Road area combination method and device

By constructing multiple road zone sets and using path planning models to generate target road zone combinations, the problem that the existing technology middle road zone combination is difficult to balance workload and improve efficiency, and cost reduction and work efficiency improvement are achieved.

CN118917508APending Publication Date: 2024-11-08BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411125380.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the road area combination method in the logistics field, it is difficult to ensure the balanced workload and efficiency of the delivery staff at the same time, and the operational cost is high. The machine learning recommended prediction model relies on a large amount of historical data and has low classification accuracy. The greedy algorithm relies on the initial. It is difficult to obtain an optimal combination plan when choosing a road area.

Method used

By constructing multiple road area collections, using the path planning model to calculate the number of people invested, and generating road area combinations based on the objective functions of capacity limit and time window limits, filtering out the target road area combinations to ensure balanced workload and improved efficiency.

Benefits of technology

The workload balance of road area combination is achieved, the work efficiency of delivery personnel is improved, the operating costs are reduced, and the initial road area selection is not affected.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917508A_ABST
    Figure CN118917508A_ABST
Patent Text Reader

Abstract

The invention discloses a road area combination method and device, and relates to the technical field of logistics. A specific embodiment of the method comprises the following steps: obtaining to-be-combined road areas corresponding to a current station, and constructing a plurality of road area sets according to the road areas; for each road area set, calculating the number of input people corresponding to the road area set; generating each road area combination corresponding to the road area set by using a first path planning model; screening out candidate road area combinations from the road area combinations, calculating a first index result of each candidate road area combination by using a second path planning model, and calculating a second index result of the road area set according to the first index result of each candidate road area combination; and screening out a target road area set and a target road area combination according to the second index result of each road area set. According to the embodiment, the road area combination capable of ensuring the balanced workload of each deliveryman under the condition of meeting the workload of each deliveryman can be obtained, the working efficiency of the deliveryman is improved, and the operation cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a road area combination method and device. Background Art

[0002] In the field of logistics, the delivery or collection area of ​​each logistics business department or station can be divided into multiple road areas, and each road area is assigned a delivery person to be responsible for collecting or delivering orders within the road area. However, this will lead to unsaturated workload for delivery persons, low work efficiency and high operating costs, so the road areas need to be combined.

[0003] In the related art, there are two methods for combining road zones: one is to use a machine learning recommendation prediction model; however, this method relies on a large amount of historical data, and has low classification accuracy and poor model generalization ability, and is unable to recommend combination schemes for multiple road zones at the same time; the other is to use a nearest neighbor search algorithm based on a greedy algorithm; however, the combination scheme obtained by this algorithm depends on the selection of the initial road zone, and it is difficult to obtain a better road zone combination scheme. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a road zone combination method and device, which can obtain a road zone combination that ensures a balanced workload for each deliveryman while satisfying the workload of each deliveryman, thereby improving the work efficiency of the deliverymen and reducing operating costs.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a road zone combination method is provided, comprising:

[0006] Acquire each road area to be combined corresponding to the current site, and construct multiple road area sets according to each road area, each road area set including at least two road areas;

[0007] For each of the road area sets, the number of people involved corresponding to the road area set is calculated according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination; according to the road area set and the corresponding number of people involved, each road area combination corresponding to the road area set is generated by using the first path planning model; each candidate road area combination is screened out from the each road area combination, the first index result of each candidate road area combination is calculated by using the second path planning model, and the second index result of the road area set is calculated according to the first index result of each candidate road area combination;

[0008] The target road area set and the target road area combination are screened out according to the second indicator results of each road area set.

[0009] Optionally, multiple road area sets are constructed according to each road area, including:

[0010] Preset one or more coverage ratios;

[0011] For each of the coverage ratios, the number of road areas corresponding to the coverage ratio is calculated according to the total number of the road areas;

[0012] A road area set corresponding to the number of road areas is screened out from the various road areas according to a preset rule.

[0013] Optionally, the order quantity attribute includes a preset maximum total order quantity and a preset minimum total order quantity of the road zone combination, the area attribute includes a preset maximum total area of ​​the road zone combination, and the road zone number attribute includes a preset maximum total number of road zones of the road zone combination; calculating the number of people corresponding to the road zone set according to the order quantity attribute, the area attribute, and the road zone number attribute of the preset road zone combination includes:

[0014] Obtain the total order quantity, total area and total number of road areas of the road area set;

[0015] According to the total order quantity, total area and total number of road areas of the road area set, as well as the maximum and minimum total order quantity, the maximum total area and the maximum number of road areas, the maximum number of people involved and the minimum number of people involved corresponding to the road area set are calculated;

[0016] Determine whether the minimum number of people involved is less than or equal to the maximum number of people involved;

[0017] If so, each value between the minimum number of people invested and the maximum number of people invested is used as the number of people invested;

[0018] If not, the road area set is reconstructed according to each road area in the road area set, and the number of people corresponding to the reconstructed road area set is calculated according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination.

[0019] Optionally, calculating the maximum number of people involved and the minimum number of people involved corresponding to the road zone set includes:

[0020] Calculate a first number of people according to the total area and the maximum value of the total area;

[0021] Calculate the second number of people according to the total number of orders and the maximum value of the total number of orders;

[0022] Calculate the third person number according to the total number of road areas and the maximum number of the total number of road areas;

[0023] The maximum number of people involved is calculated based on the total number of orders and the minimum number of total orders;

[0024] The largest one is selected from the first number of people, the second number of people and the third number of people as the minimum number of people invested.

[0025] Optionally, reconstructing the road zone set according to each road zone in the road zone set includes:

[0026] Sorting each road area in the road area set according to a preset index;

[0027] According to the sorting result, first road area sets are selected from the road area sets, wherein the ratio of the total area to the maximum total area is less than the maximum number of people, and the ratio of the total number of road areas to the maximum total number of road areas is less than the maximum number of people; and the first road area set with the largest number of road areas is used as the second road area set;

[0028] Determine whether the ratio of the total number of orders of the second road zone set to the minimum total number of orders is less than the maximum number of people involved;

[0029] If yes, update the maximum number of people involved, update the second road area set according to the updated maximum number of people involved, and use the updated second road area set as the reconstructed road area set;

[0030] If not, obtain the geographical location information of each road area in the candidate road area set, filter out the largest connected subgraph from the second road area set according to the geographical location information, and use the largest connected subgraph as the reconstructed road area set.

[0031] Optionally, the first path rule model includes a target loss function based on capacity constraints, and using the first path planning model to generate each road zone combination corresponding to the road zone set includes:

[0032] According to the road zone set and the corresponding number of people involved, and the target loss function based on capacity limitation, each road zone combination corresponding to the road zone set when the target loss function is minimized is calculated,

[0033] Among them, the target loss function based on capacity limitation includes a distance loss function and an order balance loss function. The capacity limitation includes order limitation for each number of people, area limitation and road zone number limitation. The distance loss function is constructed based on the distance between road zones, and the order loss function is constructed based on the order quantity of each road zone.

[0034] Optionally, the second planning model includes an objective function based on a time window restriction, and the second path planning model is used to calculate a first indicator result of each candidate road zone combination, including:

[0035] For each candidate road zone combination, obtain the order point set corresponding to the candidate road zone combination, calculate the minimum value of the objective function according to the order point set and the objective function based on the time window restriction; calculate the first indicator result of the candidate road zone set according to the minimum value of the objective function;

[0036] The time window restriction includes the arrival time restriction of each order point in the set of all order points, and the objective function is constructed according to the distance between the order points in the set of order points.

[0037] According to another aspect of the embodiments of the present invention, a road area combination device is provided, comprising:

[0038] A construction module, which obtains each road area to be combined corresponding to the current site, and constructs a plurality of road area sets according to each road area, each road area set including at least two road areas;

[0039] The calculation module calculates the number of people corresponding to each road zone set according to the preset single quantity attribute, area attribute and road zone number attribute of the road zone combination; generates each road zone combination corresponding to the road zone set by using the first path planning model according to the road zone set and the corresponding number of people; selects each candidate road zone combination from each road zone combination, calculates the first index result of each candidate road zone combination by using the second path planning model, and calculates the second index result of the road zone set according to the first index result of each candidate road zone combination;

[0040] The screening module screens out target road area sets and target road area combinations according to the second indicator results of each road area set.

[0041] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0042] one or more processors;

[0043] a storage device for storing one or more programs,

[0044] When the one or more programs are executed by the one or more processors, the one or more processors implement the road zone combination method provided by the present invention.

[0045] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the road zone combination method provided by the present invention is implemented.

[0046] One embodiment of the above invention has the following advantages or beneficial effects: the road area combination method of the embodiment of the present invention constructs multiple road area sets through the road areas to be combined at the current station, and determines the number of people to be deployed for each road area set according to the attributes of the preset road area combination, so as to realize the flexible deployment of the number of people in different road area sets; solves the optimization problem of road area combination through the first path planning model, and obtains the road area combinations corresponding to each road area set; obtains the first indicator result of each road area combination and the second indicator result of each road area set through the second path planning model simulation, so as to screen out the target road area set and the target road area combination. The road area combination obtained by the road area combination method can meet the workload requirements and improve the work efficiency, and ensures the workload balance among the delivery personnel, improves the work enthusiasm of the delivery personnel, and reduces the operating cost.

[0047] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0049] Figure 1 is a schematic diagram of the main process of a road zone combination method according to an embodiment of the present invention;

[0050] Figure 2 is a schematic diagram of the main process of another road zone combination method according to an embodiment of the present invention;

[0051] Figure 3 is a flow chart of a method for calculating the number of people involved in a road zone set according to an embodiment of the present invention;

[0052] Figure 4 is a schematic flow chart of a road zone combination method according to an embodiment of the present invention;

[0053] Figure 5 is a schematic diagram of main modules of a road area combination device according to an embodiment of the present invention;

[0054] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0055] Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0057] In the field of logistics, the last level before the logistics goods reach the user is the business department unit. The area under the business department is divided into several sub-areas, which are the smallest working areas, namely the road areas. The "last mile" door-to-door delivery service in the logistics distribution terminal process is completed by the logistics terminal delivery personnel. Usually, the road area is divided according to the collection and delivery workload in the work area. Each road area corresponds to a delivery person, but this pre-divided work area is not universally applicable to all application scenarios. In the scenario of full-time collection or delivery, if the delivery person is only responsible for the work in a single road area, on the one hand, the pure collection workload is insufficient; on the other hand, there are many road areas under the business department, and all the delivery personnel will be redundant and the cost is too high. In order to adapt to the application scenarios of the exclusive collection mode or the special dispatch mode, it is necessary to combine the existing minimum working area, namely the road area, to provide a reference for configuring the work scope of the delivery person.

[0058] There are two main methods for traditional workspace combination recommendation: a machine learning recommendation prediction model based on mathematical combination and a nearest neighbor search algorithm based on a greedy algorithm. The machine learning prediction model is implemented by first combining any two of the road area set to be recommended, and then putting it into the machine learning classification model to determine whether the combination can be used as a work area that can meet the workload requirements and help improve work efficiency. However, this method based on the machine learning model is highly dependent on historical data, and the model training effect has certain requirements on the accuracy of sample classification; the number of road areas in the recommended combination result needs to be unified, and it cannot be generalized to achieve the combination recommendation of multiple road areas.

[0059] The implementation method of the nearest neighbor search algorithm based on the greedy algorithm is to select a road area as the initial seed area, start searching from the first-order neighboring area of ​​the road area, find the current optimal road area that meets the objective function, then search from all the first-order neighboring areas of the selected road area set, select the optimal road area that meets the objective function, and so on until the maximum road area combination that meets the boundary conditions is found as the final recommendation. The nearest neighbor search method based on the greedy algorithm is highly sensitive to the selected initial seed area. Selecting different road areas as seed areas will affect the search speed and the effect of the final combination solution.

[0060] Based on the above technical problems, an embodiment of the present invention provides a road zone combination method to achieve reasonable allocation of road zone combinations and the number of people involved, without setting a limit on the number of road zones in the road zone combination, and meeting the requirements of workload and work efficiency.

[0061] Figure 1 FIG. 1 is a schematic diagram of the main process of a road zone combination method according to an embodiment of the present invention. Figure 1 As shown, the road area combination method includes the following steps:

[0062] Step S101: Acquire each road area to be combined corresponding to the current site, and construct multiple road area sets according to each road area, each road area set including at least two road areas;

[0063] Step S102: for each road area set, the number of people corresponding to the road area set is calculated according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination; according to the road area set and the corresponding number of people, each road area combination corresponding to the road area set is generated by using the first path planning model; each candidate road area combination is screened out from each road area combination, the first index result of each candidate road area combination is calculated by using the second path planning model, and the second index result of the road area set is calculated according to the first index result of each candidate road area combination;

[0064] Step S103: Filter out a target road area set and a target road area combination according to the second indicator result of each road area set.

[0065] In an embodiment of the present invention, the road area combination method is used to combine road areas within the jurisdiction of a station so that the combined road areas meet the working requirements of a full-time collection mode or a full-time delivery mode. For the current station for which a road area combination scheme is to be generated, each road area to be combined corresponding to the current station is obtained, wherein each road area to be combined corresponding to the current station may be all road areas of the current station or may be a problem road area of ​​the current station, wherein the problem road area is a part of the road area selected from all road areas of the current station.

[0066] Among them, if each road area to be combined is a problem road area, then each road area to be combined corresponding to the current station is obtained, including: obtaining all road areas of the current station, and filtering out the problem road areas from all road areas according to preset filtering rules. Filtering out the problem road areas from all road areas according to preset filtering rules may include: obtaining the road area of ​​each road area in all road areas, and filtering out the road areas with a road area smaller than a preset area as the problem road areas; it may also include: obtaining the collection timeliness rate of each road area in all road areas, and filtering out the road areas with a collection timeliness rate smaller than a preset timeliness rate threshold as the problem road areas; it may also include: obtaining the number of customer complaints for collection (i.e., the number of customer complaints for collection urging) for each road area in all road areas, and filtering out the road areas with the number of customer complaints for collection greater than a preset number threshold as the problem road areas.

[0067] In an embodiment of the present invention, the conditions that a road zone combination needs to meet are pre-configured, namely, the single quantity attribute, area attribute and road zone number attribute of the preset road zone combination. The single quantity attribute includes the maximum total single quantity and the minimum total single quantity of the preset road zone combination, the area attribute includes the maximum total area of ​​the preset road zone combination, and the road zone number attribute includes the maximum total number of road zones of the preset road zone combination.

[0068] Before constructing multiple road area sets according to each road area, a pre-pruning strategy is used to perform pre-pruning processing on each road area. The pre-pruning strategy includes a top1 principle and a topN principle. The top1 and / or topN principle is used to perform pre-pruning processing on each road area.

[0069] Specifically, the top1 principle is used for pre-pruning, including: obtaining the area of ​​each road area, sorting the road areas in descending order of area, calculating the sum of the areas of the road area with the largest area and the road area with the smallest area, and if the sum of the areas is greater than the maximum total area, then the road area with the largest area is eliminated, and so on, to determine whether other road areas need to be eliminated.

[0070] The topN principle is used for pre-pruning, including: obtaining the order volume of each road area in each road area, which is the historical order volume within a preset time; sorting each road area in order from large to small according to the order volume, and if the sum of the order volumes of the first N road areas is less than the minimum value of the total order volume, the site is removed.

[0071] In an embodiment of the present invention, a plurality of road area sets are constructed according to each road area, including: presetting one or more coverage ratios; for each coverage ratio, calculating the number of road areas corresponding to the coverage ratio according to the total number of each road area; and filtering out a road area set corresponding to the number of road areas from each road area according to a preset rule.

[0072] In the embodiment of the present invention, one or more coverage ratios are preset, such as 100%, 90%, 80%, 70%, and 60%; for each coverage ratio, the coverage amount is calculated according to the coverage ratio and the total number of each road area, and the coverage amount is the number of road areas corresponding to the coverage ratio; the road areas are sorted according to the preset rules, and the preset rules can be the collection timeliness rate, such as sorting the road areas in the order of small to large collection timeliness rate; according to the sorting result, a road area set corresponding to the number of road areas is selected from each road area, that is, the road area with the worst collection timeliness rate is selected. Each coverage ratio corresponds to a road area set, and the road area sets corresponding to different coverage ratios can be S 100% , S 90% , S 80% S 70% S 60%Indicates. For example, the total number of road areas is 100, and for a coverage ratio of 90%, 100*90%=90 road areas need to be screened out in the order of timely collection rate from small to large. Among them, the coverage ratio can be set according to the lower threshold of coverage. If the total number of road areas is large, more enumeration values ​​of coverage ratio can be set so that the number of road areas corresponding to the lowest coverage ratio is equal to or less than the lower threshold of coverage. By setting multiple coverage ratios, multiple road area sets are obtained, so that a target road area set with better effect and a target road area combination corresponding to the target road area set can be screened out from multiple road area sets.

[0073] In the embodiment of the present invention, for each road zone set, the number of people corresponding to the road zone set is calculated according to the single quantity attribute, area attribute and road zone number attribute of the preset road zone combination, so as to divide the road zone set according to the number of people, specifically including:

[0074] Get the total order quantity, total area and total number of road areas in the road area set;

[0075] According to the total order quantity, total area and total number of road areas of the road area set, as well as the maximum and minimum total order quantity, the maximum total area and the maximum number of road areas, the maximum and minimum number of people involved in the road area set are calculated;

[0076] Determine whether the minimum number of people invested is less than or equal to the maximum number of people invested;

[0077] If so, take each value between the minimum number of people invested and the maximum number of people invested as the number of people invested;

[0078] If not, the road area set is reconstructed according to each road area in the road area set, and the number of people corresponding to the reconstructed road area set is calculated according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination.

[0079] In an embodiment of the present invention, for each road zone set, the total area, total order volume and total number of road zones of the road zone set can be obtained according to the area and order volume of each road zone in the road zone set. Then, according to the total order volume, total area and total number of road zones of the road zone set, as well as the maximum value and minimum value of the total order volume, the maximum value and the maximum value of the total area and the maximum value of the total number of road zones, the maximum value and the minimum value of the number of people involved corresponding to the road zone set can be calculated.

[0080] Specifically, the first number of people is calculated based on the total area and the maximum value of the total area; the second number of people is calculated based on the total number of orders and the maximum value of the total number of orders; the third number of people is calculated based on the total number of road areas and the maximum value of the total number of road areas; the maximum number of people invested is calculated based on the total number of orders and the minimum value of the total number of orders; the largest one among the first number of people, the second number of people and the third number of people is selected as the minimum number of people invested.

[0081] That is, calculate the quotient of the total area of ​​the road area set and the maximum total area of ​​the preset road area combination, and round up the quotient to obtain the first number of people; calculate the quotient of the total order quantity of the road area set and the maximum total order quantity of the preset road area combination, and round up the quotient to obtain the second number of people; calculate the quotient of the total number of road areas according to the road area set and the maximum total number of road areas of the preset road area combination, and round up the quotient to obtain the third number of people; the largest one among the first number of people, the second number of people and the third number of people is used as the minimum number of people to be invested. Calculate the quotient of the total order quantity of the road area set and the minimum total order quantity of the preset road area combination, and round down the quotient to obtain the maximum number of people to be invested.

[0082] In the embodiment of the present invention, after obtaining the maximum number of people and the minimum number of people in the road zone set, it is determined whether the minimum number of people is less than or equal to the maximum number of people. If so, the number of people is normal, and the number of people corresponding to the road zone set can be determined, and the number of people in the road zone set is the minimum number of people in the road zone set. and the maximum number of people involved The values ​​between , thus obtaining the input data pairs, each of which includes a road area set and the number of people involved in the road area set , each road zone set can have one or more people involved. , ;

[0083] If not, the number of people is inconsistent, and the input data pair cannot be generated. It is necessary to reconstruct the road area set, that is, update each road area in the road area set.

[0084] In the embodiment of the present invention, Figure 2 As shown, the road area set is reconstructed according to each road area in the road area set, including:

[0085] Step S201: sorting each road area in the road area set according to a preset index;

[0086] Step S202: Filter out from the road area sets, according to the sorting result, first road area sets whose ratio of total area to maximum total area is less than the maximum number of people, and whose ratio of total number of road areas to maximum total number of road areas is less than the maximum number of people; and select the first road area set with the largest number of road areas as the second road area set;

[0087] Step S203: Determine whether the ratio of the total number of orders in the second route zone set to the minimum total number of orders is less than the maximum number of people involved; if so, execute step S204; if not, execute step S205;

[0088] Step S204: updating the maximum number of people involved, updating the second road area set according to the updated maximum number of people involved, and using the updated second road area set as the reconstructed road area set;

[0089] Step S205: obtaining geographical location information of each road area in the candidate road area set, screening out a maximum connected subgraph from the second road area set according to the geographical location information, and using the maximum connected subgraph as the reconstructed road area set.

[0090] Specifically, the preset index can be the number of orders for each road area, or other indicators such as area. The road areas in the road area set can be sorted in descending order according to the number of orders to obtain the sorting result; then, the road area with the highest number of orders is selected one by one until the first road area sets are screened out, which meet the conditions that the ratio of the total area to the maximum total area is less than the maximum number of people invested (the total area of ​​the first road area set is less than or equal to the product of the maximum number of people invested in the road area set and the maximum total area), and the ratio of the total number of road areas to the maximum number of road areas is less than the maximum number of people invested (that is, the total area of ​​the first road area set is less than the product of the maximum number of people invested in the road area set and the maximum number of road areas). Then, the number of road areas in each first road area set is obtained, and the one with the largest number of road areas is used as the second road area set.

[0091] For the second road area set, determine whether the ratio of the total order quantity of the second road area set to the minimum total order quantity is less than the maximum number of people invested (i.e., the total order quantity of the second road area set is less than the product of the maximum number of people invested and the minimum total order quantity). If so, it means that the order quantity of the second road area set cannot meet the workload of the maximum number of people invested, and the maximum number of people invested needs to be updated, such as reducing the maximum number of people invested by one, and re-screening the second road area set; if not, the second road area set can be adjusted, such as obtaining the geographical location information of each road area in the second road area set, such as the boundary location information of each road area, the boundary location information includes a boundary coordinate point set, if two road areas have more than two identical boundary coordinate points, it means that the two road areas are adjacent, and the two road areas are considered to be connected, and can also be determined based on the stored adjacent road areas of each road area. Then all adjacent road areas in the second road area set are connected, and the largest connected subgraph is screened out, that is, the connected subgraph with the largest number of road areas or the largest area, and the largest connected subgraph is the reconstructed road area set. For example, road area a is adjacent to road area b, road area b is adjacent to road area c, road area c is adjacent to road area d, road area e is adjacent to road area f, and there is no other adjacent relationship. At this time, abcd is a connected subgraph, and ef is a connected subgraph. Therefore, abcd is the largest connected subgraph of this road area set and contains the largest number of road areas.

[0092] Then, the corresponding new maximum number of people and the new minimum number of people are recalculated for the reconstructed road area set. The new number of people in the reconstructed road area set is the values ​​between the new maximum number of people and the new minimum number of people, thereby obtaining multiple input data pairs. If the number of people is inconsistent again, the new number of people can be determined to be the new maximum number of people minus one, the new maximum number of people, or the new maximum number of people plus one.

[0093] Figure 3 Flow chart of a method for determining the number of people involved in a road zone set according to an embodiment of the present invention. Obtain a road zone set (S p% ), obtain the total number of orders, total area and total number of road areas corresponding to the road area set; calculate the maximum number of people and the minimum number of people according to the preset maximum number of total orders and minimum number of total orders (ds), the maximum total area and the maximum number of total road areas of the road area combination, and judge whether the minimum number of people is less than or equal to the maximum number of people to judge the number of people. If so, the number of people is normal, and the number sequence corresponding to the road area set (i.e. the number of people) is obtained; if not, the number of people is inconsistent, and the road area set is reconstructed;

[0094] Sort each road area in the road area set in descending order according to the order quantity, and traverse and filter out the first road area set that meets the conditions (S p% '), determine whether the total number of orders in the first road area set is greater than the product of the maximum number of people invested and the minimum total number of orders;

[0095] If so, obtain the largest connected subgraph of the first road area set as the reconstructed road area set (S p% ''), recalculate the new maximum number of people (maxpeople') and the new minimum number of people, and make a judgment on the number of people. If the number of people is normal, get the number sequence corresponding to the reconstructed road area set. If not, the number enumeration value is the new maximum number of people minus one, the new maximum number of people (maxpeople'), and the new maximum number of people plus one;

[0096] If not, the maximum number of people invested is reduced by one, and the second road area set is selected from the road area set again.

[0097] In an embodiment of the present invention, the first path rule model includes a target loss function based on capacity constraints, and the first path planning model is used to generate each road zone combination corresponding to the road zone set, including:

[0098] According to the road zone set and the corresponding number of people, as well as the target loss function based on capacity constraints, the road zone combinations corresponding to the road zone set when the target loss function is minimized are calculated.

[0099] Among them, the target loss function based on capacity limitation includes distance loss function and order balance loss function. The capacity limitation includes order limitation for each number of people, area limitation and number of road zones. The distance loss function is constructed according to the distance between road zones, and the order loss function is constructed according to the order quantity of each road zone.

[0100] In an embodiment of the present invention, the first path planning model can be a Capacitated Vehicle Routing Problem (CVRP) model based on capacity constraints. In the vehicle path planning problem, there is a warehouse and N customer points, each customer point is denoted as i, i∈{1,2,⋯,N}, each customer point has a quantity to be served, each tool vehicle starts from the warehouse and ends at the warehouse, serving multiple customers along the way, and the total number of customers served by each tool vehicle cannot exceed the total carrying capacity of the vehicle. The loss of the tool vehicle from point i to point j is denoted as , where i,j∈V={0,1,2,⋯N}, and 0 is used to represent the warehouse location by default. The goal is to find a route planning method with the lowest cost to provide services to all customers without violating the vehicle capacity limit. In the embodiment of the present invention, the tool can be regarded as a person who can be put into use, the customer point can be regarded as a road area, the starting point can be regarded as the location of the sales department, that is, the site location, and each path obtained by solving the CVRP can be regarded as a different combination of road areas.

[0101] The model includes a target loss function based on capacity constraints. The model is constructed by minimizing the target loss function. The capacity constraints include the order quantity limit for each person, the area limit and the number of road zones, that is, the maximum acceptable order quantity for each person, the maximum responsible road zone, and the maximum number of responsible road zones. The target loss function includes a distance loss function and an order balance loss function. The distance loss function includes the sum of the distance losses between each road zone for each person, and the order balance loss includes the difference between the order quantity in the road zone for which each person is responsible and the average order quantity. According to the road zone set and the corresponding number of people, combined with the target loss function based on capacity constraints, with the goal of minimizing the target loss function, the road zone combinations corresponding to the road zone set can be obtained.

[0102] Specifically, the model is shown in formula (1):

[0103] , formula (1),

[0104] Formula (2)

[0105] Formula (3),

[0106] Formula (4),

[0107] Formula (5):

[0108] , formula (6),

[0109] Formula (7),

[0110] , formula (8),

[0111] Formula (9):

[0112] Formula (10).

[0113] Among them, in formula (1), the first term represents the distance loss function, that is, the distance loss function when k deliverymen are responsible for picking up the goods in the road area respectively, and the second term represents the order balance loss function, in order to make the order volume in the road area where K deliverymen are responsible for each other more balanced, is the weight of the single-volume equilibrium loss function. K represents the number of people involved, k represents the kth person, is the kth brother; 0 in V represents the station, and other elements in V represent the road area; Indicates whether there is a path from road area i to road area j for the delivery person in a certain road area combination plan. If so, then is 1, if it does not exist, then is 0; is the distance between road area i and road area j;

[0114] Formulas (5) and (6) represent the order quantity restriction constraint, where C is the maximum acceptable order quantity for each person, Indicates The number of orders in each road area, Indicates passing road area After that, the delivery personnel will be burdened with all the orders;

[0115] Formulas (7) and (8) represent the road area restriction constraints, where R represents the maximum road area that each person is responsible for. Indicates The area of ​​the road area, Indicates passing road area The sum of the orders in all the routes that the delivery person has traveled;

[0116] Formula (9) represents the constraint on the number of road zones, where M represents the maximum number of road zones that each person is responsible for. Indicates passing road area The number of all road areas that the delivery person has traveled through afterwards.

[0117] In the embodiment of the present invention, after the first path planning model is used to generate each road zone combination corresponding to the road zone set, each candidate road zone combination is screened out from each road zone combination.

[0118] Specifically, since there may be road area combinations that do not meet the constraints in the process of determining each road area combination corresponding to each road area set by the first path rule model, it is necessary to further screen each road area combination. After obtaining each road area combination corresponding to each road area set according to the first path planning model, each road area combination is post-pruned using a post-pruning strategy. Specifically, the post-pruning process can be performed using principles such as strong adjacency, combined unit quantity, combined area, and number of combined road areas. For example, the strong adjacency principle can be used to determine whether each road area in each road area combination is adjacent to each other in terms of geographical location; whether the unit quantity of the road area combination is greater than the minimum total unit quantity and less than the maximum total unit quantity, whether the area of ​​the road area combination is less than the maximum total area, and whether the number of the road area combination is greater than the minimum total number of road areas and less than the maximum total number of road areas; after post-pruning each road area combination in the road area set, each candidate road area combination is screened out from each road area combination.

[0119] In an embodiment of the present invention, the second planning model includes an objective function based on a time window restriction, and the first indicator result of each candidate road zone combination is calculated using the second path planning model, including:

[0120] For each candidate road area combination, obtain the order point set corresponding to the candidate road area combination, calculate the minimum value of the objective function based on the order point set and the objective function based on the time window restriction; calculate the first indicator result of the candidate road area set based on the minimum value of the objective function;

[0121] Among them, the time window restriction includes the arrival time restriction of each order point in the set of all order points, and the objective function is constructed according to the distance between the order points in the set of order points.

[0122] In an embodiment of the present invention, the second path planning model is a Vehicle Routing Problem with Time Windows (VRPTW) model based on time window constraints. Through this model, the walking path of the deliveryman can be obtained when the minimum delivery time or minimum delivery distance corresponding to all order collections is completed in the corresponding candidate road area combination. After obtaining each candidate road area combination corresponding to each road area set, the candidate road area combination corresponding to each deliveryman is obtained. However, since the candidate road areas are of different sizes, the difficulty of completing the collection tasks with different geographical density distributions of orders is also different, which will affect the work efficiency of the deliveryman. Therefore, the embodiment of the present invention simulates the collection of all orders in the candidate road area combination that the deliveryman is responsible for. A set of order points under the candidate road area combination of the deliveryman on a certain day in history is selected. Each order point in the order point set is customer point i. The site is selected as the starting point of the warehouse. Each order has an appointment time window. According to the VRPTW simulation, the time when the delivery person arrives at each order point is obtained. After the simulation, for each order, it can be determined if , then the order is collected on time, otherwise, the order is not collected on time. By counting the timeliness of all orders, we can get the collection timeliness rate of the deliveryman's special collection tasks in the road area combination throughout the day. According to the collection timeliness rate, the number of timely collection orders corresponding to the road area set is calculated to screen out the target road area set and target road area combination.

[0123] Specifically, the second path planning model includes an objective function based on a time window restriction, with the goal of minimizing the objective function. The objective function is constructed based on the distance between order points in the order point set corresponding to the road area set. Specifically, the objective function can be the sum of the collection time or the sum of the collection distance of all order points constructed based on the distance between the order points. The time window restriction is a constraint on the time of departure from each order point or a constraint on the time of arrival at each order point. According to the second path planning model, the first indicator result of each candidate road area combination can be calculated, and the first indicator result can be the collection timeliness rate of each candidate road area combination.

[0124] Then, the second indicator result of the road area set is calculated based on the first indicator result of each candidate road area combination, such as calculating the timely collection order quantity of the road area set based on the timely collection rate of each candidate road area combination and the order quantity of each candidate road area combination. Each road area set is sorted according to the timely collection order quantity, and the one with the highest timely collection order quantity is taken as the target road area set, and each candidate road area combination in the target road area set is taken as the target road area combination.

[0125] It is also possible to screen each candidate road area combination according to the first indicator result, and eliminate the candidate road area combination whose first indicator result is lower than the indicator threshold. For example, each candidate road area combination can be further screened according to the timely collection rate of each candidate road area combination, and the candidate road area combination whose timely collection rate is lower than the preset timely collection rate threshold is eliminated to obtain the target candidate road area combination corresponding to the road area set.

[0126] The second indicator result of the road area set is calculated based on the first indicator result of each target candidate road area combination, that is, the timely collection order quantity of the road area set can be calculated based on the timely collection rate of each target candidate road area combination and the order quantity of each target candidate road area combination, and each road area set is sorted according to the timely collection order quantity, and the road area set with the highest timely collection order quantity is taken as the target road area set, and each target candidate road area combination in the target road area set is a target road area combination

[0127] For example, the objective function can be expressed as formula (11), and the constraints of the objective function can be expressed as formulas (12)-(15).

[0128] , formula (11),

[0129] Formula (12)

[0130] Formula (13)

[0131] Formula (14)

[0132] (15)

[0133] in, Represents a set of order points, where 0 represents the starting point and the end point;

[0134] Indicates order The order point to be served immediately afterwards, the value set is [0,1,…,n], ;

[0135] Indicates from order To order the time or distance taken;

[0136] Indicates from order To order the time or distance taken;

[0137] Indicates from order The time of departure;

[0138] Indicated in the order The length of time the location has been in service.

[0139] Through the objective function and its constraints, the walking path corresponding to the minimum collection time or the shortest collection distance of each candidate road area combination can be obtained. According to the minimum collection time or the shortest collection distance, the departure time of the deliveryman from the site is set, and the arrival time of each order point on the walking path can be simulated and calculated to determine whether the arrival time is within the appointment time window of the order point. If so, the collection is timely, otherwise, the collection is untimely. By calculating the collection situation of each order point in the candidate road area combination corresponding to the deliveryman, the collection timeliness rate corresponding to the candidate road area combination can be obtained.

[0140] Figure 4 A flowchart of a road area combination method according to an embodiment of the present invention. First, all road areas of the station for which a road area combination scheme is to be generated are obtained; various problematic road areas are screened out from all road areas by preset rules, and the preset rules may include area, timely collection rate, etc.; a pre-pruning strategy (such as the top principle and / or the topN principle) is used to perform pre-pruning processing on each road area to obtain various road areas to be combined; multiple coverage ratios are preset, each coverage ratio is traversed, and a road area set corresponding to each coverage ratio is obtained; the number of people involved corresponding to each road area set is calculated; for each road area set and the corresponding number of people involved, a path planning model with capacity constraints is used to perform parallel calculations to obtain various road area combinations corresponding to each road area set, each road area set corresponds to a general scheme, and each road area combination corresponds to a sub-scheme; for each road For each road area combination corresponding to the area set, a post-pruning strategy is used to perform post-pruning processing to obtain each candidate road area combination corresponding to each road area set; a path planning algorithm with a time window restriction is used to estimate the collection timeliness rate of each candidate combination road area, and the candidate road area combinations with a lower collection timeliness rate are eliminated to obtain the target candidate road area combination for each road area set; then, the collection timeliness order quantity of each road area set is calculated according to the collection timeliness rate of the target candidate road area combination corresponding to each road area set and the order quantity of the target candidate road area combination; the one with the highest collection timeliness order quantity is taken as the target road area set, and the target candidate road area combinations corresponding to the target road area set are the target road area combinations; and the optimal overall solution finally output is the target road area set and its corresponding target road area combination.

[0141] For example, a road area set includes 10 road areas, and the corresponding number of people involved is 3. The road area combinations obtained after the first path planning model and post-pruning processing are [001, 002, 003], [004, 005, 006], and [007, 008, 009, 010]. The second path planning model is used to simulate the timely collection rate of each road area combination, and the timely collection rate [007, 008, 009, 010] with a lower timely collection rate is eliminated. The timely collection volume of the road area set is calculated based on the timely collection rate and corresponding order quantity of each remaining road area combination. If the timely collection volume of the road area set is the maximum value, the output total plan is [001, 002, 003], [004, 005, 006].

[0142] The road area combination method of the embodiment of the present invention constructs multiple road area sets through the road areas to be combined at the site, and determines the number of people to be deployed for each road area set according to the attributes of the preset road area combination, so as to realize the flexible deployment of the number of people in different road area sets; solves the optimization problem of the road area combination through the first path planning model, obtains each road area combination of each road area set, and simulates the first index result of each road area combination and the second index result of each road area set through the second path planning model, so as to screen out the target road area set. The road area combination obtained by the road area combination method can improve the work efficiency while meeting the workload requirements, and ensure the workload balance among the delivery personnel, improve the work enthusiasm of the delivery personnel, and reduce the operating cost.

[0143] According to another aspect of the embodiment of the present invention, Figure 5 As shown, a road area combination device 500 is provided, comprising

[0144] A construction module 501 is used to obtain each road area to be combined corresponding to the current station, and to construct a plurality of road area sets according to each road area, each road area set including at least two road areas;

[0145] The calculation module 502 calculates the number of people involved in the road zone set according to the preset single quantity attribute, area attribute and road zone number attribute of each road zone set for each road zone set; generates each road zone combination corresponding to the road zone set by using the first path planning model according to the road zone set and the corresponding number of people involved; selects each candidate road zone combination from each road zone combination, calculates the first index result of each candidate road zone combination by using the second path planning model, and calculates the second index result of the road zone set according to the first index result of each candidate road zone combination;

[0146] The screening module 503 screens out target road area sets and target road area combinations according to the second indicator results of each road area set.

[0147] In the embodiment of the present invention, the construction module 501 is further used to: pre-set one or more coverage ratios; for each coverage ratio, calculate the number of road areas corresponding to the coverage ratio according to the total number of each road area; and filter out a road area set corresponding to the number of road areas from each road area according to a preset rule.

[0148] In the embodiment of the present invention, the order quantity attribute includes the maximum total order quantity and the minimum total order quantity of the preset road area combination, the area attribute includes the maximum total area of ​​the preset road area combination, and the road area number attribute includes the maximum total road area number of the preset road area combination; the calculation module 502 is further used to: obtain the total order quantity, total area and total road area number of the road area set;

[0149] According to the total order quantity, total area and total number of road areas of the road area set, as well as the maximum and minimum total order quantity, the maximum total area and the maximum number of road areas, the maximum and minimum number of people involved in the road area set are calculated;

[0150] Determine whether the minimum number of people invested is less than or equal to the maximum number of people invested;

[0151] If so, take each value between the minimum number of people invested and the maximum number of people invested as the number of people invested;

[0152] If not, the road area set is reconstructed according to each road area in the road area set, and the number of people corresponding to the reconstructed road area set is calculated according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination.

[0153] In an embodiment of the present invention, the calculation module 502 is further used to: calculate the first number of people based on the total area and the maximum value of the total area; calculate the second number of people based on the total number of orders and the maximum value of the total number of orders; calculate the third number of people based on the total number of road areas and the maximum value of the total number of road areas; calculate the maximum number of people invested based on the total number of orders and the minimum value of the total number of orders; select the largest one from the first number of people, the second number of people and the third number of people as the minimum number of people invested.

[0154] In the embodiment of the present invention, the calculation module 502 is further used to: sort each road area in the road area set according to a preset index; filter out each first road area set from the road area set according to the sorting result, in which the ratio of the total area to the maximum total area is less than the maximum number of people invested, and the ratio of the total number of road areas to the maximum number of road areas is less than the maximum number of people invested; use the first road area set with the largest number of road areas as the second road area set; determine whether the ratio of the total order quantity of the second road area set to the minimum total order quantity is less than the maximum number of people invested;

[0155] If yes, update the maximum number of people involved, update the second road area set according to the updated maximum number of people involved, and use the updated second road area set as the reconstructed road area set;

[0156] If not, obtain the geographical location information of each road area in the candidate road area set, filter out the largest connected subgraph from the second road area set according to the geographical location information, and use the largest connected subgraph as the reconstructed road area set.

[0157] In the embodiment of the present invention, the first path rule model includes a target loss function based on capacity constraints, and the calculation module 502 is further used to: calculate each road zone combination corresponding to the road zone set when the target loss function is minimized according to the road zone set and the corresponding number of people invested, and the target loss function based on capacity constraints,

[0158] Among them, the target loss function based on capacity limitation includes distance loss function and order balance loss function. The capacity limitation includes order limitation for each number of people, area limitation and number of road zones. The distance loss function is constructed according to the distance between road zones, and the order loss function is constructed according to the order quantity of each road zone.

[0159] In the embodiment of the present invention, the second planning model includes an objective function based on a time window restriction, and the calculation module 502 is further used to: for each candidate road area combination, obtain an order point set corresponding to the candidate road area combination, and calculate the minimum value of the objective function according to the order point set and the objective function based on the time window restriction; calculate the first indicator result of the candidate road area set according to the minimum value of the objective function;

[0160] Among them, the time window restriction includes the arrival time restriction of each order point in the set of all order points, and the objective function is constructed according to the distance between the order points in the set of order points.

[0161] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the road zone combination method provided by the present invention.

[0162] According to another aspect of an embodiment of the present invention, a computer readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the road zone combination method provided by the present invention is implemented.

[0163] Figure 6 An exemplary system architecture 600 to which the road-region combination method or road-region combination device according to the embodiment of the present invention can be applied is shown.

[0164] like Figure 6As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0165] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 601, 602, 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0166] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0167] The server 605 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 601, 602, and 603. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0168] It should be noted that the road zone combination method provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the road zone combination device is generally disposed in the server 605 .

[0169] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0170] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present invention. Figure 7 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0171] like Figure 7As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0172] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0173] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0174] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0175] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0176] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor, for example, it may be described as: a processor includes a construction module, a calculation module and a screening module. The names of these modules do not constitute a limitation on the modules themselves in some cases. For example, the construction module may also be described as "a module for obtaining each road area to be combined corresponding to the current station and constructing multiple road area sets according to each road area".

[0177] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: obtaining each road area to be combined corresponding to the current station, constructing multiple road area sets according to each road area, and each road area set includes at least two road areas; for each road area set, calculating the number of people corresponding to the road area set according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination; according to the road area set and the corresponding number of people, using the first path planning model to generate each road area combination corresponding to the road area set; screening each candidate road area combination from each road area combination, using the second path planning model to calculate the first index result of each candidate road area combination, and calculating the second index result of the road area set according to the first index result of each candidate road area combination; screening the target road area set and the target road area combination according to the second index result of each road area set.

[0178] According to the technical solution of the embodiment of the present invention, the road area combination method of the embodiment of the present invention constructs multiple road area sets through the road areas to be combined at the site, and determines the number of people to be invested for each road area set according to the attributes of the preset road area combination, so as to realize the flexible deployment of the number of people in different road area sets; solves the optimization problem of road area combination through the first path planning model, obtains each road area combination of each road area set, and simulates the first index result of each road area combination and the second index result of each road area set through the second path planning model, so as to screen out the target road area set. The road area combination obtained by the road area combination method can improve work efficiency while meeting the workload requirements, and ensure the workload balance among the delivery personnel, improve the work enthusiasm of the delivery personnel, and reduce the operating cost.

[0179] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A road area combination method, characterized in that: include: Acquire each road area to be combined corresponding to the current site, and construct multiple road area sets according to each road area, each road area set including at least two road areas; For each of the road area sets, the number of people involved corresponding to the road area set is calculated according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination; according to the road area set and the corresponding number of people involved, each road area combination corresponding to the road area set is generated by using the first path planning model; each candidate road area combination is screened out from the each road area combination, the first index result of each candidate road area combination is calculated by using the second path planning model, and the second index result of the road area set is calculated according to the first index result of each candidate road area combination; The target road area set and the target road area combination are screened out according to the second indicator results of each road area set.

2. The method according to claim 1, characterized in that Construct multiple road area sets based on each road area, including: Preset one or more coverage ratios; For each of the coverage ratios, the number of road areas corresponding to the coverage ratio is calculated according to the total number of the road areas; A road area set corresponding to the number of road areas is screened out from the various road areas according to a preset rule.

3. The method according to claim 1, characterized in that The order quantity attribute includes a preset maximum total order quantity and a preset minimum total order quantity of a road area combination, the area attribute includes a preset maximum total area of ​​a road area combination, and the road area number attribute includes a preset maximum total road area number of a road area combination; Calculating the number of people corresponding to the road zone set according to the preset single quantity attribute, area attribute and road zone number attribute of the road zone combination includes: Obtain the total order quantity, total area and total number of road areas of the road area set; According to the total order quantity, total area and total number of road areas of the road area set, as well as the maximum and minimum total order quantity, the maximum total area and the maximum number of road areas, the maximum number of people involved and the minimum number of people involved corresponding to the road area set are calculated; Determine whether the minimum number of people involved is less than or equal to the maximum number of people involved; If so, each value between the minimum number of people invested and the maximum number of people invested is used as the number of people invested; If not, the road area set is reconstructed according to each road area in the road area set, and the number of people corresponding to the reconstructed road area set is calculated according to the single quantity attribute, area attribute and road area number attribute of the preset road area combination.

4. The method according to claim 3, characterized in that The maximum number of people involved and the minimum number of people involved corresponding to the road zone set are calculated, including: Calculate a first number of people according to the total area and the maximum value of the total area; Calculate the second number of people according to the total number of orders and the maximum value of the total number of orders; Calculate the third person number according to the total number of road areas and the maximum number of the total number of road areas; The maximum number of people involved is calculated based on the total number of orders and the minimum number of total orders; The largest one is selected from the first number of people, the second number of people and the third number of people as the minimum number of people invested.

5. The method according to claim 3, characterized in that: Reconstructing the road zone set according to each road zone in the road zone set includes: Sorting each road area in the road area set according to a preset index; According to the sorting result, first road area sets are selected from the road area sets, wherein the ratio of the total area to the maximum total area is less than the maximum number of people, and the ratio of the total number of road areas to the maximum total number of road areas is less than the maximum number of people; and the first road area set with the largest number of road areas is used as the second road area set; Determine whether the ratio of the total number of orders of the second road zone set to the minimum total number of orders is less than the maximum number of people involved; If yes, update the maximum number of people involved, update the second road area set according to the updated maximum number of people involved, and use the updated second road area set as the reconstructed road area set; If not, obtain the geographical location information of each road area in the candidate road area set, filter out the largest connected subgraph from the second road area set according to the geographical location information, and use the largest connected subgraph as the reconstructed road area set.

6. The method according to claim 1, characterized in that The first path rule model includes a target loss function based on capacity constraints, and uses the first path planning model to generate each road zone combination corresponding to the road zone set, including: According to the road zone set and the corresponding number of people involved, and the target loss function based on capacity limitation, each road zone combination corresponding to the road zone set when the target loss function is minimized is calculated, Among them, the target loss function based on capacity limitation includes a distance loss function and an order balance loss function. The capacity limitation includes order limitation for each number of people, area limitation and road zone number limitation. The distance loss function is constructed based on the distance between road zones, and the order loss function is constructed based on the order quantity of each road zone.

7. The method according to claim 1, characterized in that The second planning model includes an objective function based on a time window restriction, and the second path planning model is used to calculate a first indicator result of each candidate road zone combination, including: For each candidate road zone combination, obtain the order point set corresponding to the candidate road zone combination, calculate the minimum value of the objective function according to the order point set and the objective function based on the time window restriction; calculate the first indicator result of the candidate road zone set according to the minimum value of the objective function; The time window restriction includes the arrival time restriction of each order point in the set of all order points, and the objective function is constructed according to the distance between the order points in the set of order points.

8. A road area combination device, characterized in that: include: A construction module, which obtains each road area to be combined corresponding to the current site, and constructs a plurality of road area sets according to each road area, each road area set including at least two road areas; The calculation module calculates the number of people corresponding to each road zone set according to the preset single quantity attribute, area attribute and road zone number attribute of the road zone combination; generates each road zone combination corresponding to the road zone set by using the first path planning model according to the road zone set and the corresponding number of people; selects each candidate road zone combination from each road zone combination, calculates the first index result of each candidate road zone combination by using the second path planning model, and calculates the second index result of the road zone set according to the first index result of each candidate road zone combination; The screening module screens out target road area sets and target road area combinations according to the second indicator results of each road area set.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.