Robust optimization-based medical first aid resource scheduling method
By adopting a robust optimization-based medical emergency resource scheduling method, the problem of intelligent management and control of batch medical emergency events in urban medical emergency centers was solved, realizing efficient resource allocation and rapid response, and improving the success rate of treatment and system adaptability.
Patent Information
- Application Number
- CN202411084081.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-08-08
AI Technical Summary
Existing urban emergency medical centers lack intelligent management methods and systems for handling large-scale emergency medical events, and cannot effectively utilize existing case data to support regional collaborative intelligent management.
A robust optimization-based medical emergency resource scheduling method is adopted. By constructing a ground cost matrix and an optimal transmission model, and combining robust optimization theory, a model of resource allocation and transportation problems is established, solved, and scheduled to achieve efficient resource allocation.
This ensures a rapid and economical response to emergency needs, improves the success rate of treatment, provides scientific data for medical decision-makers, and enhances the system's adaptability and flexibility.
Smart Images

Figure CN119047753A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of intelligent health technology, and in particular relates to a medical emergency resource scheduling method based on robust optimization. Background Art
[0002] Intelligent regional linkage control of medical emergency resources for batch emergency needs has become a hot topic in the field of intelligent health technology. Here, batch medical emergency events refer to events in which more than three people have major emergencies and need medical emergency, such as large-scale casualties caused by large-scale traffic accidents and gas explosions. This type of medical emergency event is different from conventional medical emergency tasks for individuals. The difference includes that the scale must be more than three people; it is different from medical emergency tasks for large-scale events or competitions. The difference is that the time and place of the accident are generally unpredictable and occur in activities that are not planned in advance; it is also different from medical emergency tasks for large-scale disasters (such as earthquakes). The difference lies in the range of dispatchable resources for medical emergency tasks. Disaster medical emergency tasks may be directly dispatched at the national level, while the batch medical emergency events referred to here are often routinely handled by regional medical centers. They occur more frequently and have a smaller range than medical emergency tasks for large-scale disasters. However, the existing urban medical emergency centers lack methods and systems for intelligent control of batch medical emergency events for handling conventional medical emergency tasks for individuals. Although these medical emergency centers have accumulated cases and stored certain data in the database of the medical emergency center, these cases have not been fully utilized and their potential knowledge has not been mined to support regional linkage intelligent management and control for batch medical emergency. In view of this, a systematic solution for regional linkage intelligent management and control for batch medical emergency is very urgent. Summary of the invention
[0003] In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a medical emergency resource scheduling method based on robust optimization, the method comprising: obtaining current rescue information, and constructing a ground cost matrix according to the rescue information; judging whether rescue resources are needed according to the current rescue information, and if rescue resources are needed, establishing an optimal transmission model for the resource allocation problem according to the ground cost matrix and the optimal transmission theory; if it is uncertain whether rescue resources are needed, constructing an uncertain set based on the robust optimization theory, and establishing a robust optimization model for the transportation problem based on the uncertain set; solving the optimal transmission model for the resource allocation problem and the robust optimization model for the transportation problem respectively, and obtaining a resource allocation matrix and an optimal decision; and scheduling rescue resources according to the resource allocation matrix and the optimal decision.
[0004] Beneficial effects of the present invention:
[0005] The present invention ensures that emergency needs can be responded to quickly and economically in emergency situations by accurately calculating and optimizing resource allocation, while improving the success rate of treatment. The present invention provides scientific data basis for medical decision makers, enhances the adaptability and flexibility of the system, and enables medical resources in the entire region to be linked more efficiently. BRIEF DESCRIPTION OF THE DRAWINGS
[0006] Figure 1 It is the overall technical framework flow chart of the present invention;
[0007] Figure 2 It is a tree structure diagram of the model of the present invention;
[0008] Figure 3 It is a flow chart of the rescue resource dispatching method based on the optimal route of the present invention;
[0009] Figure 4 The decision optimization flow chart of the present invention. DETAILED DESCRIPTION
[0010] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0011] Example 1
[0012] A method for scheduling medical emergency resources based on robust optimization, such as Figure 3 As shown, the method includes: obtaining current rescue information, and constructing a ground cost matrix according to the rescue information; judging whether rescue resources are needed according to the current rescue information, and if rescue resources are needed, establishing an optimal transmission model for the resource allocation problem according to the ground cost matrix and the optimal transmission theory; if it is uncertain whether rescue resources are needed, constructing an uncertain set based on the robust optimization theory, and establishing a robust optimization model for the transportation problem based on the uncertain set; solving the optimal transmission model for the resource allocation problem and the robust optimization model for the transportation problem respectively, and obtaining a resource allocation matrix and an optimal decision; and scheduling rescue resources according to the resource allocation matrix and the optimal decision.
[0013] In this embodiment, after obtaining the rescue information, the data needs to be preprocessed, specifically including: cleaning and standardizing the collected data to ensure the quality and consistency of the data, and provide an accurate basis for subsequent resource allocation. The rescue information includes the actual distance between the medical resource point and the emergency demand point, traffic conditions, and resource capacity. According to factors such as the actual distance between the medical resource point and the emergency demand point, traffic conditions, and resource capacity, a ground cost matrix (C) is constructed. The matrix records in detail the deployment cost from each resource point to each demand point, providing a quantitative basis for optimal resource allocation.
[0014] The optimal transmission theory, especially the Wasserstein distance and Sinkhorn algorithm, is used to solve the resource allocation problem. After obtaining the transportation matrix solved by the OT model, the model will determine which demand points each resource point should allocate resources to, as well as the specific amount of allocation. The model is verified in a simulation environment, and the performance and accuracy of the model are evaluated by comparing the response time and cost under different scheduling strategies. The OT resource scheduling model is integrated into the regional linkage intelligent management and control system to achieve real-time resource allocation. In actual medical emergency events, the system will guide medical personnel to respond quickly based on the resource allocation plan automatically generated by the model.
[0015] Specifically, the Kantorovich optimal transport problem is the most typical OT problem. It seeks an optimal coupling γ that makes the discrete measure a to the discrete measure b relative to the ground cost To be a transportation plan, γ must be the set When the ground cost is a metric, the optimal value of the OT problem is also a metric, called the Wasserstein distance. In this discrete case, the OT problem is defined as:
[0016] W C (a,b)=min γ∈Π(a,b) <γ,C>,
[0017] Among them, 1 n1 is an n2-dimensional vector whose components are all 1, is the transpose of the optimal coupling matrix, is an n1-dimensional vector whose components are all 1, W C is the Wasserstein loss based on the ground cost C.
[0018] The above optimization problem is often amenable to including a regularization term for the transportation plan γ, such as entropy regularization or squared L2. For entropy regularized OT problems, the Sinkhorn-Knopp algorithm (or variants) or a stochastic optimization algorithm can be used.
[0019] A set of probability measures {a1,a2,…,a N}as follows:
[0020]
[0021] Among them, a * In order to make The a value of , N is the transmission dimension.
[0022] When entropy regularization is used, an efficient Bregman projection algorithm is provided in POT. On the other hand, an LP solver is used to solve the non-regularized problem. The calculation process includes:
[0023] The Kantorovich optimal transport problem is:
[0024]
[0025] Where U is the set of all possible transmission plans (also called coupling), C is the cost matrix, γ is the transmission plan matrix, and C i,j is the cost of transporting a unit mass of material from source i to target j, γ i,j is the amount of material transferred from source i to target j.
[0026] The p-Wasserstein distance is:
[0027]
[0028] The original optimization problem and the dual problem are:
[0029]
[0030] Among them, c T is the transpose of the cost vector, γ is the vector representation of the transmission plan matrix P, A is the constraint matrix, which ensures that the rows and columns of the transmission plan γ are equal to the source probability measure a and the target probability measure b respectively, and h is the dual variable of the original optimization problem.
[0031] Entropy regularization is:
[0032]
[0033] Among them, the non-negative matrix γ is the transportation plan, and its elements γ i,j represents the amount of material transferred from source i to target j, U(a,b) represents a collection of transportation plans, is the optimal transmission distance from a to b, ε is the regularization parameter, and H(γ) is the entropy function
[0034] The iterative process of the Sinkhorn algorithm is as follows:
[0035] Step 1: Initialization: Choose a non-negative matrix γ (0) , which can usually be initialized to the identity matrix.
[0036] Step 2: Iterative update: Alternately update the rows and columns of the matrix γ so that after each step, the rows and columns of the matrix approximate the source distribution a and the target distribution b respectively. The update formula is as follows:
[0037]
[0038] Here, e is a vector whose elements are all 1, and the superscript T indicates the transpose of the matrix.
[0039] Step 3: Iterate until convergence: Repeat step 2 until the row and column sums of γ converge to a and b respectively. Finally, the resulting γ matrix is the desired approximate optimal transportation plan. The convergence of this algorithm ensures that under appropriate conditions, a solution to the entropy regularized optimal transportation problem can be found.
[0040] In this embodiment, in the context of vehicle pre-assignment, the sample robust model can be written as the following two-stage problem:
[0041]
[0042] in, is a vector of intermediate variables representing the worst-case recovery cost for each scenario, and is an ε neighborhood uncertainty set consisting of each demand sample The general norm around ||·|| is defined.
[0043] Note that the multi-strategy approximation of the waiting decision y allows each demand sample With different affine mappings, we get a two-dimensional decision rule (y(d)) s∈[S],j∈[J] .
[0044] Example 2
[0045] The present invention is based on a resource scheduling model with optimal transmission distance, which aims to solve the resource allocation problem in batch medical emergency events. The model optimizes the resource allocation strategy by calculating the "ground cost" (i.e. the cost of resource allocation) between different medical resource points (such as hospitals, emergency centers, ambulances, etc.) and emergency demand points, ensuring that emergency needs are met in the shortest time and at the lowest cost. Figure 1 As shown, the specific steps include:
[0046] Step S11: Rescue resources include search and rescue teams, medical rescue vehicles, emergency medical equipment, etc. It is necessary to determine how to optimally allocate these resources to the accident site and how to quickly and effectively transport the injured to the hospital. For this purpose, Python's POT (Python Optimal Transport) library can be used to calculate the optimal transmission distance. By loading the data set, the coordinates of various rescue resources and the location of the accident are obtained.
[0047] Step 12: Based on the actual distance between the medical resource point and the emergency demand point, traffic conditions, resource capacity and other factors, a ground cost matrix (C) is constructed. The element C_ij of the matrix represents the deployment cost from resource point i to demand point j. Use the ot.dist function to calculate the cost matrix, that is, the transportation cost matrix.
[0048] Step 13: To solve the optimal transmission problem, you can choose to use Earth Mover's Distance (EMD) or Sinkhorn algorithm. The goal is to find the transmission matrix gamma such that:
[0049]
[0050] stγ1=a
[0051] γ T 1 = b
[0052] γ≥0
[0053] Where C is the cost matrix, a and b are the source distribution and target distribution respectively.
[0054] Step S14: When the algorithm takes a long time to calculate, regularize it to obtain a simpler or faster solution to the problem. The Sinkhorn algorithm does this by adding an entropy regularization term, which solves the following problem.
[0055]
[0056] stγ1=a
[0057] γ T 1 = b
[0058] γ≥0
[0059] Among them, reg is a hyperparameter and Ω is the entropy regularization term, which is defined as follows:
[0060]
[0061] Step S15: In the actual resource scheduling operation, the Sinkhorn algorithm is first used to calculate the optimal transmission matrix. This can be achieved by calling the ot.sinkhorn function in the POT library. The resource source distribution (such as the available resources of the hospital) and the target distribution (such as the emergency needs at the accident site) and the cost matrix (C) are taken as input parameters. The choice of the regularization parameter (reg) will affect the calculation speed of the algorithm and the sparsity of the results. In emergency situations, a smaller regularization parameter is selected to quickly obtain a solution.
[0062] Step S16: After obtaining the optimal transmission matrix (γgamma), use it for actual resource scheduling. Each element γ i,j gamma_ij represents the optimal transportation volume from resource point i to demand point j. The rescue team can allocate ambulances, medical equipment and personnel based on this matrix. For example, if the value of gamma_ij is large, then resource point i should give priority to allocating resources to demand point j. In actual operation, the rescue team will formulate a detailed rescue plan based on this matrix and adjust it according to the actual situation during the implementation process.
[0063] Example 3
[0064] The present invention is based on a robust vehicle pre-allocation method and aims to solve the problem of regional linkage intelligent control in batch medical emergency. Figure 4 As shown in the figure, the method predicts and optimizes the allocation of vehicles between different emergency demand points to ensure a quick and effective response in an emergency while reducing resource waste. The specific steps include:
[0065] Step S21: Before an accident occurs, a network model including supply nodes (such as hospitals, emergency centers) and demand nodes (accident sites) is established by analyzing historical data and real-time information. The goal is to achieve optimal pre-allocation of vehicles under uncertain emergency demand, so a reasonable model assumption is extremely important. Assume that there are I supply nodes and J demand nodes in a city area. In the case of random demand Before realization, the unit cost c ij Allocate x from supply node i∈[I] (where i has a large number of idle vehicles) to demand node j∈[J] ij When the vehicle realizes the uncertain demand, the calculated benefit is:
[0066]
[0067] The parameters of the network model are: the number of supply nodes I = 1; the number of demand nodes J = 10; the income coefficient τ = (4.50, 4.41, 3.61, 4.49, 4.38, 4.58, 4.53, 4.64, 4.58, 4.32); the cost coefficient c j =3, where j = 1, 2, ..., J; the maximum supply of vehicles q i =400, where i=1,2,...,I.
[0068] Step S22: Use robust optimization methods, such as the RSOME framework, to handle demand uncertainty, including: vehicle pre-allocation will be solved by using the robust and sample robust optimization methods of the RSOMEro framework.
[0069]
[0070] Among them, the waiting decision y representing the payoff is defined by the linear decision rule Approximately, this means that for each affine y j Depends on the implementation of requirement d. Here is a box uncertainty set where the upper and lower bounds are determined based on historical data.
[0071] Step S23: In the RSOME framework, the benefits of waiting decisions are approximated by linear decision rules (ldr), ensuring that each decision depends on the realization of demand. This allows for efficient resource allocation under uncertain conditions.
[0072] Step S24: Construct a robust model, which includes the worst-case objective function and robust constraints. This requires that in the worst case, the vehicle allocation decision can meet all demands while not exceeding the maximum supply of vehicles.
[0073] Step S25: Solve the robust model through the Gurobi solver to obtain the optimal vehicle pre-allocation decision. In this case, the optimal vehicle pre-allocation decision x = (0, 0, 0, 0, 0, 39.6138, 0, 0, 0, 0) is relatively conservative, and the optimal target value is -62.59. This method can help rescue teams make more efficient and adaptable decisions under uncertainty to meet the challenges in urban traffic management.
[0074] In addition, the sample robust model method described in the description can be used to further optimize the vehicle pre-assignment decision. In this method, historical demand samples are integrated into the decision process to better adapt to uncertainty. By defining an ε neighborhood uncertainty set, the upper and lower bounds of the demand can be adjusted to obtain new vehicle assignment decisions.
[0075] In the sample robust model, each demand sample has a corresponding worst-case backtracking cost to ensure that vehicles can be effectively allocated in various situations. Assuming that the conservative parameter ε=0.25, the optimal vehicle pre-allocation decision is x=(0.341, 0.358, 0, 4.289, 0, 69.456, 2.452, 4.578, 5.229, 2.486), and the optimal target value is -103.656. Note that in the special case of ε=0, the sample robust model is equivalent to the sample mean approximation method. With this method, rescue teams can make better use of historical data and real-time information to make vehicle allocation decisions in a more flexible and efficient way, thereby improving the efficiency and response capabilities of urban traffic management.
[0076] Step S26: After implementing the rescue plan, the upper and lower bounds of the demand are adjusted according to the actual situation, i.e., the state of the demand node (J) and the supply node (I), the maximum supply of vehicles (q), the cost coefficient (c) and the revenue coefficient (r), to obtain a new vehicle allocation decision. In this way, the rescue team can make more efficient and adaptable decisions under uncertain conditions.
[0077] Example 3
[0078] The present invention is based on a distributed and robust vehicle pre-allocation method, which aims to solve the problem of regional linkage intelligent management and control in batch medical emergency events. The method predicts emergency needs and pre-allocates medical vehicles to ensure rapid response and effective resource management in emergency situations. Specifically, it includes:
[0079] Step S31: Establish the following distributed robust optimization model:
[0080]
[0081] in, is the vector of all random variables, including the random demand quantity and possible auxiliary random variables whose distribution is characterized by an event uncertainty set The RSOME dro module provides modeling tools specifically designed to handle such event uncertainty sets and the associated event-help adaptability.
[0082] Step S32: Use the robust model of the dro framework to transform the vehicle pre-assignment problem into a distribution robust optimization problem. The uncertainty set is written as:
[0083]
[0084] The random vector is And for each sample s∈[S], the weight w s= 1 / S, the corresponding support (uncertainty set) is defined as An ε-sphere around sample data points The multi-policy approximation proposed by Bertsimas et al. shows that: for each y j Affine depends on the requirement implementation d. The affine dependency is different for each sample record and can therefore be captured by event adaptation, where and
[0085] Step S33: Create a DRO model through the dro module, define random variables, uncertainty sets, scenario weights, etc. Convert the sample robust model into a distributional robust optimization problem.
[0086] Step S34: Define decision variables in each scenario, which are adapted to random variables through affine to adapt to demand changes in different situations. The model will consider the worst-case expected value, robust constraints and deterministic constraints during the solution process.
[0087] Step S35: Generate an uncertainty set through a decision tree regressor, taking into account the conditional mean and variance to construct more accurate scenarios and parameters. is constructed to take into account the conditional mean μ s and variance φ s ,For the S scenario, the expression is:
[0088]
[0089] in, is the improvement support rate of each scenario s, and the vector of all random variables is The vector w represents the context weights, which are equivalent to the scores of the data points in each context.
[0090] Step S36: Use Gurobi solver to solve the distributed robust optimization model and obtain the optimal ambulance dispatch plan. Gurobi is an efficient solver suitable for handling large-scale optimization problems. Specifically, if the lambda result is in the uncertain set, input y, conservative parameter e, and historical sample demand information d; model based on sample robust optimization, which includes determining decision variables, constructing e domain uncertainty set, establishing objective function, and setting constraints; call Gurobi to solve and output the optimal deployment decision xij and the minimum resource allocation cost.
[0091] If the result is in the uncertain set and the covariates are considered, the following steps are performed: input the historical sample demand D and covariate information, call the decision tree regressor to calculate the conditional mean mu and variance phi, the scenario weight w, and the upper and lower bounds of demand d_ub and d_lb; distributed robust optimization modeling, specifically: determine the decision variables, construct the scenario fuzzy set F, establish the objective function, and set constraints; call Gurobi to solve, and output the optimal allocation decision xij and the lowest resource allocation cost.
[0092] Step S37: Analyze the solution results and evaluate the effect of the vehicle allocation strategy in different scenarios to ensure that the strategy can achieve the expected effect in practical application. Figure 2 The tree structure is shown, taking four leaf nodes as an example, and the minimum sample size of each node is three.
[0093] The event is specified by the affine adaptation formula as and This means that each appeal decision y j Affine Adaptive Random Variables And in each case, the affine adaptation may be different.
[0094] Step S38: Adjust the actual operation strategy according to the model output, such as adjusting vehicle allocation, optimizing route selection, etc., to improve response speed and service quality. Adjust the model parameters according to the actual application effect feedback to improve the accuracy and adaptability of the model.
[0095] The above embodiments further illustrate the purpose, technical solutions and advantages of the present invention in detail. It should be understood that the above embodiments are only preferred implementation modes of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made to the present invention within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for scheduling medical emergency resources based on robust optimization, characterized in that: include: The current rescue information is obtained, and a ground cost matrix is constructed based on the rescue information; Determine whether rescue resources are needed based on the current rescue information. If rescue resources are needed, establish the optimal transmission model for the resource allocation problem based on the ground cost matrix and the optimal transmission theory. If it is uncertain whether rescue resources are needed, construct an uncertainty set based on the robust optimization theory, and establish a robust optimization model for the transportation problem based on the uncertainty set. Solve the optimal transmission model for the resource allocation problem and the robust optimization model for the transportation problem respectively to obtain the resource allocation matrix and the optimal decision. Schedule rescue resources based on the resource allocation matrix and the optimal decision.
2. According to the method for scheduling medical emergency resources based on robust optimization according to claim 1, it is characterized in that: Rescue information includes the actual distance between medical resource points and emergency demand points, traffic conditions, and resource capacity.
3. The method for scheduling medical emergency resources based on robust optimization according to claim 1, characterized in that: Establishing the optimal transmission model for the resource allocation problem includes: determining the number of rescue resources required based on the rescue information. If the supply and demand of the rescue resources are balanced, a discrete optimal transmission model based on distance is constructed; if the supply exceeds the demand, an entropy regularized optimal transmission model based on distance is constructed.
4. The method for scheduling medical emergency resources based on robust optimization according to claim 3, characterized in that: The expression of the distance-based discrete optimal transmission model is: The entropy regularized optimal transmission model based on distance is expressed as: Among them, a is the supply quantity distribution; b is the demand quantity distribution; C is the ground cost matrix, F represents the Frobenius inner product, that is, the corresponding matrix elements are multiplied and summed; γ is the optimal transportation matrix, T is the transpose; reg is the hyperparameter, Ω is the entropy regularization term, i is the row of the OT matrix, and j is the column of the OT matrix.
5. The method for scheduling medical emergency resources based on robust optimization according to claim 4, characterized in that: Solving the optimal transmission model of the resource allocation problem includes: calculating the optimal solution of the distance-based discrete optimal transmission model and the optimal solution of the distance-based entropy regularized optimal transmission model; Calculating the optimal solution of the distance-based discrete optimal transmission model includes: Step 11: Use the minimum cost method or potential method to obtain an initial feasible solution; mark each supply point and demand point, set the potential of the supply point to 0, calculate the potential of the demand point according to the minimum cost method, and determine the initial basic variables; Step 12: Calculate the test number for each non-basic variable; the specific process includes for each non-basic variable γ ij , whose test number is C ij -U i -V j , where C ij is the unit transportation cost from supply point i to demand point j, U i and V j are the potentials of supply point i and demand point j respectively; Step 13: Select the non-basic variable with the smallest negative test number as the basic variable to be transferred in; start from the basic variable to be transferred in, perform a closed loop along the transportation network to obtain the basic variables in the loop; calculate the ratio of the transportation volume of each basic variable in the loop to the negative test number of the basic variable to be transferred in, and select the basic variable corresponding to the smallest ratio as the basic variable to be transferred out; Step 14: Adjust the transport volume of the transferred basic variables and the transferred basic variables, update the transport routes and transport volumes in the network; recalculate the potential of the supply point and demand point according to the new transport plan; Step 15: Repeat steps 12 to 14 until the optimal solution is found; Step 16: Calculate the distance-based entropy regularized optimal transmission model according to the optimal solution output OT matrix. The optimal solution of the model includes: Step 21: Parameter input, including the cost matrix C, supply quantity distribution a, demand quantity distribution b, regularization hyperparameter reg and convergence parameter itermax; Step 22: Initialize the parameters, u (0) =1, Step 23: Set the number of loop iterations, where i is the current number of iterations; Step 24: Update parameter v (i) =K T u (i-1) / b;u (i) =Kv (i) / a; Step 25: Repeat steps 23 to 24 until the convergence parameter itermax is reached, and then stop iterating; Step 26: Output OT matrix γ = diag(u (itermax) )Kdiag(v (itermax) ).
6. A method for scheduling medical emergency resources based on robust optimization according to claim 1, characterized in that: Uncertain sets include box-type uncertainty sets, domain uncertainty sets, and scenario uncertainty sets.
7. A method for scheduling medical emergency resources based on robust optimization according to claim 1, characterized in that: The robust optimization models for transportation problems include: the robust optimization model for box type uncertain sets, the sample robust optimization model for domain uncertain sets, the distributed robust optimization model for scene uncertain sets, and the distributed robust optimization model for scene fuzzy sets considering covariates.
8. The method for scheduling medical emergency resources based on robust optimization according to claim 7, characterized in that: The robust optimization model expression of the box-type uncertain set is: The sample robust optimization model expression of the domain uncertainty set is: The distributed robust optimization model expression of the scene uncertainty set is: The distributed robust optimization model of the scene fuzzy set considering covariates is expressed as: Among them, y is the demand realization, x is the decision variable representation matrix, and d is the demand quantity matrix. is the uncertainty set, [I] is the vehicle supply point, [J] is the vehicle demand point, c ij is the unit cost of scheduling, r j is the unit cost of the demand node, x ij represents the number of vehicles assigned from supply point i to demand point j, y j is the demand realization affected by the demand quantity d, d j is the demand of the jth demand point, is a linear decision rule, q i is the maximum number of vehicles supplied; S is the historical data sample collectively referred to as the scene, [S] is the set of samples, a s The worst-case recovery cost for each scenario, y sj Waiting for the decision, is the uncertainty set of the ε neighborhood; is the expected uncertainty set under p distribution, is the uncertain set of events, is the vector of all random variables; for y j The affine adaptation rule of y j According to the scene and events Select different linear functions for adjustment, where For the scene, for events; Based on the above uncertainty distribution, is the set of all uncertain distributions, is a J-dimensional space, is the uncertain random variable of the vehicle, is an auxiliary random variable.
Citation Information
Patent Citations
Emergency resource mobilization and transport dispatching plan generation method based on robust optimization
CN107742182A
High-efficiency full-discrete optimal transmission method
CN108022005A
Robust optimization model solving method for site selection problem
CN108665089A
Transmission chain unsupervised domain adaptive fault diagnosis method based on optimal transportation
CN112232252A
Unbalanced data classification method based on regularization optimal transmission theory
CN113420820A
Cited By
Face-time and urgent-time dual-purpose logistics network design method and system considering demand robust matching
CN120494250A
