Inventory path planning method and device, electronic device and storage medium

Abstract

The present application provides an inventory path planning method and its device, electronic device and storage medium, which belong to the field of transportation optimization technology. The method comprises the following steps: performing inventory level assessment and out-of-stock level assessment according to initial inventory data, replenishment data and product demand data, respectively, to obtain intermediate inventory data and out-of-stock data, obtaining storage cost according to unit storage cost and intermediate inventory data, calculating risk data, obtaining out-of-stock cost according to unit out-of-stock cost and out-of-stock data, performing path planning on the path between the supply node and the demand node to obtain an initial transportation path, calculating the transportation cost of transporting the product according to the initial transportation path, obtaining target cost according to storage cost, out-of-stock cost and transportation cost, adjusting the initial replenishment strategy according to the target cost and risk data, obtaining target inventory planning result, adjusting the initial transportation path according to the target cost, obtaining path planning result, and improving the accuracy of inventory path planning.

Description

Technical Field

[0001] The present application relates to the field of transportation optimization technology, and in particular to an inventory path planning method and device, electronic device and storage medium. Background Art

[0002] In related technologies, the total cost is used as the objective function, and inventory and routes are planned by minimizing the objective function. However, the space for cost compression is limited, which makes this planning method by compressing costs unable to be close to the actual scenario, resulting in erroneous inventory and route planning results, and the inability to obtain the optimal inventory and route, thereby reducing the accuracy of inventory route planning. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose an inventory path planning method and its device, electronic device and storage medium, aiming to improve the accuracy of inventory path planning.

[0004] To achieve the above objectives, a first aspect of an embodiment of the present application provides an inventory path planning method, the method comprising:

[0005] Dividing a preset planning time period into a plurality of periods; the preset planning time period includes a start time;

[0006] Determine product demand data of the demand node in the period according to the preset demand set;

[0007] Acquire the initial replenishment strategy of the supply node for the demand node and the initial inventory data of the demand node at the start time;

[0008] Obtaining replenishment data of the supply node for the demand node according to the initial replenishment strategy and the initial inventory data;

[0009] Performing inventory level evaluation based on the initial inventory data, the replenishment data, and the product demand data to obtain intermediate inventory data of the demand node in the period, and performing out-of-stock level evaluation based on the initial inventory data, the replenishment data, and the product demand data to obtain out-of-stock data of the demand node in the period;

[0010] The storage cost of the demand node is obtained according to the preset unit storage cost and the intermediate inventory data, and the risk data that the intermediate inventory data is not in the preset inventory level interval is calculated; the out-of-stock cost of the demand node is obtained according to the preset unit out-of-stock cost and the out-of-stock data; the path between the supply node and the demand node is planned to obtain an initial transportation path; and the transportation cost of transporting the product according to the initial transportation path is calculated;

[0011] Obtaining a target cost according to the storage cost, the out-of-stock cost and the transportation cost;

[0012] The initial replenishment strategy is adjusted according to the target cost and the risk data to obtain a target inventory planning result, and the initial transportation path is adjusted according to the target cost to obtain a path planning result.

[0013] In some embodiments, obtaining the replenishment data of the supply node for the demand node according to the initial replenishment strategy and the initial inventory data includes:

[0014] Obtaining the maximum inventory capacity of the demand node;

[0015] Performing a supply level assessment according to the initial replenishment strategy and the maximum inventory capacity to obtain supply data for the demand node;

[0016] A replenishment level assessment is performed according to the supply data and the initial inventory data to obtain the replenishment data.

[0017] In some embodiments, the performing inventory level assessment according to the initial inventory data, the replenishment data, and the product demand data to obtain the intermediate inventory data of the demand node in the cycle, and the performing out-of-stock level assessment according to the initial inventory data, the replenishment data, and the product demand data to obtain the out-of-stock data of the demand node in the cycle include:

[0018] Perform product total quantity evaluation based on the initial inventory data and the replenishment data to obtain total product data of the demand node in the period;

[0019] Perform product surplus evaluation based on the total product data and the product demand data to obtain the intermediate inventory data;

[0020] The product out-of-stock quantity is evaluated according to the total product data and the product demand data to obtain the out-of-stock data.

[0021] In some embodiments, the preset inventory level interval includes first endpoint data and second endpoint data, the first endpoint data is less than the second endpoint data, and the calculating of the risk data that the intermediate inventory data is not within the preset inventory level interval includes:

[0022] Performing difference calculation on the intermediate inventory data and the first endpoint data to obtain first difference data; performing difference calculation on the intermediate inventory data and the second endpoint data to obtain second difference data; and obtaining the risk data according to the first difference data and the second difference data;

[0023] or,

[0024] Obtain a risk parameter, wherein the risk parameter is used to represent the risk that the product demand data is not met; perform a risk assessment based on the risk parameter, the first endpoint data, and the intermediate inventory data to obtain a first risk; perform a risk assessment based on the risk parameter, the second endpoint data, and the intermediate inventory data to obtain a second risk; and obtain the risk data based on the first risk and the second risk.

[0025] In some embodiments, performing path planning on the path between the supply node and the demand node to obtain an initial transportation path includes:

[0026] Acquire a first distance, a second distance, and a third distance, wherein the first distance is used to represent the distance between the supply node and the demand node, the second distance is used to represent the distance between the supply node and another demand node, and the third distance is used to represent the distance between the demand node and the another demand node;

[0027] Performing distance calculation according to the first distance, the second distance, and the third distance to obtain mileage saving data between the demand node and the other demand node;

[0028] Planning a path from the demand node to the other demand node according to the mileage saving data to obtain an initial path;

[0029] A route is constructed according to the initial path to obtain the initial transportation path.

[0030] In some embodiments, adjusting the initial replenishment strategy according to the target cost and the risk data to obtain a target inventory planning result, and adjusting the initial transportation path according to the target cost to obtain a path planning result include:

[0031] The initial replenishment strategy is screened according to the target cost and the preset cost threshold to obtain an intermediate replenishment strategy, and the initial transportation path is screened according to the target cost and the preset cost threshold to obtain the path planning result;

[0032] Selecting the intermediate replenishment strategy with the smallest risk data as the target replenishment strategy;

[0033] An inventory level assessment is performed according to the target replenishment strategy to obtain the target inventory planning result.

[0034] In some embodiments, the screening of the initial replenishment strategy according to the target cost and the preset cost threshold to obtain the intermediate replenishment strategy, and the screening of the initial transportation path according to the target cost and the preset cost threshold to obtain the path planning result include:

[0035] If the target cost is less than or equal to a preset cost threshold, the initial replenishment strategy is used as the first replenishment strategy, and the initial transportation path is used as the path planning result;

[0036] Perturbing the first replenishment strategy according to a preset perturbation operator to obtain a second replenishment strategy;

[0037] A neighborhood search is performed on the second replenishment strategy according to a preset neighborhood structure to obtain the intermediate replenishment strategy.

[0038] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides an inventory path planning device, the device comprising:

[0039] A division module, used to divide a preset planning time period into a plurality of periods; the preset planning time period includes a start time;

[0040] A determination module, used to determine product demand data of a demand node in the period according to a preset demand set;

[0041] An acquisition module, used to acquire the initial replenishment strategy of the supply node for the demand node and the initial inventory data of the demand node at the start time;

[0042] A first calculation module, configured to obtain replenishment data of the supply node for the demand node according to the initial replenishment strategy and the initial inventory data;

[0043] A second calculation module is used to perform inventory level evaluation based on the initial inventory data, the replenishment data and the product demand data to obtain the intermediate inventory data of the demand node in the period, and to perform out-of-stock level evaluation based on the initial inventory data, the replenishment data and the product demand data to obtain the out-of-stock data of the demand node in the period;

[0044] A third calculation module is used to obtain the storage cost of the demand node according to the preset unit storage cost and the intermediate inventory data, and calculate the risk data that the intermediate inventory data is not in the preset inventory level range; obtain the out-of-stock cost of the demand node according to the preset unit out-of-stock cost and the out-of-stock data; perform path planning on the path between the supply node and the demand node to obtain an initial transportation path; and calculate the transportation cost of transporting the product according to the initial transportation path;

[0045] a fourth calculation module, configured to obtain a target cost according to the storage cost, the out-of-stock cost and the transportation cost;

[0046] The planning module is used to adjust the initial replenishment strategy according to the target cost and the risk data to obtain a target inventory planning result, and to adjust the initial transportation path according to the target cost to obtain a path planning result.

[0047] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the inventory path planning method described in the first aspect when executing the computer program.

[0048] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the inventory path planning method described in the first aspect.

[0049] The inventory path planning method, inventory path planning device, electronic device and computer-readable storage medium proposed in the present application quantitatively describe the service level of the supply node to the demand node through risk data, adjust the initial replenishment strategy according to the target cost and risk data, and obtain the target inventory planning result. Inventory planning is carried out according to the target cost and service level. In the inventory planning process, not only the cost issue is considered, but also the service level of the supply node to the demand node is considered, so as to achieve a balance between cost and service level, make inventory planning closer to the real scene, and improve the accuracy of inventory planning. At the same time, path planning is carried out according to the target cost that has reached a balance, so as to improve the accuracy of path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of the inventory path planning method provided by an embodiment of the present application;

[0051] Figure 2 yes Figure 1 Flow chart of step S140 in FIG.

[0052] Figure 3 yes Figure 1 Flow chart of step S150 in FIG.

[0053] Figure 4 yes Figure 1 A first flow chart of step S160 in FIG. 1 ;

[0054] Figure 5 yes Figure 1 A second flow chart of step S160 in FIG. 1 ;

[0055] Figure 6 yes Figure 1 Flow chart of step S180 in FIG.

[0056] Figure 7 yes Figure 6 Flowchart of step S610 in FIG.

[0057] Figure 8 It is a structural schematic diagram of the inventory path planning device provided in an embodiment of the present application;

[0058] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0062] In related technologies, the total cost is used as the objective function, and inventory and routes are planned by minimizing the objective function. However, the space for cost compression is limited, which makes this planning method by compressing costs unable to be close to the actual scenario, resulting in erroneous inventory and route planning results, and the inability to obtain the optimal inventory and route, thereby reducing the accuracy of inventory route planning.

[0063] Based on this, the embodiments of the present application provide an inventory path planning method, an inventory path planning device, an electronic device and a computer-readable storage medium, aiming to improve the accuracy of inventory path planning.

[0064] The inventory path planning method, inventory path planning device, electronic device and computer-readable storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the inventory path planning method in the embodiments of the present application is described.

[0065] The inventory path planning method provided in the embodiment of the present application relates to the field of transportation optimization technology. The inventory path planning method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the inventory path planning method, etc., but is not limited to the above forms.

[0066] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0067] Figure 1 is an optional flow chart of the inventory path planning method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S110 to S180.

[0068] Step S110, dividing the preset planning time period into a plurality of periods; the preset planning time period includes a start time;

[0069] Step S120, determining product demand data of a demand node in a cycle according to a preset demand set;

[0070] Step S130, obtaining the initial replenishment strategy of the supply node to the demand node and the initial inventory data of the demand node at the start time;

[0071] Step S140, obtaining replenishment data of the supply node for the demand node according to the initial replenishment strategy and the initial inventory data;

[0072] Step S150, performing inventory level assessment based on the initial inventory data, replenishment data and product demand data to obtain the intermediate inventory data of the demand node in the cycle, performing out-of-stock level assessment based on the initial inventory data, replenishment data and product demand data to obtain the out-of-stock data of the demand node in the cycle;

[0073] Step S160, obtaining the storage cost of the demand node according to the preset unit storage cost and the intermediate inventory data, and calculating the risk data that the intermediate inventory data is not in the preset inventory level range; obtaining the out-of-stock cost of the demand node according to the preset unit out-of-stock cost and the out-of-stock data; performing path planning on the path between the supply node and the demand node to obtain an initial transportation path; calculating the transportation cost of transporting the product according to the initial transportation path;

[0074] Step S170, obtaining a target cost according to storage cost, out-of-stock cost and transportation cost;

[0075] Step S180, adjusting the initial replenishment strategy according to the target cost and risk data to obtain a target inventory planning result, and adjusting the initial transportation path according to the target cost to obtain a path planning result.

[0076] Steps S110 to S180 shown in the embodiment of the present application, by dividing the preset planning time period into multiple cycles, can plan the inventory of the demand node in each cycle, and plan the path from the supply node to the demand node. Since the product demand data is random and uncertain, the product demand data of the demand node in the cycle is determined according to the preset demand set, and the product demand data can be quantitatively described deterministically. Further, the target cost is obtained according to the storage cost, out-of-stock cost and transportation cost. By introducing the storage cost, out-of-stock cost and transportation cost, the solution to the inventory path planning problem is closer to the real scene. Finally, the initial replenishment strategy is adjusted according to the target cost and risk data to obtain the target inventory planning result. The service level can be quantitatively described by the risk data. The target cost and service level are used for inventory planning. In the inventory planning process, not only the cost problem is considered, but also the service level of the supply node to the demand node is considered, achieving a balance between cost and service level, and improving the accuracy of inventory planning. At the same time, path planning is performed according to the optimized target cost, which improves the accuracy of path planning.

[0077] In step S110 of some embodiments, the preset planning time period is divided into multiple cycles according to the time step, and the preset planning time period is a time range, including a start time and an end time. The preset planning time period is a collection of multiple cycles. If the preset planning time period is represented by T, the multiple cycles are represented by T={1,2,...,t,...,|Q|}, where t∈T represents the tth cycle, and |Q| is determined by the ratio of the preset planning time period to the time step.

[0078] In step S120 of some embodiments, in a multi-period random inventory routing problem within a limited planning time, a supply node is responsible for delivering products to multiple demand nodes within a preset planning time period to meet the random demand of each demand node. The supply node and each demand node belong to the same set N. If the number of supply nodes is n, then N = {0, 1, ..., i, ..., n}, 0 represents the supply node, i represents the i-th demand node, and n demand nodes constitute a set S, expressed as S = N\{0}. The supply node can be a merchant that supplies products, and the demand node can be a merchant that obtains products from the supply node and sells the products. The supply node has an unlimited number of homogeneous fleets with loading capacity restrictions. The homogeneous fleet means that the loading capacity, transportation efficiency and transportation cost of each vehicle in the fleet are roughly the same. The supply node needs to determine the number of products and delivery routes to be delivered to n demand nodes in each cycle, so that the homogeneous fleet delivers a preset number of products to the demand nodes along the delivery route. It should be noted that unlimited quantity means that the size of the fleet is not restricted and the fleet has sufficient vehicles to transport products. Loading capacity limit means that the loading capacity of the vehicle is limited and each vehicle can only carry a certain number of products. Transport efficiency refers to the vehicle's delivery speed, loading and unloading efficiency, etc.

[0079] In period t, the product demand data of each demand node is uncertain. Through distributed robust optimization, a preset demand set, namely the demand uncertainty set, is established. The product demand data of each demand node in different periods is characterized according to the demand uncertainty set, where the product demand data is used to represent the number of product demands of the user for the demand node. The specific representation of the demand uncertainty set is shown in formula (1).

[0080]

[0081] Among them, F represents the demand uncertainty set; is an integer, representing the product demand data of the demand node, and the product demand data follows the probability distribution P; ξ is the lower bound of product demand data, is the upper limit value of the product demand data, the product demand data is greater than or equal to the lower limit value or less than or equal to the upper limit value; U is the mean of the product demand data, and each demand node has a mean.

[0082] In step S130 of some embodiments, if the inventory level of the demand node in the current cycle cannot meet the demand of the next cycle, the supply node needs to replenish the demand node in the current cycle according to the initial replenishment strategy. The initial replenishment strategy is the ratio of the replenishment quantity to the maximum inventory capacity of the demand node, and its value is [0, rmax], where rmax is 1. It can be understood that when the value of the initial replenishment strategy is rmax, it means that the quantity is equal to the maximum inventory capacity, and the initial inventory data of the demand node at the start time is the number of products stored by the demand node at the start time. The initial replenishment strategy can be 0, that is, the demand node can only rely on the current inventory level to meet the product demand of the next cycle, or it can be 0.25, 0.5, 0.75 and 1.

[0083] See also Figure 2 In some embodiments, step S140 may include but is not limited to steps S210 to S230:

[0084] Step S210, obtaining the maximum inventory capacity of the demand node;

[0085] Step S220, evaluating the supply level according to the initial replenishment strategy and the maximum inventory capacity to obtain supply data of the demand node;

[0086] Step S230, evaluating the replenishment level according to the supply data and the initial inventory data to obtain replenishment data.

[0087] In step S210 of some embodiments, the supply capacity of the supply node is not limited, and it is responsible for the inventory management of n demand nodes. The warehouse of the demand node has storage capacity limitations, and the maximum inventory capacity of the demand node is obtained, where the maximum inventory capacity is used to represent the maximum number of products that the demand node can store.

[0088] In step S220 of some embodiments, the initial replenishment strategy is multiplied by the maximum inventory capacity to obtain the supply data supplied by the supply node to the demand node.

[0089] In step S230 of some embodiments, the inventory data of the demand node in the previous cycle is obtained based on the initial inventory data of the demand node at the initial time, and the inventory data of the previous cycle is subtracted from the supply data to obtain the replenishment data of the demand node in the current cycle. The replenishment data is used to represent the product replenishment quantity received by the demand node from the supply node in the current cycle. The calculation method of the replenishment data is shown in formula (2).

[0090]

[0091] Among them, r is the initial replenishment strategy; d it [r] represents the replenishment data of demand node i in period t when the initial replenishment strategy is r; Ci is the maximum inventory capacity of demand node i; is the inventory data of demand node i at the beginning of period t, which is equal to the inventory data of demand node i at the end of the previous period t-1.

[0092] It should be noted that inventory data is divided into inventory data at the beginning of a cycle and inventory data at the end of a cycle. The inventory data at the beginning of the current cycle is equal to the inventory data at the end of the previous cycle. The inventory data at the end of the cycle is the inventory level after the supply node transports the product to the demand node and the demand node sells the product. The inventory data of the cycle in the embodiment of the present application refers to the inventory data at the end of the cycle.

[0093] Through the above steps S210 to S230, the replenishment data of each cycle of the demand node under the initial replenishment strategy can be obtained, so as to perform inventory planning or route planning according to the replenishment data.

[0094] See also Figure 3 In some embodiments, step S150 may include but is not limited to steps S310 to S330:

[0095] Step S310, evaluating the total product quantity based on the initial inventory data and replenishment data, and obtaining the total product data of the demand node in the cycle;

[0096] Step S320, evaluating product surplus according to total product data and product demand data to obtain intermediate inventory data;

[0097] Step S330, evaluating the product out-of-stock quantity according to the total product data and the product demand data to obtain out-of-stock data.

[0098] In step S310 of some embodiments, according to the inventory data I of the demand node i in the previous cycle t-1, i,t-1 , replenishment data d in the current cycle t it and product demand data in the current cycle t Evaluate the inventory level and obtain the intermediate inventory data I of the demand node in the current cycle t i,t , the calculation method of intermediate inventory data is shown in formula (3).

[0099]

[0100] The previous cycle of the previous cycle is cycle t-2. The inventory data of the previous cycle t-1 is obtained based on the inventory data of cycle t-2, the replenishment data of the previous cycle t-1, and the product demand data of the previous cycle t-1. The intermediate inventory data is obtained by iterating the inventory data of the previous cycle layer by layer. The calculation method of the intermediate inventory data is shown in formula (4).

[0101]

[0102] Among them, I i0 is the initial inventory data of demand node i at the initial time; s represents cycle s, the sth cycle; d is is the replenishment data of demand node i in period s; is the product demand data of demand node i in period s.

[0103] Specifically, the replenishment data of each cycle of the demand node from cycle 1 to the current cycle are summed to obtain the cumulative replenishment data. The initial inventory data and the cumulative replenishment data are summed to evaluate the total number of products in the demand node warehouse to obtain the total product data of the demand node i, that is, the total product data is

[0104] In step S320 of some embodiments, the inventory of the demand node will be consumed due to user demand. In order to obtain the actual inventory of the demand node, the total product data is subtracted from the product demand data of each cycle from cycle 1 to the current cycle to obtain the intermediate inventory data of the demand node i: The intermediate inventory data is used to represent the actual inventory level of demand node i in the current period t. Since the intermediate inventory data is a non-negative integer, the intermediate inventory data of demand node i is It can be understood that the intermediate inventory data of demand node i in period t is the initial inventory data of demand node i at the initial time plus the difference in the cumulative number of inbound and outbound products, where the difference in the cumulative number of inbound and outbound products is the difference between the replenishment data and the product demand data accumulated from period 1 to period t.

[0105] In step S330 of some embodiments, it is allowed that the demand node may be out of stock. When the product demand data of the demand node i in period t is greater than the total product data, it indicates that the demand node i is out of stock in period t. The product demand data of each period from period 1 to period t is summed to obtain the total demand data. The total product data is subtracted from the total demand data to obtain the out of stock data of the demand node i in period t: The out-of-stock data is a non-negative integer.

[0106] Through the above steps S310 to S330, the actual product quantity and the number of out-of-stock products of each demand node in each cycle can be obtained, so as to plan the inventory of the demand node in each cycle and the path from the supply node to the demand node according to the actual product quantity and the number of out-of-stock products.

[0107] See also Figure 4In some embodiments, the preset inventory level interval includes first endpoint data and second endpoint data, and step S160 may include but is not limited to step S410 or step S420:

[0108] Step S410, performing difference calculation on the intermediate inventory data and the first endpoint data to obtain first difference data; performing difference calculation on the intermediate inventory data and the second endpoint data to obtain second difference data; and obtaining risk data according to the first difference data and the second difference data;

[0109] Step S420, obtaining risk parameters, where the risk parameters are used to represent the risk that product demand data is not met; performing risk assessment based on the risk parameters, the first endpoint data, and the intermediate inventory data to obtain a first risk; performing risk assessment based on the risk parameters, the second endpoint data, and the intermediate inventory data to obtain a second risk; and obtaining risk data based on the first risk and the second risk.

[0110] In step S410 of some embodiments, the unit storage cost is multiplied by the intermediate inventory data of a certain demand node in a certain period to obtain the storage cost of the demand node in the period, the storage cost of each period of the demand node in the preset planning time period is summed to obtain the storage cost of the demand node in the preset planning time period, and the storage cost of each demand node in the set S in the preset planning time period is summed to obtain the storage cost of the demand node. The calculation method of the storage cost of the demand node is shown in formula (5).

[0111]

[0112] Among them, h i is the unit storage cost. Each demand node needs to maintain a target inventory level interval in each cycle. The target interval is a preset inventory level interval, which is used to limit the intermediate inventory data of the demand node. The preset inventory level interval includes a first endpoint data and a second endpoint data. The first endpoint data is less than the second endpoint data. The first endpoint data is used to determine the lower limit value of the inventory level, and the second endpoint data is used to determine the upper limit value of the inventory level. By presetting the inventory level interval, the intermediate inventory data can be greater than or equal to the first endpoint data or less than or equal to the second endpoint data. It can be understood that if the first endpoint data is represented as τ and the second endpoint data is represented as The preset inventory level range is The intermediate inventory data of the demand node should be greater than or equal to the lower limit value τ or less than or equal to the upper limit value Right now The service level of the supply node is improved by maintaining the intermediate inventory data of n demand nodes within the preset planning time period within the preset inventory level range.

[0113] The goal of the inventory path problem in the embodiment of the present application is to maximize the service level of the supply node. The service level is added to the basic inventory path model, and a robust inventory path model with the service level as the goal is constructed. The intermediate inventory data of each cycle of the demand node has an interval requirement, and the service level is measured by the expected probability that the intermediate inventory data remains within the target interval within the preset planning time period. Maximizing the service level means minimizing the risk that the intermediate inventory data is not within the preset inventory level interval.

[0114] The same initial replenishment strategy is assigned to each cycle of each demand node i∈S, S=N\{0}, that is, each cell of the S×T matrix has the same initial replenishment strategy value, and the same initial replenishment strategy is used to replenish all demand nodes in each cycle. After determining the initial replenishment strategy, the risk value of the initial replenishment strategy violating the preset inventory level interval within the preset planning time period is calculated based on the product demand data and inventory consumption. When a certain demand node adopts the initial replenishment strategy, the risk of the intermediate inventory data of each cycle of the demand node not being in the preset inventory level interval is summed to obtain the risk data of the demand node within the preset planning time period. The risk data of all demand nodes within the preset planning time period are summed to obtain the risk data of the intermediate inventory data of the demand node not being in the preset inventory level interval under the initial supply strategy. It should be noted that the risk that the intermediate inventory data of a certain period is not within the preset inventory level range is measured in the following way: the first endpoint data is subtracted from the intermediate inventory data of a certain demand node in the current period to obtain the first difference data, the intermediate inventory data of the demand node in the current period is subtracted from the second endpoint data to obtain the second difference data, and the minimum value of the first difference data and the second difference data is used as the risk value that the intermediate inventory data of the demand node in the current period is not within the preset inventory level range.

[0115] Specifically, when demand node i adopts the initial replenishment strategy r in period t, the intermediate inventory data is obtained. If the intermediate inventory data is within the preset inventory level range, the risk is 0. If the intermediate inventory data is not within the preset inventory level range, the gap between the intermediate inventory data and the first endpoint data and the second endpoint data is calculated respectively, and the minimum gap is used as the risk value. That is, when the initial replenishment strategy is r, the risk value of demand node i violating the preset inventory level range is in is the beginning inventory level of period t+1, which is equivalent to the ending inventory level of period t, that is, the intermediate inventory data of period t; τ it is the first endpoint data of demand node i in cycle t; is the second endpoint data of demand node i in cycle t. The risk values ​​of demand node i in each cycle are added together to obtain the risk value ∑ of the demand node in the preset planning time period using the initial replenishment strategy r.t∈T risk it [r], add up the risk values ​​of all demand nodes using the initial replenishment strategy r within the preset planning time period, and get the risk data Risk[r] of the demand node under the initial replenishment strategy r as ∑ i∈S ∑ t∈T risk it [r].

[0116] Once a demand node is out of stock, it means that the opportunity to sell the product is lost, which cannot be compensated by replenishment, and a corresponding penalty cost is required. In the embodiment of the present application, the unit out-of-stock cost is multiplied by the out-of-stock data of a certain demand node in a certain period to obtain the out-of-stock cost of the demand node in the period, and the out-of-stock cost of each period of the demand node in the preset planning time period is summed to obtain the out-of-stock cost of the demand node in the preset planning time period, and the out-of-stock cost of each demand node in the set S in the preset planning time period is summed to obtain the out-of-stock cost of the demand node. The calculation method of the out-of-stock cost of the demand node is shown in formula (6).

[0117]

[0118] Among them, s i is the unit out-of-stock cost of demand node i.

[0119] In step S420 of some embodiments, a multi-period short-term risk measurement model based on a utility function is applied to measure the service level, which takes into account both the probability of violating the target and the magnitude of violating the target. Compared with the method of using a probability model to characterize the service level, it can overcome the disadvantage that the probability model cannot reflect the degree of deviation from the target. At the same time, taking the service level as the target, it solves the problem that the random demand distribution function is difficult to characterize due to insufficient data. The multi-period short-term risk measurement model concretizes the service level as:

[0120]

[0121] Among them, α it is a risk parameter, which is used to represent the risk that the product demand data of demand node i in period t is not met; μ is a concave utility function; The first risk; The second risk.

[0122] It should be noted that the available inventory of demand node i in period t is the sum of the intermediate inventory data of the demand node in period t-1 and the replenishment data of period t. The available inventory is divided by the product demand data of the demand node in period t to obtain the actual demand satisfaction rate of demand node i in period t. The probability that the actual demand satisfaction rate is less than the expected demand satisfaction rate is used as the risk parameter.

[0123] In order to reduce the amount of calculation and facilitate the solution of large-scale inventory routing problems, a piecewise linear function is used to replace the utility function μ, that is, Translate service levels into:

[0124]

[0125] Substitute formula (4) into formula (8) and decompose it to ensure that the intermediate inventory data is within the target range, and finally convert the service level into:

[0126]

[0127]

[0128]

[0129]

[0130] Among them, the probability distribution P belongs to the distribution family F, Represents the lower bound of the probability distribution.

[0131] Substituting the first risk into formula (10), we get the first probability Substituting the second risk into formula (11), we get the second probability The minimum value of the first probability and the second probability is taken as the risk data.

[0132] Through the above steps S410 to S420, risk data that the intermediate inventory data is not in the target interval can be obtained. By minimizing the risk data, the inventory path problem is solved, thereby improving the accuracy of inventory path planning.

[0133] See also Figure 5 In some embodiments, step S160 may also include but is not limited to steps S510 to S540:

[0134] Step S510, obtaining a first distance, a second distance, and a third distance, wherein the first distance is used to represent the distance between a supply node and a demand node, the second distance is used to represent the distance between a supply node and another demand node, and the third distance is used to represent the distance between a demand node and another demand node;

[0135] Step S520, performing distance calculation according to the first distance, the second distance and the third distance to obtain mileage saving data between the demand node and another demand node;

[0136] Step S530, planning a path from a demand node to another demand node according to the mileage saving data to obtain an initial path;

[0137] Step S540, constructing a route according to the initial path to obtain an initial transportation path.

[0138] In step S510 of some embodiments, a vehicle can only deliver products to multiple demand nodes along one path in the same period. The product demand data of the same demand node in the same period can be split and delivered by multiple vehicles. The embodiment of the present application adopts the CW saving algorithm to plan the path between the supply node and the demand node to determine the order in which the vehicle visits each demand node and obtain the initial transportation path. Get the first distance l between the supply node 0 and the demand node i 0i , obtain the second distance l between the supply node and another demand node j 0j , obtain the third distance l between demand node i and another demand node j ij .

[0139] In step S520 of some embodiments, the mileage saving data from demand node i to another demand node j is calculated according to the CW saving algorithm, and the calculation method of the mileage saving data is shown in formula (13).

[0140] S(i,j)=l 0i +l 0j -l ij Formula (13)

[0141] In step S530 of some embodiments, S(i,j) is sorted from large to small. The larger the mileage saving data is, the higher the priority should be given to the path from i to j to obtain the initial path.

[0142] In step S540 of some embodiments, the initial paths are connected into a complete access route to obtain an initial transportation path. The supply node distributes products to n demand nodes along the initial transportation path by vehicles with a capacity limit of V. The number of vehicles and the number of visited demand nodes are not limited. The transportation cost of transporting products according to the initial transportation path is calculated. The calculation method of the transportation cost is shown in formula (14).

[0143]

[0144] The first item of transportation cost is variable transportation cost, the second item is fixed transportation cost, and the third item is empty truck return cost. ij is the unit transportation cost from node i to node j, q ijt is the number of products transported from node i to node j in period t, f is the fixed cost of using the vehicle once, x 0it is the number of times the supply node 0 passes through the demand node j in cycle t, The cost of returning an empty vehicle per unit.

[0145] It should be noted that there are vehicle loading constraints during the transportation process. The number of products transported by the vehicle from node i to node j in period t does not exceed the vehicle load limit, that is, The product shipping quantity is an integer greater than or equal to 0, i.e. q ijt ≥0; There is also a vehicle in-and-out balance constraint in the transportation process. The number of vehicles entering and exiting each node in the same cycle is equal, that is, ∑ j∈N,j≠i x ijt =∑ j∈N,j≠i x jit , and x ijt is a positive integer; there is also a sub-ring elimination constraint in the transportation process. The replenishment data of demand node i in cycle t is equal to the product transportation quantity of the vehicle passing through (j, i) in cycle t minus the product transportation quantity of the vehicle passing through (i, j) in cycle t, that is, The total amount of products sent from the supply node in period t is equal to the total amount of replenishment data of all demand nodes in period t, that is,

[0146] Through the above steps S510 to S540, the route for the vehicle to visit each demand node can be determined, so as to deliver products to the demand node according to the route.

[0147] In step S170 of some embodiments, a total cost assessment is performed based on the storage cost, the out-of-stock cost, and the transportation cost, and the storage cost, the out-of-stock cost, and the transportation cost are summed to obtain the target cost.

[0148] See also Figure 6 In some embodiments, step S180 may include but is not limited to steps S610 to S630:

[0149] Step S610, screening the initial replenishment strategy according to the target cost and the preset cost threshold to obtain the intermediate replenishment strategy, and screening the initial transportation path according to the target cost and the preset cost threshold to obtain the path planning result;

[0150] Step S620, selecting the intermediate replenishment strategy with the smallest risk data as the target replenishment strategy;

[0151] Step S630, evaluating the inventory level according to the target replenishment strategy to obtain a target inventory planning result.

[0152] In step S610 of some embodiments, a heuristic algorithm such as a variable neighborhood search algorithm (VNS) is used for inventory path planning to solve large-scale inventory path problems, thereby improving the accuracy and efficiency of inventory path planning and enhancing the service level of supply nodes. The variable neighborhood search algorithm is divided into two steps: initial solution construction and variable neighborhood search optimization. The initial solution construction step is divided into two stages. In the first stage, risk data of different initial replenishment strategies that are not in a preset inventory level range is calculated. In the second stage, a CW saving algorithm is used to plan a specific path for each initial replenishment strategy and calculate the target cost. Since there is a budget constraint on the inventory path problem, the target cost needs to be controlled. On the premise of controlling the target cost within the budget range, replenishment decisions and path decisions are made. Using cost as a constraint to make inventory path decisions can also enable decision makers to choose inventory planning results and path planning results that are more in line with their own budgets.

[0153] In step S620 of some embodiments, in order to improve the service level of the supply node, the intermediate replenishment strategy with the smallest risk data is selected as the target replenishment strategy.

[0154] In step S630 of some embodiments, the demand node is replenished according to the target replenishment strategy to obtain replenishment data, and the inventory data of the demand node in the previous cycle and the replenishment data are added to perform inventory level evaluation to obtain the target inventory planning result.

[0155] In the above steps S610 to S630, a variable neighborhood search algorithm is used to make inventory path decisions, which can efficiently solve large-scale inventory path problems and improve the efficiency of inventory path planning.

[0156] See also Figure 7 In some embodiments, step S610 may include but is not limited to steps S710 to S730:

[0157] Step S710, if the target cost is less than or equal to the preset cost threshold, the initial replenishment strategy is used as the first replenishment strategy, and the initial transportation path is used as the path planning result;

[0158] Step S720, perturbing the first replenishment strategy according to a preset perturbation operator to obtain a second replenishment strategy;

[0159] Step S730: Perform neighborhood search on the second replenishment strategy according to the preset neighborhood structure to obtain an intermediate replenishment strategy.

[0160] In step S710 of some embodiments, if the target cost is less than or equal to the preset cost threshold, indicating that the target cost is within the decision maker's budget, the initial replenishment strategy is used as the first replenishment strategy, and the initial transportation path is used as the path planning result. If the target cost is greater than the preset cost threshold, the first stage and the second stage are repeated to readjust the initial replenishment strategy and path planning until the first replenishment strategy is obtained.

[0161] In step S720 of some embodiments, in order to ensure that an accurate replenishment strategy is obtained, the initial replenishment strategy is optimized by variable neighborhood search. Each first replenishment strategy that meets the budget constraint is added to the feasible solution set basesol, and the first replenishment strategy with the smallest risk data is added to the excellent solution set elitesol. A decimal between [0, 1] is randomly generated by a perturbation operator as an alternative replenishment strategy, and the first replenishment strategy is updated according to the alternative replenishment strategy to obtain a second replenishment strategy, and the second replenishment strategy is used as a new solution newsol.

[0162] It should be noted that the principle of perturbation is to randomly select an element from the original replenishment strategy matrix for modification. The number of modifications is determined by the preset number of perturbations. As the number of modifications increases, the number of randomly modified elements in the original replenishment strategy matrix also gradually increases, and the change in the original replenishment strategy matrix also gradually increases.

[0163] It should be further explained that, in the initial solution construction step, each cell of the S×T matrix has the same initial replenishment strategy value, and an integer is randomly generated in (0,|S|-1) as the target row row, and an integer is randomly generated in (0,|T|-1) as the target column col. According to the target row row and the target column col, the target cell basesol[row][col] is selected from multiple cells of the matrix, and the first replenishment strategy on the target cell is updated to the alternative replenishment strategy. The new solution newsol is obtained by perturbation with a preset number of perturbations.

[0164] In step S730 of some embodiments, a new solution is generated by perturbation, and a local search is performed in the neighborhood of the new solution through a neighborhood structure to obtain a local minimum value in the neighborhood of the current new solution, and then a new solution is obtained again, and the neighborhood structure is a local neighborhood search operator. Specifically, based on the perturbation, a local neighborhood search operator is used to perform a neighborhood search on the second replenishment strategy, and the second replenishment strategy with the smallest risk data is selected as the intermediate replenishment strategy, and the intermediate replenishment strategy is used as the new solution newsol.

[0165] It can be understood that the principle of local neighborhood search is to randomly determine the position of an element in the replenishment strategy matrix after the disturbance and modify the value of the element multiple times to obtain the local optimal solution in the neighborhood of the current solution.

[0166] Determine whether the number of solutions in the elitesol set is less than the quantity threshold. If the judgment result is yes, add the new solution newsol to the elitesol set. If the judgment result is no, calculate the risk data Risk(newsol) of the intermediate replenishment strategy, identify the worst solution worstsol from the elitesol set, calculate the risk data Risk(worstsol) of the worst solution worstsol, if Risk(newsol) is less than Risk(worstsol), replace the worstsol in the elitesol set with newsol, if Risk(newsol) is greater than or equal to Risk(worstsol), do not update worstsol. It can be understood that the worst solution worstsol is the solution with the largest risk data in the elitesol set.

[0167] Determine whether the risk Risk(newsol) of the new solution newsol is less than the risk Risk(basesol) of the feasible solution set basesol. If the judgment result is yes, add the new solution newsol to the feasible solution set basesol; if the judgment result is no, do not update it, and record the number of times it has not been updated until the number of times it has not been updated is greater than S×T times.

[0168] Iterate continuously, update the excellent solution set elitesol and the feasible solution set basesol, until the number of iterations reaches the maximum number of iterations, stop iteration, and take the intermediate replenishment strategy with the smallest risk data in the excellent solution set elitesol as the target replenishment strategy bestsol.

[0169] In the above steps S710 to S730, the initial replenishment strategy is optimized through perturbation and local neighborhood search, which can improve the accuracy of replenishment decisions.

[0170] See also Figure 8 The embodiment of the present application also provides an inventory path planning device, which can implement the above inventory path planning method, and the device includes:

[0171] A division module 810 is used to divide the preset planning time period into a plurality of periods; the preset planning time period includes a start time;

[0172] A determination module 820, for determining product demand data of a demand node in a period according to a preset demand set;

[0173] An acquisition module 830 is used to acquire the initial replenishment strategy of the supply node to the demand node and the initial inventory data of the demand node at the start time;

[0174] A first calculation module 840 is used to obtain replenishment data of the supply node for the demand node according to the initial replenishment strategy and the initial inventory data;

[0175] The second calculation module 850 is used to evaluate the inventory level according to the initial inventory data, the replenishment data and the product demand data to obtain the intermediate inventory data of the demand node in the cycle, and to evaluate the out-of-stock level according to the initial inventory data, the replenishment data and the product demand data to obtain the out-of-stock data of the demand node in the cycle;

[0176] The third calculation module 860 is used to obtain the storage cost of the demand node according to the preset unit storage cost and the intermediate inventory data, and calculate the risk data that the intermediate inventory data is not in the preset inventory level range; obtain the out-of-stock cost of the demand node according to the preset unit out-of-stock cost and out-of-stock data; perform path planning on the path between the supply node and the demand node to obtain an initial transportation path; calculate the transportation cost of transporting the product according to the initial transportation path;

[0177] A fourth calculation module 870, configured to obtain a target cost according to the storage cost, the shortage cost and the transportation cost;

[0178] The planning module 880 is used to adjust the initial replenishment strategy according to the target cost and risk data to obtain the target inventory planning result, and to adjust the initial transportation path according to the target cost to obtain the path planning result.

[0179] The specific implementation of the inventory path planning device is basically the same as the specific implementation of the above-mentioned inventory path planning method, and will not be repeated here.

[0180] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above inventory path planning method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0181] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0182] The processor 910 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0183] The memory 920 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 920 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 920, and the processor 910 calls and executes the inventory path planning method of the embodiment of this application;

[0184] Input / output interface 930, used to implement information input and output;

[0185] Communication interface 940, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0186] bus 950 , which transmits information between the various components of the device (e.g., processor 910 , memory 920 , input / output interface 930 , and communication interface 940 );

[0187] The processor 910 , the memory 920 , the input / output interface 930 , and the communication interface 940 are connected to each other in communication within the device via a bus 950 .

[0188] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned inventory path planning method is implemented.

[0189] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0190] The inventory path planning method, inventory path planning device, electronic device and computer-readable storage medium provided in the embodiments of the present application quantitatively describe the service level of the demand node through risk data, adjust the initial replenishment strategy according to the target cost and risk data, and obtain the target inventory planning result. Inventory planning is performed according to the target cost and service level. In the inventory planning process, not only the cost issue but also the service level to the user is considered, thus achieving a balance between cost and service level, making inventory planning closer to the real scene and improving the accuracy of inventory planning. At the same time, path planning is performed according to the target cost that has been balanced, thereby improving the accuracy of path planning.

[0191] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0192] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0193] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0194] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0195] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0196] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0197] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0198] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0199] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0200] If the integrated unit is implemented in the form of a software functional unit 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, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0201] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. Inventory path planning method, characterized in that: The method comprises: Dividing a preset planning time period into a plurality of periods; the preset planning time period includes a start time; Determine product demand data of the demand node in the period according to the preset demand set; Acquire the initial replenishment strategy of the supply node for the demand node and the initial inventory data of the demand node at the start time; Obtaining replenishment data of the supply node for the demand node according to the initial replenishment strategy and the initial inventory data; Performing inventory level evaluation based on the initial inventory data, the replenishment data, and the product demand data to obtain intermediate inventory data of the demand node in the period, and performing out-of-stock level evaluation based on the initial inventory data, the replenishment data, and the product demand data to obtain out-of-stock data of the demand node in the period; The storage cost of the demand node is obtained according to the preset unit storage cost and the intermediate inventory data, and the risk data that the intermediate inventory data is not in the preset inventory level interval is calculated; the out-of-stock cost of the demand node is obtained according to the preset unit out-of-stock cost and the out-of-stock data; the path between the supply node and the demand node is planned to obtain an initial transportation path; and the transportation cost of transporting the product according to the initial transportation path is calculated; Obtaining a target cost according to the storage cost, the out-of-stock cost and the transportation cost; Adjust the initial replenishment strategy according to the target cost and the risk data to obtain a target inventory planning result, and adjust the initial transportation path according to the target cost to obtain a path planning result; The preset inventory level interval includes first endpoint data and second endpoint data, the first endpoint data is less than the second endpoint data, and the calculating of the risk data that the intermediate inventory data is not within the preset inventory level interval includes: The intermediate inventory data and the first endpoint data are calculated to obtain first difference data; the intermediate inventory data and the second endpoint data are calculated to obtain second difference data; the minimum value of the first difference data and the second difference data is used as the risk value that the intermediate inventory data of the demand node i in the period t is not within the preset inventory level range, and the risk values ​​of all demand nodes in multiple periods within the preset planning time period are added to obtain the risk data; the calculation method of the risk data is as follows: Risk[r]=∑ i∈S ∑ t∈T risk it [r], Among them, r represents the initial replenishment strategy; S represents the set of all demand nodes; T represents the preset planning time period; risk it [r] represents the risk value of the intermediate inventory data of demand node i in period t not being within the preset inventory level range when the initial replenishment strategy is r; is the initial inventory level of period t+1, which is used to represent the intermediate inventory data of period t; τ it is the first endpoint data of demand node i in cycle t; is the second endpoint data of demand node i in period t; Risk[r] is the risk data; or, Acquire a risk parameter, wherein the risk parameter is used to represent the risk that the product demand data is not met; perform risk assessment according to the risk parameter, the first endpoint data, and the intermediate inventory data to obtain a first risk; perform risk assessment according to the risk parameter, the second endpoint data, and the intermediate inventory data to obtain a second risk; obtain the risk data according to the first risk and the second risk; The multi-period short-term risk measurement model specifies the service level as: Among them, α it is a risk parameter, which is used to represent the risk that the product demand data of demand node i in period t is not met; μ is a concave utility function; The first risk; For the second risk; The available inventory of demand node i in period t is the sum of the intermediate inventory data of demand node i in period t-1 and the replenishment data of period t. The available inventory is divided by the product demand data of demand node i in period t to obtain the actual demand satisfaction rate of demand node i in period t. The probability that the actual demand satisfaction rate is less than the expected demand satisfaction rate is used as the risk parameter. The utility function μ is replaced by a piecewise linear function. Translate service levels into: Based on intermediate inventory data Translate service levels into: Among them, the probability distribution P belongs to the distribution family F, represents the lower bound of the probability distribution; Substitute the first risk into Get the first probability Substituting the second risk into Get the second probability The minimum value of the first probability and the second probability is taken as risk data; The performing path planning on the path between the supply node and the demand node to obtain an initial transportation path includes: Acquire a first distance, a second distance, and a third distance, wherein the first distance is used to represent the distance between the supply node and the demand node, the second distance is used to represent the distance between the supply node and another demand node, and the third distance is used to represent the distance between the demand node and the another demand node; Performing distance calculation according to the first distance, the second distance, and the third distance to obtain mileage saving data between the demand node and the other demand node; Planning a path from the demand node to the other demand node according to the mileage saving data to obtain an initial path; A route is constructed according to the initial path to obtain the initial transportation path.

2. The inventory path planning method according to claim 1, characterized in that: The obtaining, according to the initial replenishment strategy and the initial inventory data, replenishment data of the supply node for the demand node comprises: Obtaining the maximum inventory capacity of the demand node; Performing a supply level assessment according to the initial replenishment strategy and the maximum inventory capacity to obtain supply data for the demand node; A replenishment level assessment is performed according to the supply data and the initial inventory data to obtain the replenishment data.

3. The inventory path planning method according to claim 1, characterized in that: The performing inventory level evaluation according to the initial inventory data, the replenishment data, and the product demand data to obtain the intermediate inventory data of the demand node in the cycle, and the performing out-of-stock level evaluation according to the initial inventory data, the replenishment data, and the product demand data to obtain the out-of-stock data of the demand node in the cycle, include: Perform product total quantity evaluation based on the initial inventory data and the replenishment data to obtain total product data of the demand node in the period; Perform product surplus evaluation based on the total product data and the product demand data to obtain the intermediate inventory data; The product out-of-stock quantity is evaluated according to the total product data and the product demand data to obtain the out-of-stock data.

4. The inventory path planning method according to any one of claims 1 to 3, characterized in that: The step of adjusting the initial replenishment strategy according to the target cost and the risk data to obtain a target inventory planning result, and adjusting the initial transportation path according to the target cost to obtain a path planning result includes: The initial replenishment strategy is screened according to the target cost and the preset cost threshold to obtain an intermediate replenishment strategy, and the initial transportation path is screened according to the target cost and the preset cost threshold to obtain the path planning result; Selecting the intermediate replenishment strategy with the smallest risk data as the target replenishment strategy; An inventory level assessment is performed according to the target replenishment strategy to obtain the target inventory planning result.

5. The inventory path planning method according to claim 4, characterized in that: The initial replenishment strategy is screened according to the target cost and the preset cost threshold to obtain the intermediate replenishment strategy, and the initial transportation path is screened according to the target cost and the preset cost threshold to obtain the path planning result, including: If the target cost is less than or equal to a preset cost threshold, the initial replenishment strategy is used as the first replenishment strategy, and the initial transportation path is used as the path planning result; Perturbing the first replenishment strategy according to a preset perturbation operator to obtain a second replenishment strategy; A neighborhood search is performed on the second replenishment strategy according to a preset neighborhood structure to obtain the intermediate replenishment strategy.

6. Inventory path planning device, characterized in that: The device comprises: A division module, used to divide a preset planning time period into a plurality of periods; the preset planning time period includes a start time; A determination module, used to determine product demand data of a demand node in the period according to a preset demand set; An acquisition module, used to acquire the initial replenishment strategy of the supply node for the demand node and the initial inventory data of the demand node at the start time; A first calculation module, configured to obtain replenishment data of the supply node for the demand node according to the initial replenishment strategy and the initial inventory data; A second calculation module is used to perform inventory level evaluation based on the initial inventory data, the replenishment data and the product demand data to obtain the intermediate inventory data of the demand node in the period, and to perform out-of-stock level evaluation based on the initial inventory data, the replenishment data and the product demand data to obtain the out-of-stock data of the demand node in the period; A third calculation module is used to obtain the storage cost of the demand node according to the preset unit storage cost and the intermediate inventory data, and calculate the risk data that the intermediate inventory data is not in the preset inventory level range; obtain the out-of-stock cost of the demand node according to the preset unit out-of-stock cost and the out-of-stock data; perform path planning on the path between the supply node and the demand node to obtain an initial transportation path; and calculate the transportation cost of transporting the product according to the initial transportation path; a fourth calculation module, configured to obtain a target cost according to the storage cost, the out-of-stock cost and the transportation cost; A planning module, configured to adjust the initial replenishment strategy according to the target cost and the risk data to obtain a target inventory planning result, and adjust the initial transportation path according to the target cost to obtain a path planning result; The preset inventory level interval includes first endpoint data and second endpoint data, the first endpoint data is less than the second endpoint data, and the calculating of the risk data that the intermediate inventory data is not within the preset inventory level interval includes: The intermediate inventory data and the first endpoint data are calculated to obtain first difference data; the intermediate inventory data and the second endpoint data are calculated to obtain second difference data; the minimum value of the first difference data and the second difference data is used as the risk value that the intermediate inventory data of the demand node i in the period t is not within the preset inventory level range, and the risk values ​​of all demand nodes in multiple periods within the preset planning time period are added to obtain the risk data; the calculation method of the risk data is as follows: Risk[r]=Σ i∈S Σ t∈T risk it [r], Among them, r represents the initial replenishment strategy; S represents the set of all demand nodes; T represents the preset planning time period; risk it [r] represents the risk value of the intermediate inventory data of demand node i in period t not being within the preset inventory level range when the initial replenishment strategy is r; is the initial inventory level of period t+1, which is used to represent the intermediate inventory data of period t; τ it is the first endpoint data of demand node i in cycle t; is the second endpoint data of demand node i in period t; Risk[r] is the risk data; or, Acquire a risk parameter, wherein the risk parameter is used to represent the risk that the product demand data is not met; perform risk assessment according to the risk parameter, the first endpoint data, and the intermediate inventory data to obtain a first risk; perform risk assessment according to the risk parameter, the second endpoint data, and the intermediate inventory data to obtain a second risk; obtain the risk data according to the first risk and the second risk; The multi-period short-term risk measurement model specifies the service level as: Among them, α it is a risk parameter, which is used to represent the risk that the product demand data of demand node i in period t is not met; μ is a concave utility function; The first risk; For the second risk; The available inventory of demand node i in period t is the sum of the intermediate inventory data of demand node i in period t-1 and the replenishment data of period t. The available inventory is divided by the product demand data of demand node i in period t to obtain the actual demand satisfaction rate of demand node i in period t. The probability that the actual demand satisfaction rate is less than the expected demand satisfaction rate is used as the risk parameter. The utility function μ is replaced by a piecewise linear function. Translate service levels into: Based on intermediate inventory data Translate service levels into: Among them, the probability distribution P belongs to the distribution family F, represents the lower bound of the probability distribution; Substitute the first risk into Get the first probability Substituting the second risk into Get the second probability The minimum value of the first probability and the second probability is taken as risk data; The performing path planning on the path between the supply node and the demand node to obtain an initial transportation path includes: Acquire a first distance, a second distance, and a third distance, wherein the first distance is used to represent the distance between the supply node and the demand node, the second distance is used to represent the distance between the supply node and another demand node, and the third distance is used to represent the distance between the demand node and the another demand node; Performing distance calculation according to the first distance, the second distance, and the third distance to obtain mileage saving data between the demand node and the other demand node; Planning a path from the demand node to the other demand node according to the mileage saving data to obtain an initial path; A route is constructed according to the initial path to obtain the initial transportation path.

7. An electronic device, characterized in that The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the inventory path planning method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the inventory path planning method according to any one of claims 1 to 5 is implemented.

Images