the path planning to take into account newly emerging obstacles or new tasks; Dynamic resource rescheduling: Update the real-time location and job progress of resources, and perform dynamic rescheduling accordingly; Instruction and work order issuance: Generate new path instructions and work orders, and issue them to mobile terminals; Human interaction support: Allows manual intervention in the scheduling process and supports task merging or splitting operations.

7. A path optimization and intelligent resource scheduling system based on digital twins, applied to the path optimization and intelligent resource scheduling method based on digital twins as described in any one of claims 1-6, characterized in that, include: The scene modeling and reconstruction module is used to build a digital twin 3D model of the disaster area's infrastructure to achieve 3D scene reconstruction. The path optimization module is used to construct an emergency repair path optimization model based on a multi-objective function to optimize the paths between various locations in the digital twin 3D model; The resource scheduling module is used to establish a multi-objective scheduling model for job resources and realize intelligent resource scheduling in the digital twin 3D model. The constraint module is used to set constraints for scheduling and execution, including personnel / equipment attendance constraints, path accessibility constraints, task completion time constraints, personnel capability matching constraints, and dynamic post-disaster obstacle constraints. The real-time update module is used to update the multi-objective path optimization model and the multi-objective scheduling model of job resources once every scheduling cycle, using the model predictive control concept.

8. An electronic device, characterized in that, The system includes a processor, a memory, and a bus, wherein the processor and the memory are connected via the bus, and the memory is used to store a set of program code. The processor is used to call the program code stored in the memory to execute a path optimization and resource intelligent scheduling method based on digital twins as described in any one of claims 1-6.

9. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer can execute instructions to perform the path optimization and intelligent resource scheduling method based on digital twins as described in any one of claims 1-6.

Images