Urban closed-loop supply chain optimization method considering uncertainty

Abstract

The invention discloses an urban closed-loop supply chain optimization method considering uncertainty, and particularly relates to the technical field of supply chain optimization. Through extraction and analysis of historical supply chain data, a core distribution node set, a returned goods recovery node set and a resource transfer node set are constructed, and a path uncertainty disturbance model is established based on a cooperative relationship among core nodes. And in combination with distribution area distribution characteristics and node load distribution characteristics, dynamically dividing distribution areas and generating an optimized path set. According to the method, a comprehensive optimization model is constructed, real-time supply chain operation data is input into the model for optimization, and an optimization decision result set is output, so that scheduling optimization, resource allocation and path planning adjustment of supply chain nodes are realized, and the problem of uncertainty in supply chain operation is effectively solved; the operation efficiency, the response capability and the resource utilization rate of the urban closed-loop supply chain are improved, and the method is suitable for dynamic optimization management in a complex supply chain environment.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain optimization, and more specifically, to an optimization method for urban closed-loop supply chains considering uncertainty. Background Art

[0002] With the acceleration of urbanization and the intensification of resource and environmental pressures, urban supply chain systems are gradually evolving towards a closed-loop supply chain model, that is, by integrating product distribution, recycling, and reuse into a unified system to achieve efficient recycling of resources. However, there are various uncertain factors in the operation of urban supply chains, such as demand fluctuations, transportation delays, and route interruptions, which pose significant challenges to the reliability and efficiency of the supply chain. In addition, traditional supply chain optimization methods often rely on fixed routes and static planning, making it difficult to adapt to the complex and changing urban logistics environment, especially in the face of multi-node collaboration and dynamic load distribution requirements, where efficiency and accuracy are insufficient.

[0003] To address the above problems, a technical solution is provided. Summary of the Invention

[0004] To overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an optimization method for urban closed-loop supply chains considering uncertainty to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solution:

[0006] An optimization method for urban closed-loop supply chains considering uncertainty, comprising the following steps:

[0007] Extract the core distribution node set, return and recycling node set, and resource transfer node set respectively according to historical supply chain data;

[0008] Establish a path uncertainty perturbation model according to the collaboration relationship between the core distribution node set and the return and recycling node set;

[0009] Dynamically divide according to the core distribution node set based on the distribution characteristics of the distribution area, and output the distribution area data set;

[0010] Combine with the resource transfer node set, and generate an optimized path set within the region based on the node load distribution characteristics;

[0011] Construct an integrated optimization model for urban closed-loop supply chains based on the path uncertainty perturbation model, the distribution area data set, and the optimized path set within the region;

[0012] Input the real-time supply chain operation data into the integrated optimization model for urban closed-loop supply chains for real-time optimization, and output the optimized decision result set;

[0013] According to the optimized decision result set, adjust the scheduling plan, resource allocation, and path planning of the supply chain nodes.

[0014] In a preferred embodiment, according to the historical supply chain data, respectively extract the core distribution node set, return and recycling node set, and resource transfer node set, specifically:

[0015] According to the distribution flow characteristics of the nodes, screen out the nodes that meet the core distribution requirements and generate the core distribution node set;

[0016] According to the return and recycling flow characteristics of the nodes, screen out the nodes with high recycling efficiency and generate the return and recycling node set;

[0017] According to the goods flow transfer efficiency of the nodes, screen out the nodes that meet the resource allocation requirements and generate the resource transfer node set.

[0018] In a preferred embodiment, according to the collaborative relationship between the core distribution node set and the return and recycling node set, establish a path uncertainty perturbation model, specifically:

[0019] Obtain the historical distribution data of each node in the core distribution node set, and count the path load fluctuations caused by urban renewal;

[0020] Obtain the historical recycling data of each node in the return and recycling node set, and count the return path load fluctuations;

[0021] According to the dynamic interaction relationship between the distribution path and the return path, generate a path uncertainty perturbation factor set;

[0022] Combining the path load fluctuations caused by urban renewal, the return path load fluctuations, and the path uncertainty perturbation factor set, establish a path uncertainty perturbation model.

[0023] In a preferred embodiment, according to the core distribution node set, perform dynamic division based on the distribution characteristics of the distribution area, and output the distribution area data set, specifically:

[0024] According to the geographical distribution of each node in the core distribution node set, delimit the initial distribution area;

[0025] Based on the historical flow distribution data within the initial distribution area, adjust the distribution area boundary, optimize the node coverage range, and output the distribution area data set.

[0026] In a preferred embodiment, in combination with the resource transfer node set, based on the node load distribution characteristics, generate an optimized path set within the region, specifically:

[0027] Obtain the historical load data of each node in the resource transfer node set, and statistically analyze the load distribution characteristics of each node;

[0028] Optimize the transportation route planning within the region according to the cargo flow and path costs between resource transfer nodes;

[0029] Output the optimized path set within the region that meets the maximization of resource transfer efficiency.

[0030] In a preferred embodiment, based on the path uncertainty perturbation model, the distribution area data set, and the optimized path set within the region, construct an integrated optimization model for the urban closed-loop supply chain, specifically:

[0031] Use the path uncertainty perturbation model as the input source for dynamically adjusting parameters to construct a multi-objective optimization function;

[0032] Use the distribution area data set and the optimized path set within the region as optimization constraint conditions to generate optimized variable constraint rules;

[0033] Based on the optimization function and the constraint rules, establish an integrated optimization model for the urban closed-loop supply chain.

[0034] In a preferred embodiment, input the real-time supply chain operation data into the integrated optimization model for the urban closed-loop supply chain for real-time optimization, and output the optimized decision result set, specifically:

[0035] Obtain the real-time operation data of the supply chain, including the load of distribution nodes, the flow of recycling nodes, and the scheduling status of transfer nodes;

[0036] Match the real-time operation data of the supply chain with the historical decision rules in the integrated optimization model;

[0037] Generate an optimized decision result set according to the matching results.

[0038] The technical effects and advantages of an optimization method for an urban closed-loop supply chain considering uncertainty according to the present invention:

[0039] By extracting the core distribution node set, return and recycling node set, and resource transfer node set, comprehensively analyze the key structure of the supply chain operation, laying a data foundation for supply chain optimization; based on the collaborative relationship between the core distribution nodes and return and recycling nodes, establish a path uncertainty perturbation model to effectively quantify the uncertainty impact in the supply chain operation, improving the adaptability and reliability of the path uncertainty perturbation model; by dynamically dividing the distribution area and generating an optimized path set in combination with the node load distribution characteristics, realize the intelligent planning of the distribution path, improving the rationality of resource allocation and regional logistics efficiency; based on the constructed comprehensive optimization model, be able to dynamically integrate real-time supply chain operation data, conduct real-time optimization and adjustment for uncertainties, ensuring the flexibility of the supply chain operation; the output optimized decision result set can achieve comprehensive optimization of node scheduling, resource allocation, and path planning, improving the operation efficiency, response ability, and resource utilization rate of the urban closed-loop supply chain. Fully consider the complexity and uncertainty in the supply chain operation, be able to meet the logistics needs of high-efficiency, green, and sustainable development in the urban environment, and be applicable to dynamic optimization management in complex supply chain environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of an optimization method for an urban closed-loop supply chain considering uncertainties according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0042] Embodiment

[0043] Figure 1 An optimization method for an urban closed-loop supply chain considering uncertainties according to the present invention is given, which includes the following steps:

[0044] According to historical supply chain data, extract the core distribution node set, return and recycling node set, and resource transfer node set respectively;

[0045] According to the collaborative relationship between the core distribution node set and the return and recycling node set, establish a path uncertainty perturbation model;

[0046] According to the core distribution node set, dynamically divide it according to the distribution characteristics of the distribution area, and output the distribution area data set;

[0047] Combine with the resource transfer node set, and generate an optimized path set within the area based on the node load distribution characteristics;

[0048] Based on the path uncertainty perturbation model, the distribution area dataset, and the optimized path set within the area, a comprehensive optimization model for the urban closed-loop supply chain is constructed;

[0049] Input the real-time supply chain operation data into the comprehensive optimization model of the urban closed-loop supply chain for real-time optimization, and output the optimized decision result set;

[0050] According to the optimized decision result set, adjust the scheduling plan, resource allocation, and path planning of the supply chain nodes.

[0051] Specifically, according to the historical supply chain data, respectively extract the core distribution node set, the return and recycling node set, and the resource transfer node set, including:

[0052] According to the distribution flow characteristics of the nodes, screen out the nodes that meet the core distribution requirements and generate the core distribution node set; specifically, a node refers to an entity in the supply chain network that may undertake distribution, recycling, or transfer functions; for example, in practical applications, a logistics center, a warehouse, or an e-commerce sorting center, etc. can all be regarded as a node; the distribution flow characteristics usually include the average shipment volume, peak shipment volume, distribution timeliness, etc. of the node within a certain time range; meeting the core distribution requirements means that in historical data, some nodes continuously undertake large-scale distribution tasks and can maintain a high fulfillment rate or response speed during demand fluctuations; for example: a warehousing center with a daily average shipment volume much higher than other warehouses; or a node that can still deliver goods on time during peak periods and has a high inventory turnover efficiency;

[0053] According to the return and recycling flow characteristics of the nodes, screen out the nodes with high recycling efficiency and generate the return and recycling node set; specifically, the return and recycling flow characteristics often refer to the ability and historical data performance of a node in recycling and return processing, including return processing volume, recycling processing efficiency, repackaging or reuse ability, etc.; high recycling efficiency means that the node can quickly sort, detect, or remanufacture the returned products, environmentally process or reuse the resources of the products that are no longer suitable for secondary sales, and perform well in terms of overall operating costs, timeliness, etc.

[0054] According to the goods flow transfer efficiency of the nodes, screen out the nodes that meet the resource allocation requirements and generate the resource transfer node set; specifically, the goods flow transfer efficiency refers to the key indicators such as the speed and accuracy of a node in allocating and transferring goods when acting as a transfer station, including loading and unloading efficiency, site throughput capacity, error rate, etc.; meeting the resource allocation requirements means that the node has a high connection efficiency and a low delay rate when integrating or transferring multiple sources of goods.

[0055] Specifically, according to the collaborative relationship between the core distribution node set and the return collection node set, a path uncertainty disturbance model is established, including:

[0056] Obtain the historical delivery data of each node in the core delivery node set, and count the load fluctuations of the routes caused by urban renewal; specifically, the historical delivery data may include delivery volume, delivery route, delivery time, peak and valley delivery volume, etc.; Count the load fluctuations of the delivery routes, that is, make a quantitative analysis of the load (volume, frequency, etc.) of each delivery route in different time periods to identify whether there are large fluctuations or periodic overloads;

[0057] Obtain the historical recycling data of each node in the return recycling node set, and count the load fluctuations of the return path; specifically, the historical recycling data includes the return volume, distribution of return sources, return peak hours, processing time, etc.; Counting the load fluctuations of the return path means analyzing the trend of return volume changes at different times or activity cycles on the path from the user end or other nodes to the return recycling node; if the return fluctuations are abnormally large, such as a surge in certain seasons or after the end of an activity, it will significantly affect the processing capacity of the recycling node and the subsequent resource redistribution of the supply chain;

[0058] According to the dynamic interaction between the delivery path and the return path, a set of path uncertainty disturbance factors is generated; specifically, the dynamic interaction between the delivery path and the return path means that delivery and return may share some sections or nodes, or return and delivery may affect each other in time periods (such as sharing of resources such as vehicles and warehouses); at this time, the following situations may occur: when the delivery volume increases sharply in a certain period of time, vehicles or storage resources will be occupied, resulting in a decrease in return processing efficiency; for example, a core delivery node and a return recovery node operate in the same urban area. If the public road is severely congested in a certain period of time, the delivery and return vehicles may be delayed. This "overlapping of congestion periods" is one of the disturbance factors;

[0059] A path uncertainty disturbance model is established by combining the path load fluctuations caused by urban renewal, the return path load fluctuations and the path uncertainty disturbance factor set.

[0060] Specifically, according to the core distribution node set, dynamic division is performed based on the distribution characteristics of the distribution area, and the distribution area data set is output, including:

[0061] According to the geographical distribution of each node in the core distribution node set, delimit the initial distribution area; specifically, the geographical distribution includes longitude and latitude information where the node is located, the administrative region or urban area that can be covered, etc.; when delimiting the initial distribution area, factors such as the service radius of the core node, traffic convenience, and covered population are usually considered; it may also be initially delimited in combination with historical experience or existing administrative boundaries; for example, if the core distribution nodes are mainly distributed in the northwest of the city, then the initial distribution area can be concentrated within the scope of several administrative divisions or logistics areas in the northwest region.

[0062] Based on the historical traffic distribution data within the initial distribution area, adjust the boundary of the distribution area, optimize the node coverage range, and output the distribution area dataset; specifically, the historical traffic distribution data refers to the actual number of distribution orders, the utilization rate of transportation routes, etc. within the initially delimited area; adjusting the boundary of the distribution area means expanding or shrinking the initial area according to the actual demand concentration or dispersion situation, or re-dividing the marginal area; the purpose of optimizing the node coverage range is to enable each core distribution node to achieve relatively higher distribution efficiency and resource utilization rate within its area; outputting the distribution area dataset finally forms a set of definite or dynamic distribution area division plans; for example, if the order demand of a core node A in the northwest is significantly higher than that of surrounding nodes, the coverage radius of node A can be increased; while another node B has few orders in the northeast, a part of its area can be correspondingly reduced and assigned to node A to achieve a more balanced load.

[0063] Specifically, in combination with the resource transfer node set, based on the node load distribution characteristics, generate an optimized path set within the area, including:

[0064] Obtain the historical load data of each node in the resource transfer node set, and count the load distribution characteristics of each node; specifically, the selection criteria of the resource transfer node set have been pointed out in the previous explanation; the key is to collect the cargo flow of each transfer node in the past operation (including peak values, average values, fluctuation frequencies of inbound and outbound volumes, etc.); the load distribution characteristics may involve the change of transfer efficiency of the same node at different time periods, different seasons, and different activity periods; for example, the cargo flow of a transfer node varies greatly between morning and afternoon, or it is particularly busy in some months of the year and relatively idle in other months, which are all manifestations of the load distribution characteristics.

[0065] According to the cargo flow and path cost between resource transfer nodes, the transportation route planning in the region is optimized; specifically, the cargo flow between resource transfer nodes refers to the scale and frequency of cargo that needs to be transferred between nodes on a daily or periodic basis; the path cost includes transportation cost (fuel cost, road fee, driver fee, etc.), time cost (delay impact) and other potential risk costs; the transportation route planning in the region is optimized based on the cargo flow and path cost between resource transfer nodes, and the path plan with the lowest overall cost, the highest efficiency or a balance of multiple objectives is selected; for example, the optimal transfer path combination may be obtained through mathematical programming, linear programming, heuristic algorithms, etc.; for example, if the highway between node C and node D is frequently congested, it can be replaced by a transfer path of node C→node E→node D. Although the detour is longer, the overall timeliness and cost may be better due to the smooth flow of highways;

[0066] Output is the optimized path set within the region that maximizes the resource transfer efficiency; specifically, the optimization result is the optimized path set within the region, that is, a combination of several optimal or approximately optimal paths in the resource transfer link; maximizing resource transfer efficiency means achieving the balance point with the lowest overall transfer cost or the fastest transfer speed under restrictive conditions (such as time window, vehicle capacity, road restrictions).

[0067] Specifically, based on the path uncertainty disturbance model, the distribution area dataset and the optimized path set within the area, a comprehensive optimization model of the urban closed-loop supply chain is constructed, including:

[0068] The path uncertainty disturbance model is used as the input source of dynamic adjustment parameters to construct a multi-objective optimization function. Specifically, the path uncertainty disturbance model takes into account the load fluctuations and coordinated disturbance factors of the distribution and recovery paths. Dynamic adjustment parameters refer to the real-time or periodic parameter adjustments made by the model according to the fluctuation range of uncertain factors when doing path planning or resource allocation. The multi-objective optimization function includes multiple goals such as minimizing total cost, minimizing carbon emissions, shortest transportation time or maximizing customer satisfaction, and requires a trade-off between the goals. For example, when considering uncertain factors such as weather, congestion caused by the construction or reconstruction of urban roads, the complexity of temporary traffic organization and the uncertainty of policy adjustments may increase traffic congestion and reduce vehicle speeds.

[0069] The distribution area dataset and the optimized path set within the area are used as optimization constraints to generate optimization variable constraint rules. Specifically, the distribution area dataset specifies which geographical areas the core distribution node covers; the optimized path set within the area specifies the optimal or suboptimal path in the resource transfer link. When the distribution area dataset and the optimized path set within the area are used as optimization constraints, it means:

[0070] When tasks are assigned, they must be completed or connected within the corresponding delivery area;

[0071] The transit path selection must comply with the evaluated optimal path set to avoid repeated detours or unnecessary waste of resources;

[0072] Generate optimization variable constraint rules including upper and lower limits of traffic between nodes, vehicle capacity limits, time window constraints, path length or cost upper limits, etc.;

[0073] Based on optimization functions and constraint rules, a comprehensive optimization model of urban closed-loop supply chain is established.

[0074] Specifically, the real-time supply chain operation data is input into the comprehensive optimization model of the urban closed-loop supply chain for real-time optimization, and the optimization decision result set is output, including:

[0075] Obtain real-time operation data of the supply chain, including the load of distribution nodes, the flow of recycling nodes, and the scheduling status of transfer nodes; specifically, the real-time operation data comes from the monitoring and information systems of each node and transportation vehicle, such as WMS (warehouse management system), TMS (transportation management system) or OMS (order management system), etc.; the load of distribution nodes can refer to the current inventory, order queue, personnel and vehicle utilization; the flow of recycling nodes refers to the return volume, return frequency, recycling processing rate, etc.; the scheduling status of the transfer node includes whether the transfer station is currently idle, the size of the available yard, the number of loading and unloading platforms, the number of vehicles in operation, etc.; for example, at a certain moment, it is monitored that the delivery vehicles of node A are already full, while node B is still idle, and part of the assigned tasks can be transferred to node B for processing;

[0076] Match the real-time operation data of the supply chain with the historical decision rules in the comprehensive optimization model of the urban closed-loop supply chain; specifically, the historical decision rules in the comprehensive optimization model of the urban closed-loop supply chain are the empirical rules or parameter settings formed by the comprehensive optimization model of the urban closed-loop supply chain after analyzing massive historical data, such as when the load exceeds 80%, it is necessary to call for spare vehicles, etc.; matching is to compare the real-time data with these rules to determine whether to trigger an early warning or response strategy; when matching the corresponding situation, such as load peak or resource shortage, the comprehensive optimization model of the urban closed-loop supply chain will automatically adjust the plan; for example, if the model rules are set: when the orders of node A surge to more than 10,000 orders a day, outsourcing logistics must be started; if it is monitored that this threshold is exceeded, instructions are automatically sent to the outsourcing company or neighboring nodes are deployed for collaboration;

[0077] Based on the matching results, an optimized decision result set is generated.

[0078] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0079] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0080] Those of ordinary skill in the art can realize that the modules and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0081] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0082] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings, direct couplings, or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0083] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical module. It may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, in each embodiment of the present application, each functional module can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0085] If the described function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0086] As described above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0087] Finally: The above description is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for optimizing a closed-loop urban supply chain considering uncertainty, characterized in that: The steps include: Based on historical supply chain data, extract the core distribution node set, return and recovery node set, and resource transfer node set respectively; According to the collaborative relationship between the core distribution node set and the return collection node set, a path uncertainty disturbance model is established; Based on the core distribution node set, the distribution area is dynamically divided according to the distribution characteristics, and the distribution area data set is output; Combined with the resource transfer node set, based on the node load distribution characteristics, an optimized path set within the region is generated; Based on the path uncertainty perturbation model, the distribution area dataset and the optimized path set within the area, a comprehensive optimization model of the urban closed-loop supply chain is constructed; Input the real-time supply chain operation data into the comprehensive optimization model of the urban closed-loop supply chain, perform real-time optimization, and output the optimization decision result set; According to the optimization decision result set, the scheduling plan, resource allocation and path planning of the supply chain nodes are adjusted.

2. The method for optimizing a closed-loop urban supply chain taking uncertainty into consideration according to claim 1, characterized in that: According to the historical supply chain data, the core distribution node set, return and recovery node set and resource transfer node set are extracted respectively, specifically: According to the distribution flow characteristics of the nodes, select the nodes that meet the core distribution requirements and generate a set of core distribution nodes; According to the return and recovery flow characteristics of the nodes, the nodes with efficient recovery are screened out and a set of return and recovery nodes is generated; According to the cargo flow transfer efficiency of the nodes, the nodes that meet the resource allocation requirements are screened out and a resource transfer node set is generated.

3. The method for optimizing a closed-loop urban supply chain taking uncertainty into consideration according to claim 2 is characterized in that: According to the collaborative relationship between the core distribution node set and the return collection node set, a path uncertainty disturbance model is established, specifically: Obtain the historical distribution data of each node in the core distribution node set, and count the path load fluctuations caused by urban renewal; Obtain the historical recycling data of each node in the return recycling node set, and count the load fluctuation of the return path; According to the dynamic interaction between the delivery path and the return path, a set of path uncertainty disturbance factors is generated; A path uncertainty disturbance model is established by combining the path load fluctuations caused by urban renewal, the return path load fluctuations and the path uncertainty disturbance factor set.

4. The method for optimizing a closed-loop urban supply chain taking uncertainty into consideration according to claim 3 is characterized in that: Based on the core distribution node set, dynamic division is performed according to the distribution characteristics of the distribution area, and the distribution area data set is output, specifically: Determine the initial delivery area based on the geographical distribution of each node in the core delivery node set; Based on the historical traffic distribution data in the initial delivery area, the delivery area boundaries are adjusted, the node coverage is optimized, and the delivery area dataset is output.

5. The method for optimizing a closed-loop urban supply chain taking uncertainty into consideration according to claim 4, characterized in that: Combined with the resource transfer node set, based on the node load distribution characteristics, the optimized path set in the region is generated, specifically: Obtain the historical load data of each node in the resource transfer node set and count the load distribution characteristics of each node; Optimize transportation route planning within the region based on cargo flow and path costs between resource transfer nodes; Output the optimized path set within the region that maximizes resource transfer efficiency.

6. The method for optimizing a closed-loop urban supply chain taking uncertainty into consideration according to claim 5, characterized in that: Based on the path uncertainty perturbation model, the distribution area dataset and the optimized path set within the area, a comprehensive optimization model of the urban closed-loop supply chain is constructed. Specifically: The path uncertainty disturbance model is used as the input source of dynamic adjustment parameters to construct a multi-objective optimization function; The distribution area data set and the optimized path set within the area are used as optimization constraints to generate optimization variable constraint rules; Based on optimization functions and constraint rules, a comprehensive optimization model of urban closed-loop supply chain is established.

7. The method for optimizing a closed-loop urban supply chain taking uncertainty into consideration according to claim 6, characterized in that: The real-time supply chain operation data is input into the comprehensive optimization model of the urban closed-loop supply chain for real-time optimization, and the optimization decision result set is output, specifically: Obtain real-time operation data of the supply chain, including distribution node load, recycling node flow, and transfer node scheduling status; Matching real-time operational data of the supply chain with historical decision rules in the integrated optimization model; Based on the matching results, an optimized decision result set is generated.

Images