Logistics sorting method fusing geographic map network under actual sorting constraint

Abstract

The invention discloses a logistics sorting method fusing a geographic map network under actual sorting constraints, and the method comprises the steps: S1, defining a distance function between package flow directions, and carrying out the modeling of the placement constraints of adjacent grids; s2, defining a peak productivity index and an average productivity index, and constructing a target function for maximizing the sorting productivity; s3, defining a maximum capacity index function under the actual package constraint; s4, based on a digital twin system, performing a simulation test which is the same as a real sorting environment to obtain a peak productivity index and an average productivity index of the whole shift; and S5, on the basis of a Monte Carlo tree search method, constructing a parcel geographic map network, limiting each action space in an effective parcel flow direction range selected by the geographic map network, and performing parcel selection completely conforming to actual parcel constraints. According to the method, a geographic map network structure between parcels is constructed, and a Monte Carlo tree search framework is embedded, so that an optimal sorting plan meeting a reasonable placement strategy of adjacent grids under the target of capacity maximization is obtained.

Description

Technical Field

[0001] The present invention relates to the field of logistics sorting, and in particular to a logistics sorting method integrating a geographic map network under actual sorting constraints. Background Art

[0002] In the small-item sorting scenario at the logistics transfer station, the core of the sorting optimization strategy is to build a dynamic mapping relationship between the package flow direction and the grid (i.e., the sorting plan) to maximize the sorting capacity index. However, the practical application of this field faces multiple technical bottlenecks: First, due to differences in physical layout and operating scene characteristics, the transfer station has different placement constraints on the geographical relationship of the package flow direction mapped by adjacent grids, which makes it difficult for the traditional standardized sorting model to adapt across scenarios; secondly, the existing optimization algorithms mostly focus on the design of a single capacity objective function, and do not incorporate spatial constraints into the systematic modeling framework. In practice, they need to rely on manual experience for local adjustments, which is easy to fall into suboptimal solutions and lack global strategy stability; more importantly, in the complex optimization problem of simultaneously satisfying capacity maximization and multi-dimensional spatial constraints, the current academic community has not yet established a complete theoretical system, and related research is still in the exploratory stage. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a logistics sorting method that integrates a geographic map network under actual sorting constraints. By constructing a geographic map network structure between packages and embedding it into a Monte Carlo tree search framework, it is possible to effectively search for the optimal sorting plan that meets the reasonable placement strategy of adjacent grids under the goal of maximizing production capacity.

[0004] The object of the present invention is achieved through the following technical solution: a logistics sorting method integrating a geographic map network under actual sorting constraints, comprising the following steps: S1. Define the distance function between two package flows and model the placement constraints of adjacent grids; S2. For input sorting plan , based on the number of packages sorted per minute, define the peak capacity indicator and average capacity index , construct the objective function of maximizing sorting capacity; S3. Based on the defined maximum sorting capacity objective function and the constraints of adjacent grid placement, define the maximum capacity index function under the actual package constraints; S4. Based on the digital twin system, sorting plan Conduct simulation tests that are exactly the same as the actual sorting environment to obtain peak capacity indicators for the entire shift And the average capacity index ; S5. Based on the Monte Carlo tree search method, a package geographic map network is constructed to restrict each action space to the effective package flow range selected by the geographic map network, effectively performing package selection that fully complies with the actual package constraints.

[0005] The beneficial effects of the present invention are as follows: the present invention conducts in-depth modeling of the geographical relationship between packages mapped by adjacent grids in a logistics transfer yard, integrates the geographical relationship into the sorting optimization problem, and constructs a multi-objective sorting optimization model; based on this model, by constructing a geographical graph network structure between packages and embedding it into a Monte Carlo tree search framework, it is possible to effectively search for the optimal sorting plan that satisfies the reasonable placement strategy of adjacent grids under the goal of maximizing production capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0007] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0008] like Figure 1 As shown, a logistics sorting method integrating a geographic graph network under actual sorting constraints comprises the following steps: S1. Define the distance function between two package flows and model the placement constraints of adjacent grids; In the actual sorting process of the logistics transfer station, the sorting machine relies on the conveyor belt roller to throw the parcel from the sorting machine into the corresponding sorting grid. However, due to the differences in friction and inertia between different cargo packaging and types, some parcels may not fall accurately into the predetermined grid, but mistakenly enter the adjacent grid. Usually, these missorted parcels are not discovered until they are mistakenly transported to the next transfer station, which leads to significant additional transportation costs and logistics time loss. In order to reduce the additional transportation costs and time delays caused by correcting missorting, the transfer station usually restricts the parcel flow in adjacent grids during actual sorting, that is, it requires that the parcels placed in adjacent grids be as close as possible in the destination city. Specifically, the priority of proximity is as follows: 1. The destination city is in the same province; 2. The destination city is in an adjacent province; 3. The destination city is in a non-adjacent province.

[0009] Under this constraint, we first model the constraint: First, the slot of the sorting machine is defined as , is the total number of sorting machine slots. The mapped package flow is defined as For different sorting areas in the sorter, we define ,in, Belong to two different sorting areas. For the parcel flow directions i and o, we define the distance function between the two flow directions as : in, is the province between package flows i and o. Under the defined distance function, we model the adjacent grid placement constraints as: in, and Number the first and last slot in each sorting area.

[0010] S2. For input sorting plan , based on the number of packages sorted per minute, define the peak capacity indicator and average capacity index , construct the objective function of maximizing sorting capacity; Considering the sorting plan entered within the parcel sorting shift , based on the number of parcels sorted per minute, we define two capacity indicators: peak capacity indicator , which measures the maximum sorting capacity during the entire sorting shift; average capacity index , which measures the average sorting capacity in the entire sorting shift. Under the two capacity indicators defined, the objective function of maximizing the sorting capacity is defined as the weighted maximum of the two capacity indicators: in, and is the weighted coefficient, and each transfer station assigns corresponding priorities to the peak capacity and average capacity.

[0011] S3. Based on the defined maximum sorting capacity objective function and the constraints of adjacent grid placement, define the maximum capacity index function under the actual package constraints; Based on the defined objective function of maximizing sorting capacity and the constraint of placing adjacent grids, we add the constraint of placing adjacent grids as a soft constraint (taking into account the situation that in actual sorting, there is a situation where a single package flow is far away from other package flows, such as packages sent to Urumqi are not adjacent to other flows) to the objective function. The maximum capacity index function defined under the actual package constraint is: Among them, the weight For the balance coefficient, each transfer station assigns corresponding priorities to maximize production capacity and the emphasis on adjacent grid constraints.

[0012] S4. Based on the digital twin system, sorting plan Conduct simulation tests that are exactly the same as the actual sorting environment to obtain peak capacity indicators for the entire shift And the average capacity index ; In the process of solving the maximum capacity index function under the actual package constraints, considering that the maximum capacity index has great deployment test costs and personnel scheduling difficulties in field tests, we use the established digital twin system to optimize the sorting plan. Conduct simulation tests that are exactly the same as the actual sorting environment to obtain peak capacity indicators for the entire shift And the average capacity index .

[0013] S5. Based on the Monte Carlo tree search method, a package geographic map network is constructed to restrict each action space to the effective package flow range selected by the geographic map network, effectively performing package selection that fully complies with the actual package constraints.

[0014] However, considering that the existing algorithms (dynamic programming, genetic algorithm, simulated annealing algorithm, reinforcement learning, etc.) cannot effectively avoid exploring allocations that do not meet the actual package constraints in the process of solving the maximum capacity index function under the actual package constraints, it leads to great difficulties in solving efficiency and obtaining effective solutions. Therefore, we build a package geographic graph network based on the Monte Carlo tree search method, restrict each action space to the effective package flow range selected by the geographic graph network, and effectively select packages that fully meet the actual package constraints. The specific implementation is as follows: First, we construct a parcel geographic graph network. For the parcel flow within each sorting shift, we construct a graph network as , in The set of vertices representing the flow of all packages, Represents the set of edges connecting all packages flowing to vertices. For each package flowing to vertex Contains package flow Flow to cities information , timeliness information , and the proportion of sorting shifts , that is Based on the constructed parcel geographic graph network, we design the state-action set ,state Represents the parcel flow direction and action corresponding to the current logistics sorting grid Represents the flow of packages allowed to be placed at the next slot, where the action The action space of is constrained by the constructed package geographic graph network, that is, only the package flow vertices that are legally connected under the package flow adjacent constraints are allowed to be selected, so that in each state Select the action It fully complies with the actual wrapping constraints. Under this state-action set definition, we construct the Monte Carlo tree node: in is the evaluation value and number of evaluations of the node in the Monte Carlo tree search tree for the capacity. is the reward value and number of selections under the expansion strategy of this node in the Monte Carlo tree search tree, is the weighted value mean of the node: Unlike the traditional Monte Carlo tree search tree, the state transition no longer depends on the pre-defined similarity probability matrix, because the similarity probability matrix will still lead to the selection of package flows that do not meet the actual package constraints, and if the probability threshold is set to perform action shielding, it is also impossible to accurately quantify the similarity probability value threshold between each package flow under the actual package constraints according to different logistics special fields. Considering the universal setting of the algorithm, the present invention strictly uses the geographic map network as the action space for action selection. On this basis, the expansion of the Monte Carlo tree still expands the nodes of the Monte Carlo tree according to the process of selection, expansion, evaluation, and backtracking: Selection steps: At the root node, explore the child node information and select the current optimal child node according to the polynomial confidence selection rule. The strategy is: in, The coefficient is the coefficient for balancing exploration and utilization of existing high-quality nodes. is the sum of the exploration times of the parent nodes of the node. Different from the traditional Monte Carlo tree search, considering that the similarity probability matrix is ​​no longer used, this selection strategy uses the classic UCT algorithm to ensure that each node is explored once before further selection.

[0015] Expansion steps: Directly use the constructed parcel geographic graph network to expand the Monte Carlo tree search: In the expansion phase of the Monte Carlo tree search, the specified number of child nodes to be selected for each expansion is first determined. According to the constructed parcel geographic graph network, the specified number of expandable nodes are then selected as the expansion child nodes of the current node in the order of distance function values ​​from small to large. The specified number of sub-nodes selected for each expansion is set by the user and should be much smaller than the number of expandable nodes; for example, 5 or 10; Specifically, the distance function value between the current node and all expandable nodes is first calculated; then a specified number of expandable nodes are selected in the order of distance function value from small to large. For example, the flow direction nodes in the same province are first selected, that is, the distance function value =0, and then select the adjacent province flow node, i.e. the distance function value =1 expandable node, and then select the distance function value =2 expandable nodes until the number of selected expandable nodes equals the specified number; In the traditional Monte Carlo tree search, all expandable nodes will be selected during package expansion. Then, in this application, in the geographic map network architecture, the child nodes of other provinces are directly excluded through the distance function of the package map network, avoiding the waste of computing resources caused by the expansion simulation of useless nodes; the constructed geographic map network effectively prunes the Monte Carlo tree for invalid actions, so that all computing resources are concentrated on high-quality, constrained nodes, effectively accelerating the convergence performance of the Monte Carlo tree search.

[0016] Evaluation steps: In the process of Monte Carlo tree expansion, starting from the leaf node and continuing until the Monte Carlo tree is fully expanded, the reward value of the current branch selection is obtained according to the parcel slot allocation of the current branch and the reward function. The reward value is completely the weighted sum of the two capacity indicators returned by the established digital twin system: , and assign the weighted sum to the reward value under the expansion strategy of the node in the Monte Carlo tree search tree, that is, .

[0017] Backtracking steps: After the Monte Carlo tree is fully expanded, the number of selections is updated upward from the current leaf node of the Monte Carlo tree. And the corresponding node evaluation value And the reward value under the expansion strategy , through the backtracking process, the weighted value mean of the node can be calculated After multiple rounds of Monte Carlo tree expansion exploration interactions, when all the slots have been selected in the selection stage, the expansion path under the current root node is the optimal path, that is, the optimal slot sorting strategy.

[0018] The above is a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art do not depart from the spirit and scope of the present invention, and should be within the scope of protection of the claims attached to the present invention.

Claims

1. A logistics sorting method integrating geographic graph network under actual sorting constraints, characterized by: The following steps are involved: S1. Define the distance function between two package flows and model the placement constraints of adjacent grids; S2. For input sorting plan , based on the number of packages sorted per minute, define the peak capacity indicator and average capacity index , construct the objective function of maximizing sorting capacity; S3. Based on the defined maximum sorting capacity objective function and the constraints of adjacent grid placement, define the maximum capacity index function under the actual package constraints; S4. Based on the digital twin system, sorting plan Conduct simulation tests that are exactly the same as the actual sorting environment to obtain peak capacity indicators for the entire shift And the average capacity index ; S5. Based on the Monte Carlo tree search method, a package geographic map network is constructed to restrict each action space to the effective package flow range selected by the geographic map network, effectively performing package selection that fully complies with the actual package constraints.

2. According to claim 1, a logistics sorting method integrating geographic map network under actual sorting constraints is characterized by: The step S1 comprises: Define the sorter slot as , is the total number of sorting machine slots, for the slots The mapped package flow is defined as ; For different sorting areas in the sorter, it is defined as ,in, Belonging to two different sorting areas, for the parcel flow directions i and o, the distance function between the two flow directions is defined as : in, The province between which the package flows is i and o; Under the defined distance function, the adjacent grid placement constraints are modeled as: in, and Number the first and last slot in each sorting area.

3. The logistics sorting method integrating geographic map network under actual sorting constraints according to claim 2 is characterized by: The step S2 comprises: In the parcel sorting shift, for the input sorting plan , based on the number of packages sorted per minute, two capacity indicators are defined: Peak capacity index , which measures the maximum sorting capacity during the entire sorting shift; Average capacity index , which measures the sorting capacity averaged over the entire sorting shift; Under the two defined capacity indicators, the objective function of maximizing sorting capacity is defined as the weighted maximum of the two capacity indicators: ； in, , It is the weighting coefficient of the peak capacity index and the average capacity index.

4. The logistics sorting method integrating geographic map network under actual sorting constraints according to claim 3 is characterized by: The step S3 comprises: Based on the defined objective function of maximizing sorting capacity and the constraints of adjacent slots placement, the constraints of adjacent slots placement are added to the objective function as soft constraints, and the maximum capacity index function defined under the actual package constraints is: Among them, the weight For the balance coefficient, each transfer station assigns corresponding priorities to maximize production capacity and the emphasis on adjacent grid constraints.

5. The method for logistics sorting by integrating geographic map network under actual sorting constraints according to claim 1 is characterized by: The step S4 comprises: Construct a parcel geomap network: For the parcel flow in each sorting shift, the construction graph network is: , in The set of vertices representing the flow of all packages, Represents the set of edges connecting all packages flowing to the vertex; For each package flowing to a vertex Contains package flow Flow to cities information , timeliness information , and the proportion of sorting shifts , that is ; Design state-action sets based on the constructed parcel geographic graph network ,state Represents the parcel flow direction and action corresponding to the current logistics sorting grid Represents the flow of packages allowed to be placed at the next slot, where the action The action space of is constrained by the constructed package geographic graph network, that is, only the package flow vertices that are legally connected under the package flow adjacent constraints are allowed to be selected, so that in each state Select the action Full compliance with actual package constraints; Under this state-action set definition, construct a Monte Carlo tree node: in is the evaluation value and number of evaluations of the node in the Monte Carlo tree search tree for the capacity. is the reward value and number of selections under the expansion strategy of this node in the Monte Carlo tree search tree, is the weighted mean value of the node: in, is the weight coefficient of the node; Use geographic graph networks as action spaces for action selection; On this basis, the expansion of the Monte Carlo tree still follows the process of selection, expansion, evaluation, and backtracking to expand the nodes of the Monte Carlo tree: Selection steps: At the root node, explore the child node information and select the current optimal child node according to the polynomial confidence selection rule. The strategy is: in, The coefficient is the coefficient for balancing exploration and utilization of existing high-quality nodes. is the sum of the exploration times of the parent nodes of the node; the strategy uses the classic UCT algorithm to ensure that each node is explored once before further selection; Expansion steps: Directly use the constructed parcel geographic graph network to expand the Monte Carlo tree search: In the expansion phase of the Monte Carlo tree search, the specified number of child nodes to be selected for each expansion is first determined. According to the constructed parcel geographic graph network, the specified number of expandable nodes are then selected as the expansion child nodes of the current node in the order of distance function values ​​from small to large. Evaluation steps: In the process of Monte Carlo tree expansion, starting from the leaf node and continuing until the Monte Carlo tree is fully expanded, the reward value of the current branch selection is obtained according to the parcel slot allocation of the current branch and the reward function. The reward value is completely the weighted sum of the two capacity indicators returned by the established digital twin system: , and assign the weighted sum to the reward value under the expansion strategy of the node in the Monte Carlo tree search tree, that is, ; Backtracking steps: After the Monte Carlo tree is fully expanded, the number of selections is updated upward from the current leaf node of the Monte Carlo tree. And the corresponding node evaluation value And the reward value under the expansion strategy , through the backtracking process, the weighted value mean of the node is calculated : After multiple rounds of Monte Carlo tree expansion exploration interactions, when all the slots have been selected in the selection stage, the expansion path under the current root node is the optimal path, that is, the optimal slot sorting strategy.

Images