Transport capacity boundary generation method and device, program product and storage medium
By obtaining the AOI and merchant locations in the target business district, determining the initial capacity boundary, and selecting adjacent AOI to expand the capacity boundary through the cyclic diffusion method, the bubble problem when generating capacity boundary in the existing technology is solved, and accurate and efficient capacity boundary generation is achieved.
Patent Information
- Application Number
- CN202411781832.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-04
- Publication Date
- 2025-03-28
AI Technical Summary
The prior art is prone to bubble problems when generating capacity boundaries, resulting in inaccurate capacity boundaries.
By obtaining the AOI and merchant locations in the target business district, determining the initial capacity boundary, and through the cyclic diffusion method, selecting adjacent AOI to expand the capacity boundary until the preset termination conditions are met.
The bubble problem is effectively avoided, ensuring that the generated capacity boundary is accurate and efficient, and the final capacity boundary can be generated from the better initial boundary.
Smart Images
Figure CN119721887A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of this specification relate to the field of logistics and distribution technology, and in particular to methods, devices, program products and storage media for generating capacity boundaries. Background Art
[0002] The capacity boundary indicates the logistics distribution service scope corresponding to the target object. For example, for a business district, the capacity boundary of the business district can indicate the maximum logistics distribution service scope of the business district. In related technologies, when generating the capacity boundary, bubbles are easily generated. For example, when selecting AOI to construct the capacity boundary, the geographical location span between the selected multiple AOIs is large, resulting in the appearance of unselected AOIs inside the capacity boundary constructed by the selected AOI, which ultimately leads to inaccurate generated capacity boundary. Summary of the invention
[0003] To overcome the problems existing in the related art, the embodiments of this specification provide a method, device, program product and storage medium for generating a capacity boundary.
[0004] According to a first aspect of an embodiment of this specification, a method for generating a capacity boundary is provided, the method comprising:
[0005] Obtain multiple AOIs included in the target business district and the number of historical orders corresponding to each of the AOIs;
[0006] Obtaining the business locations of multiple businesses in the target business district;
[0007] Based on the merchant locations of the multiple merchants and the number of historical orders of each of the AOIs, an initial transportation capacity boundary is determined; wherein the initial transportation capacity boundary surrounds the multiple merchants and an initial AOI set selected from the multiple AOIs, and the total number of historical orders of the initial AOI set meets a preset quantity condition;
[0008] After taking the initial capacity boundary as the current capacity boundary, the following steps are executed in a loop until the preset termination condition is met to obtain the capacity boundary of the target business district: an adjacent AOI is selected for the boundary AOI of the current capacity boundary, so as to diffuse the current capacity boundary outward to form a new current capacity boundary based on the selected adjacent AOI.
[0009] According to a second aspect of an embodiment of this specification, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method embodiment described in the first aspect are implemented.
[0010] According to a third aspect of the embodiments of this specification, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method embodiment described in the first aspect are implemented.
[0011] According to a fourth aspect of the embodiments of this specification, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method embodiment described in the first aspect are implemented.
[0012] The technical solutions provided by the embodiments of this specification may have the following beneficial effects:
[0013] In an embodiment of the present specification, multiple AOIs included in a target business district and the number of historical orders corresponding to each of the AOIs are obtained; the merchant locations of multiple merchants in the target business district are obtained; based on the merchant locations of the multiple merchants and the number of historical orders of each of the AOIs, an initial capacity boundary is determined; wherein the initial capacity boundary surrounds the multiple merchants and an initial AOI set selected from the multiple AOIs, and the total number of historical orders of the initial AOI set meets a preset quantity condition; after taking the initial capacity boundary as the current capacity boundary, the following steps are executed in a loop until a preset termination condition is met to obtain the capacity boundary of the target business district: an adjacent AOI is selected for the boundary AOI of the current capacity boundary, so as to diffuse the current capacity boundary outward to form a new current capacity boundary based on the selected adjacent AOI.
[0014] In this embodiment, the initial capacity boundary can surround multiple merchants and the initial AOI set. On the one hand, it is considered that the capacity boundary of the target business district is to provide capacity services to the merchants in the business district, so the merchants need to be located within the capacity boundary; on the other hand, in order to accelerate the generation of the capacity boundary, the total number of historical orders of the initial AOI set meets the preset quantity condition, so that the final capacity boundary can be generated from the better initial capacity boundary, thereby improving the generation efficiency of the capacity boundary; and the initial capacity boundary surrounds the initial AOI set, so the initial capacity boundary is a boundary that will not have bubble problems, and thus, on the basis of the initial capacity boundary that will not have bubble problems, the adjacent AOI of the boundary AOI is selected based on the boundary AOI of the current capacity boundary, so that it can be ensured that the newly selected AOI will not span a large distance, and since it is adjacent to the boundary AOI of the current capacity boundary, the new current capacity boundary that diffuses out will not have bubble problems.
[0015] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the embodiments of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the specification, and together with the description, serve to explain the principles of the embodiments of the specification.
[0017] Figure 1A It is a schematic diagram of a delivery scenario shown in this specification according to an exemplary embodiment.
[0018] Figure 1B It is a schematic diagram of a capacity boundary shown in this specification according to an exemplary embodiment.
[0019] Figure 2A It is a flow chart of a method for generating a capacity boundary according to an exemplary embodiment of the present specification.
[0020] Figure 2B It is a schematic diagram of another capacity boundary shown in this specification according to an exemplary embodiment.
[0021] Figure 3 It is a hardware structure diagram of a computer device where a device for generating a capacity boundary is located according to an exemplary embodiment shown in this specification.
[0022] Figure 4 It is a structural diagram of a device for generating a capacity boundary according to an exemplary embodiment of this specification. DETAILED DESCRIPTION
[0023] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying 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 implementations described in the following exemplary embodiments do not represent all implementations consistent with this specification. Instead, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.
[0024] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. The singular forms "a", "the" and "the" used in this specification and the appended claims are also intended to include 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 associated listed items.
[0025] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this 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 this specification, 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 "at the time of" or "when" or "in response to determining".
[0026] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0027] At present, delivery services are widely used in online shopping, food delivery, errand shopping, etc. Figure 1A Shown is a schematic diagram of a delivery scenario according to an exemplary embodiment of this specification, including a service party, delivery capacity and users. Among them, the service party has built a server and provided a client to users, and users can use the services provided by the business party through the client; different from the client for users, the business party also provides a client for the store party to use, and the store party can use the services provided by the business party through the client. Among them, users can view the stores that can provide services for them through the client, can trade with the store party, and can initiate delivery orders; the business party can allocate delivery capacity for the instant delivery order. The delivery capacity of this embodiment refers to the party with delivery capabilities, including but not limited to delivery personnel, such as so-called riders. The delivery capacity can communicate with the service end through the client used for the delivery capacity; in other examples, the delivery capacity can also include unmanned delivery equipment, such as drones, unmanned vehicles, etc.
[0028] The service provider needs to determine the capacity boundary of the business district. For example, for a business district, the capacity boundary of the business district can represent the maximum logistics and distribution service scope of the business district. After determining the capacity boundary of the business district, the capacity boundary can be used as a reference for the online logistics and distribution services within the business district. For example, merchants located in a business district can be exposed to users within the capacity boundary of the business district. In other words, merchants in the business district can provide services to users within the capacity boundary of the business district, and merchants in the business district may not provide services to users outside the capacity boundary of the business district.
[0029] For example, after defining the capacity boundary of a business district, if a user needs to use an online service provided by a merchant in the business district, if the user is within the capacity boundary of the business district, the user can find and use the online service provided by the merchant on the client, such as food delivery service, etc. If the user is outside the capacity boundary of the business district, the user may not be able to find and use the online service provided by the merchant on the client.
[0030] The idea of the related scheme is to generate multiple capacity boundaries and then select the optimal solution through sorting and screening. The process is complicated and inefficient. Figure 1B As shown, it is a schematic diagram of a method for generating a capacity boundary in an embodiment of this specification, wherein both the solid small ellipse and the hollow small ellipse are AOIs, and the solid small ellipse is the AOI selected by the capacity boundary generation algorithm. The capacity boundary is composed based on the geographical scope surrounding the selected AOI, such as the boundary surrounding the solid small ellipse in the figure, which is the capacity boundary. It can be seen that some unselected hollow small ellipses are surrounded by the capacity boundary, and these unselected AOIs surrounded by the generated capacity boundary can be called "bubbles". The generation of "bubbles" is related to the algorithm design. Since there are a large number of AOIs in the business district, it may be that the algorithm has not designed a better initial boundary, or there may be problems with the AOI selection strategy. For example, multiple AOIs are selected at the same time, and the selected AOIs include multiple AOIs that are relatively far away, while there are unselected AOIs in the middle area.
[0031] Based on this, the embodiment of this specification provides a method for generating a capacity boundary, which can solve the bubble problem. Figure 2A FIG. 1 is a flow chart of a method for generating a capacity boundary in an embodiment of the present specification. The method may include the following steps:
[0032] In step 202, multiple AOIs included in the target business district and the number of historical orders corresponding to each of the AOIs are obtained.
[0033] In step 204, the business location of each business in the target business district is obtained.
[0034] In step 206, an initial capacity boundary is determined based on the merchant locations of the various merchants and the historical order quantities of the various AOIs.
[0035] The initial transportation capacity boundary surrounds the merchant locations of the various merchants and an initial AOI set selected from the multiple AOIs, and the total number of historical orders of the initial AOI set meets a preset quantity condition.
[0036] In step 208, after taking the initial capacity boundary as the current capacity boundary, the following steps are executed in a loop until the preset termination condition is met to obtain the capacity boundary of the target business district: an adjacent AOI is selected for the boundary AOI of the current capacity boundary, so as to diffuse the current capacity boundary into a new current capacity boundary based on the selected adjacent AOI.
[0037] The method for generating the capacity boundary of this embodiment can be run on a computer device, including but not limited to a server, a cloud server, a server cluster, a tablet computer, a personal digital assistant, a laptop computer, or a desktop computer. The method of this embodiment can be applied to a variety of application scenarios, such as Figure 1A In the application scenario shown, the service provider can apply the solution of this embodiment to generate the capacity boundary of the business district in advance or in real time.
[0038] As an example, in a geographic information system, an Area of Interest (AOI) can be used to express regional geographic entities in a map, such as residential areas, schools, scenic spots, etc. A Point of Interest (POI) can be a house, a shop, a mailbox, a bus stop, etc. When defining an AOI, it is necessary to clarify the location information of the boundary points. From the perspective of spatial geometry, an AOI is a collection of multiple POI data. Therefore, compared with a POI, an AOI has better expressiveness and can intuitively feel the data's distribution, area, density, and other information.
[0039] The capacity boundary can represent the logistics distribution service scope corresponding to the business district, and is an important basic data for logistics distribution. Taking the target object as a business district, a business district can be an area with concentrated commercial and service facilities, usually the city center or a specific area of the city. There are usually various types of stores, restaurants, entertainment venues, offices, residences, etc. in the business district, which is also one of the main places for people to shop, consume, socialize and relax. The scale, type and positioning of the business district vary from city to city. Some business districts are mainly high-end shopping, while others are mainly mass consumption.
[0040] As an example, a certain geographical range can be defined as a business district. Specifically, the geographical range of the business district can be flexibly configured according to business needs, and this embodiment does not limit this. Multiple AOIs within the business district can be obtained. In the distribution scenario of this embodiment, the AOI here can include the user's AOI, such as the AOI of the user's geographical location that can be delivered by the distribution capacity. An AOI can be understood as an area where the user's geographical location belongs. The method of obtaining the AOI within the business district can be configured as needed. As an example, the distribution service provider can pre-build a map system. The map system can pre-store geographic data related to one or more business districts. Based on the geographical location of the business district with the capacity boundary to be obtained, all user AOIs within the business district can be obtained from the map system.
[0041] This embodiment can generate a capacity boundary that meets the set target based on each user AOI in the business district. The capacity boundary can be understood as a closed polygon that surrounds some AOIs. The process of generating the capacity boundary is to select which AOIs are included in the closed polygon and which are not included in the closed polygon to meet the set target; different selections can obtain different AOI sets, and thus different capacity boundaries.
[0042] As an example, data corresponding to each AOI (Area of Interest) can be prepared in advance, including but not limited to: geographic location range (which can be composed of multiple geographic location coordinates), number of historical orders, and total historical transaction amount GMV (Gross Merchandise Value) (which can be obtained by multiplying the order quantity by the average order price, or calculated by the transaction amount of each historical order).
[0043] In this embodiment, the merchant locations of each merchant in the target business district can also be obtained in step 204, so that in step 206, the initial capacity boundary can be determined based on the merchant locations of each merchant and the historical order quantity of each AOI, wherein the initial capacity boundary of this embodiment can surround multiple merchants and an initial AOI set. On the one hand, it is considered that the capacity boundary of the target business district is to provide capacity services to the merchants in the business district, so the merchants need to be located within the capacity boundary; on the other hand, in order to accelerate the generation of the capacity boundary, the total number of historical orders of the initial AOI set meets the preset quantity condition, and the preset quantity condition can be used to characterize that the total number of historical orders of the initial AOI set is greater than a preset threshold, so that the final capacity boundary can be generated starting from a better initial capacity boundary, thereby improving the generation efficiency of the capacity boundary.
[0044] As an example, when selecting a business district, the business district can be determined from an area where certain businesses gather, with the area as the center and a set distance (for example, a set value such as ten kilometers); and the capacity boundary of the business district actually refers to the boundary surrounding the business district. Therefore, in this embodiment, the initial capacity boundary can be determined, and the range surrounding the multiple businesses can be determined from the target business district first, and then the initial AOI set can be selected from the multiple AOIs based on these ranges, and the total number of historical orders of the initial AOI set can be limited to meet a preset quantity condition.
[0045] In some examples, determining the initial capacity boundary based on the merchant locations of the merchants and the historical order quantity of each AOI may include:
[0046] Determine a graphic surrounding each of the businesses based on the business locations of each of the businesses;
[0047] An initial AOI set is selected based on the AOIs covered by the graph to determine an initial capacity boundary.
[0048] As an example, Figure 2B , which is a schematic diagram of another capacity boundary shown in this specification according to an exemplary embodiment; the triangle in the figure represents the location of the merchant, and the innermost ellipse represents a figure surrounding all the merchants in the business district. Among them, the figure here is illustrated by an ellipse. In actual application, the shape of the figure here can be configured according to actual needs; for example, the minimum polygon that surrounds each merchant. Alternatively, the shape of the figure can be determined based on the shape of the target business district, for example, a figure similar to the shape of the target business district.
[0049] As an example, the AOIs covered by the graphic can be determined first, and the initial AOI set can be determined based on the number of historical orders of these AOIs. For example, it can be determined whether the number of historical orders of these AOIs meets the preset quantity condition. If so, these AOIs can be determined as the initial AOI set; if not, more AOIs can be selected based on these AOIs to obtain an initial AOI set whose total number of historical orders meets the preset quantity condition. The method of selecting more AOIs based on the AOIs covered by the graphic can be configured according to actual needs, and this embodiment does not limit this. Among them, the initial capacity boundary also surrounds the initial AOI set, so the initial capacity boundary is a boundary where there will be no bubble problem.
[0050] Therefore, on the basis of the initial capacity boundary without bubble problem, a new capacity boundary is gradually diffused outward based on the initial capacity boundary until the final capacity boundary that meets the requirements of the target business district is obtained. Considering the large number of AOIs in the target business district, the step of diffusing the capacity boundary is iteratively executed in step 208. In order to prevent the bubble problem, when diffusing the new capacity boundary from the current capacity boundary, the adjacent AOI of the boundary AOI is selected based on the boundary AOI of the current capacity boundary. Therefore, it can be ensured that the newly selected AOI will not span a large distance, and because it is adjacent to the boundary AOI of the current capacity boundary, the diffused new current capacity boundary will not have the bubble problem.
[0051] Furthermore, in order to ensure that the ultimately determined capacity boundary meets the order requirements and prevent the generated capacity boundary from causing a decrease in the number of future orders of internal merchants, the present embodiment also selects an initial AOI set based on the historical order quantity of the AOI, so that the total number of historical orders of the initial AOI set meets a preset quantity condition, wherein the preset quantity condition can be configured as needed, for example, the total number of historical orders of the initial AOI set may be greater than a set threshold, which may be configured according to actual needs; or, the ratio of the total number of historical orders of the initial AOI set to the total number of historical orders of all AOIs may be greater than a preset ratio threshold, which may be configured according to actual needs.
[0052] As an example, the adjacency relationship between the AOIs in the target business district may be recorded in advance, which may be achieved in a variety of ways. For example, it may be recorded in the form of an adjacency matrix. In some examples, the selection of adjacent AOIs for the boundary AOI of the current capacity boundary may include:
[0053] After obtaining the row number or column number of each boundary AOI of the current capacity boundary in the preset adjacency relationship matrix, the adjacent AOI having an adjacency relationship with the boundary AOI is determined based on the preset adjacency relationship matrix; wherein the adjacency relationship matrix is pre-constructed in the following manner:
[0054] Constructing a matrix based on the number of AOIs of the multiple AOIs, and determining the row number and column number of each AOI in the multiple AOIs in the adjacency matrix to be constructed;
[0055] An adjacency relationship between the plurality of AOIs is obtained, indicating whether the AOIs are adjacent to each other, and an adjacency relationship matrix is constructed according to the row number and column number of each AOI.
[0056] The AOIs of this embodiment can be used as nodes in a graph structure, and the adjacency matrix can be a two-dimensional binary matrix used to represent the connection relationship between nodes (AOIs) in the graph. Assuming there are N AOIs, the adjacency matrix A can be N*N, where:
[0057] A[i][j]=1: indicates that the i-th AOI is adjacent to the j-th AOI.
[0058] A[i][j]=0: indicates that the i-th AOI and the j-th AOI are not adjacent.
[0059] As an example, suppose there are four AOIs: AOI1, AOI2, AOI3, AOI4, and the adjacency matrix A is as follows:
[0060]
[0061] Right now:
[0062] AOI1 is connected to AOI2 and AOI3.
[0063] AOI2 is connected to AOI1, AOI3, and AOI4.
[0064] AOI3 is connected to AOI1 and AOI2.
[0065] AOI4 is only connected to AOI2.
[0066] In order to efficiently use the adjacency matrix, a one-to-one correspondence can be established between the unique identifier (ID) of each AOI and the row and column numbers of the matrix, thereby constructing the adjacency matrix. In this way, each time the adjacent AOI is selected in each iteration, the adjacent AOIs of each boundary AOI can be quickly obtained.
[0067] Optionally, whether two AOIs have an adjacency relationship can be determined according to actual needs.
[0068] As an example, obtaining the adjacency relationship between the multiple AOIs, indicating whether the AOIs are adjacent to each other, may include:
[0069] Based on the geographical location range of each AOI, determine the geographically adjacent AOIs corresponding to each AOI;
[0070] Based on whether there is a traversable path between each AOI and each of its corresponding geographically adjacent AOIs, an adjacency relationship between the AOIs is determined.
[0071] In this embodiment, whether two AOIs have an adjacency relationship can be determined based on the geographical location range of the two AOIs. For example, the geographical location adjacency of two AOIs may mean that the two AOIs are geographically adjacent. In addition, based on the instant delivery scenario of this embodiment, there may be two AOIs that are geographically adjacent, but there may be no passable path between the two AOIs for delivery capacity to pass, that is, the two AOIs cannot be connected. For example, the actual geographical passable path between the two AOIs is an overpass or other path that is not suitable for delivery capacity to pass. Therefore, such AOIs that cannot be connected in the delivery scenario do not have an adjacency relationship. Based on this, this embodiment pre-constructs an adjacency relationship matrix based on the delivery scenario, thereby accelerating the generation of capacity boundaries.
[0072] In some examples, there may be a situation where an AOI is only connected to one AOI. For example, some AOIs may be located in closed communities or restricted areas, which restrict the entry and exit of distribution capacity. Some AOIs can only be entered by the road between another AOI, and other locations cannot enter or exit the AOI. For this case, when selecting adjacent AOIs for the diffusion capacity boundary, these two AOIs need to be selected together, and not just one of them. For example, assuming that AOI_A and AOI_B are connected, and AOI_A is only connected to AOI_B, then when selecting the boundary AOI of the current capacity boundary for the boundary AOI of the current capacity boundary, AOI_A and AOI_B need to be selected as adjacent AOIs; assuming that only AOI_B is selected and AOI_A is not selected
[0073] As an example, a graph structure can be used to represent the relationship between the above multiple AOIs. For example, a node in the graph represents each AOI. The edge in the graph represents the adjacency relationship between the AOIs corresponding to the node. The degree of the node in the graph structure can be used to identify whether there is a situation where an AOI is only connected to one AOI. In the graph structure, the degree of a node refers to the number of edges directly connected to it. That is, the degree of an AOI is equal to the number of its adjacent AOIs.
[0074] For the adjacency matrix, the degree di can be obtained by calculating the number of values 1 in the i-th row of the matrix; traverse all nodes and find the degree di=1. These nodes are the target AOIs that are only connected to one AOI. Based on this, when using the adjacency matrix to find the adjacent AOI, the present embodiment can also use the adjacency matrix to find the target AOI that is only connected to one AOI, so that the target AOI can be selected as the adjacent AOI together with the AOI it is connected to.
[0075] Still taking the above adjacency matrix as an example, AOI4 is only connected to AOI2. Since its degree is 1, it means it is in the distribution network, so it is a "leaf node". The connectivity between AOI1, AOI2, and AOI3 is good, and AOI2 has a higher degree of connectivity. As an AOI that is only connected to AOI2, if AOI4 is selected alone, the connectivity of the distribution network cannot be maintained. Therefore, when expanding the capacity boundary, AOI2 and AOI4 must be selected at the same time. The leaf nodes in the graph structure can be identified to obtain all the leaf nodes in the graph, that is, the target AOI that has an adjacency relationship with only one AOI. Alternatively, the graph structure is stored using an adjacency matrix, and the degree di of each AOI can be obtained by summing the rows of the adjacency matrix.
[0076] As another example, in the above graph structure, AOI2 is a cut point. The meaning of a cut point is that if the node and all edges associated with the node are deleted from the graph, the graph will be divided into two or more disconnected subgraphs, then the node is a cut point. In the above embodiment, AOI2 connects AOI1, AOI3 and AOI4. If AOI2 is removed, AOI1, AOI3 and AOI4 will become disconnected subgraphs. In this way, the AOI corresponding to the cut point needs to be selected. In addition, AOI4 can only be distributed through AOI2. Therefore, when selecting AOI4 as the extended AOI, AOI2 must be selected at the same time to ensure that each AOI in the distribution network has at least one valid distribution path.
[0077] Based on this, this embodiment can obtain the graph structure corresponding to multiple AOIs included in the target business district, identify the cut point and the leaf node connected to only one AOI from the graph structure, determine the first type AOI corresponding to the cut point, and the second type AOI corresponding to the leaf node connected to only one AOI; thus, in the process of diffusing the capacity boundary, when selecting the adjacent AOIs of the boundary AOI of the current capacity boundary, determine whether each adjacent AOI of the boundary AOI belongs to the first type AOI, and whether it belongs to the second type AOI. If yes, the adjacent AOI belonging to the first type AOI is selected first, for example, directly selected first; and the adjacent AOI belonging to the second type AOI and the AOI connected to it are selected together.
[0078] In some examples, selecting an adjacent AOI for the boundary AOI of the current capacity boundary to diffuse the current capacity boundary outward to form a new current capacity boundary based on the selected adjacent AOI may include:
[0079] Obtaining multiple different adjacent AOI selection results planned by a preset operations optimization model for the current transportation capacity boundary with preset constraints; wherein the preset constraints include: the total number of historical orders of each selected adjacent AOI is greater than a preset threshold;
[0080] After determining the historical transaction amount of each adjacent AOI selection result based on the historical transaction amount of each AOI, determine the optimal adjacent AOI selection result with the highest historical transaction amount among the multiple adjacent AOI selection results;
[0081] According to the optimal adjacent AOI selection result, a new current capacity boundary is determined by expanding the current capacity boundary outward.
[0082] In this embodiment, each time the capacity boundary diffuses outward, there may be a variety of different diffusion results. In order to obtain the optimal diffusion result, this embodiment is implemented in conjunction with an operations optimization model, wherein the operations optimization model is designed to generate a plurality of different adjacent AOI selection results on the premise of satisfying restriction conditions, and aims to maximize the total historical transaction amount of the AOI within the boundary.
[0083] As an example, the process may be: from each adjacent AOI of the boundary AOI of the current capacity boundary, based on the historical order quantity threshold, the AOI that meets the conditions is screened out as a candidate set. The operations optimization model can generate a variety of different adjacent AOI selection schemes according to different combinations. As an example, each adjacent AOI selection scheme may include the adjacent AOIs belonging to the cut point of the aforementioned boundary AOI. In each adjacent AOI selection scheme, if the second type of AOI is included, the second type of AOI and the AOIs connected to it need to be included. For example, the first type of AOI and the second type of AOI can be determined from all the adjacent AOIs of each boundary AOI, and then the first type of AOI, the second type of AOI and the AOI connected to the second AOI are selected first, and then based on the first type of AOI, the second type of AOI and the AOI connected to the second AOI, a variety of different adjacent AOI selection schemes are generated.
[0084] Among them, the total historical transaction amount of each adjacent AOI selection scheme is the key evaluation indicator. The operations optimization model can generate a variety of different adjacent AOI selection schemes, calculate their corresponding total historical transaction amount GMV, and sort all schemes from high to low according to GMV, and select the scheme at the top of the sort as the optimal adjacent AOI selection result.
[0085] The AOI set in the optimal adjacent AOI selection result can be added to the current capacity boundary to form a new capacity boundary. Then, based on the fact that the new capacity boundary may include new boundary AOIs, continue to enter the next round of expansion. Continue to iterate the above steps and gradually expand the capacity boundary until the preset retention order ratio or coverage target is reached. When the total number of orders within the current capacity boundary reaches or exceeds the target retention ratio, or when it is impossible to continue to expand effectively, stop iteration and determine the final capacity boundary.
[0086] Among them, the preset restriction conditions of this embodiment include: the total number of historical orders of each adjacent AOI selected is greater than a preset threshold, which is used to limit the number of AOIs diffused by the operations optimization model each time; for example, the order quantity growth ratio can be used for restriction, for example, each time the capacity boundary is diffused, the total number of historical orders of each AOI in the adjacent AOI selection result increases by a set ratio.
[0087] In some examples, after determining the historical transaction amount of each adjacent AOI selection result based on the historical transaction amount of the AOI, determining the optimal adjacent AOI selection result with the highest historical transaction amount among the multiple adjacent AOI selection results may include:
[0088] Based on the historical transaction amount and historical average delivery efficiency of the AOI, determine the historical transaction amount and historical average delivery efficiency of each adjacent AOI selection result;
[0089] From the multiple adjacent AOI selection results, the optimal adjacent AOI selection result with the highest historical transaction amount and the highest historical average delivery efficiency is obtained.
[0090] In this embodiment, considering that different capacity boundaries contain different AOI sets, and the delivery difficulty of the delivery capacity under different AOI sets may be different, this embodiment uses delivery efficiency to represent the delivery difficulty, which can be specifically represented by dividing the delivery time of multiple historical orders by the number of historical orders.
[0091] As an example, the pre-established adjacency matrix can be used to quickly find all adjacent AOIs of the current boundary AOI through the AOI ID to ensure that the selected adjacent AOI is not only geographically adjacent, but also has a feasible path for actual delivery, avoiding delivery problems caused by actual traffic difficulties. The operations optimization model can generate multiple different adjacent AOI selection results for the initial capacity boundary based on preset constraints (such as the total number of historical orders for each adjacent AOI must be greater than a threshold, etc.). Among them, the constraints of the operations optimization model include a historical order quantity threshold, that is, it is necessary to ensure that each selected adjacent AOI has sufficient order volume, and give priority to covering high-demand areas. At the same time, the selected adjacent AOI must be connected to the existing capacity boundary to avoid the formation of separate AOI sets or bubbles.
[0092] The operations optimization model can generate a variety of different adjacent AOI selection results for the initial capacity boundary, and can evaluate the historical transaction amount and delivery efficiency of each selection plan. For example, for each selection plan, the historical transaction amount of all selected AOIs can be accumulated, and the average historical delivery efficiency of all selected AOIs can be determined. Delivery efficiency can be represented by the reciprocal or negative number of the average delivery time (high efficiency, low time). Among all the generated selection plans, select the plan with the highest historical transaction amount and the highest historical average delivery efficiency. As an example, different weights can be given to GMV and delivery efficiency, and the plan with the highest comprehensive score can be selected. After adding the selected optimal adjacent AOI set to the current capacity boundary and obtaining the diffused current capacity boundary, continue to loop the above steps to gradually expand the capacity boundary until the preset retention order ratio or other termination conditions are reached.
[0093] Therefore, this embodiment can combine the historical average delivery efficiency to spread the capacity boundary, so that the finally generated capacity boundary meets both the GMV target and the target of optimal historical average delivery efficiency.
[0094] like Figure 2B As shown, Figure 2B The triangle in the figure is the merchant location, and the boundary of the ellipse inside is the initial capacity boundary f(0). Gradually diffuse outward from the initial capacity boundary, for example, after diffusion k times, the capacity boundary f(k) is obtained, and after diffusion once more, the capacity boundary f(k+1) is obtained.
[0095] Specifically, a function f(r, AOIs) can be defined, where r is the proportion of retained orders, AOIs is the included AOI (the input AOI set), and f represents the capacity boundary for optimizing the maximum GMV.
[0096] Initialize f(r0, AOI), for example, r0 is the range that retains all merchant locations. Then, starting from this order quantity, gradually iterate backwards. In the next diffusion capacity boundary, the proportion of the total number of historical orders can be the proportion of the total number of historical orders in the previous capacity boundary, plus the optimal choice of the selected AOI for logistics optimization. The formula can be described as:
[0097] f(r k+1 ,AOIS k+1 )=MAX{f(r i ,AOIS i ),i=0…k}
[0098] The iteration can be continued until the target reserved order volume ratio is reached; each time the diffusion is performed, the incremental span of the reserved order volume can be set as needed, such as a ratio of 1-30%, etc. In this way, the GMV optimal capacity boundary of the reserved order volume ratio can be generated.
[0099] In some examples, the termination condition can be configured as needed, for example, it can be configured based on the order quantity, it can be that the number of historical orders within the determined capacity boundary meets the set condition, the set condition can be configured as needed, for example, it can be that the set order quantity threshold is reached, or the proportion of the number of historical orders within the capacity boundary to the total number of historical orders in the AOI set reaches a set proportion threshold, etc. The embodiments of this specification are not limited to this.
[0100] In some examples, the method may further include:
[0101] In response to a store display request from a user located within the transportation capacity boundary of the target business district, multiple stores located in the target business district are recalled and pushed to the user.
[0102] After obtaining the capacity boundary of the target business district, when the user uses the client, the service provider can determine the business district to which the user belongs based on the user's geographical location; for example, in response to a store display request from a user located within the capacity boundary of the target business district, the service provider can recall multiple stores located in the target business district based on the capacity boundary and push them to the user, thereby exposing the online stores of merchants that can provide services to the user to the user.
[0103] It can be seen from the above embodiments that the initial capacity boundary can surround multiple merchants and the initial AOI set. On the one hand, it is considered that the capacity boundary of the target business district is to provide capacity services to the merchants in the business district, so the merchants need to be located within the capacity boundary; on the other hand, in order to accelerate the generation of the capacity boundary, the total number of historical orders of the initial AOI set meets the preset quantity condition, and the preset quantity condition can be used to characterize that the total number of historical orders of the initial AOI set is greater than the preset threshold, so that the final capacity boundary can be generated from the better initial capacity boundary, thereby improving the generation efficiency of the capacity boundary; and the initial capacity boundary surrounds the initial AOI set, so the initial capacity boundary is a boundary that will not have bubble problems, and thus, on the basis of the initial capacity boundary that will not have bubble problems, the adjacent AOI of the boundary AOI is selected based on the boundary AOI of the current capacity boundary, so that it can be ensured that the newly selected AOI will not span a large distance, and since it is adjacent to the boundary AOI of the current capacity boundary, the diffused new current capacity boundary will not have bubble problems either.
[0104] Corresponding to the aforementioned embodiment of the method for generating a capacity boundary, this specification also provides an embodiment of an apparatus for generating a capacity boundary and a computer device used therein.
[0105] The embodiments of the device for generating the capacity boundary of this specification can be applied to computer devices, such as servers or terminal devices. The device embodiments can be implemented by software, hardware, or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor in which it is located reading the corresponding computer program instructions in the non-volatile memory into the memory and running them. From the hardware level, if Figure 3 The figure is a hardware structure diagram of the computer device where the device for generating the capacity boundary of this specification is located, except Figure 3 In addition to the processor 310, memory 330, network interface 320, and non-volatile memory 340 shown, the computer device where the capacity boundary generation device is located in the embodiment may also include other hardware according to the actual function of the computer device, which will not be described in detail.
[0106] As an example, Figure 4 FIG. 1 is a structural diagram of a device for generating a capacity boundary in an embodiment of the present specification, which may include:
[0107] The AOI acquisition module 41 is used to: acquire multiple AOIs included in the target business district and the number of historical orders corresponding to each of the AOIs;
[0108] The location acquisition module 42 is used to: acquire the merchant locations of multiple merchants in the target business district;
[0109] The initial boundary determination module 43 is used to determine an initial capacity boundary based on the merchant locations of the multiple merchants and the number of historical orders of each of the AOIs; wherein the initial capacity boundary surrounds the merchant locations of each merchant and an initial AOI set selected from the multiple AOIs, and the total number of historical orders of the initial AOI set meets a preset quantity condition;
[0110] The execution module 44 is used to: after taking the initial capacity boundary as the current capacity boundary, loop through the following steps until a preset termination condition is met to obtain the capacity boundary of the target business district: select an adjacent AOI for the boundary AOI of the current capacity boundary, so as to diffuse the current capacity boundary outward to form a new current capacity boundary based on the selected adjacent AOI.
[0111] In some examples, the location acquisition module 42 is further used to:
[0112] Determine a graphic surrounding each of the businesses based on the business locations of each of the businesses;
[0113] Based on each AOI covered by the graph, the initial AOI set is determined to determine the initial capacity boundary.
[0114] In some examples, the execution module 44 is further configured to:
[0115] Obtaining multiple different adjacent AOI selection results planned by a preset operations optimization model for the current transportation capacity boundary with preset constraints; wherein the preset constraints include: the total number of historical orders of each selected adjacent AOI is greater than a preset threshold;
[0116] After determining the historical transaction amount of each adjacent AOI selection result based on the historical transaction amount of each AOI, determine the optimal adjacent AOI selection result with the highest historical transaction amount among the multiple adjacent AOI selection results;
[0117] According to the optimal adjacent AOI selection result, a new current capacity boundary is determined by expanding the current capacity boundary outward.
[0118] In some examples, the execution module 44 is further configured to:
[0119] Based on the historical transaction amount and historical average delivery efficiency of the AOI, determine the historical transaction amount and historical average delivery efficiency of each adjacent AOI selection result;
[0120] From the multiple adjacent AOI selection results, the optimal adjacent AOI selection result with the highest historical transaction amount and the highest historical average delivery efficiency is obtained.
[0121] In some examples, the execution module 44 is further configured to:
[0122] After obtaining the row number or column number of each boundary AOI of the current capacity boundary in the preset adjacency relationship matrix, the adjacent AOI having an adjacency relationship with the boundary AOI is obtained from the preset adjacency relationship matrix; wherein the adjacency relationship matrix is pre-determined in the following manner:
[0123] Constructing a matrix based on the number of AOIs of the multiple AOIs, and determining the row number and column number of each AOI in the multiple AOIs in the adjacency matrix to be constructed;
[0124] An adjacency relationship between the plurality of AOIs is obtained, indicating whether the AOIs are adjacent to each other, and an adjacency relationship matrix is constructed according to the row number and column number of each AOI.
[0125] In some examples, the execution module 44 is further configured to:
[0126] Based on the geographical location range of each AOI, determine the geographically adjacent AOIs corresponding to each AOI;
[0127] Based on whether there is a traversable path between each AOI and each of its corresponding geographically adjacent AOIs, an adjacency relationship between the AOIs is determined.
[0128] In some examples, the apparatus further includes a push module, configured to:
[0129] In response to a store display request from a user located within the transportation capacity boundary of the target business district, multiple stores located in the target business district are recalled and pushed to the user.
[0130] The implementation process of the functions and effects of each module in the above-mentioned capacity boundary generation device is specifically described in the implementation process of the corresponding steps in the above-mentioned capacity boundary generation method, and will not be repeated here.
[0131] Accordingly, an embodiment of the present specification also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the aforementioned capacity boundary generation method embodiment.
[0132] Accordingly, an embodiment of the present specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of an embodiment of a method for generating a capacity boundary are implemented.
[0133] Accordingly, an embodiment of the present specification also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the embodiment of the method for generating a capacity boundary are implemented.
[0134] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. A person of ordinary skill in the art can understand and implement it without paying creative labor.
[0135] The above embodiments can be applied to one or more computer devices, where the computer device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. The hardware of the computer device includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.
[0136] The computer device may be any electronic product that can perform human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.
[0137] The computer device may also include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.
[0138] The network where the computer device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.
[0139] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0140] The step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the protection scope of this application.
[0141] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claim protection, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.
[0142] The description of "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0143] Those skilled in the art will readily appreciate other embodiments of the specification after considering the specification and practicing the invention claimed herein. The specification is intended to cover any variations, uses or adaptations of the specification that follow the general principles of the specification and include common knowledge or customary techniques in the art that are not claimed in the specification. The specification and examples are to be considered exemplary only, and the true scope and spirit of the specification are indicated by the following claims.
[0144] It should be understood that the present description is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.
[0145] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.
Claims
1. A method for generating a capacity boundary, the method comprising: Obtain multiple AOIs included in the target business district and the number of historical orders corresponding to each of the AOIs; Obtaining the business location of each business in the target business district; Based on the merchant locations of the various merchants and the number of historical orders of the various AOIs, an initial transportation capacity boundary is determined; wherein the initial transportation capacity boundary surrounds the merchant locations of the various merchants and an initial AOI set selected from the multiple AOIs, and the total number of historical orders of the initial AOI set meets a preset quantity condition; After taking the initial capacity boundary as the current capacity boundary, the following steps are executed in a loop until the preset termination condition is met to obtain the capacity boundary of the target business district: an adjacent AOI is selected for the boundary AOI of the current capacity boundary, so as to diffuse the current capacity boundary into a new current capacity boundary based on the selected adjacent AOI.
2. The method according to claim 1, wherein determining the initial capacity boundary based on the merchant location of each merchant and the number of historical orders of each AOI comprises: Determine a graphic surrounding each of the businesses based on the business locations of each of the businesses; Based on each AOI covered by the graph, the initial AOI set is determined to determine the initial capacity boundary.
3. The method according to claim 1, wherein the selecting an adjacent AOI from the boundary AOI of the current capacity boundary, and spreading the current capacity boundary outward to form a new current capacity boundary based on the selected adjacent AOI, comprises: Obtaining multiple different adjacent AOI selection results planned by a preset operations optimization model for the current transportation capacity boundary with preset constraints; wherein the preset constraints include: the total number of historical orders of each selected adjacent AOI is greater than a preset threshold; After determining the historical transaction amount of each adjacent AOI selection result based on the historical transaction amount of each AOI, determine the optimal adjacent AOI selection result with the highest historical transaction amount among the multiple adjacent AOI selection results; According to the optimal adjacent AOI selection result, a new current capacity boundary is determined by expanding the current capacity boundary outward.
4. The method according to claim 3, wherein after determining the historical transaction amount of each adjacent AOI selection result based on the historical transaction amount of the AOI, determining the optimal adjacent AOI selection result with the highest historical transaction amount among the multiple adjacent AOI selection results comprises: Based on the historical transaction amount and historical average delivery efficiency of the AOI, determine the historical transaction amount and historical average delivery efficiency of each adjacent AOI selection result; From the multiple adjacent AOI selection results, the optimal adjacent AOI selection result with the highest historical transaction amount and the highest historical average delivery efficiency is obtained.
5. The method according to claim 1, wherein selecting an adjacent AOI from the boundary AOI of the current capacity boundary comprises: After obtaining the row number or column number of each boundary AOI of the current capacity boundary in the preset adjacency relationship matrix, an adjacent AOI having an adjacency relationship with the boundary AOI is selected based on the preset adjacency relationship matrix; wherein the adjacency relationship matrix is pre-constructed in the following manner: Constructing a matrix based on the number of AOIs of the multiple AOIs, and determining the row number and column number of each AOI in the multiple AOIs in the adjacency relationship matrix to be constructed; An adjacency relationship between the plurality of AOIs is obtained, indicating whether the AOIs are adjacent to each other, and an adjacency relationship matrix is constructed according to the row number and column number of each AOI.
6. The method according to claim 5, wherein obtaining the adjacency relationship between the plurality of AOIs, i.e., whether the AOIs are adjacent to each other, comprises: Based on the geographical location range of each AOI, determine the geographically adjacent AOIs corresponding to each AOI; Based on whether there is a traversable path between each AOI and each of its corresponding geographically adjacent AOIs, an adjacency relationship is determined as to whether the AOIs are adjacent to each other.
7. The method according to claim 1, further comprising: In response to a store display request from a user located within the transportation capacity boundary of the target business district, multiple stores located in the target business district are recalled and pushed to the user.
8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.