Delivery position determination method and device, electronic equipment and storage medium

Abstract

The invention relates to a distribution position determination method and device, electronic equipment and a storage medium, and the method comprises the steps: determining the number of historical orders in each sub-region of a target region according to the distribution terminal points of a plurality of historical orders in the target region, and enabling the target region to have a plurality of sub-regions; according to the number of the historical orders in each sub-region, at least one peak sub-region is determined in the multiple sub-regions, and the peak sub-region is the sub-region with the maximum number of the historical orders in the range of the corresponding first number of sub-regions; and determining a distribution position in the target area according to the at least one peak value sub-area.

Description

Technical Field

[0001] The present disclosure relates to the technical field of delivery order processing, and in particular, to a method, an apparatus, an electronic device, and a storage medium for determining a delivery location. Background Art

[0002] In recent years, delivery services such as takeout services and express delivery services have brought great convenience to people's lives. The delivery service system needs to coordinate orders and delivery personnel to achieve effective utilization of resources and full guarantee of user experience. When the delivery service system executes services such as determining the delivery time and planning the delivery route, it needs to be based on the accurate delivery location (that is, the delivery end point of the delivery service, accurately speaking, the location where the rider completes the handover of the delivered item); currently, in user gathering areas such as communities and office buildings, it is often impossible to deliver to the user's order address, but to a designated location commonly known as a pick-up point. In related technologies, the delivery service system cannot accurately and real-time know the location of the pick-up points within the service area, that is, cannot accurately and real-time determine the delivery location, resulting in poor accuracy of the delivery service and a decline in user experience. Summary of the Invention

[0003] The present disclosure provides a method, an apparatus, a device, and a storage medium for determining a delivery location to solve the defects in related technologies.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for determining a delivery location is provided, and the method includes:

[0005] Determine the number of historical orders in each sub-region of the target region according to the delivery end points of multiple historical orders in the target region, where there are multiple sub-regions in the target region;

[0006] Determine at least one peak sub-region in the multiple sub-regions according to the number of historical orders in each sub-region, where the peak sub-region is the sub-region with the largest number of historical orders within the range of a corresponding first number of sub-regions;

[0007] Determine the delivery location in the target region according to the at least one peak sub-region.

[0008] In a possible embodiment of the present disclosure, the range of the corresponding first number of sub-regions of the peak sub-region includes: a range composed of the first number of sub-regions centered on the peak sub-region.

[0009] In a possible embodiment of the present disclosure, the determining the peak sub-region in the multiple sub-regions according to the number of historical orders in each sub-region includes:

[0010] Determine the maximum number of sub-regions that the delivery location occupies according to the size of the sub-region and the number of points of interest in the target region;

[0011] Determine peak sub - regions within the top N sub - regions with the largest number of historical orders among the multiple sub - regions, where the value of N is the number of sub - regions occupied by the delivery locations at most.

[0012] In a possible embodiment of the present disclosure, determining peak sub - regions within the multiple sub - regions according to the number of historical orders in each sub - region includes:

[0013] According to the number of historical orders in the sub - region, successively determine extreme - value sub - regions of multiple levels within the multiple sub - regions, and determine the extreme - value sub - region of the highest level as the peak sub - region;

[0014] Among them, determine the extreme - value sub - regions of higher levels within the extreme - value sub - regions of lower levels;

[0015] Among them, the extreme - value sub - region is the sub - region with the largest number of historical orders within the range of the corresponding second number of sub - regions. The second number of the sub - region range corresponding to the extreme - value sub - region of lower level is less than the second number of the sub - region range corresponding to the extreme - value sub - region of higher level. The second number of the sub - region range corresponding to the extreme - value sub - region of the highest level is equal to the first number.

[0016] In a possible embodiment of the present disclosure, the sub - region range of the corresponding second number of the extreme - value sub - region includes: the range composed of the corresponding second number of sub - regions centered on the extreme - value sub - region.

[0017] In a possible embodiment of the present disclosure, the extreme - value sub - regions of multiple levels include the extreme - value sub - regions of the first level and the extreme - value sub - regions of the second level; among them, the sub - region range corresponding to the extreme - value sub - region of the first level includes the extreme - value sub - region and one layer of sub - regions surrounding the extreme - value sub - region, and the sub - region range corresponding to the extreme - value sub - region of the second level includes the extreme - value sub - region and multiple layers of sub - regions surrounding the extreme - value sub - region.

[0018] In a possible embodiment of the present disclosure, determining the delivery locations within the target region according to the at least one peak sub - region includes:

[0019] According to the number of historical orders in the peak sub - region and the number of historical orders in multiple sub - regions adjacent to the peak sub - region, determine the quantity decline degree of the multiple sub - regions adjacent to the peak sub - region, where the quantity decline degree is used to characterize the decline ratio of the number of historical orders in the adjacent sub - regions relative to the number of historical orders in the peak sub - region;

[0020] Determine the sub-regions with the quantity decline degree meeting the preset requirements among the peak sub-region and multiple sub-regions adjacent to the peak sub-region as the distribution area range, and determine the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range, where the preset requirements include at least one of the following:

[0021] The quantity decline degree is less than a preset threshold;

[0022] The quantity decline degree is one of the quantity decline degrees of the third largest quantity among the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region.

[0023] In a possible embodiment of the present disclosure, the determining the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range includes:

[0024] Determine the distribution location corresponding to the peak sub-region according to the mean value of the location coordinates of the delivery end points of historical orders within the distribution area range.

[0025] In a possible embodiment of the present disclosure, the method further includes:

[0026] In response to the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region not meeting the preset requirements, determine the peak sub-region as the distribution area range.

[0027] In a possible embodiment of the present disclosure, the determining the distribution location within the target area according to the at least one peak sub-region includes:

[0028] Determine the distribution location corresponding to the peak sub-region according to the mean value of the location coordinates of the delivery end points of historical orders within the sub-region range of the fourth quantity corresponding to the peak sub-region.

[0029] According to a second aspect of the embodiments of the present disclosure, there is provided a distribution location determining device, the device includes:

[0030] A quantity module, configured to determine the quantity of historical orders within each sub-region of the target area according to the delivery end points of multiple historical orders within the target area, where there are multiple sub-regions within the target area;

[0031] A peak module, configured to determine at least one peak sub-region within the multiple sub-regions according to the quantity of historical orders within each sub-region, where the peak sub-region is the sub-region with the largest quantity of historical orders within the sub-region range corresponding to the first quantity;

[0032] A location module, configured to determine the distribution location within the target area according to the at least one peak sub-region.

[0033] In a possible embodiment of the present disclosure, the range of the first number of sub-regions corresponding to the peak sub-region includes: the range composed of the first number of sub-regions centered on the peak sub-region.

[0034] In a possible embodiment of the present disclosure, the peak module is used for:

[0035] Determine the maximum number of sub-regions occupied by the delivery location according to the size of the sub-region and the number of areas of interest in the target area;

[0036] Determine the peak sub-region among the top N sub-regions with the largest number of historical orders in the multiple sub-regions, where the value of N is the maximum number of sub-regions occupied by the delivery location.

[0037] In a possible embodiment of the present disclosure, the peak module is used for:

[0038] Determine multiple levels of extreme value sub-regions in the multiple sub-regions in sequence according to the number of historical orders in the sub-region, and determine the extreme value sub-region of the highest level as the peak sub-region;

[0039] Among them, determine the extreme value sub-region of the higher level in the extreme value sub-region of the lower level;

[0040] Among them, the extreme value sub-region is the sub-region with the largest number of historical orders within the range of the second number of sub-regions corresponding to it. The second number of the sub-region range corresponding to the extreme value sub-region of the lower level is less than the second number of the sub-region range corresponding to the extreme value sub-region of the higher level. The second number of the sub-region range corresponding to the extreme value sub-region of the highest level is equal to the first number.

[0041] In a possible embodiment of the present disclosure, the range of the second number of sub-regions corresponding to the extreme value sub-region includes: the range composed of the second number of sub-regions centered on the extreme value sub-region.

[0042] In a possible embodiment of the present disclosure, the multiple levels of extreme value sub-regions include the extreme value sub-region of the first level and the extreme value sub-region of the second level; among them, the sub-region range corresponding to the extreme value sub-region of the first level includes the extreme value sub-region and one layer of sub-regions surrounding the extreme value sub-region, and the sub-region range corresponding to the extreme value sub-region of the second level includes the extreme value sub-region and multiple layers of sub-regions surrounding the extreme value sub-region.

[0043] In a possible embodiment of the present disclosure, the position module is used for:

[0044] Determine the quantity decline degree of multiple sub-regions adjacent to the peak sub-region according to the quantity of historical orders in the peak sub-region and the quantity of historical orders in multiple sub-regions adjacent to the peak sub-region, where the quantity decline degree is used to characterize the decline ratio of the quantity of historical orders in adjacent sub-regions relative to the quantity of historical orders in the peak sub-region;

[0045] Determine the sub-regions whose quantity decline degree meets the preset requirements among the peak sub-region and multiple sub-regions adjacent to the peak sub-region as the distribution area range, and determine the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range, where the preset requirements include at least one of the following:

[0046] The quantity decline degree is less than a preset threshold;

[0047] The quantity decline degree is one of the quantity decline degrees of the third largest quantity among the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region.

[0048] In a possible embodiment of the present disclosure, when the location module is used to determine the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range, it is used to:

[0049] Determine the distribution location corresponding to the peak sub-region according to the mean value of the distribution end position coordinates of historical orders within the distribution area range.

[0050] In a possible embodiment of the present disclosure, the device further includes a regional range module, which is used to:

[0051] In response to the fact that the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region do not meet the preset requirements, determine the peak sub-region as the distribution area range.

[0052] In a possible embodiment of the present disclosure, the location module is used to:

[0053] Determine the distribution location corresponding to the peak sub-region according to the mean value of the distribution end position coordinates of historical orders within the sub-region range of the fourth quantity corresponding to the peak sub-region.

[0054] According to the third aspect of the embodiments of the present disclosure, there is provided an electronic device, which includes a memory and a processor. The memory is used to store computer instructions that can run on the processor, and the processor is used to implement the method described in the first aspect when executing the computer instructions.

[0055] According to the fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in the first aspect is implemented.

[0056] According to the above embodiments, it is possible to determine the number of historical orders in each sub-region of the target region based on the delivery destinations of multiple historical orders in the target region, and determine at least one peak sub-region among the multiple sub-regions according to the number of historical orders in each sub-region. Finally, the delivery location in the target region is determined based on the at least one peak sub-region. Since the peak sub-region is the sub-region with the largest number of historical orders within the range of the corresponding first number of sub-regions, that is, the peak sub-region has the largest number of historical orders and the most concentrated historical orders within a certain range where it is located, the probability of the existence of a delivery location such as a pick-up point in the peak sub-region is relatively high. Therefore, it is relatively accurate to determine the delivery location in the target region based on the peak sub-region; moreover, this method determines the delivery location based on the completion configuration of historical orders, which can be updated in real time, improving the real-time performance and effectiveness of the determination of the delivery location, so as to be able to respond in a timely manner when the delivery location changes, and ensure the quality and efficiency of services such as the delivery route planning and delivery time prediction of the delivery service system.

[0057] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0059] Figure 1 is a flowchart of a method for determining a delivery location shown in an embodiment of the present disclosure;

[0060] Figure 2 is a schematic diagram showing the size comparison between a pick-up point and a sub-region in an embodiment of the present disclosure;

[0061] Figure 3 is a schematic diagram of an extreme value sub-region shown in an embodiment of the present disclosure;

[0062] Figure 4 is a schematic diagram of an extreme value sub-region shown in an embodiment of the present disclosure;

[0063] Figures 5 to 9 is a schematic diagram of the shape of the delivery area range shown in an embodiment of the present disclosure;

[0064] Figure 10 is a schematic diagram showing multiple sub-regions of a target region and extreme value sub-regions among the multiple sub-regions in an embodiment of the present disclosure;

[0065] Figure 11Schematic diagrams of multiple sub-regions of a target region and a peak sub-region among the multiple sub-regions shown in an embodiment of the present disclosure;

[0066] Figure 12 Schematic diagram of the degree of decline of sub-regions around each peak sub-region within a target region shown in an embodiment of the present disclosure;

[0067] Figure 13 Schematic structural diagram of a delivery location determination device shown in an embodiment of the present disclosure;

[0068] Figure 14 Schematic structural diagram of an electronic device shown in an embodiment of the present disclosure. Detailed implementation manners

[0069] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0070] The terms used in the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. The singular forms "a", "the", and "said" used in the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0071] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0072] In recent years, delivery services such as food delivery services and express delivery services have brought great convenience to people's lives. The delivery service system needs to coordinate orders and delivery personnel to achieve efficient use of resources and full guarantee of user experience. When the delivery service system executes services such as determining the delivery time and planning the delivery route, it needs to be based on the accurate delivery location (i.e., the delivery end point of the delivery service, specifically the location where the rider completes the handover of the delivered item); currently, in user gathering areas such as communities and office buildings, it is often impossible to deliver to the user's order address, but to a designated location commonly known as a collection point. In related technologies, the delivery service system cannot accurately and real-time obtain the location of the collection point within the service area, that is, it cannot accurately and real-time determine the delivery location, resulting in poor delivery service accuracy and a decline in user experience.

[0073] Based on this, at least one embodiment of the present disclosure provides a method for determining a delivery location, which can be applied to a delivery service system, such as a food delivery system, an express delivery system, etc., so that the delivery service system can accurately and real-time obtain the delivery location (such as the location of the collection point) within the service area; furthermore, the delivery service system can execute services such as delivery time prediction and delivery route planning based on the accurate delivery location, thereby improving the service quality and efficiency of the above services.

[0074] First, the concepts involved in this application are explained.

[0075] Order placement location: In the delivery service scenario, the designated delivery location in the customer order is called the order placement location, that is, the location filled in by the user when placing the order.

[0076] Order completion location: In the delivery service scenario, the location when the rider clicks "delivery completed" is called the order completion location, that is, the location where the rider completes the handover of the delivered item.

[0077] For example, if the designated delivery location when the user places an order is unit c, building b, building a in community X, then unit c, building b, building a in community X is the order placement location of this order; due to community management and other issues, the rider can only deliver the delivered item to the collection point x at the entrance of community X, then the collection point x is the order completion location of this order.

[0078] Area of interest: (AOI), also called information surface, refers to the regional geographical entities in map data, including the following four basic pieces of information: name, address, category, longitude and latitude coordinates; mainly used to express regional geographical entities in the map, such as a residential community, a university, an office building, an industrial park, a comprehensive shopping mall, a hospital, a scenic spot or a stadium, etc.

[0079] Please refer to the appendix Figure 1, which exemplarily shows the process of the delivery location determination method, including step S101 to step S103.

[0080] In step S101, according to the delivery destinations of multiple historical orders in the target area, determine the number of historical orders in each sub-area of the target area, where there are multiple sub-areas in the target area.

[0081] Among them, the target area can be the service area targeted by this method. For example, if the service area of the delivery service system that executes this method is all areas of Town A, then all areas of Town A are the target area in this step.

[0082] The target area includes multiple sub-areas. For example, it includes multiple sub-areas distributed in a grid pattern, that is, multiple sub-areas distributed in multiple rows and columns. The size and shape of each sub-area can be the same or different; preferably, the size and shape of each sub-area are the same, for example, all are square.

[0083] The delivery destination is the position actually reached by the delivery person during the delivery process. For example, the delivery completion position can be used as the delivery destination.

[0084] It can be understood that by dividing the target area into multiple sub-areas, this method can determine the sub-areas containing delivery locations such as pick-up points in multiple sub-areas, and then determine the delivery location. Therefore, the larger the size of the sub-area, the lower the accuracy of determining the delivery location; and the smaller the size of the sub-area, the larger the number of sub-areas, and the greater the calculation amount of screening the sub-areas containing delivery locations such as pick-up points. Preferably, the size of the sub-area is determined according to the size of the configured location such as the pick-up point. For example, the coverage size of the pick-up point is determined as the size of the sub-area (the size d*d covered by the pick-up point is determined as the side length d of the square sub-area, etc.). Then, as shown in the appendix Figure 2 shown, the pick-up point occupies at most 4 sub-areas in the grid-like multiple sub-areas.

[0085] Exemplarily, in this step, first determine the sub-area to which each historical order belongs according to the delivery destination of each historical order, and then count the number of historical orders in each sub-area.

[0086] In step S102, according to the number of historical orders in each of the sub-areas, determine at least one peak sub-area in the multiple sub-areas, where the peak sub-area is the sub-area with the largest number of historical orders within the range of the sub-areas corresponding to the first quantity.

[0087] Among them, the range of the first number of sub-regions corresponding to the peak sub-region can be the range composed of the first number of sub-regions including the peak sub-region. Preferably, the range of the first number of sub-regions corresponding to the peak sub-region includes: the range composed of the first number of sub-regions centered on the peak sub-region. For example, the first number of sub-regions can be square regions. In this preferred example, the peak sub-region is located at the center of the corresponding sub-region range, which makes each peak sub-region higher than one or more adjacent sub-regions, and the probability of having a delivery location in the peak sub-region is relatively high, thereby improving the accuracy of determining the delivery location by this method.

[0088] It can be understood that there must be a certain distance between any delivery location and its nearest delivery location. Therefore, the size of the sub-region range for screening the peak sub-region can be matched with the minimum distance between any two delivery locations. For example, based on empirical values such as the area of the community, the minimum distance between any two delivery locations is D, and the target area contains multiple sub-regions with side length d distributed in a grid pattern. Then, the size of the sub-region range of the peak sub-region can be set to the sum of the side lengths of 2*(D / d)+1 sub-regions (when determining the values of D and d, they can be set as integer multiples), and the shape of the sub-region range of the peak sub-region can be set as a square centered on the peak sub-region.

[0089] Exemplarily, within the range of the first number of sub-regions corresponding to each sub-region, the number of historical orders of the sub-region can be compared with that of other sub-regions. If the number of historical orders in the sub-region is greater than that in other sub-regions, then the sub-region is a peak sub-region; otherwise, it is not. It can be understood that when a certain sub-region is determined to be a peak sub-region, other sub-regions within the corresponding range of the first number of sub-regions can be directly determined not to be peak sub-regions.

[0090] Furthermore, the following optional method can be adopted to simplify the screening process of the peak sub-region in the above example.

[0091] Optional method 1: First, determine the maximum number of sub-regions that the delivery location can occupy (i.e., the upper limit of the total number of sub-regions occupied by all delivery locations) according to the size of the sub-region and the number of areas of interest in the target area; next, determine the peak sub-region within the top N sub-regions with the largest number of historical orders among the multiple sub-regions, where the value of N is the maximum number of sub-regions that the delivery location can occupy.

[0092] Among them, the number of delivery locations such as pick-up points within the target area is limited and often matches the number of areas of interest. Therefore, this optional method first roughly filters sub-areas based on the finiteness of the delivery locations and their matching relationship with the areas of interest, and then determines the peak sub-areas from the roughly filtered results, thereby reducing the computational effort for determining the peak sub-areas.

[0093] As introduced above, the areas of interest can be geographical entities such as residential communities, universities, office buildings, industrial parks, etc. Therefore, the number of delivery locations for each area of interest is fixed, or rather, limited. For example, pick-up points are often set at the entrances of the areas of interest, and an area of interest has at most 8 entrances, namely the east gate, west gate, south gate, north gate, southeast gate, northeast gate, southwest gate, and northwest gate. Thus, each area of interest has at most 8 delivery locations.

[0094] As mentioned above, based on the size of the area where the delivery location such as the pick-up point is located (such as a store, supermarket, guard room, etc.) and the size of the sub-areas in the grid-like multiple sub-areas, the maximum number of sub-areas that each delivery location occupies in the grid-like multiple sub-areas can be determined. For example, each delivery location occupies at most 4 sub-areas in the grid-like multiple sub-areas.

[0095] Based on the number of areas of interest within the target area, the maximum number of delivery locations for each area of interest, and the maximum number of sub-areas that each delivery location occupies in the grid-like multiple sub-areas, the upper limit of the number of sub-areas occupied by all delivery locations can be determined. For example, there are M areas of interest within the target area, each area of interest has at most 8 delivery locations, and each delivery location occupies at most 4 sub-areas in the grid-like multiple sub-areas. Therefore, the maximum number of sub-areas occupied by all delivery locations is M * 8 * 4 = 32M.

[0096] This optional method can narrow down the range of sub-areas for screening peak sub-areas, that is, only need to determine whether some sub-areas are peak sub-areas, rather than traversing whether all sub-areas are peak sub-areas, greatly reducing the computational load of this method for determining delivery locations and improving the efficiency of this method for determining delivery locations.

[0097] Optional method 2: According to the number of historical orders within the sub-areas, successively determine multiple levels of extreme value sub-areas within the multiple sub-areas, and determine the highest-level extreme value sub-area as the peak sub-area.

[0098] Among them, a high-level extreme value sub-region can be determined within a low-level extreme value sub-region, that is, in the order from low to high in terms of level, the next higher-level extreme value sub-region is determined in each level of extreme value sub-region in turn. For example, if the extreme value sub-regions of multiple levels include the extreme value sub-region of the first level and the extreme value sub-region of the second level, then multiple extreme value sub-regions of the first level are first determined within the multiple sub-regions according to the number of historical orders within the sub-region, and then at least one extreme value sub-region of the second level is determined within the multiple extreme value sub-regions of the first level according to the number of historical orders within the extreme value sub-region of the first level.

[0099] Among them, the extreme value sub-region is the sub-region with the largest number of historical orders within the sub-region range corresponding to the second quantity. The second quantity of the sub-region range corresponding to the extreme value sub-region with a lower level is less than the second quantity of the sub-region range corresponding to the extreme value sub-region with a higher level. The second quantity of the sub-region range corresponding to the extreme value sub-region of the highest level is equal to the first quantity. Preferably, the sub-region range corresponding to the second quantity of the extreme value sub-region includes: the range composed of the second quantity of sub-regions centered on the extreme value sub-region; the shapes of the sub-region ranges corresponding to the extreme value sub-regions of each level can be the same and the same as the shape of the sub-region range corresponding to the peak sub-region, for example, all are square. In this preferred example, the extreme value sub-region is located at the center of the corresponding sub-region range, which makes each extreme value sub-region higher than one or more adjacent layers of sub-regions, and the probability of having a delivery location within the extreme value sub-region is relatively high, thereby improving the accuracy of determining the delivery location by this method.

[0100] In the example where the extreme value sub-regions of multiple levels include the extreme value sub-region of the first level and the extreme value sub-region of the second level, the sub-region range corresponding to the extreme value sub-region of the first level may include the extreme value sub-region and one layer of sub-regions surrounding the extreme value sub-region, that is, Figure 3 the 3*3 sub-region range shown centered on the extreme value sub-region, and the sub-region range corresponding to the extreme value sub-region of the second level includes the extreme value sub-region and multiple layers of sub-regions surrounding the extreme value sub-region, such as Figure 4 the 5*5 sub-region range shown centered on the extreme value sub-region. Setting the extreme value sub-regions of two levels can not only simplify the determination process of the peak sub-region, but also avoid the increase in the amount of calculation caused by too many levels, that is, maximize the determination efficiency of the peak sub-region.

[0101] This optional method can screen the extreme value sub-regions level by level, avoiding the step of traversing whether all sub-regions are peak sub-regions, greatly reducing the calculation load of determining the delivery location by this method, and improving the efficiency of determining the delivery location by this method.

[0102] It is understandable that the above two optional methods can be used in combination. For example, first determine the maximum number of sub-regions occupied by the delivery location according to the size of the sub-region and the number of areas of interest in the target region; then, according to the number of historical orders in the sub-region, determine multiple levels of extreme value sub-regions in the top N sub-regions with the largest number of historical orders among the multiple sub-regions in sequence, and determine the highest-level extreme value sub-region as the peak sub-region, where the value of N is the maximum number of sub-regions occupied by the delivery location.

[0103] In step S103, determine the delivery location in the target region according to the at least one peak sub-region.

[0104] Exemplarily, this step can be executed in the following manner:

[0105] First, determine the quantity decline degree of the multiple sub-regions adjacent to the peak sub-region according to the number of historical orders in the peak sub-region and the number of historical orders in the multiple sub-regions adjacent to the peak sub-region, where the quantity decline degree is used to characterize the decline ratio of the number of historical orders in the adjacent sub-regions relative to the number of historical orders in the peak sub-region. For example, the quantity decline degree is the ratio value of the first difference to the number of historical orders in the peak sub-region, where the first difference is the difference between the number of historical orders in the peak sub-region and the number of historical orders in the adjacent sub-region.

[0106] Taking the peak sub-region in the multiple sub-regions distributed in a grid pattern as an example, if this peak sub-region is the sub-region in the i-th row and j-th column among the multiple sub-regions, then:

[0107] The quantity decline degree of the sub-region to the left of this peak sub-region is:

[0108] The quantity decline degree of the sub-region above this peak sub-region is:

[0109] The quantity decline degree of the sub-region to the right of this peak sub-region is:

[0110] The quantity decline degree of the sub-region below this peak sub-region is:

[0111] The quantity decline degree of the sub-region to the upper left of this peak sub-region is:

[0112] The quantity decline degree of the sub-region to the upper right of this peak sub-region is:

[0113] The degree of decrease in the number of sub-regions on the lower right side of the peak sub-region is:

[0114] The degree of decrease in the number of sub-regions on the lower left side of the peak sub-region is:

[0115] In the expression of the degree of decrease in the number of the above-mentioned multiple sub-regions, n i,j is the number of historical orders in the peak sub-region, n i-1,j is the number of historical orders in the sub-region to the left of the peak sub-region, n i+1,j is the number of historical orders in the sub-region to the right of the peak sub-region, n i,j+1 is the number of historical orders in the sub-region above the peak sub-region, n i,j-1 is the number of historical orders in the sub-region below the peak sub-region, n i-1,j+1 is the number of historical orders in the sub-region at the upper left of the peak sub-region, n i-1,j-1 is the number of historical orders in the sub-region at the lower left of the peak sub-region, n i+1,j+1 is the number of historical orders in the sub-region at the upper right of the peak sub-region, n i+1,j-1 is the number of historical orders in the sub-region at the lower right of the peak sub-region.

[0116] Next, determine the sub-regions with the degree of decrease in the number meeting the preset requirements among the peak sub-region and multiple sub-regions adjacent to the peak sub-region as the distribution area range, and determine the distribution position corresponding to the peak sub-region according to the positions of the historical orders within the distribution area range, where the preset requirements include at least one of the following: the degree of decrease is less than the preset threshold; the degree of decrease is one of the degrees of decrease of the largest third number of the degrees of decrease of multiple sub-regions adjacent to the peak sub-region. For example, the third number is the maximum number of sub-regions occupied by each distribution position in multiple grid-shaped sub-regions.

[0117] Taking the peak sub-region in multiple grid-shaped distributed sub-regions as an example, if each distribution position occupies at most 4 sub-regions in multiple grid-shaped sub-regions, and the preset requirements include: the degree of decrease is less than the preset threshold (for example, 50%), and the degree of decrease is one of the degrees of decrease of the largest 4 degrees of decrease of multiple sub-regions adjacent to the peak sub-region; then the distribution area range can at least be in the shape as Figures 5 to 9 shown.

[0118] Such as Figure 5The shape shown is such that each adjacent sub-region of the peak sub-region does not meet the above preset conditions.

[0119] As Figure 6 The shape shown is such that only the sub-region adjacent to the right of the peak sub-region meets the above preset conditions.

[0120] As Figure 7 The shape shown is such that only the sub-region adjacent to the upper right of the peak sub-region meets the above preset conditions.

[0121] As Figure 8 The shape shown is such that only the sub-regions adjacent to the right and upper right of the peak sub-region meet the above preset conditions.

[0122] As Figure 9 The shape shown is such that only the sub-regions adjacent to the right, upper side, and upper right of the peak sub-region meet the above preset conditions.

[0123] It can be understood that the shapes shown above are only examples and do not limit the scope of the delivery area. Moreover, in response to the situation where the degree of decline in the number of multiple sub-regions adjacent to the peak sub-region does not meet the preset requirements, the peak sub-region can be determined as the scope of the delivery area, so that when historical orders are concentrated in a single sub-region of the peak sub-region, the scope of the delivery area can be accurately obtained, avoiding the situation where the scope of the delivery area cannot be obtained. Figures 5 to 9

[0124] Optionally, according to the mean of the position coordinates of the delivery endpoints of historical orders within the delivery area, the delivery position corresponding to the peak sub-region is determined. For example, the average longitude of the delivery endpoints of historical orders within the delivery area is determined as the longitude value of the delivery position, and the average latitude of the delivery endpoints of historical orders within the delivery area is determined as the latitude value of the delivery position. Another example is to determine the delivery endpoint of the historical order closest to the average position within the delivery area as the delivery position, where the average position is the position represented by the average longitude and average latitude of the delivery endpoints of historical orders within the delivery area. In this optional example, the range where historical orders are most concentrated - the delivery endpoints of historical orders within the delivery area - is combined, so that the delivery position such as the pick-up point within the target area can be obtained more accurately; especially when the delivery endpoint of the historical order closest to the average position within the delivery area is used as the delivery position, it can also avoid taking some unreasonable positions (such as in the middle of the road, etc.) as the delivery position, improving the rationality and authenticity of the delivery position.

[0125] ​This example can accurately measure the difference in the historical order aggregation degree between the peak sub-region and its surrounding sub-regions, so as to adapt to different regions where the delivery location belongs, such as regions with more covered sub-regions or regions with fewer covered sub-regions, making the delivery area range reasonable and accurate, and also increasing the adaptability of this method to different situations of the delivery location.

[0126] Exemplarily again, this step can be executed in the following manner: Determine the delivery location corresponding to the peak sub-region according to the mean value of the position coordinates of the delivery end points of the historical orders within the range of the fourth number of sub-regions corresponding to the peak sub-region.

[0127] For example, the range of the fourth number of sub-regions corresponding to the peak sub-region may include: a range composed of the fourth number of sub-regions centered on the peak sub-region, such as a square range. When the fourth number is 0, determine the delivery location corresponding to the peak sub-region according to the mean value of the position coordinates of the delivery end points of the historical orders within the peak sub-region. When the fourth number is 9, the range of the fourth number of sub-regions corresponding to the peak sub-region may be in the form of Figure 3 the 3*3 sub-region range shown; when the fourth number is 9, the range of the fourth number of sub-regions corresponding to the peak sub-region may be in the form of Figure 4 the 5*5 sub-region range shown.

[0128] For example, the average longitude value of the delivery end points of the historical orders within the range of the fourth number of sub-regions corresponding to the peak sub-region can be determined as the longitude value of the delivery location, and the average latitude value of the delivery end points of the historical orders within the range of the fourth number of sub-regions corresponding to the peak sub-region can be determined as the latitude value of the delivery location. For another example, determine the delivery end point of the historical order closest to the average position within the range of the fourth number of sub-regions corresponding to the peak sub-region as the delivery location, where the average position is the position represented by the average longitude value and the average latitude value of the delivery end points of the historical orders within the range of the fourth number of sub-regions corresponding to the peak sub-region.

[0129] This example determines the delivery area range based on the range of the fourth number of sub-regions corresponding to the peak sub-region, and determines the delivery location in combination with the historical orders within this range, avoiding the increase in computational load caused by determining personalized delivery area ranges for each peak sub-region and improving the determination efficiency of the delivery location.

[0130] Next, taking the complete process of determining the delivery location in an embodiment of the present disclosure as an example, the various steps of the present disclosure will be described more vividly. Among them, the target area has a total of 96 sub-regions distributed in a grid pattern, and the number of historical orders in each sub-region is as shown in Figure 10As shown; the delivery location occupies at most 4 sub-regions in a 2*2 shape, and the range of the preset number of sub-regions corresponding to the peak sub-region includes: a 7*7 square range composed of 49 sub-regions centered on the peak sub-region.

[0131] First, determine the extreme value sub-region of the first level. The range of sub-regions corresponding to the extreme value sub-region of the first level is the 3*3 sub-region range centered on the extreme value sub-region shown in the appendix. Please refer to the appendix. Figure 3 Shown, where the shaded sub-regions are the extreme value sub-regions of the first level. Figure 10

[0132] Next, determine the extreme value sub-region of the second level within the extreme value sub-region of the first level, and determine the extreme value sub-region of the second level as the peak sub-region. The range of sub-regions corresponding to the extreme value sub-region of the second level is the 5*5 sub-region range centered on the extreme value sub-region shown in the appendix. Please refer to the appendix. Figure 4 Shown, where the shaded sub-regions are the peak sub-regions. Figure 11

[0133] Then, determine the quantity decline degree of the sub-regions adjacent to each peak sub-region in the appendix. Please refer to the appendix. Figure 11 Shown, which shows the quantity decline degree of the sub-regions adjacent to each peak sub-region in the appendix (note that the percentages are omitted in the numbers in the figure). Figure 12 Shown, which shows the appendix. Figure 11

[0134] Finally, for each peak sub-region, determine the delivery area range by taking the peak sub-region and the sub-regions whose quantity decline degree adjacent to it meets the preset requirements, and determine the longitude and latitude mean value of the positions of all historical orders within the delivery area range as the longitude and latitude of the delivery position. Among them, the preset requirements are that the quantity decline degree is less than 50%, and the quantity decline degree belongs to the top 3 of the largest quantity decline degrees of all adjacent sub-regions. Please refer to the appendix. Figure 12 Shown, which shows the delivery area range of each peak sub-region.

[0135] According to the above embodiments, the number of historical orders in each sub-region of the target region can be determined based on the delivery destinations of multiple historical orders in the target region. Then, at least one peak sub-region can be determined from the multiple sub-regions according to the number of historical orders in each sub-region. Finally, the delivery location in the target region can be determined based on the at least one peak sub-region. Since the peak sub-region is the sub-region with the largest number of historical orders within the range of the corresponding first number of sub-regions, that is, the peak sub-region has the largest number of historical orders and the most concentrated historical orders within a certain range where it is located, the probability of having a pick-up point or other delivery locations in the peak sub-region is relatively high. Therefore, determining the delivery location in the target region based on the peak sub-region is relatively accurate. Moreover, this method determines the delivery location based on the completion configuration of historical orders, which can be updated in real time, improving the real-time performance and effectiveness of delivery location determination. Thus, it can respond in a timely manner when the delivery location changes, ensuring the quality and efficiency of services such as delivery route planning and delivery time prediction in the delivery service system.

[0136] Since this method can accurately and real-time determine the delivery location (such as a pick-up point) in the target region, when a new order is generated, the delivery service system can determine the delivery location of the order and perform services such as delivery route planning and delivery time prediction based on this delivery location. Thus, it can be more accurate compared to directly performing delivery route planning, delivery time prediction, etc. based on the order placement location in the related art.

[0137] According to a second aspect of the embodiments of the present disclosure, a delivery location determination device is provided. Please refer to the appendix Figure 13 , the device includes:

[0138] A quantity module 1301, configured to determine the number of historical orders in each sub-region of the target region according to the delivery destinations of multiple historical orders in the target region, where there are multiple sub-regions in the target region;

[0139] A peak module 1302, configured to determine at least one peak sub-region from the multiple sub-regions according to the number of historical orders in each sub-region, where the peak sub-region is the sub-region with the largest number of historical orders within the range of the corresponding first number of sub-regions;

[0140] A location module 1303, configured to determine the delivery location in the target region according to the at least one peak sub-region.

[0141] In a possible embodiment of the present disclosure, the range of the corresponding first number of sub-regions of the peak sub-region includes: a range composed of the first number of sub-regions centered on the peak sub-region.

[0142] In a possible embodiment of the present disclosure, the peak module is configured to:

[0143] Determine the maximum number of sub-regions occupied by the delivery location according to the size of the sub-region and the number of areas of interest in the target region;

[0144] Determine peak sub-regions within the top N sub-regions with the largest number of historical orders among the multiple sub-regions, where the value of N is the maximum number of sub-regions occupied by the delivery location.

[0145] In a possible embodiment of the present disclosure, the peak module is configured to:

[0146] Determine multiple levels of extreme value sub-regions in sequence within the multiple sub-regions according to the number of historical orders in the sub-regions, and determine the highest-level extreme value sub-region as the peak sub-region;

[0147] Among them, high-level extreme value sub-regions are determined within low-level extreme value sub-regions;

[0148] Among them, the extreme value sub-region is the sub-region with the largest number of historical orders within the range of the corresponding second number of sub-regions. The second number of the sub-region range corresponding to the low-level extreme value sub-region is smaller than that of the high-level extreme value sub-region, and the second number of the sub-region range corresponding to the highest-level extreme value sub-region is equal to the first number.

[0149] In a possible embodiment of the present disclosure, the sub-region range of the corresponding second number of the extreme value sub-region includes: the range composed of the second number of sub-regions centered on the extreme value sub-region.

[0150] In a possible embodiment of the present disclosure, the multiple levels of extreme value sub-regions include the extreme value sub-regions of the first level and the extreme value sub-regions of the second level; among them, the sub-region range corresponding to the extreme value sub-regions of the first level includes the extreme value sub-region and one layer of sub-regions surrounding the extreme value sub-region, and the sub-region range corresponding to the extreme value sub-regions of the second level includes the extreme value sub-region and multiple layers of sub-regions surrounding the extreme value sub-region.

[0151] In a possible embodiment of the present disclosure, the position module is configured to:

[0152] Determine the quantity decline degree of the multiple sub-regions adjacent to the peak sub-region according to the number of historical orders in the peak sub-region and the number of historical orders in the multiple sub-regions adjacent to the peak sub-region, where the quantity decline degree is used to characterize the decline ratio of the number of historical orders in the adjacent sub-regions relative to the number of historical orders in the peak sub-region;

[0153] Determine the sub-regions with the quantity decline degree meeting the preset requirements among the peak sub-region and multiple sub-regions adjacent to the peak sub-region as the distribution area range, and determine the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range, where the preset requirements include at least one of the following:

[0154] The quantity decline degree is less than a preset threshold;

[0155] The quantity decline degree is one of the quantity decline degrees of the third largest quantity among the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region.

[0156] In a possible embodiment of the present disclosure, when the location module is used to determine the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range, it is used to:

[0157] Determine the distribution location corresponding to the peak sub-region according to the mean value of the location coordinates of the delivery end points of historical orders within the distribution area range.

[0158] In a possible embodiment of the present disclosure, the device further includes a region range module, which is used to:

[0159] In response to the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region not meeting the preset requirements, determine the peak sub-region as the distribution area range.

[0160] In a possible embodiment of the present disclosure, the location module is used to:

[0161] Determine the distribution location corresponding to the peak sub-region according to the mean value of the location coordinates of the delivery end points of historical orders within the sub-region range of the fourth quantity corresponding to the peak sub-region.

[0162] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments of the method in the first aspect, and will not be elaborated here.

[0163] At least one embodiment of the present disclosure further provides a device. Please refer to the appendix Figure 14 , which shows the structure of the device. The device includes a memory and a processor. The memory is used to store computer instructions that can be run on the processor, and the processor is used to process orders based on the method described in the first aspect or the second aspect when executing the computer instructions.

[0164] At least one embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect or the second aspect is implemented.

[0165] In the present disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The term "plurality" refers to two or more, unless otherwise specifically defined.

[0166] Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0167] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for determining a delivery location, characterized in that, The method includes: Determining the number of historical orders in each sub-region of the target region according to the delivery destinations of multiple historical orders in the target region, where there are multiple sub-regions in the target region; Determining at least one peak sub-region in the multiple sub-regions according to the number of historical orders in each sub-region, where the peak sub-region is the sub-region with the largest number of historical orders within the range of the first number of sub-regions corresponding thereto; Determining the delivery location in the target region according to the at least one peak sub-region.

2. The method for determining a delivery location according to claim 1, characterized in that, The range of the first number of sub-regions corresponding to the peak sub-region includes: the range composed of the first number of sub-regions centered on the peak sub-region.

3. The method for determining a delivery location according to claim 1, characterized in that, The determining of the peak sub-region in the multiple sub-regions according to the number of historical orders in each sub-region includes: Determining the maximum number of sub-regions that the delivery location can occupy according to the size of the sub-region and the number of areas of interest in the target region; Determining the peak sub-region within the top N sub-regions with the largest number of historical orders in the multiple sub-regions, where the value of N is the maximum number of sub-regions that the delivery location can occupy.

4. The method for determining a delivery location according to claim 1, characterized in that, The determining of the peak sub-region in the multiple sub-regions according to the number of historical orders in each sub-region includes: Sequentially determining multiple levels of extreme value sub-regions in the multiple sub-regions according to the number of historical orders in the sub-region, and determining the highest-level extreme value sub-region as the peak sub-region; Wherein, determining the higher-level extreme value sub-region within the lower-level extreme value sub-region; Wherein, the extreme value sub-region is the sub-region with the largest number of historical orders within the range of the second number of sub-regions corresponding thereto, the second number of the sub-region range corresponding to the lower-level extreme value sub-region is less than the second number of the sub-region range corresponding to the higher-level extreme value sub-region, and the second number of the sub-region range corresponding to the highest-level extreme value sub-region is equal to the first number.

5. The method for determining a delivery location according to claim 4, characterized in that, The range of the second number of sub-regions corresponding to the extreme value sub-region includes: the range composed of the second number of sub-regions centered on the extreme value sub-region.

6. The method for determining a delivery location according to claim 4 or 5, characterized in that, The multiple levels of extreme value sub-regions include the first-level extreme value sub-region and the second-level extreme value sub-region; wherein, the sub-region range corresponding to the first-level extreme value sub-region includes the extreme value sub-region and one layer of sub-regions surrounding the extreme value sub-region, and the sub-region range corresponding to the second-level extreme value sub-region includes the extreme value sub-region and multiple layers of sub-regions surrounding the extreme value sub-region.

7. The method for determining a delivery location according to claim 1, characterized in that, The determining of the delivery location in the target region according to the at least one peak sub-region includes: Determining the quantity decline degree of the multiple sub-regions adjacent to the peak sub-region according to the number of historical orders in the peak sub-region and the number of historical orders in the multiple sub-regions adjacent to the peak sub-region, where the quantity decline degree is used to characterize the decline ratio of the number of historical orders in the adjacent sub-regions relative to the number of historical orders in the peak sub-region; Determine the sub-regions with the quantity decline degree meeting the preset requirements among the peak sub-region and multiple sub-regions adjacent to the peak sub-region as the distribution area range, and determine the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range, where the preset requirements include at least one of the following: The quantity decline degree is less than a preset threshold; The quantity decline degree is one of the quantity decline degrees of the third largest quantity among the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region.

8. The method for determining a delivery location according to claim 7, characterized in that, The determining the distribution location corresponding to the peak sub-region according to the locations of historical orders within the distribution area range includes: Determine the distribution location corresponding to the peak sub-region according to the average value of the location coordinates of the delivery end points of historical orders within the distribution area range.

9. The method for determining a delivery location according to claim 7, characterized in that, The method further includes: In response to the quantity decline degrees of multiple sub-regions adjacent to the peak sub-region not meeting the preset requirements, determine the peak sub-region as the distribution area range.

10. The method for determining a delivery location according to claim 1, characterized in that, The determining the distribution location within the target area according to the at least one peak sub-region includes: Determine the distribution location corresponding to the peak sub-region according to the average value of the location coordinates of the delivery end points of historical orders within the sub-region range of the fourth quantity corresponding to the peak sub-region.

11. A device for determining a delivery location, characterized in that, The device includes: A quantity module, configured to determine the quantity of historical orders in each sub-region within the target area according to the delivery end points of multiple historical orders within the target area, where there are multiple sub-regions within the target area; A peak module, configured to determine at least one peak sub-region within the multiple sub-regions according to the quantity of historical orders in each sub-region, where the peak sub-region is the sub-region with the largest quantity of historical orders within the sub-region range of the corresponding first quantity; A location module, configured to determine the distribution location within the target area according to the at least one peak sub-region.

12. An electronic device, characterized in that, The device includes a memory and a processor, the memory is used to store computer instructions that can be run on the processor, and the processor is used to implement the method according to any one of claims 1 to 10 when executing the computer instructions.

13. A computer-readable storage medium, on which a computer program is stored, characterized in that, The program, when executed by the processor, implements the method according to any one of claims 1 to 10.

Images