Road area division method and device

Abstract

The invention discloses a road area division method and device, and relates to the technical field of logistics. A specific embodiment of the method comprises the following steps: for each road area of a current station, obtaining an actual order quantity and an estimated order quantity of the road area in a first time period, and obtaining a diagnosis result of the road area according to the actual order quantity and the estimated order quantity; dividing each road area of the current station according to the diagnosis result of each road area to obtain a plurality of division schemes; and screening out a target division scheme from the multiple division schemes according to a preset rule, and dividing each road area according to the target division scheme. According to the embodiment, the deliveryman can be stimulated according to the collection capability of the deliveryman, the personnel efficiency is improved, the cost is reduced, and the time-efficient experience of the user is improved.

Description

Technical Field

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

[0002] In the field of logistics, it is necessary to divide the delivery range of a site into multiple road areas and assign corresponding delivery personnel to each road area so that the delivery personnel are responsible for collecting and delivering items in the corresponding road area.

[0003] In the related technologies, the road area division methods mainly include expert strategies, clustering algorithms, local search algorithms, etc. However, the results obtained by expert strategies and clustering algorithms are not good, and the local search algorithm lacks incentives for the initiative of delivery personnel, resulting in low personnel efficiency and poor user experience. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a road area division method and device, which can motivate delivery personnel according to their collection capabilities, thereby improving personnel efficiency, reducing costs, and improving users' timeliness experience.

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

[0006] For each road section of the current station, obtaining an actual order quantity and an estimated order quantity of the road section in a first time period, and obtaining a diagnosis result of the road section according to the actual order quantity and the estimated order quantity;

[0007] Dividing each road area of ​​the current station according to the diagnosis result of each road area to obtain multiple division schemes;

[0008] A target division scheme is selected from the multiple division schemes according to a preset rule, and each road area is divided according to the target division scheme.

[0009] Optionally, the road area includes one or more sub-areas;

[0010] Obtaining the estimated order quantity of the road area in the first time period, including:

[0011] For each sub-region, acquiring characteristic data of the sub-region in the second time period; inputting the characteristic data into an order quantity estimation model to obtain an estimated order quantity of the sub-region in the first time period;

[0012] The estimated order volume of each sub-area in the road area is summed up to obtain the estimated order volume of the road area within the first time.

[0013] Optionally, the order quantity estimation model is obtained by the following training method:

[0014] Obtaining historical order volume, points of interest distribution data, and user distribution data in the sub-area within a third time period;

[0015] Constructing sample feature data according to the historical order volume, point of interest distribution data and user distribution data of the sub-area;

[0016] The order quantity estimation model is trained based on the sample feature data and the order quantity in the fourth time period.

[0017] Optionally, obtaining a diagnosis result of the road area according to the actual order quantity and the estimated order quantity includes:

[0018] In response to a difference between the actual order quantity and the estimated order quantity being greater than a preset order quantity threshold, determining that the diagnosis result of the road area is a first diagnosis result;

[0019] In response to the difference between the estimated order quantity and the actual order quantity being greater than the preset order quantity threshold, the diagnosis result of the road area is determined to be a second diagnosis result.

[0020] Optionally, the road areas of the current station are divided according to the diagnosis result of each road area to obtain multiple division schemes, including:

[0021] Acquire, from the road areas, each first road area having a diagnosis result that is a first diagnosis result and each second road area having a diagnosis result that is a second diagnosis result;

[0022] One or more sub-areas in the second road area are divided into the first road area according to a road area division algorithm to obtain multiple division schemes, wherein the road area division algorithm is at least one of a local search algorithm, a taboo search algorithm, and a particle swarm algorithm.

[0023] Optionally, selecting a target partitioning scheme from the multiple partitioning schemes according to a preset rule includes:

[0024] For each division scheme, obtaining each candidate road area obtained by division using the division scheme;

[0025] For each candidate road area, obtaining the actual order volume and the estimated order volume of the candidate road area in the first time period; obtaining the order volume ratio of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area;

[0026] Calculate the target value corresponding to the division scheme according to the actual order volume of each candidate road area, the order volume ratio, the average actual order volume of each candidate road area, and the number of each candidate road area;

[0027] The partitioning scheme with the smallest target value is taken as the target partitioning scheme.

[0028] Optionally, calculating the order quantity ratio of the candidate road area according to the actual order quantity and the estimated order quantity of the candidate road area includes:

[0029] Determine the diagnosis result of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area;

[0030] In response to the diagnosis result being the first diagnosis result or the second diagnosis result, calculating the weight of the candidate road section according to the actual order volume and the estimated order volume of each candidate road section;

[0031] In response to the diagnosis result not being one of the first diagnosis result and the second diagnosis result, using a preset value as a weight of the candidate road area;

[0032] The order quantity ratio of the candidate road area is calculated according to the weight of the candidate road area and the sum of the weights of each candidate road area.

[0033] According to another aspect of an embodiment of the present invention, there is provided a road area division device, comprising:

[0034] An acquisition module, for each road section of the current station, acquires an actual order quantity and an estimated order quantity of the road section in a first time period, and obtains a diagnosis result of the road section according to the actual order quantity and the estimated order quantity;

[0035] A division module, which divides each road area of ​​the current station according to the diagnosis result of each road area to obtain multiple division schemes;

[0036] The screening module screens out a target partitioning scheme from the multiple partitioning schemes according to a preset rule, and divides each road area according to the target partitioning scheme.

[0037] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0038] one or more processors;

[0039] a storage device for storing one or more programs,

[0040] When the one or more programs are executed by the one or more processors, the one or more processors implement the road area division method provided by the present invention.

[0041] 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 area division method provided by the present invention is implemented.

[0042] One embodiment of the above invention has the following advantages or beneficial effects: the road zone division method of the embodiment of the present invention first obtains the actual order volume and estimated order volume of each road zone in the first time period, and then obtains the diagnosis result of the road zone based on the actual order volume and the estimated order volume, and divides each road zone according to the diagnosis result of the road zone to obtain multiple division schemes, and selects the target division scheme from the multiple division schemes according to the preset rules to divide the road zone according to the target division scheme. The road zone division method judges the diagnosis result of the road zone according to the actual order volume and the estimated order volume of the road zone to judge whether the deliveryman's collection ability exceeds expectations or falls short of expectations, thereby realizing road zone adjustment according to the diagnosis result of the road zone, so as to increase the delivery range of the deliveryman who exceeds expectations and reduce the delivery range of the deliveryman who falls short of expectations, so as to achieve the purpose of motivating the deliveryman with collection ability, improve personnel efficiency, reduce costs, and improve the user's time experience.

[0043] 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

[0044] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0045] Figure 1 is a schematic diagram of the main process of a road area division method according to an embodiment of the present invention;

[0046] Figure 2 is a schematic diagram of a process for determining a diagnosis result of a road area according to an embodiment of the present invention;

[0047] Figure 3 is a schematic flow chart of a road area division method according to an embodiment of the present invention;

[0048] Figure 4 is a schematic diagram of a comparison before and after a road zone adjustment according to an embodiment of the present invention;

[0049] Figure 5 is a schematic diagram of main modules of a road area division device according to an embodiment of the present invention;

[0050] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0051] 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

[0052] 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.

[0053] In the field of logistics, by dividing the distribution range of the site into road zones, different road zones are assigned to different couriers, who are responsible for the collection and delivery within the corresponding road zones. Road zone division can adopt road zone fence planning technology, which is a technical means to combine and divide multiple Areas of Interests (AOIs) in an existing designated area. Different AOIs have different coverage areas and geographical shape attributes, corresponding to the order quantity, difficulty, weight, time and other characteristics of distribution scenarios or transportation scenarios. Under certain geographical factor restrictions, the core of road zone fence planning technology is to find a road zone fence division scheme that meets actual production needs around multiple optimization objectives. Road zone fence planning technology can be used to create efficient distribution or transportation responsibility areas, improve transportation and distribution efficiency, thereby improving personnel efficiency, reducing costs and improving user time experience.

[0054] The relevant technologies mainly use expert strategies, clustering, genetic algorithms, local search, etc. to plan the demand space points to potential AOI combinations, and then generate the circumscribed polygons of these AOI combinations. However, the above methods have the following disadvantages: the division method based on expert strategies depends on the level of experts, and its experience is difficult to quickly replicate on a large scale, and the results are uneven; the clustering algorithm cannot strictly meet the geographical restrictions required under objective production conditions in actual implementation, such as the prohibition of flying islands (the phenomenon of isolated AOIs or road areas being divided into non-adjacent points), etc., and the clustering stage only considers the constraints without considering the optimization goals, and finally adopts a small-scale search to try to find the optimal solution, so that the optimization degree of the final solution cannot be guaranteed, and the actual effect is poor; the genetic algorithm needs to rely on large-scale population search, which brings large-scale computing costs and time overhead; the local search algorithm does not require too much expert experience, can consider multiple factors at the same time, and set goals and constraints according to the actual business scenario, but it mainly divides the road area by considering the order volume, delivery time, and delivery distance, with the purpose of balancing efficiency and the production capacity of each deliveryman, and lacks incentives for the initiative of the deliveryman.

[0055] Based on the above problems, an embodiment of the present invention provides a road zone division method, which can motivate the initiative of delivery personnel, enhance work enthusiasm, improve personnel efficiency, reduce costs, and thus enhance the user's timeliness experience.

[0056] Figure 1 FIG. 1 is a schematic diagram of the main process of a road area division method according to an embodiment of the present invention. Figure 1 As shown, the road area division method includes the following steps:

[0057] Step S101: for each road area of ​​the current station, the actual order quantity and the estimated order quantity of the road area in the first time period are obtained, and a diagnosis result of the road area is obtained according to the actual order quantity and the estimated order quantity;

[0058] Step S102: Divide each road area of ​​the current station according to the diagnosis result of each road area to obtain multiple division schemes;

[0059] Step S103: Filter out a target division scheme from multiple division schemes according to preset rules, and divide each road area according to the target division scheme.

[0060] In the embodiment of the present invention, in the field of logistics, each logistics site has a corresponding delivery range, which is divided into multiple areas, i.e., multiple road areas, and each area is assigned a delivery person, who is responsible for collecting and delivering orders in their respective areas. That is, the delivery range of the current site is divided into multiple road areas, and for each road area of ​​the current site, the actual order volume of the road area in the first time period is obtained, wherein the first time period is a preset historical time period, and the actual order volume includes the number of collected orders.

[0061] When obtaining the actual order volume of a road area in the first time period, the various sub-areas contained in the road area can be first obtained, the actual order volume of each sub-area in the first time period can be obtained, and then the actual order volume of each sub-area can be summed up to obtain the actual order volume of the road area in the first time period. The sub-area can be an area of ​​interest, i.e., AOI, and each AOI is a map polygon with corresponding information attributes such as name, geographic information, order volume, and delivery difficulty.

[0062] Among them, the actual number of orders in each sub-region within the first time period is determined according to the collection address of each order, that is, it is necessary to determine the order list corresponding to each sub-region. Specifically, first obtain the order list corresponding to the current site within the first time period, and each order in the order list is a collection order; according to the collection address and map data of each order in the order list, obtain the location coordinates of the collection address of each order on the map, and map the location coordinates to the geocoding block, that is, determine the geocoding block where the location coordinates are located. The geocoding block is obtained by dividing according to longitude and latitude. The size of the geocoding block can be customized. The coordinates of the geocoding block can be represented by the center point of the geocoding block, so that the geocoding block corresponding to each order can be obtained; since each sub-region is a closed area composed of multiple boundary coordinates, according to the center point of each geocoding block and the boundary coordinates of the sub-region, determine whether the geocoding block is within the sub-region. If the geocoding block is within the sub-region, then take each order corresponding to the geocoding block as the order corresponding to the sub-region, so as to obtain the number of orders for each sub-region.

[0063] In an embodiment of the present invention, a road area includes one or more sub-areas; obtaining an estimated order volume of the road area within a first time period includes: for each sub-area, obtaining characteristic data of the sub-area within a second time period; inputting the characteristic data into an order volume estimation model to obtain an estimated order volume of the sub-area within the first time period; adding up the estimated order volume of each sub-area in the road area to obtain the estimated order volume of the road area within the first time period.

[0064] In the embodiment of the present invention, since each road area includes one or more sub-areas, for each sub-area, characteristic data of the sub-area in the second time period is obtained, and the second time period corresponds to the first time period, and the second time period is the historical time period corresponding to the first time period, such as the first time period is the last week, and the second time period is the week before last. The characteristic data is obtained based on the constructed features. After the characteristic data of the sub-area in the second time period is obtained, the characteristic data is input into the order quantity estimation model to obtain the estimated order quantity of the sub-area in the first time period, and the sum of the estimated order quantities of each sub-area is the estimated order quantity of the road area.

[0065] In this embodiment of the present invention, the estimated order volume of a road area in a first time period can be obtained based on the average value of the estimated order volume of the road area in multiple second time periods. The estimated order volume of the road area in each second time period is the sum of the estimated order volume of each sub-area in the road area in each second time period.

[0066] In an embodiment of the present invention, the order quantity prediction model is obtained by the following training method: obtaining the historical order quantity, interest point distribution data and user distribution data in the sub-area within the third time period; constructing sample feature data based on the historical order quantity, interest point distribution data and user distribution data of the sub-area; and training the order quantity prediction model based on the sample feature data and the order quantity in the fourth time period.

[0067] In an embodiment of the present invention, the order volume estimation model is obtained by training based on the sample feature data and its corresponding sample labels, and the order volume estimation model can be a regression model. Specifically, firstly, the historical order volume, point of interest (POI, coordinate point) distribution data and user distribution data of the sub-area in the third time period are obtained. The third time period is a historical time period relative to the second time period. The point of interest distribution data includes the type of point of interest, the number and proportion of each type of point of interest, and the user distribution data includes the number of users corresponding to the historical order volume. Thus, the sample feature data is constructed according to the historical order volume, point of interest distribution data and user distribution data of the sub-area, and the training sample set is obtained according to the sample feature data. The sample label is the order volume in the fourth time period, and the third time period is the historical time period corresponding to the fourth time period, such as the fourth time period is the last month, and the third time period is the month before the last month. During the training process, the prediction accuracy is calculated according to the label predicted by the model and the sample label. If the prediction accuracy reaches the set accuracy (such as the set accuracy is 15%), the condition is met, the iteration ends, and the order volume estimation model is obtained. If the condition is not met, the iteration continues.

[0068] Since the order volume of a sub-area is strongly correlated with the distribution of internal points of interest, when training the order volume estimation model, in order to improve the accuracy of model estimation, the sub-areas can be divided into different types according to the types of points of interest. For example, if the POI type of shopping services accounts for a large proportion in a sub-area, the type of the sub-area is shopping service type, and then the training samples of each type of sub-area are screened. For example, training samples with a collection timeliness rate higher than the preset timeliness rate can be selected to train the order volume estimation model.

[0069] In an embodiment of the present invention, a diagnosis result of a road area is obtained based on the actual order quantity and the estimated order quantity, including: in response to the difference between the actual order quantity and the estimated order quantity being greater than a preset order quantity threshold, determining the diagnosis result of the road area to be a first diagnosis result; in response to the difference between the estimated order quantity and the actual order quantity being greater than the preset order quantity threshold, determining the diagnosis result of the road area to be a second diagnosis result.

[0070] In an embodiment of the present invention, before the diagnosis result of the road area can be obtained according to the actual order volume and the estimated order volume of the road area, a diagnosis rule is configured, and the diagnosis result of the road area is determined according to the diagnosis rule, and the diagnosis rule includes the diagnosis rule of exceeding expectations and falling short of expectations. The actual order volume of the road area is compared with the estimated order volume. If the actual order volume is greater than the estimated order volume, such as the difference between the actual order volume and the estimated order volume is greater than the preset order volume threshold, the diagnosis result of the road area is determined to be the first diagnosis result, and the first diagnosis result is a diagnosis result that exceeds expectations; if the actual order volume is less than the estimated order volume, such as the difference between the estimated order volume and the actual order volume is greater than the preset order volume threshold, the diagnosis result of the road area is determined to be the second diagnosis result, and the second diagnosis result is a diagnosis result that is lower than expectations. If the actual order volume is equal to the estimated order volume, or the difference between the actual order volume and the estimated order volume (or the difference between the estimated order volume and the actual order volume) is less than or equal to the preset order volume threshold, the diagnosis result of the road area is the third diagnosis result, and the third diagnosis result is a diagnosis result that is basically the same as expectations. Among them, the preset order volume threshold can be customized according to business needs, such as being set to 2. If the diagnosis result of the road area is beyond expectations, it means that the road area has collection potential, and the delivery personnel corresponding to the road area can be incentivized to improve their initiative.

[0071] Figure 2 The present invention is a flowchart of a road area diagnosis result according to an embodiment of the present invention. First, AOI feature data is obtained, and the order quantity estimation model is trained using the AOI feature data. The estimation accuracy is analyzed during the training process. If the estimation accuracy is reached, the road area is diagnosed according to the diagnosis rules. If the estimation accuracy is not reached, the model is iterated until the estimation accuracy is reached, and the training is completed to obtain the order quantity estimation model. The estimated order quantity of each AOI can be obtained through the order quantity estimation model. The road area is diagnosed according to the actual order quantity and estimated order quantity of each AOI and the diagnosis rules to obtain a diagnosis result of whether the road area exceeds or falls short of expectations.

[0072] In the embodiment of the present invention, the road areas of the current station are divided according to the diagnosis result of each road area, and multiple division schemes are obtained, including:

[0073] Acquire, from each road area, each first road area having a diagnosis result that is a first diagnosis result and each second road area having a diagnosis result that is a second diagnosis result;

[0074] One or more sub-areas in the second road area are divided into the first road area according to a road area division algorithm to obtain multiple division schemes, wherein the road area division algorithm is at least one of a local search algorithm, a taboo search algorithm, and a particle swarm algorithm.

[0075] In an embodiment of the present invention, after obtaining the diagnosis result of each road area of ​​the current site, each road area can be divided according to the diagnosis result of each road area to adjust the size of each road area. The road area division can be performed in a variety of ways to obtain a variety of division schemes, each of which includes the sub-areas contained in each road area.

[0076] Specifically, after obtaining the diagnosis result of each road area, the first road area of ​​the first diagnosis result and the second road area of ​​the second diagnosis result are screened out from each road area, and the third road area of ​​the third diagnosis result can also be screened out; then, each road area is divided according to each sub-area, such as adjusting the first road area and the second road area, such as dividing one or more sub-areas in the second road area into the first road area, or dividing one or more sub-areas in the third road area and the second road area into the first road area. A road area division algorithm can be used for road area division, and multiple road area division schemes can be quickly generated. The road area division algorithm can be a heuristic search algorithm, such as at least one of a local search algorithm, a taboo search algorithm, and a particle swarm algorithm.

[0077] When using the road zone division algorithm to divide the road area, the business objectives and constraints are defined in advance according to business needs. First, the feasible solutions are initialized. Each solution corresponds to a division scheme. According to the actual number of orders, estimated number of orders, business objectives and constraints of each sub-area, the feasible solutions are updated through the road zone division algorithm to obtain multiple division schemes. Among them, the business objectives are set according to business needs. The business objectives can be to improve personnel efficiency or the potential for growth in collection, so that sub-areas with growth potential are allocated to delivery personnel with strong collection capabilities, and each delivery person is guaranteed to have a certain amount of collection growth orders to improve the work enthusiasm of the delivery personnel.

[0078] Among them, the feasible solution is updated through the road area division algorithm to obtain multiple division schemes, and the specific reference can be made to patents CN116645022A and CN118057423. For example, if a local search algorithm is used, the initialization division schemes of multiple road areas are first constructed, and then multiple seed sub-areas are selected, and the sub-areas around each seed sub-area are merged into the seed sub-area until all sub-areas are merged to obtain a division scheme, wherein the seed sub-areas can be selected in order from high to low according to the actual unit quantity.

[0079] If the taboo search algorithm is used, multiple pairs of adjacent road areas are selected in each iteration, and the sub-areas on the borders of the adjacent road areas are exchanged in the direction of reducing the goose formation loss value. If the exchange fails, the road area pair is added to the taboo list and no longer exchanged until the sub-areas contained in at least one of the road areas change, then the road area pair is removed from the taboo list.

[0080] If the particle swarm algorithm is used, a vector can be used to represent the correspondence between each sub-area and the road area. The direction and speed of the next iteration can be determined through the motion equation of the particle swarm algorithm. The spatial connectivity is checked in each iteration to ensure the shape of the road area.

[0081] In an embodiment of the present invention, a target partitioning scheme is screened out from a plurality of partitioning schemes according to a preset rule, including:

[0082] For each division scheme, obtain each candidate road area obtained by using the division scheme;

[0083] For each candidate road area, obtaining the actual order volume and the estimated order volume of the candidate road area in the first time period; obtaining the order volume ratio of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area;

[0084] Calculate the target value corresponding to the division scheme according to the actual order volume of each candidate road area, the order volume ratio, the actual order volume average of each candidate road area, and the number of each candidate road area;

[0085] The partitioning scheme with the smallest target value is taken as the target partitioning scheme.

[0086] In an embodiment of the present invention, after obtaining a plurality of road zone division schemes, it is necessary to screen the plurality of road zone division schemes to divide the road zones according to the target division scheme. First, obtain each candidate road zone obtained by each division scheme, each candidate road zone contains one or more sub-areas, obtain the actual order volume and estimated order volume of the candidate road zone according to the actual order volume and estimated order volume of each sub-area in the candidate road zone in the first time period, and then obtain the order volume ratio according to the actual order volume and estimated order volume of the candidate road zone; obtain the expected order volume of the candidate road zone according to the order volume ratio and the average actual order volume of each candidate road zone and the number of each candidate road zone, calculate the loss value of the candidate road zone according to the actual order volume and expected order volume of the candidate road zone, add up the loss values ​​of each candidate road zone, and obtain the target value corresponding to the division scheme. Then select the division scheme with the smallest target value as the target division scheme. Using the target division scheme for division can motivate the delivery personnel and improve personnel efficiency. Among them, the objective function for calculating the minimum target value can be shown as formula (1),

[0087] , formula (1),

[0088] In formula (1), cost represents the objective function of the business objective, N is the number of candidate road areas, is the actual number of orders for the i-th AOI in the candidate road area, is the unit quantity ratio of the candidate road area, is the average number of orders for each candidate road area.

[0089] In an embodiment of the present invention, calculating the order quantity ratio of the candidate road area according to the actual order quantity and the estimated order quantity of the candidate road area includes:

[0090] Determine the diagnosis result of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area;

[0091] In response to the diagnosis result being the first diagnosis result or the second diagnosis result, calculating the weight of the candidate road section according to the actual order volume and the estimated order volume of each candidate road section;

[0092] In response to the diagnosis result not being one of the first diagnosis result and the second diagnosis result, using a preset value as a weight of the candidate road area;

[0093] The order quantity ratio of the candidate road area is calculated according to the weight of the candidate road area and the sum of the weights of each candidate road area.

[0094] In the embodiment of the present invention, when calculating the order volume ratio of the candidate road area, the diagnosis result of the candidate road area is first determined according to the actual order volume and the estimated order volume of the candidate road area. If the candidate road area is the first diagnosis result or the second diagnosis result, that is, it exceeds expectations or is lower than expectations, the calculation formula of the weight of the candidate road area is as shown in formula (2):

[0095] , formula (2),

[0096] in, is the weight of the j-th candidate road area, is the actual number of orders for the i-th AOI in the candidate road area, is the estimated order quantity of the i-th AOI in the candidate road area;

[0097] If the candidate road area is neither the first diagnosis result nor the second diagnosis result, that is, the third diagnosis result, the weight of the candidate road area is a preset value, such as 1. The single quantity ratio of the candidate road area is the ratio of the weight of the candidate road area to the sum of the weights of each candidate road area, that is, the single quantity ratio .

[0098] Figure 3The present invention is a flowchart of a road zone division method according to an embodiment of the present invention. Business data is obtained, including station information and order width table, so as to obtain an order list corresponding to the current station, and the characteristic data of each AOI is obtained in combination with map data, and the estimated order quantity of each AOI is obtained according to the characteristic data of each AOI, and the diagnosis result of each road zone is obtained according to the actual order quantity and estimated order quantity of each AOI; business problems are defined based on business needs, including defining business goals, constraints, etc., and then any road zone division algorithm is used to divide the road zone to obtain multiple division schemes; the target value of each division scheme is calculated, and the multiple division schemes are sorted according to the target value, and the target division scheme with the smallest target value is output, so as to adjust the road zone according to the target division scheme.

[0099] Figure 4 : is a schematic diagram of the road area before and after adjustment obtained by the road area division method of the embodiment of the present invention. Among them, (a) is each road area before adjustment, and (b) is each road area after adjustment. It can be seen that the shape of each road area has changed before and after adjustment. For example, the collection capacity and willingness of road area 029 are stronger than those of other surrounding road areas, so more AOIs with collection potential are divided into road area 029. It can be seen that the adjusted road area 029 includes the AOI on the left, and the AOI below the road area 003 is also divided into the road area 003, thereby realizing the incentive for the delivery personnel in the corresponding road area.

[0100] The road zone division method of the embodiment of the present invention first obtains the actual order volume and estimated order volume of each road zone in the first time period, and then obtains the diagnosis result of the road zone based on the actual order volume and the estimated order volume, and divides each road zone according to the diagnosis result of the road zone to obtain multiple division schemes, and selects the target division scheme from the multiple division schemes according to the preset rules to divide the road zone according to the target division scheme. The road zone division method determines the diagnosis result of the road zone according to the actual order volume and the estimated order volume of the road zone to determine whether the deliveryman's collection ability exceeds expectations or falls short of expectations, thereby realizing road zone adjustment according to the diagnosis result of the road zone, so as to increase the delivery range of the deliveryman who exceeds expectations and reduce the delivery range of the deliveryman who falls short of expectations, so as to achieve the purpose of motivating the deliveryman with collection ability, improve personnel efficiency, reduce costs, and improve the user's time experience.

[0101] According to another aspect of the embodiment of the present invention, Figure 5 As shown, a road area division device 500 is provided, comprising:

[0102] An acquisition module 501 acquires, for each road section of the current station, an actual order quantity and an estimated order quantity of the road section in a first time period, and obtains a diagnosis result of the road section according to the actual order quantity and the estimated order quantity;

[0103] A division module 502 divides each road area of ​​the current station according to the diagnosis result of each road area to obtain multiple division schemes;

[0104] The screening module 503 screens out a target partitioning scheme from a plurality of partitioning schemes according to a preset rule, and divides each road area according to the target partitioning scheme.

[0105] In an embodiment of the present invention, the road area includes one or more sub-areas; the acquisition module 501 is further used to: for each sub-area, obtain characteristic data of the sub-area in the second time period; input the characteristic data into the order quantity estimation model to obtain the estimated order quantity of the sub-area in the first time period; add up the estimated order quantity of each sub-area in the road area to obtain the estimated order quantity of the road area in the first time period.

[0106] In an embodiment of the present invention, in the acquisition module 501, the order quantity estimation model is obtained by the following training method: obtaining the historical order quantity, interest point distribution data and user distribution data in the sub-area within the third time period; constructing sample feature data based on the historical order quantity, interest point distribution data and user distribution data of the sub-area; and training the order quantity estimation model based on the sample feature data and the order quantity in the fourth time period.

[0107] In an embodiment of the present invention, the acquisition module 501 is further used to: in response to the difference between the actual order quantity and the estimated order quantity being greater than the preset order quantity threshold, determine that the diagnosis result of the road area is the first diagnosis result; in response to the difference between the estimated order quantity and the actual order quantity being greater than the preset order quantity threshold, determine that the diagnosis result of the road area is the second diagnosis result.

[0108] In an embodiment of the present invention, the division module 502 is further used to: obtain each first road area whose diagnosis result is the first diagnosis result and each second road area whose diagnosis result is the second diagnosis result from each road area; divide one or more sub-areas in the second road area into the first road area according to the road area division algorithm to obtain multiple division schemes, wherein the road area division algorithm is at least one of a local search algorithm, a taboo search algorithm, and a particle swarm algorithm.

[0109] In the embodiment of the present invention, the screening module 503 is further used to: for each division scheme, obtain each candidate road area obtained by using the division scheme;

[0110] For each candidate road area, obtaining the actual order volume and the estimated order volume of the candidate road area in the first time period; obtaining the order volume ratio of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area;

[0111] Calculate the target value corresponding to the division scheme according to the actual order volume of each candidate road area, the order volume ratio, the actual order volume average of each candidate road area, and the number of each candidate road area;

[0112] The partitioning scheme with the smallest target value is taken as the target partitioning scheme.

[0113] In the embodiment of the present invention, the screening module 503 is further used to: determine the diagnosis result of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area;

[0114] In response to the diagnosis result being the first diagnosis result or the second diagnosis result, calculating the weight of the candidate road section according to the actual order volume and the estimated order volume of each candidate road section;

[0115] In response to the diagnosis result not being one of the first diagnosis result and the second diagnosis result, using a preset value as a weight of the candidate road area;

[0116] The order quantity ratio of the candidate road area is calculated according to the weight of the candidate road area and the sum of the weights of each candidate road area.

[0117] 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 area division method provided by the present invention.

[0118] 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 area division method provided by the present invention is implemented.

[0119] Figure 6 An exemplary system architecture 600 to which the road zone division method or road zone division device according to the embodiment of the present invention can be applied is shown.

[0120] like Figure 6 As 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] It should be noted that the road area division method provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the road area division device is generally disposed in the server 605 .

[0125] 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.

[0126] 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.

[0127] like Figure 7 As 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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, may be described as: a processor includes an acquisition module, a division module and a screening module. The names of these modules do not constitute limitations on the modules themselves in certain cases. For example, the acquisition module may also be described as "a module that acquires the actual number of orders and the estimated number of orders for each road area of ​​the current station in the first time period, and obtains the diagnosis result of the road area based on the actual number of orders and the estimated number of orders".

[0133] 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 without being 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: for each road area of ​​the current station, obtaining the actual order volume and estimated order volume of the road area in the first time period, and obtaining the diagnosis result of the road area according to the actual order volume and the estimated order volume; dividing each road area of ​​the current station according to the diagnosis result of each road area, and obtaining multiple division schemes; filtering out a target division scheme from multiple division schemes according to preset rules, and dividing each road area according to the target division scheme.

[0134] According to the technical solution of the embodiment of the present invention, the road zone division method of the embodiment of the present invention first obtains the actual order volume and estimated order volume of each road zone in the first time period, and then obtains the diagnosis result of the road zone based on the actual order volume and the estimated order volume, and divides each road zone according to the diagnosis result of the road zone to obtain multiple division schemes, and selects the target division scheme from the multiple division schemes according to the preset rules to divide the road zone according to the target division scheme. The road zone division method judges the diagnosis result of the road zone according to the actual order volume and the estimated order volume of the road zone to judge whether the deliveryman's collection ability exceeds expectations or falls short of expectations, thereby realizing road zone adjustment according to the diagnosis result of the road zone, so as to increase the delivery range of the deliveryman who exceeds expectations and reduce the delivery range of the deliveryman who falls short of expectations, so as to achieve the purpose of motivating the deliveryman with collection ability, improve personnel efficiency, reduce costs, and improve the user's time experience.

[0135] 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 division method, It is characterized in that include: For each road section of the current station, obtaining an actual order quantity and an estimated order quantity of the road section in a first time period, and obtaining a diagnosis result of the road section according to the actual order quantity and the estimated order quantity; Dividing each road area of ​​the current station according to the diagnosis result of each road area to obtain multiple division schemes; A target division scheme is selected from the multiple division schemes according to a preset rule, and each road area is divided according to the target division scheme.

2. The method according to claim 1, It is characterized in that The road area includes one or more sub-areas; Obtaining the estimated order quantity of the road area in the first time period, including: For each sub-region, acquiring characteristic data of the sub-region in the second time period; inputting the characteristic data into an order quantity estimation model to obtain an estimated order quantity of the sub-region in the first time period; The estimated order volume of each sub-area in the road area is summed up to obtain the estimated order volume of the road area within the first time.

3. The method according to claim 2, It is characterized in that The order quantity estimation model is obtained through the following training method: Obtaining historical order volume, points of interest distribution data, and user distribution data in the sub-area within a third time period; Constructing sample feature data according to the historical order volume, point of interest distribution data and user distribution data of the sub-area; The order quantity estimation model is trained based on the sample feature data and the order quantity in the fourth time period.

4. The method according to claim 1, It is characterized in that Obtaining a diagnosis result of the road area according to the actual order quantity and the estimated order quantity includes: In response to a difference between the actual order quantity and the estimated order quantity being greater than a preset order quantity threshold, determining that the diagnosis result of the road area is a first diagnosis result; In response to the difference between the estimated order quantity and the actual order quantity being greater than the preset order quantity threshold, the diagnosis result of the road area is determined to be a second diagnosis result.

5. The method according to claim 4, It is characterized in that The road areas of the current station are divided according to the diagnosis result of each road area, and multiple division schemes are obtained, including: Acquire, from the road areas, each first road area having a diagnosis result that is a first diagnosis result and each second road area having a diagnosis result that is a second diagnosis result; One or more sub-areas in the second road area are divided into the first road area according to a road area division algorithm to obtain multiple division schemes, wherein the road area division algorithm is at least one of a local search algorithm, a taboo search algorithm, and a particle swarm algorithm.

6. The method according to claim 1, It is characterized in that The target partitioning scheme is screened out from the multiple partitioning schemes according to preset rules, including: For each division scheme, obtaining each candidate road area obtained by division using the division scheme; For each candidate road area, obtaining the actual order volume and the estimated order volume of the candidate road area in the first time period; obtaining the order volume ratio of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area; Calculate the target value corresponding to the division scheme according to the actual order volume of each candidate road area, the order volume ratio, the average actual order volume of each candidate road area, and the number of each candidate road area; The partitioning scheme with the smallest target value is taken as the target partitioning scheme.

7. The method according to claim 6, It is characterized in that Calculating the order quantity ratio of the candidate road area according to the actual order quantity and the estimated order quantity of the candidate road area includes: Determine the diagnosis result of the candidate road area according to the actual order volume and the estimated order volume of the candidate road area; In response to the diagnosis result being the first diagnosis result or the second diagnosis result, calculating the weight of the candidate road section according to the actual order volume and the estimated order volume of each candidate road section; In response to the diagnosis result not being one of the first diagnosis result and the second diagnosis result, using a preset value as a weight of the candidate road area; The order quantity ratio of the candidate road area is calculated according to the weight of the candidate road area and the sum of the weights of each candidate road area.

8. A road area division device, It is characterized in that include: An acquisition module, for each road section of the current station, acquires an actual order quantity and an estimated order quantity of the road section in a first time period, and obtains a diagnosis result of the road section according to the actual order quantity and the estimated order quantity; A division module, which divides each road area of ​​the current station according to the diagnosis result of each road area to obtain multiple division schemes; The screening module screens out a target partitioning scheme from the multiple partitioning schemes according to a preset rule, and divides each road area according to the target partitioning scheme.

9. An electronic device, It is 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, It is characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images