Logistics site optimization method and device, electronic equipment and storage medium

Abstract

The invention provides a logistics site optimization method and device, electronic equipment and a storage medium, and belongs to the technical field of logistics operation optimization. The method comprises the following steps: acquiring first line attribute data of a first site line of a to-be-shut-down site in a to-be-shut-down time interval, and acquiring second line attribute data of a second site line of a candidate shunting site in the to-be-shut-down time interval; according to the to-be-shut-down mode data, predicting a line dimension prediction cargo volume; constructing a line constraint condition according to the first line attribute data and the second line attribute data, and constructing a goods quantity constraint condition according to the line dimension prediction goods quantity and the second line attribute data; and constructing a target optimization function according to the distance between the to-be-shut-down site and the candidate shunting site and the line dimension prediction cargo volume, and solving the target optimization function according to the constructed constraint condition so as to adjust the first site line according to the obtained optimization scheme. According to the invention, the optimization efficiency and optimization accuracy of the logistics site can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics operation optimization, and particularly relates to a logistics site optimization method and device, an electronic device and a storage medium. BACKGROUND

[0002] In a logistics transfer scene, a transfer site serves as a hub for sorting and transferring goods, and undertakes the core functions of goods distribution, sorting, temporary storage and transportation connection. During some periods with less transportation business volume (such as holidays, weekends, etc.), if full-load operation of all sites in the logistics transfer scene is still maintained, it is easy to cause waste of human and equipment resources. Therefore, by optimizing the logistics scene, the effective utilization of the site in the logistics transfer scene can be improved, and the waste of human and equipment resources can be reduced.

[0003] At present, the related art usually adopts manual experience decision and basic mathematical modeling to optimize the site. The manual experience decision refers to operation adjustment by relying on the experience of decision makers, that is, the decision makers make operation adjustment on part of the site during specific periods such as holidays and weekends according to historical data and personal experience. This method is simple and intuitive, but has the problems of strong subjectivity, low decision efficiency and difficulty in handling complex constraint conditions. The basic mathematical modeling refers to site optimization by using a simple linear programming or analysis model, but this method can usually only handle a single optimization target (such as any one of cost, time efficiency and capacity), thereby leading to insufficient accuracy of site optimization. SUMMARY

[0004] The main purpose of the embodiments of the present application is to provide a logistics site optimization method and device, an electronic device and a storage medium, which can improve the optimization efficiency and optimization accuracy of the logistics site.

[0005] To achieve the above object, a first aspect of an embodiment of the present application provides a logistics site optimization method, which comprises: obtaining shutdown configuration data of a to-be-shutdown site in a logistics transfer scene, the shutdown configuration data comprising a to-be-shutdown time interval, to-be-shutdown mode data, and a candidate shunting site, the candidate shunting site being a shunting site that can receive transported goods in the to-be-shutdown site; obtaining first line attribute data corresponding to a first site line associated with the to-be-shutdown time interval of the to-be-shutdown site, and obtaining second line attribute data corresponding to a second site line associated with the to-be-shutdown time interval of the candidate shunting site; performing goods volume prediction on the first site line according to the to-be-shutdown mode data to obtain line-dimension predicted goods volume corresponding to the first site line; constructing line constraint conditions according to the first line attribute data and the second line attribute data, and constructing goods volume constraint conditions according to the line-dimension predicted goods volume and the second line attribute data; constructing a target optimization function according to the distance between the to-be-shutdown site and the candidate shunting site and the line-dimension predicted goods volume, and solving the target optimization function according to the line constraint conditions and the goods volume constraint conditions to obtain a logistics site optimization scheme, so as to adjust the first site line according to the logistics site optimization scheme.

[0006] To achieve the above object, a second aspect of an embodiment of the present application provides a logistics site optimization device, which comprises: a configuration data obtaining module configured to obtain shutdown configuration data of a to-be-shutdown site in a logistics transfer scene, the shutdown configuration data comprising a to-be-shutdown time interval, to-be-shutdown mode data, and a candidate shunting site, the candidate shunting site being a shunting site that can receive transported goods in the to-be-shutdown site; an attribute data obtaining module configured to obtain first line attribute data corresponding to a first site line associated with the to-be-shutdown time interval of the to-be-shutdown site, and obtain second line attribute data corresponding to a second site line associated with the to-be-shutdown time interval of the candidate shunting site; a goods volume prediction module configured to perform goods volume prediction on the first site line according to the to-be-shutdown mode data to obtain line-dimension predicted goods volume corresponding to the first site line; a condition constructing module configured to construct line constraint conditions according to the first line attribute data and the second line attribute data, and construct goods volume constraint conditions according to the line-dimension predicted goods volume and the second line attribute data; and an optimization module configured to construct a target optimization function according to the distance between the to-be-shutdown site and the candidate shunting site and the line-dimension predicted goods volume, and solve the target optimization function according to the line constraint conditions and the goods volume constraint conditions to obtain a logistics site optimization scheme, so as to adjust the first site line according to the logistics site optimization scheme.

[0007] To achieve the above object, a third aspect of an embodiment of the present application provides an electronic device, which comprises a memory and a processor, the memory storing a computer program, and the processor implementing the method of any one of the above-mentioned first aspect embodiments when executing the computer program.

[0008] To achieve the above object, a fourth aspect of the embodiments of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method in any one of the first aspect embodiments.

[0009] The logistics site optimization method and device, the electronic device and the storage medium provided by the embodiments of the present application can obtain the shutdown configuration data of the to-be-shutdown site in the logistics transfer scene when optimizing the logistics site, the shutdown configuration data indicates the to-be-shutdown time interval, the to-be-shutdown mode data and the candidate diversion site that can receive the transported goods in the to-be-shutdown site related to the to-be-shutdown site; then, the first site line associated with the to-be-shutdown time interval of the to-be-shutdown site is predicted in terms of goods volume according to the to-be-shutdown mode data, and the line dimension predicted goods volume corresponding to the first site line is obtained; further, the line constraint condition is constructed according to the first line attribute data and the second line attribute data, and the goods volume constraint condition is constructed according to the line dimension predicted goods volume and the second line attribute data; then, the target optimization function is constructed according to the distance between the to-be-shutdown site and the candidate diversion site and the line dimension predicted goods volume, and the target optimization function is solved according to the line constraint condition and the goods volume constraint condition, and the logistics site optimization scheme is obtained, so as to adjust the first site line according to the logistics site optimization scheme. Since the embodiments of the present application can comprehensively consider various factors to construct different types of constraint conditions, and when constructing the target optimization function, the line distance, the goods volume and other targets can be considered, so as to simultaneously process the complex constraint conditions and diversified optimization targets in the site shutdown decision, therefore, the embodiments of the present application can effectively improve the optimization efficiency and the optimization accuracy of the logistics site. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 is a flow chart of the logistics site optimization method provided by the embodiments of the present application; Figure 2 is a process schematic diagram of the site optimization adjustment in the logistics transfer scene; Figure 3 is a flow chart of step S130 in Figure 1 ; Figure 4 is a flow chart of step S330 in Figure 3 ; Figure 5 is a flow chart of constructing the line constraint condition provided by the embodiments of the present application; Figure 6 is a flow chart of constructing the goods volume constraint condition provided by the embodiments of the present application; Figure 7 is a flow chart of step S150 in Figure 1 ; Figure 8yes Figure 7 A flowchart of step S730 in the process; Figure 9 This is a schematic diagram of an algorithm process for the logistics site optimization method provided in the embodiments of this application. Figure 10 This is a schematic diagram of a logistics site optimization device provided in an embodiment of this application; Figure 11 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0012] It should be noted that although functional modules are divided in the device schematic diagram and a 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., used in the specification, claims, and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0013] First, let's analyze some of the terms used in this application: Transit hubs, also known as transfer stations, distribution centers, or transit centers, are the collection and distribution nodes in a network. Transit hubs are responsible for centralizing, sorting, and re-distributing parcels from different upstream nodes according to their destination / route, and then transferring them to the next node or higher / lower-level transit hubs via trunk / branch lines.

[0014] Outlets: These are the last (or front) service nodes that directly face customers and are responsible for pickup and delivery. They are also often referred to as service outlets, pickup and delivery points, business offices, etc.

[0015] In a logistics network, a route is a fixed or predetermined path followed by transport vehicles carrying goods from its origin to its destination. Together with logistics nodes (such as stations, ports, warehouses, and distribution centers), it forms the network structure. Specific route tasks can include: vehicle tasks from one point to a transit hub, from one transit hub to another, and from one transit hub to another; these are collectively referred to as "routes." Each transit hub has several points under its jurisdiction; routes from points to transit hubs are called "consolidation routes," and routes from transit hubs to points are called "bulk cargo routes."

[0016] Shift: The time of a transit site will be divided into several time-continuous operation shifts (2-4). There is only one departure shift and one arrival shift for each line.

[0017] In the logistics transit scene, the transit site serves as the hub of goods sorting and transfer, and undertakes the core functions of goods distribution, sorting, temporary storage and transportation connection. Due to some periods of low transportation volume (such as holidays, weekends, etc.), if the full-load operation of all sites in the logistics transit scene is still maintained, it is easy to cause waste of human and equipment resources. Therefore, by optimizing the logistics scene, the effective utilization of the site in the logistics transit scene can be improved, and the waste of human and equipment resources can be reduced.

[0018] Currently, the related technologies usually adopt manual experience decision, basic mathematical modeling or traditional operations research optimization to optimize the site. Among them, manual experience decision refers to relying on the experience of decision makers to make operation adjustment, that is, the decision maker adjusts or stops part of the site according to historical data and personal experience in specific periods such as holidays and weekends. This method is simple and intuitive, but it has strong subjectivity, low decision efficiency and difficulty in handling complex constraint conditions. Basic mathematical modeling refers to using simple linear programming or analysis model to optimize the site. This method can provide data support to a certain extent, but it can usually only handle a single optimization target (such as any one of cost, time efficiency, and capacity), which leads to insufficient accuracy of site optimization. In the field of logistics network design, operations research methods such as integer programming and network flow optimization have been widely used, mainly for long-term network layout planning. However, these methods are mostly for static scenarios and lack the ability to adapt to dynamic business changes, and cannot effectively solve the problem of temporary site closure and shunting. Therefore, the logistics site optimization methods adopted by related technologies generally lack comprehensive optimization ability under multiple scenarios and multiple constraint conditions, especially in the automatic generation of goods shunting schemes after site closure.

[0019] Therefore, the logistics site optimization method adopted by the related technology has some problems, including: (1) mainly relying on manual experience to judge the feasibility of closing a single site, which cannot effectively solve the global adjustment problem after the site is closed. This is because after a site is actually closed, it is necessary to consider how to reasonably distribute the remaining line freight volume to the surrounding sites, which involves the coordination and optimization of multiple sites. The existing single-point decision-making method cannot achieve global optimal configuration among multiple sites, and lacks a systematic technical solution. (2) The related technology cannot handle complex constraint conditions and diversified optimization objectives in site closure decision-making. This is because in terms of constraints, it needs to consider the capacity limit of the shunt site, the flow direction constraint, and other factors. In terms of optimization objectives, it needs to consider the sorting cost and transfer cost difference of different shunt sites. Thus, it is difficult to make scientific comprehensive judgments and optimization calculations on these multi-constraint and multi-objective factors by relying on offline manual methods. (3) Lack of unified technical support capability for different closure scenarios. There are different closure time scenarios such as weekend closure and holiday closure in the time dimension, and different closure mode scenarios such as bulk cargo closure and scattered cargo closure in the business mode. The related technology cannot use the same set of calculation techniques to cover all these differentiated scenarios, and cannot achieve adaptive modeling and unified calculation of multiple scenarios.

[0020] Based on this, the embodiments of the present application provide a logistics site optimization method and device, electronic equipment and storage medium, which can improve the optimization efficiency and optimization accuracy of the logistics site.

[0021] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (Artificial Intelligence, AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Theory, method, technology and application system. Artificial intelligence basic technologies generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. Artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc. several major directions.

[0022] The logistics site optimization method provided by the embodiments of the present application relates to the technical field of logistics operation optimization. The logistics site optimization method provided by the embodiments of the present application can be applied to a terminal, can be applied to a server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like; the server side can be configured as a stand-alone physical server, can be configured as a server cluster or a distributed system formed by multiple physical servers, can also be configured as a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content delivery network (CDN), and big data and artificial intelligence platform; and the software can be an application for implementing the logistics site optimization method, but is not limited to the above forms.

[0023] 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 personal computers (PCs), minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. 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, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0024] Please refer to Figure 1 , Figure 1 is an optional flowchart of the logistics site optimization method provided by the embodiments of the present application. In some embodiments of the present application, the method can specifically include but is not limited to steps S110 to S150, which will be described below in combination with Figure 1 The five steps will be described in detail.

[0025] In step S110, the shutdown configuration data of a to-be-shutdown site in a logistics transfer scenario is acquired. In step S120, first line attribute data corresponding to a first site line associated with a to-be-shutdown time interval of the to-be-shutdown site is acquired, and second line attribute data corresponding to a second site line associated with the to-be-shutdown time interval of a candidate shunt site is acquired. In step S130, the first site line is predicted according to the to-be-shut-down mode data, and a line dimension predicted cargo volume corresponding to the first site line is obtained. In step S140, a line constraint condition is constructed according to the first line attribute data and the second line attribute data, and a cargo volume constraint condition is constructed according to the line dimension predicted cargo volume and the second line attribute data. In step S150, a target optimization function is constructed according to the distance between the to-be-shut-down site and the candidate diversion site, and the line dimension predicted cargo volume, and the target optimization function is solved according to the line constraint condition and the cargo volume constraint condition, so as to obtain a logistics site optimization scheme, and the first site line is adjusted according to the logistics site optimization scheme.

[0026] In step S110 of some embodiments, the application embodiments can obtain shut-down configuration data of a to-be-shut-down site from a logistics management system or an artificial configuration interface. The to-be-shut-down site refers to a site that needs to be shut down and optimized at present. In the logistics transfer scene, the site is a transfer site, and there can be one or more transfer sites in a city. The shut-down configuration data refers to data related to the shut-down mode pre-configured for the to-be-shut-down site. The shut-down configuration data includes a to-be-shut-down time interval, to-be-shut-down mode data, and a candidate diversion site. The to-be-shut-down time interval refers to a pre-configured specific time period during which the site stops operating (for example, three days from XX month XX day of XXXX to XX month XX day of XXXX, or holiday shut-down, etc.), which is used to limit the validity period of all subsequent data and optimization operations. The to-be-shut-down time interval can be determined by the operator according to the maintenance plan, emergency, or strategic adjustment. The to-be-shut-down mode data is used to indicate the business mode of the to-be-shut-down site during the to-be-shut-down time interval, such as the collection shut-down (referring to closing only the collection line of the site→transfer site), the scattered cargo shut-down (closing only the scattered cargo line of the transfer site→site), the mixed shut-down (closing both the collection and scattered cargo functions), etc. The candidate diversion site is a diversion site that can receive the transportation cargo of the to-be-shut-down site, which is equivalent to a substitute logistics node that can receive the cargo of the to-be-shut-down site. For example, for the to-be-shut-down site 510VC, the set of candidate diversion sites that can be diverted is [510WD, 510WF], and 510WD and 510WF respectively indicate different candidate diversion sites.

[0027] It should be noted that one to-be-shut-down site can correspond to at least one candidate diversion site in the application embodiments, that is, the to-be-shut-down site and the candidate diversion site are mutually exclusive. The selection of the candidate diversion site usually needs to consider the transportation accessibility (such as distance, traffic network), the warehousing capacity (such as remaining capacity, equipment compatibility), and the operation stability (such as historical performance rate), and then the diversion site in the same city as the to-be-shut-down site can be usually selected as the candidate diversion site during calculation.

[0028] It should be noted that the shutdown mode data is a prerequisite parameter, because each site has its own functional attributes (only collection function, only bulk cargo function, or both collection and bulk cargo functions). Therefore, the embodiments of this application can determine the shutdown mode based on the site function.

[0029] For example, such as Figure 2 The diagram illustrates a process of site optimization and adjustment in a logistics transit scenario. Collection points A, B, and C each have transportation routes to the site to be closed (as shown by the dashed lines in the diagram). The site to be closed also has transportation routes to transit points A, B, and C (as shown by the dashed lines in the diagram). When optimizing site diversion for the site to be closed, diversion routes can be established between collection points A and B and diversion point E (a candidate diversion point for the site to be closed) when the site is closed. Furthermore, diversion routes can be established between diversion point E and transit points A and B (as shown by the solid lines in the diagram), ensuring that goods in collection points A and B can be transported normally. At the same time, a diversion route is constructed between the collection point C and the diversion site F (a candidate diversion site for the site to be closed), and a diversion route is constructed between the diversion site F and the transit site C (as shown by the solid lines in the figure), so that the goods in the collection point C can be transferred and transported normally.

[0030] In step S120 of some embodiments, the first site route refers to the original transportation route of the site to be closed within the closure time interval and closure mode. The site to be closed may include at least one first site route, and optimization considerations are made for at least one first site route in subsequent embodiments. The first route attribute data refers to attribute information related to the first site route, which may specifically include the cargo volume of the first site route in the historical reference period (e.g., average daily throughput over the past 30 days), the originating point type of the route, the destination point type of the route (point type may include points and transit points), transportation frequency (e.g., daily departures), turnaround time (e.g., average loading / unloading + transportation time), and route carrying capacity (e.g., maximum cargo volume threshold), etc. The second route attribute data refers to attribute information related to the second site route, and the content of the second route attribute data is similar to that of the first route attribute data, and will not be described again.

[0031] In step S130 of some embodiments, when optimizing the to-be-closed site, the first site line can be subjected to line dimension predicted volume estimation according to the to-be-closed mode data to estimate the volume of the first site line in the to-be-closed time interval. Because different closing modes can predict different volumes, the embodiments of the present application can consider the to-be-closed mode data for volume prediction of the first site line. In addition, the embodiments of the present application can also consider the time mode corresponding to the to-be-closed time interval for volume prediction. For example, when the to-be-closed time interval is a holiday type and the to-be-closed model data is a pickup closing, the volume can be predicted by a prediction scenario. At this time, the daily pickup and delivery amount of the city dimension can be calculated first, and the historical line volume of the base period is further mapped to obtain the predicted line dimension predicted volume. The city dimension predicted pickup and delivery amount refers to the total amount of daily pickup and delivery of the city where the first site line is located predicted by the machine learning model. The base period historical line volume refers to the line volume corresponding to each first site line in the selected historical reference period. Further, the volume proportion of the line volume of each first site line in the entire city dimension can be determined according to the base period historical line volume (for example, line A accounts for 12.3% of the total city volume). At this time, the city dimension predicted pickup and delivery amount and the volume proportion can be multiplied to obtain the line dimension predicted volume corresponding to each first line volume.

[0032] It should be noted that when calculating the line dimension predicted volume, the embodiments of the present application can also use a backtest scenario to predict the volume, for example, when the to-be-closed time interval is a weekend closing and the to-be-closed model data is a pickup closing, at this time, only the historical volume can be used to calculate whether a certain site can be closed in history, that is, the historical line volume in the historical reference period is used as the line dimension predicted volume.

[0033] Please refer to Figure 3 , Figure 3 is a flowchart of step S130 provided by the embodiments of the present application. In some embodiments, the specific process of step S130 can include but is not limited to steps S310 to S340, which will be described in detail below. Figure 3 The four steps are described in detail.

[0034] Step S310, determining the first line type corresponding to the first site line according to the first line attribute data, and selecting a target site line matching the preset type from the first site line according to the first line type; Step S320, determining the second line type corresponding to the second site line according to the second line attribute data, and selecting a candidate site line matching the preset type from the second site line according to the second line type; Step S330, determining the site closing label of the to-be-closed site according to the target site line and the candidate site line; In step S340, when the site shutdown label is a stoppable label, the first site line is predicted according to the to-be-shutdown mode data to obtain a line dimension predicted cargo volume corresponding to the first site line.

[0035] In step S310 of some embodiments, the target site line refers to a site line matched with a preset type screened from the second site line. The site line in the embodiments of the application can be divided into different types according to the line flow direction, and the line type can include a cargo collection point type, a same-city transfer type and a cross-city type. The preset type refers to a preset site type used to determine whether the to-be-shutdown site can be shut down. The first site line in the embodiments of the application can be divided into a to-be-shutdown arrival line and a to-be-shutdown departure line, the to-be-shutdown arrival line refers to a line from other net points or transfer sites to the to-be-shutdown site, and the to-be-shutdown departure line refers to a line from the to-be-shutdown site to other net points or transfer sites. Specifically, the application can first determine whether the first site line belongs to the to-be-shutdown arrival line or the to-be-shutdown departure line according to the first line attribute data, and then determine the first line type corresponding to the first site line.

[0036] It should be noted that for the to-be-shutdown arrival line, if the origin net point type is a net point, the line type corresponding to the site line (the first site line or the second site line) is a "cargo collection point type"; if the origin net point type is a transfer site and the origin and the destination are in the same city, the line type corresponding to the site line (the first site line or the second site line) is a "same-city transfer type"; if the origin net point type is a transfer site and the origin and the destination are not in the same city, the line type corresponding to the site line (the first site line or the second site line) is a "cross-city type". Further, the embodiments of the application can aggregate lines of different line types in the to-be-shutdown arrival line, for example, the lines of the "cargo collection point type" can be aggregated to form a set according to the departure net point . Since there can be multiple lines from the same net point to the shutdown site, aggregation can reduce the model calculation scale, improve the calculation efficiency, and not affect the calculation accuracy. For the to-be-shutdown departure line, if the destination net point type is a net point, the line type corresponding to the site line (the first site line or the second site line) is a "cargo collection point type"; if the destination net point type is a transfer site and the origin and the destination are in the same city, the line type corresponding to the site line (the first site line or the second site line) is a "same-city transfer type"; if the destination net point type is a transfer site and the origin and the destination are not in the same city, the line type is a "cross-city type". Further, the embodiments of the application can aggregate lines of different line types in the to-be-shutdown arrival line, for example, the lines of the "cross-city type" can be aggregated to form a set according to the departure net point .

[0037] In step S320 of some embodiments, the second site line is divided into the same line type as the first site type, and no further description is provided. The candidate site line refers to a site line selected from the second site line and matching the preset type. For example, if the preset type is a cross-city type, the second site line of the cross-city type can be selected from the second site line.

[0038] In steps S330 and S340 of some embodiments, further, the embodiments of the present application can compare the target site line and the candidate site line according to the related line information of the target site line and the candidate site line to determine the site shutdown label of the site to be shut down. The site shutdown label is used to indicate whether the site to be shut down can be shut down, and the site shutdown label includes a shut-down label and a non-shut-down label. The non-shut-down label indicates that the current candidate site cannot bear the flow direction port required by the site to be shut down. The flow direction port is a key node or area in the transfer site for controlling the flow direction and path of goods, vehicles, etc., like a “checkpoint”, guiding, checking and recording goods, vehicles, etc. entering and exiting different functional areas of the transfer site or going to different destinations. When the site shutdown label is the shut-down label, the first site line is subjected to cargo volume prediction according to the to-be-shut-down mode data to obtain the line dimension predicted cargo volume corresponding to the first site line. When the site shutdown label is the non-shut-down label, the transfer site cannot be shut down due to the limitation of the flow direction port.

[0039] Please refer to Figure 4 , Figure 4 is a flowchart of step S330 provided by the embodiments of the present application. In some embodiments, the specific process of step S330 can include but is not limited to steps S410 to S420, which will be described below in combination with Figure 4 The two steps are described in detail.

[0040] In step S410, line coverage rate calculation is performed according to the target site line and the candidate site line to obtain the line coverage rate, which is used to represent the proportion of the candidate site line covering the target site line. In step S420, the site shutdown label of the site to be shut down is determined according to the comparison result of the line coverage rate and the preset coverage rate threshold.

[0041] In steps S410 and S420 of some embodiments, the embodiments of the present application can determine whether the to-be-closed site can be closed by calculating the line coverage of the target site line and the candidate site line, that is, the preliminary judgment of the site closure can be made by using the flow direction coverage constraint. Specifically, the embodiments of the present application can count the city flow direction set A of the cross-city lines in the to-be-closed site (that is, the set composed of the target site lines of the cross-city type) and the city flow direction set B of the cross-city lines emitted by all candidate shunting sites (that is, the set composed of the candidate site lines of the cross-city type), and calculate the line coverage according to the city flow direction set A and the city flow direction set B to determine the line coverage of the candidate site line covering the target site line. Further, the comparison result of the line coverage and the preset coverage threshold is used to determine the site closure label of the to-be-closed site. For example, assuming that the preset coverage threshold is 90%, when the line coverage is greater than the preset coverage threshold, that is, the set B covers more than 90% of the flow direction of the set A, it is considered that the to-be-closed site can be closed, that is, the corresponding site closure label is the closable label; otherwise, the transit site cannot be closed due to the flow direction card slot constraint.

[0042] In step S140 of some embodiments, when determining the site optimization scheme for the to-be-closed site, the embodiments of the present application can construct the line constraint condition related to the line optimization constraint according to the first line attribute data and the second line attribute data, and construct the freight volume constraint condition related to the shift capacity constraint according to the line dimension predicted freight volume and the second line attribute data. That is, for the site closure decision problem, the embodiments of the present application propose a comprehensive mathematical modeling method, which unifies the complex business constraint conditions such as shift capacity constraint and flow direction card slot constraint into the optimization model to generate the line constraint condition and the freight volume constraint condition containing multiple business constraint conditions, thereby improving the accuracy of line optimization.

[0043] Please refer to Figure 5 , Figure 5 is a flowchart for constructing a line constraint condition provided by the embodiments of the present application. In some embodiments, the specific process of constructing the line constraint condition can include but is not limited to steps S510 to S550, which will be described in detail below. Figure 5

[0044] Step S510, determining the to-be-closed arrival line and the to-be-closed emission line from the first site line according to the first line attribute data; Step S520, performing line adjustment on the to-be-closed arrival line and the to-be-closed emission line according to the second line attribute data to obtain a line adjustment label, the line adjustment label including a first line sub-label between the to-be-closed arrival line and the candidate shunting site, and a second line sub-label between the to-be-closed emission line and the candidate shunting site;​ Step S530, constructing a line adjustment constraint condition according to the first line sub-label and the second line sub-label; Step S540, constructing a line schedule constraint condition according to the schedule adjustment result between the to-be-shut-down arrival line and the candidate shunting site, and the schedule adjustment result between the to-be-shut-down departure line and the candidate shunting site; Step S550, constructing a line constraint condition according to the line adjustment constraint condition and the line schedule constraint condition.

[0045] In steps S510 and S520 of some embodiments, the specific implementation of the over-length of the to-be-shut-down arrival line and the to-be-shut-down departure line has been described in the above embodiments. After the to-be-shut-down arrival line and the to-be-shut-down departure line are determined, the embodiments of the present application can perform line adjustment on the to-be-shut-down arrival line and the to-be-shut-down departure line according to the second line attribute data, and determine the adjustment result of each line in the to-be-shut-down site. The line adjustment label is used to indicate the adjustment result of each line in the to-be-shut-down site. The line adjustment label includes a first line sub-label between the to-be-shut-down arrival line and the candidate shunting site, and a second line sub-label between the to-be-shut-down departure line and the candidate shunting site. Wherein, the first line sub-label can be denoted as , indicating the to-be-adjusted to-be-shut-down arrival line whether to be adjusted to the candidate shunting site d, and the first line sub-label is a 01 variable (0 represents not adjustable, and 1 represents adjustable); the second line sub-label can be denoted as , indicating the to-be-adjusted to-be-shut-down departure line whether to be adjusted to the candidate shunting site d, and the second line sub-label is a 01 variable (0 represents not adjustable, and 1 represents adjustable).

[0046] In step S530 of some embodiments, the embodiments of the present application can construct a line adjustment constraint condition according to the first line sub-label and the second line sub-label, and the line adjustment constraint condition at this time can specifically include constraint condition (1) to constraint condition (3): Constraint condition (1): the collection line from the same network point in the to-be-shut-down site needs to be adjusted to the same candidate shunting site. Specifically, it can be represented as: .

[0047] Wherein, represents a third line sub-label of whether the collection line from the network point i in the to-be-shut-down site is adjusted to the candidate shunting site d, which is a 01 variable (0 represents not adjustable, and 1 represents adjustable); represents a line task index, that is, a line mark; d represents an index of the candidate shunting site; represents an index of the collection network point in the candidate shunting site; denotes a set of pickup tasks from the pickup points in the to-be- closed-down site i . denotes a set of arrival tasks of the candidate shunting site d; denotes a set of candidate shunting sites d; I denotes a set of pickup points in the to-be-closed-down site.

[0048] Constraint (2): Each to-be-closed-down arrival route can be adjusted to only one candidate shunting site d. Specifically, it can be expressed as: .

[0049] Constraint (3): Each to-be-closed-down departure route can be adjusted to only one candidate shunting site d. Specifically, it can be expressed as: .

[0050] wherein, denotes a set of cross-city tasks in the to-be-closed-down departure route (equivalent to the city flow set A of the cross-city route in the above embodiment).

[0051] In step S540 of some embodiments, the schedule adjustment result between the to-be-closed-down arrival route and the candidate shunting site is used to indicate whether the relevant schedule of the to-be-closed-down arrival route can be adjusted to the route schedule contained in the candidate shunting site. The schedule adjustment result between the to-be-closed-down departure route and the candidate shunting site is used to indicate whether the relevant schedule of the to-be-closed-down departure route can be adjusted to the route schedule contained in the candidate shunting site. Based on the two schedule adjustment results, a route schedule constraint condition can be further constructed, and the route schedule constraint condition at this time can specifically include constraint conditions (4) to (5): Constraint (4): to-be-closed-down arrival route constraint condition indicating that no corresponding schedule is found. Specifically, it can be expressed as: . Wherein, denotes a set of to-be-closed-down arrival routes that cannot be adjusted to the candidate shunting site d. .

[0052] It should be noted that no corresponding schedule is found refers to that if the to-be-closed-down arrival route is adjusted to the candidate shunting site d, the arrival time of the to-be-closed-down arrival route at the newly adjusted candidate shunting site d does not match the schedule of the candidate shunting site d (that is, generally refers to that the route arrival time does not have a corresponding site schedule).

[0053] Constraint (5): to-be-closed-down departure route constraint condition indicating that no corresponding schedule is found. Specifically, it can be expressed as: . Wherein, denotes a set of to-be-closed-down departure routes that cannot be adjusted to the candidate shunting site d. ​​a tuple set composed of the candidate shunting sites d.

[0054] In step S550 of some embodiments, further, the application embodiments can combine the above constraint condition (1) to constraint condition (5) to obtain a line constraint condition.

[0055] Please refer to Figure 6 , Figure 6 is a flowchart provided by the application embodiments for constructing the cargo volume constraint condition. In some embodiments, the specific process of constructing the cargo volume constraint condition can include but is not limited to steps S610 to S630, which will be described below in combination with Figure 6 The three steps will be described in detail.

[0056] Step S610, determining the shift capacity data of the candidate shunting site according to the second line attribute data; Step S620, performing difference calculation on the shift capacity data and the line dimension predicted cargo volume to obtain residual shift data; Step S630, constructing the cargo volume constraint condition according to the line dimension predicted cargo volume, the first line sub-label, and the residual shift data.

[0057] In steps S610 to S630 of some embodiments, in the logistics scene, the shift capacity of a site (a network point or a transfer site) refers to the ability of the site to handle cargo within a working shift. The shift capacity reflects the maximum or average level of the site to complete the cargo handling task within a specific time period under the cooperation of personnel, equipment, etc. The cargo handling task generally includes cargo unloading, sorting, scanning, loading, etc. The application embodiments can first determine the shift capacity data of the candidate shunting site according to the second line attribute data, which is used to indicate the cargo volume that the candidate shunting site can handle within a working shift. Difference calculation on the shift capacity data and the line dimension predicted cargo volume can determine the residual shift data of the candidate shunting site, which is used to represent the current residual cargo handling capacity of the candidate shunting site. When the residual cargo handling capacity is negative, in order to ensure the accuracy of the candidate shunting site and the current optimization, the residual shift data can be set to 0, indicating that the shift of the candidate shunting site cannot be adjusted at this time, but the first site line in the site to be closed is still allowed to be adjusted to other shifts of other sites.

[0058] Based on this, the cargo volume constraint condition can be specifically expressed as: .

[0059] Among them, This represents the collection of cargo tasks arriving from point i in the site to be closed. The route tasks included in this collection must satisfy the following condition: after these route tasks are adjusted to the candidate diversion site d and issued, they will fall on shift b of the candidate diversion site d. Indicates line task The quantity of goods (i.e., the predicted quantity of goods based on the route dimension). This represents the shift capacity data corresponding to shift b. This represents the set of arrival tasks belonging to shift b among the candidate diversion sites d; This represents the set of shifts for candidate diversion sites d. The left-hand side of the inequality in the cargo volume constraint represents the cargo volume that shift b from candidate diversion site d will be adjusted to. The 0.9 on the right-hand side of the inequality in the cargo volume constraint indicates that the shift capacity after adjusting the cargo collection route will not exceed 90%. This value can be flexibly adjusted according to actual needs and is not limited.

[0060] It should be noted that, in the embodiments of this application, when adjusting routes, the routes of the first site in the site to be closed can be matched with the schedules in the candidate diversion sites. Specifically, the schedule information set of candidate diversion sites within the time interval to be closed can be filtered first. Further, the schedule matching results corresponding to all "arrival routes to be closed - candidate diversion sites" in the site to be closed can be calculated, and the schedule matching results corresponding to all "departure routes to be closed - candidate diversion sites" can be calculated, so as to apply the above constraints based on the two schedule matching results.

[0061] In step S150 of some embodiments, after constructing various constraints, the embodiments of this application can further construct an objective optimization function based on the distance between the site to be closed and the candidate diversion sites, as well as the predicted cargo volume based on the route dimension. The objective optimization function at this time is equivalent to an operations research optimization model (also known as a site closure route diversion planning algorithm model), which is used to plan the optimal diversion scheme for the remaining routes of the site to be closed in the time interval of the closure. Further, using a solver (such as the gurobi solver, a high-performance optimization solver for mathematical programming, which is specifically designed to solve complex optimization problems such as linear programming, mixed integer programming, and quadratic programming), the objective optimization function is solved according to the route constraints and cargo volume constraints (i.e., the above constraints (1) to constraints (5)) to obtain the logistics site optimization scheme (i.e., the optimal diversion scheme for the remaining routes in the site to be closed), so as to adjust the first site route according to the logistics site optimization scheme.

[0062] Please refer to Figure 7 , Figure 7 This is a flowchart of step S150 provided in an embodiment of this application. In some embodiments, the specific process of step S150 may include, but is not limited to, steps S710 to S730, as described below. Figure 7The three steps are described in detail.

[0063] In step S710, a branch cost calculation function is constructed according to the distance between the to-be-shut-down site and the candidate diversion site and the first line sub-label. In step S720, a sorting unit cost of the candidate diversion site is obtained, and a sorting cost calculation function is constructed according to the line dimension predicted cargo volume, the sorting unit cost and the first line sub-label. In step S730, a target optimization function is constructed according to the branch cost calculation function and the sorting cost calculation function.

[0064] In step S710 of some embodiments, the embodiments of the present application can construct a target optimization function based on a multi-element optimization target. The branch cost calculation function is used to optimize the adjusted line cost, and the specific calculation function of the branch cost calculation function is: wherein, represents the distance between the to-be-shut-down site and the candidate diversion site d.

[0065] In step S720 and step S730 of some embodiments, the sorting cost calculation function is used to optimize the sorting cost of the adjusted task, and the specific calculation function of the sorting cost calculation function is: wherein, represents the sorting unit cost (i.e. the average sorting cost per cargo) in the candidate diversion site d. Further, the branch cost calculation function and the sorting cost calculation function can be calculated by function weighting to construct a target optimization function.

[0066] It should be noted that the model (i.e. the target optimization function) constructed by the embodiments of the present application can automatically calculate and output the diversion scheme that guarantees the optimal branch cost and sorting cost, while providing detailed line schedule adjustment details to provide accurate execution guidance for business actual operation. In this way, the whole process automation output from the feasibility analysis to the specific implementation scheme can be realized, which greatly improves the decision efficiency of site optimization and the quality of the generated optimization scheme.

[0067] Please refer to Figure 8 , Figure 8 is a flowchart of step S730 provided by the embodiments of the present application. In some embodiments, the specific process of step S730 can include but is not limited to steps S810 to S840, which are described below in combination with Figure 7 The three steps are described in detail.

[0068] In step S810, line flow port data of the candidate diversion site is extracted from the second line attribute data. Step S820, according to the second line sub-label and the line flow direction socket data, socket matching is performed on the to-be-shut-down outgoing line to obtain a socket adjustment label; Step S830, according to the second line sub-label and the socket adjustment label, a socket adjustment function is constructed; Step S840, the branch line cost calculation function, the sorting cost calculation function and the socket adjustment function are integrated to obtain a target optimization function.

[0069] In steps S810 to S840 of some embodiments, when constructing the target optimization function, the application embodiments can further consider adding the flow direction socket constraint to the target optimization function, that is, adding the socket increase after adjusting the line task of the first site line to the candidate shunting site in the target optimization function. The line flow direction socket data is used to represent the original line socket information in the candidate shunting site. The socket adjustment label is used to represent whether a new socket needs to be added after adjusting the line task of the to-be-shut-down outgoing line to the candidate shunting site. The socket adjustment label is a 01 variable, 0 represents no need to add, and 1 represents need to add.

[0070] It should be noted that the socket adjustment function is used to optimize the socket adjustment cost of the adjusted task, and the specific calculation function of the socket adjustment function is: .

[0071] Among them, represents the outgoing line task adjusting to the candidate shunting site d whether to add a socket, that is, the socket adjustment label, if the outgoing flow direction of the candidate shunting site d contains the city flow direction of the line task , , if not, .

[0072] Further, after the function integration of the branch line cost calculation function, the sorting cost calculation function and the socket adjustment function, the target optimization function obtained can be specifically represented as: .

[0073] Among them, a, b, c respectively correspond to the function weight of the branch line cost calculation function, the sorting cost calculation function and the socket adjustment function, and a+b+c=1, which is used to represent the importance of the corresponding function in the final target optimization function, and can be flexibly adjusted according to actual needs. Based on this, the application embodiments solve the target optimization function, that is, solve the function constructed based on the branch line cost calculation function, the sorting cost calculation function and the socket adjustment function, to obtain a logistics site optimization scheme (that is, the optimal shunting scheme of the remaining line in the to-be-shut-down site).

[0074] In the above embodiments, the embodiments of this application can incorporate complex business constraints such as shift capacity constraints and flow checkpoint constraints into the optimization model, and take minimizing branch line costs, sorting costs and checkpoint adjustment costs as the objective optimization function. This achieves a technical breakthrough from single-point experience judgment to global multi-site collaborative optimization, and solves the technical problem that traditional methods cannot handle multi-dimensional constraints at the same time.

[0075] It should be noted that the constructed objective optimization function is equivalent to an optimization model. If the optimization model has no feasible solution, it means that the shutdown plan is not feasible. If the optimization model has an optimal solution, the results can be displayed. The information displayed at this time may include: (1) information on all routes before the adjustment in terms of location, date, and schedule; (2) information on all routes after the adjustment aggregated in terms of location, date, and schedule; and (3) comparison results of location, date, and schedule information before and after the adjustment.

[0076] For example, such as Figure 9 The diagram illustrates an algorithm for a logistics site optimization method provided in this application. In this embodiment, the initial input includes closure configuration data for the site to be closed and related source data (such as first route attribute data and second route attribute data). The closure configuration data can include the closure time interval, closure mode data, and candidate diversion sites. Specifically, the first and second route attribute data can include route data, shift capacity data, etc. Further, the input data can undergo preprocessing, such as calculating predicted cargo volume based on route dimensions, determining route flow direction (e.g., determining arrival and departure routes), and shift matching (the diagram is only an example and not complete information). Then, this embodiment can perform model calculations on the model corresponding to the constructed objective optimization function by combining route constraints and cargo volume constraints, i.e., minimizing branch line costs, sorting costs, and checkpoint adjustment costs. Finally, if the model calculation yields no feasible solution, the closure scheme is infeasible, and the route to be closed cannot be shut down; if the model calculation yields a feasible solution, the calculated site optimization scheme can be output, and corresponding adjustments can be performed.

[0077] The logistics site optimization method provided in the embodiments of the present application can comprehensively consider various factors to construct different types of constraint conditions, and when constructing the target optimization function, can consider the line distance, cargo volume and other targets, so as to simultaneously process the complex constraint conditions and diversified optimization targets in the site closing decision, to construct a unified calculation framework that can simultaneously adapt to diversified business scenarios such as different closing modes and different closing site ranges, and overcome the limitation that the traditional method needs to model separately for different scenarios, and significantly improve the universality and applicable range of the optimization model. Moreover, the model provided in the embodiments of the present application can automatically calculate and output the shunting scheme that guarantees the optimal branch line cost and sorting cost, and simultaneously provide detailed line schedule adjustment details, to provide accurate execution guidance for actual business operation. Therefore, the embodiments of the present application construct the site closing model based on the multi-business dimension constraint and optimization target, and can effectively improve the optimization efficiency and optimization accuracy of the logistics site.

[0078] Please refer to Figure 10 The embodiments of the present application also provide a logistics site optimization device, which comprises: The configuration data acquisition module 1010 is configured to acquire closing configuration data of a to-be-closed site in a logistics transfer scenario, the closing configuration data comprising a to-be-closed time interval, to-be-closed mode data and a candidate shunting site, the candidate shunting site being a shunting site that can receive the transport goods in the to-be-closed site; The attribute data acquisition module 1020 is configured to acquire first line attribute data corresponding to a first site line associated with the to-be-closed time interval of the to-be-closed site, and acquire second line attribute data corresponding to a second site line associated with the to-be-closed time interval of the candidate shunting site; The cargo volume prediction module 1030 is configured to perform cargo volume prediction on the first site line according to the to-be-closed mode data, to obtain line dimension predicted cargo volume corresponding to the first site line; The condition construction module 1040 is configured to construct line constraint conditions according to the first line attribute data and the second line attribute data, and construct cargo volume constraint conditions according to the line dimension predicted cargo volume and the second line attribute data; The optimization module 1050 is configured to construct a target optimization function according to the distance between the to-be-closed site and the candidate shunting site, and the line dimension predicted cargo volume, and solve the target optimization function according to the line constraint conditions and the cargo volume constraint conditions, to obtain a logistics site optimization scheme, so as to adjust the first site line according to the logistics site optimization scheme.

[0079] It should be noted that the logistics site optimization device provided in the embodiments of the present application is used to implement the logistics site optimization method provided in the above embodiments, and the specific implementation process corresponds to the logistics site optimization method of the above embodiments, and can refer to the aforementioned logistics site optimization method, which will not be described here again.

[0080] The embodiment of the present application further provides an electronic device (namely, a computer device), which comprises a memory and a processor, the memory stores a computer program, and the processor can realize the method for optimizing a logistics site in any of the above embodiments when executing the computer program. The electronic device can be any intelligent terminal such as a tablet computer, a vehicle-mounted computer and the like.

[0081] Referring to Figure 11 , Figure 11 The hardware structure of an electronic device according to another embodiment is illustrated, which comprises: The processor 1110 can be implemented in the form of a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC) or one or more integrated circuits, and is used to execute related programs to realize the technical solutions provided by the embodiments of the present application; The memory 1120 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 1120 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 1120 and are called and executed by the processor 1110 to realize the method for optimizing a logistics site according to the embodiments of the present application; The input / output interface 1130 is used to realize information input and output; The communication interface 1140 is used to realize the communication interaction between the device and other devices, and can realize communication through a wired manner (for example, a USB, a network cable and the like) or a wireless manner (for example, a mobile network, WIFI, Bluetooth and the like); The bus 1150 is used to transmit information between various components (for example, the processor 1110, the memory 1120, the input / output interface 1130 and the communication interface 1140) of the device; The processor 1110, the memory 1120, the input / output interface 1130 and the communication interface 1140 are connected to each other through the bus 1150 to realize the communication connection between them in the device.

[0082] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is used to make a computer execute the method for optimizing a logistics site in the above embodiments.

[0083] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory disposed remotely with respect to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0084] The embodiments of the present application also provide a computer program product, which stores program instructions. When the program instructions are executed by a computer, the computer implements the logistics site optimization method described in any of the above embodiments.

[0085] The embodiments described in the embodiments of the present application are used 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 by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0086] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0087] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0088] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0089] The terms "first", "second", "third", "fourth", and the like in the description and in the claims of this application, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so termed is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of orderly or chronological mundane operation, reverse order operation, based on circuitry availability, based on stated preference or the like, and that "default" or other orderings are thus permissible. Further, the terms "comprise", "comprising", "include", "including", and the like, are specifically intended to be open-ended. That is, references to individual steps and the like do not suhstantially exclude the presence of two or more of a given step or its integral presence in the process, method, system, article, or apparatus having been made with a wider scope. The use of notation such as "first", "second", "third", etc. does not generally limit the areas, but is used to connect like elements or to distinguish one claim from another. These terms can be used interchangeably when appropriate. Terms concerning the relative position of elements can be interpreted such that their use adheres to their normal meaning, but they can also be interpreted to mean the opposite according to specific claims.

[0090] It should be understood that, in the application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases: 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 represents an "or" relationship between the front and rear associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple 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, and c can be single or multiple.

[0091] In several embodiments provided by the 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 illustrative, for example, the division of the above-mentioned units is only a logical functional division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0092] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0093] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0094] If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in the form of a contribution to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0095] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method for optimizing logistics sites, characterized in that, The method includes: Obtain shutdown configuration data for sites to be shut down in a logistics transit scenario. The shutdown configuration data includes shutdown time interval, shutdown mode data, and candidate diversion sites. The candidate diversion sites are diversion sites that can receive the transported goods from the sites to be shut down. Obtain the first route attribute data corresponding to the first site route associated with the site to be shut down in the time interval to be shut down, and obtain the second route attribute data corresponding to the second site route associated with the candidate diversion site in the time interval to be shut down. Based on the data of the pending shutdown mode, the cargo volume of the first site route is predicted to obtain the predicted cargo volume of the route dimension corresponding to the first site route. Based on the first route attribute data and the second route attribute data, route constraints are constructed, and based on the predicted cargo volume according to the route dimension and the second route attribute data, cargo volume constraints are constructed. Based on the distance between the site to be closed and the candidate diversion sites, and the predicted cargo volume based on the route dimension, a target optimization function is constructed. The target optimization function is then solved based on the route constraints and the cargo volume constraints to obtain a logistics site optimization scheme. The route of the first site is then adjusted according to the logistics site optimization scheme.

2. The method according to claim 1, characterized in that, The step of predicting the cargo volume of the first site route based on the data of the pending shutdown mode to obtain the predicted cargo volume of the first site route by route dimension includes: The first route type corresponding to the first site route is determined based on the first route attribute data, and a target site route matching the preset type is selected from the first site routes based on the first route type. The second route type corresponding to the second site route is determined based on the second route attribute data, and a candidate site route matching the preset type is selected from the second site routes based on the second route type. The site closure label of the site to be closed is determined based on the target site route and the candidate site route. When the site closure label is a closureable label, the cargo volume of the first site route is predicted based on the data of the closure mode, and the predicted cargo volume of the first site route is obtained.

3. The method according to claim 2, characterized in that, The step of determining the site closure tag for the site to be closed based on the target site route and the candidate site routes includes: The route coverage rate is calculated based on the target site route and the candidate site route. The route coverage rate is used to characterize the proportion of the candidate site route that covers the target site route. Based on the comparison between the line coverage rate and the preset coverage threshold, the site closure label of the site to be closed is determined.

4. The method according to claim 1, characterized in that, The step of constructing line constraints based on the first line attribute data and the second line attribute data includes: Based on the first route attribute data, determine the arrival routes to be shut down and the departure routes to be shut down from the first site routes; Based on the second route attribute data, the arrival routes and departure routes to be shut down are adjusted to obtain route adjustment tags. The route adjustment tags include a first route sub-tag between the arrival routes to be shut down and the candidate diversion sites, and a second route sub-tag between the departure routes to be shut down and the candidate diversion sites. Construct line adjustment constraints based on the first line sub-label and the second line sub-label; Based on the schedule adjustment results between the arrival routes to be shut down and the candidate diversion sites, and the schedule adjustment results between the departure routes to be shut down and the candidate diversion sites, route schedule constraints are constructed. The route constraints are constructed based on the route adjustment constraints and the route schedule constraints.

5. The method according to claim 4, characterized in that, The step of constructing cargo volume constraints based on the predicted cargo volume according to the route dimension and the second route attribute data includes: The shift capacity data of the candidate diversion sites are determined based on the second route attribute data; The difference between the shift capacity data and the predicted freight volume based on the route dimension is calculated to obtain the remaining shift data. Cargo volume constraints are constructed based on the predicted cargo volume according to the route dimension, the first route sub-label, and the remaining schedule data.

6. The method according to claim 4, characterized in that, The step of constructing a target optimization function based on the distance between the site to be closed and the candidate diversion sites, and the predicted freight volume based on the route dimension, includes: Based on the distance between the site to be shut down and the candidate diversion site, and the first route sub-label, a branch line cost calculation function is constructed; Obtain the sorting unit cost of the candidate diversion sites, predict the cargo volume based on the route dimension, the sorting unit cost, and the first route sub-label, and construct a sorting cost calculation function; Construct a target optimization function based on the branch cost calculation function and the sorting cost calculation function.

7. The method according to claim 6, characterized in that, The step of constructing the target optimization function based on the branch cost calculation function and the sorting cost calculation function includes: Extract the line flow direction checkpoint data of the candidate diversion sites from the second line attribute data; Based on the second line sub-tag and the line flow checkpoint data, the checkpoint matching is performed on the line to be shut down to obtain the checkpoint adjustment tag; Based on the second line sub-label and the bayonet adjustment label, construct the bayonet adjustment function; The branch cost calculation function, the sorting cost calculation function, and the checkpoint adjustment function are integrated to obtain the target optimization function.

8. A logistics site optimization device, characterized in that, The device includes: The configuration data acquisition module is used to acquire the shutdown configuration data of the site to be shut down in the logistics transfer scenario. The shutdown configuration data includes the shutdown time interval, shutdown mode data and candidate diversion sites. The candidate diversion sites are diversion sites that can receive the transported goods in the site to be shut down. The attribute data acquisition module is used to acquire the first line attribute data corresponding to the first site line associated with the site to be shut down in the shutdown time interval, and to acquire the second line attribute data corresponding to the second site line associated with the candidate diversion site in the shutdown time interval. The cargo volume prediction module is used to predict the cargo volume of the first site route based on the data of the shutdown mode, and obtain the predicted cargo volume of the route dimension corresponding to the first site route. The condition construction module is used to construct route constraints based on the first route attribute data and the second route attribute data, and to construct cargo volume constraints based on the predicted cargo volume based on the route dimension and the second route attribute data. The optimization module is used to construct a target optimization function based on the distance between the site to be closed and the candidate diversion site, as well as the predicted cargo volume based on the route dimension, and to solve the target optimization function based on the route constraints and the cargo volume constraints to obtain a logistics site optimization scheme, so as to adjust the route of the first site according to the logistics site optimization scheme.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images