A distribution range determination method and device, electronic equipment and storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for determining delivery range, relating to the field of data processing, and aims to automatically determine a reasonable delivery range for a merchant. The method includes: comparing the characteristics of a target merchant with the characteristics of various other merchants to determine similar merchants and their corresponding similarity levels; determining the correlation between each of the multiple candidate areas and the similar merchants based on the historical orders of users in the multiple candidate areas; determining the correlation between each of the multiple candidate areas and the target merchant based on the similarity levels of the similar merchants and the correlation between each of the multiple candidate areas and the similar merchants; determining a set of target areas based on the correlation between each of the multiple candidate areas and the target merchant; and concatenating the target areas included in the set of target areas to obtain the delivery range of the target merchant.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, apparatus, electronic device, and storage medium for determining delivery range. Background Technology

[0002] With the continuous development of e-commerce, online shopping has become increasingly common. To avoid wasting transportation capacity and causing a poor user experience due to excessively long delivery times, it is necessary to set delivery ranges for each merchant, so that only users within the merchant's delivery range can purchase the merchant's products.

[0003] In related technologies, the delivery range of a merchant is determined directly based on the merchant's geographical location and preset straight-line distance. However, the delivery range determined in this way is often not reasonable enough. Alternatively, the delivery range of a merchant can be manually divided, which is inefficient and consumes a lot of human resources. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a method, apparatus, electronic device and storage medium for determining delivery range, so as to overcome the above problems or at least partially solve the above problems.

[0005] A first aspect of the present invention provides a method for determining a delivery range, the method comprising:

[0006] Based on the geographical location of the target merchant, obtain multiple candidate areas for the target merchant;

[0007] The characteristics of the target merchant are compared with the characteristics of each merchant to determine the similar merchants of the target merchant and the corresponding similarity.

[0008] Based on the historical orders of each user in the multiple candidate areas to the similar merchants, the correlation between each of the multiple candidate areas and the similar merchants is determined;

[0009] Based on the similarity of the similar merchants and the correlation between each of the multiple candidate areas and the similar merchants, the correlation between each of the multiple candidate areas and the target merchant is determined.

[0010] The target area set is determined based on the correlation between each of the multiple candidate areas and the target merchant;

[0011] The delivery range of the target merchant is obtained by splicing together the various target areas included in the target area set.

[0012] Optionally, the characteristics of the target merchant are compared with the characteristics of various merchants to determine similar merchants and their corresponding similarity scores, including:

[0013] Based on the characteristics of the target merchant and the characteristics of each merchant, a representation vector for the target merchant and a representation vector for each merchant are generated respectively.

[0014] Calculate the distance between the representation vector of the target merchant and the representation vectors of each of the other merchants to obtain the similar merchants of the target merchant and the corresponding similarity.

[0015] Optionally, based on the geographical location of the target merchant, multiple candidate areas for the target merchant are obtained, including:

[0016] Divide the area into a predetermined area centered on the geographical location of the target merchant;

[0017] Multiple zones within the region are identified as multiple candidate zones for the target merchant.

[0018] Optionally, based on the historical orders of each user in the multiple candidate areas with the similar merchants, the correlation between each of the multiple candidate areas and the similar merchants is determined, including:

[0019] The historical orders of each user in the multiple candidate areas from similar merchants are analyzed from multiple dimensions to obtain data from multiple dimensions;

[0020] Based on data from multiple dimensions for each candidate area, the correlation between each candidate area and the similar merchants is determined.

[0021] Optionally, the method further includes:

[0022] Based on the geographical locations of the multiple candidate areas and the geographical location of the target merchant, the geographical location scores of the multiple candidate areas are determined;

[0023] Based on the correlation between each of the multiple candidate areas and the target merchant, a set of target areas is determined, including:

[0024] The target area set is determined based on the geographical location scores of the multiple candidate areas and their correlation with the target merchants.

[0025] Optionally, a set of target areas is determined based on the correlation between each of the multiple candidate areas and the target merchant, including:

[0026] Candidate areas are selected sequentially and added to the target area set in descending order of relevance, until all target areas in the target area set meet the constraints, including: the delivery range obtained according to the target area set exceeds a preset range and / or the product delivery time exceeds a preset time.

[0027] A second aspect of the present invention provides a delivery range determination device, the device comprising:

[0028] The candidate area acquisition module is used to acquire multiple candidate areas for the target merchant based on the target merchant's geographical location.

[0029] The similar merchant determination module is used to compare the features of the target merchant with the features of each merchant to determine the similar merchants of the target merchant and the corresponding similarity.

[0030] The first correlation determination module is used to determine the correlation between each of the multiple candidate areas and the similar merchants based on the historical orders of each user in the multiple candidate areas.

[0031] The second correlation determination module is used to determine the correlation between each of the multiple candidate areas and the target merchant based on the similarity corresponding to the similar merchants and the correlation between each of the multiple candidate areas and the similar merchants.

[0032] The area set determination module is used to determine the target area set based on the correlation between each of the multiple candidate areas and the target merchant;

[0033] The delivery range determination module is used to stitch together the various target areas included in the target area set to obtain the delivery range of the target merchant.

[0034] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the delivery range determination method disclosed in the embodiments of this application.

[0035] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the delivery range determination method disclosed in the embodiments of this application.

[0036] A fifth aspect of the present invention provides a computer program product, including a computer program or computer instructions, wherein the computer program or computer instructions, when executed by a processor, implement the delivery range determination method disclosed in the embodiments of this application.

[0037] The embodiments of the present invention have the following advantages:

[0038] In this embodiment, multiple candidate areas for the target merchant can be obtained based on the target merchant's geographical location. The characteristics of the target merchant are compared with those of other merchants to determine similar merchants and their corresponding similarity scores. Based on the historical orders of users in each of the multiple candidate areas with those similar merchants, the correlation between each candidate area and the similar merchant is determined. Based on the similarity scores of the similar merchants and the correlation scores between each candidate area and the similar merchant, the correlation between each candidate area and the target merchant is determined. Based on the correlation scores between each candidate area and the target merchant, a target area set is determined. The target areas included in the target area set are then concatenated to obtain the delivery range of the target merchant. Thus, compared to simply and crudely determining the merchant's delivery range based on a preset straight-line distance, this embodiment uses a more refined granularity—the area level—to automatically determine the target area through the correlation scores between candidate areas and the target merchant, thereby determining the target merchant's delivery range. This ensures that the determined delivery range of the target merchant is reasonable and does not require a large amount of manpower.

[0039] Furthermore, this embodiment is also applicable to cold starts when the target merchant is a new merchant. The new merchant does not have historical orders, and it is impossible to directly determine the correlation between multiple candidate areas and the new merchant based on the new merchant's historical orders in order to determine the appropriate delivery range. This embodiment determines the correlation between the candidate area and the new merchant by the correlation between the candidate area and similar merchants, thereby determining the delivery range of the new merchant and solving the technical problem that it is difficult to determine the delivery range when the new merchant does not have historical orders. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of the merchant delivery range determined according to a preset straight-line distance in an embodiment of the present invention;

[0042] Figure 2 This is a flowchart illustrating the steps of a delivery range determination method according to an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram illustrating the merchant delivery range determined based on geographic location and relevance in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of a delivery range determination device according to an embodiment of the present invention. Detailed Implementation

[0045] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0046] Figure 1 This is a schematic diagram illustrating the delivery range of a merchant based on a preset straight-line distance. Black dots represent merchants, rectangles represent different areas, and large circles represent the merchant's delivery area. For example... Figure 1 As shown, the merchant's delivery range is determined based on the straight-line distance, including areas B and C, which are located on opposite sides of the river. This means that delivery personnel will consume significant resources when delivering orders to areas B and C, resulting in a poor user experience. Furthermore, even though area A is only slightly beyond the preset straight-line distance, it is outside the delivery range, causing a significant loss of customers for the merchant. A high-popularity area refers to an area with a large number of orders. For example, if many users in an office building area frequently order takeout, then that office building area is considered a high-popularity area for takeout merchants.

[0047] To address the issue of unreasonable merchant delivery ranges determined in related technologies, the applicant proposes: using regions as the granularity, indirectly determining the correlation between candidate regions and target merchants by analyzing users' historical orders from similar merchants within candidate regions, and finally determining the delivery range of the target merchant based on candidate regions with high correlation.

[0048] Reference Figure 2 The diagram illustrates a flowchart of steps for determining a delivery range according to an embodiment of the present invention. Figure 2 As shown, the method for determining the delivery range may specifically include the following steps:

[0049] Step S11: Based on the geographical location of the target merchant, obtain multiple candidate areas for the target merchant.

[0050] The target merchant can be a new merchant or any other merchant. The candidate area for the target merchant is a large area centered on the target merchant.

[0051] Optionally, as an embodiment, obtaining multiple candidate areas of the target merchant based on the target merchant's geographical location includes: dividing an area of ​​a preset size centered on the target merchant's geographical location; and determining multiple areas included in the area as multiple candidate areas of the target merchant.

[0052] To ensure that high-popularity areas are not excluded when determining candidate areas, the selected candidate areas can include a larger number of areas. Obtain the geographical location of the target merchant and divide the area into pre-defined zones centered on that location. The delivery range area for each merchant can be approximately the same, but the pre-defined zone is larger than the merchant's delivery range area. The pre-defined zone can be a circular area with the target merchant's geographical location as the center and a pre-defined distance as the radius.

[0053] After dividing the area into preset areas, the sub-areas included in the area are identified as multiple candidate sub-areas for the target merchants. These sub-areas can be residential communities, parks, buildings, etc.

[0054] Step S12: Compare the features of the target merchant with the features of each merchant to determine the similar merchants of the target merchant and the corresponding similarity.

[0055] Merchant characteristics include their geographical location, brand, product categories, product prices, and customer base.

[0056] Merchants surrounding the target merchant and sharing many of the same characteristics can be directly identified as similar merchants, with higher similarity indicating a greater number of shared characteristics. However, this method is not very accurate in determining similar merchants and their similarity scores. Therefore, similar merchants can be identified based on their representation vectors.

[0057] Optionally, as an embodiment, comparing the features of the target merchant with the features of each merchant to determine the similar merchants of the target merchant and the corresponding similarity scores includes: generating a representation vector of the target merchant and a representation vector of each merchant based on the features of the target merchant and the features of each merchant; calculating the distance between the representation vector of the target merchant and the representation vectors of each merchant to obtain the similar merchants of the target merchant and the corresponding similarity scores.

[0058] Merchant features can be obtained in advance and input into the model. The model generates representation vectors for each merchant and stores the representation vectors of each merchant in a vector database.

[0059] When determining the delivery range of a target merchant, if the target merchant is new and its representation vector does not exist in the vector database, then the features of the new merchant are obtained, its representation vector is generated through the model, and then the n merchants with the highest similarity to the new merchant's representation vector are retrieved from the vector database. If the target merchant is not new and its representation vector already exists in the vector database, then the target merchant's representation vector is directly obtained, and the n merchants with the highest similarity to the target merchant's representation vector are retrieved from the vector database.

[0060] The similarity of representation vectors can be obtained by calculating the Euclidean distance or cosine distance between them. The model that generates representation vectors based on the merchant's features can be pre-trained based on the DeepWalk algorithm or the Node2Vec algorithm, and this embodiment of the invention does not limit this.

[0061] Multiple merchants with high similarity are identified as similar merchants to the target merchant. The identification of similar merchants based on their representation vectors and corresponding similarity scores demonstrates high accuracy.

[0062] Step S13: Determine the correlation between each of the multiple candidate areas and the similar merchants based on the historical orders of each user in the multiple candidate areas.

[0063] To determine whether to include a candidate area as a target area, it is necessary to assess the correlation between the candidate area and multiple similar merchants. A higher correlation indicates that the area is more suitable for inclusion in the merchant's delivery area.

[0064] The historical orders placed by users in multiple candidate areas with similar merchants are those where the delivery address is in the candidate area and the seller is a similar merchant. These historical orders are used to determine the correlation between each candidate area and similar merchants. A candidate area with a large number of historical orders where the delivery address is in the candidate area and the seller is a similar merchant is considered to have a higher correlation with similar merchants. Furthermore, the correlation between candidate areas and similar merchants can also be obtained from factors such as delivery distance, delivery time, and user reviews of historical orders.

[0065] Optionally, as an embodiment, determining the correlation between each of the multiple candidate areas and the similar merchants based on the historical orders of each user in the multiple candidate areas at the similar merchants includes: analyzing the historical orders of each user in the multiple candidate areas at the similar merchants from multiple dimensions to obtain data from multiple dimensions; and determining the correlation between each candidate area and the similar merchants based on the data from multiple dimensions of each candidate area.

[0066] This analysis examines historical orders placed by users in multiple candidate areas with similar merchants across various dimensions, including order volume, delivery distance, delivery time, and user reviews. The resulting data is weighted and summed to determine the correlation between each candidate area and similar merchants.

[0067] In this way, the historical orders of each user in multiple candidate areas from similar merchants can be analyzed from multiple dimensions to accurately obtain the correlation between each candidate area and similar merchants.

[0068] Step S14: Determine the correlation between each of the multiple candidate areas and the target merchant based on the similarity of the similar merchants and the correlation between each of the multiple candidate areas and the similar merchants.

[0069] For each candidate area, the correlation between each candidate area and the target merchant is calculated, which can be obtained using the following formula:

[0070]

[0071] Where, r m r represents the correlation between candidate region m and target businesses. m，i Let w be the correlation between candidate area m and the i-th similar merchant; i Let be the similarity between the i-th similar merchant and the target merchant.

[0072] In this way, the correlation between the target merchant and each candidate area can be obtained by comparing the correlation between multiple similar merchants and each candidate area, and the correlation between the target merchant and each candidate area is relatively accurate.

[0073] Step S15: Determine the target area set based on the correlation between each of the multiple candidate areas and the target merchant.

[0074] After obtaining the correlation between each candidate area and the target merchant, multiple candidate areas with high correlation can be used as target areas. The target area is the area within the delivery range of the determined target merchant.

[0075] Step S16: Combine the target areas included in the target area set to obtain the delivery range of the target merchant.

[0076] After the target area is determined, the delivery range of the target merchant can be generated using a polygon outsourcing algorithm.

[0077] Compared to simply and crudely determining a merchant's delivery range based on a preset straight-line distance, the technical solution of this application uses a finer granularity—the district level—to automatically determine the target district by analyzing the correlation between candidate districts and the target merchant. This ensures that the determined delivery range is reasonable and requires minimal human resources. Furthermore, this embodiment is applicable to cold starts when the target merchant is a new merchant. New merchants lack historical orders, making it impossible to directly determine the correlation between multiple candidate districts and the new merchant to determine a suitable delivery range. This embodiment determines the correlation between candidate districts and the new merchant by analyzing the correlation between candidate districts and similar merchants, thus determining the delivery range for the new merchant and solving the technical problem of determining the delivery range for new merchants without historical orders.

[0078] Optionally, as an embodiment, the delivery range determination method further includes: determining the geographical location score of the multiple candidate areas based on the geographical location of the multiple candidate areas and the geographical location of the target merchant; and determining the target area set based on the correlation between each of the multiple candidate areas and the target merchant, including: determining the target area set based on the geographical location score of each of the multiple candidate areas and its correlation with the target merchant.

[0079] Some candidate areas with high relevance may have barriers between them and the target merchants, such as railways, rivers, or mountains. If candidate areas with barriers to the target merchants are also selected as target areas, problems such as excessively long delivery times and wasted transportation resources may occur. To avoid these problems, when determining target areas based on relevance, the geographical location of candidate areas can also be considered.

[0080] The geographical location scores of the candidate areas are determined based on the geographical locations of the candidate areas and the target merchant. If there are barriers or inconvenient transportation between the candidate areas and the target merchant, the geographical location scores of the candidate areas will be lower.

[0081] The total score of the candidate areas is determined by weighting the relevance and geographical location scores. The candidate areas with the highest total scores are then selected as the target areas.

[0082] Figure 3 This is a diagram illustrating the delivery range of merchants determined based on geographic location and relevance. Black dots represent merchants, rectangles represent different areas, and dashed lines represent the merchant's delivery area. For example... Figure 3As shown, areas B and C, located on opposite sides of the river from the merchant, had low geographical location scores, resulting in a low total score determined by the weighted sum of their relevance and geographical location scores. Therefore, they were excluded from the merchant's delivery range. Area A, which had high popularity, was slightly farther from the merchant, but its high popularity led to a higher relevance score, resulting in a higher total score. Therefore, area A, which had high popularity, was also within the merchant's delivery range.

[0083] The technical solution adopted in this application comprehensively considers the relevance and geographical location of the candidate areas when determining the target area based on the candidate areas, thus avoiding problems such as inconvenience or barriers between the candidate areas and the target merchants. As a result, the delivery range of the determined merchants is more reasonable.

[0084] Optionally, as an embodiment, determining a target area set based on the correlation between each of the multiple candidate areas and the target merchant includes: sequentially selecting candidate areas and adding them to the target area set in descending order of correlation, until each target area included in the target area set meets the constraints, the constraints including: the delivery range obtained according to the target area set exceeds a preset range and / or the product delivery time exceeds a preset time.

[0085] To ensure fairness among merchants, the delivery area of ​​each merchant, including the target merchant, should be roughly the same. To guarantee a good user experience, the delivery time from the merchant to the user's area should be limited. Therefore, when determining the target area, the delivery area determined based on the target area, as well as the delivery time between the target area and the target merchant, should be considered.

[0086] Candidate areas are sequentially selected as target areas based on their relevance, from highest to lowest, until the delivery range determined by the target areas meets the constraints. These constraints include: the delivery range obtained from the set of target areas exceeds a preset range and / or the product delivery time exceeds a preset time. The preset range is obtained based on the delivery ranges of other merchants, and the preset time can be set according to actual needs. For example, for products like noodles and dumplings, a shorter preset time can be set to ensure a better user experience; for daily necessities, a longer preset time can be set.

[0087] By adopting the technical solution of this application embodiment and setting constraints, it is possible to ensure that the delivery range of each merchant is relatively equal and fair, and also to guarantee the user experience.

[0088] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0089] Figure 4 This is a schematic diagram of the structure of a delivery range determination device according to an embodiment of the present invention, as shown below. Figure 4 As shown, a delivery range determination device includes a candidate area acquisition module, a similar merchant determination module, a first correlation determination module, a second correlation determination module, an area set determination module, and a delivery range determination module, wherein:

[0090] The candidate area acquisition module is used to acquire multiple candidate areas for the target merchant based on the target merchant's geographical location.

[0091] The similar merchant determination module is used to compare the features of the target merchant with the features of each merchant to determine the similar merchants of the target merchant and the corresponding similarity.

[0092] The first correlation determination module is used to determine the correlation between each of the multiple candidate areas and the similar merchants based on the historical orders of each user in the multiple candidate areas.

[0093] The second correlation determination module is used to determine the correlation between each of the multiple candidate areas and the target merchant based on the similarity corresponding to the similar merchants and the correlation between each of the multiple candidate areas and the similar merchants.

[0094] The area set determination module is used to determine the target area set based on the correlation between each of the multiple candidate areas and the target merchant;

[0095] The delivery range determination module is used to stitch together the various target areas included in the target area set to obtain the delivery range of the target merchant.

[0096] Optionally, as an embodiment, the similar merchant determination module includes:

[0097] The representation vector generation unit is used to generate the representation vector of the target merchant and the representation vector of each merchant based on the characteristics of the target merchant and the characteristics of each merchant, respectively.

[0098] The similarity calculation unit is used to calculate the distance between the representation vector of the target merchant and the representation vector of each merchant, so as to obtain the similar merchants of the target merchant and the corresponding similarity.

[0099] Optionally, as an embodiment, the candidate area acquisition module includes:

[0100] The area division unit is used to divide an area of ​​a preset size with the geographical location of the target merchant as the center;

[0101] The candidate area determination unit is used to determine multiple areas included in the region as multiple candidate areas for the target merchant.

[0102] Optionally, as an embodiment, the first correlation determination module includes:

[0103] The order analysis unit is used to analyze the historical orders of each user in the multiple candidate areas from the same similar merchants from multiple dimensions to obtain data from multiple dimensions.

[0104] The correlation determination unit is used to determine the correlation between each candidate area and the similar merchants based on data from multiple dimensions of each candidate area.

[0105] Optionally, as an embodiment, the apparatus further includes:

[0106] The geographic location score determination module is used to determine the geographic location score of the multiple candidate areas based on the geographic location of the multiple candidate areas and the geographic location of the target merchant;

[0107] The region set determination module includes:

[0108] The area set determination unit is used to determine the target area set based on the geographical location of each of the multiple candidate areas and their correlation with the target merchant.

[0109] Optionally, as an embodiment, the area set determination module includes:

[0110] The area set constraint unit is used to select candidate areas in descending order of relevance and add them to the target area set until all target areas included in the target area set meet the constraint conditions, which include: the delivery range obtained according to the target area set exceeds the preset range and / or the product delivery time exceeds the preset time.

[0111] Compared to simply and crudely determining a merchant's delivery range based on a preset straight-line distance, the technical solution of this application uses a finer granularity—such as a district—to automatically determine the target district by analyzing the correlation between candidate districts and the target merchant. This ensures that the determined delivery range is reasonable and requires minimal human resources. Furthermore, this embodiment is applicable to cold starts when the target merchant is a new merchant. New merchants lack historical orders, making it impossible to directly determine the correlation between multiple candidate districts and the new merchant to determine a suitable delivery range. This embodiment determines the correlation between candidate districts and the new merchant by analyzing the correlation between candidate districts and similar merchants, thus determining the delivery range for the new merchant and solving the technical problem of determining the delivery range for new merchants without historical orders. It should be noted that the device embodiment and the method embodiment are similar, and therefore the description is relatively simple; relevant details can be found in the method embodiment.

[0112] This invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the delivery range determination method disclosed in this application.

[0113] This invention also provides a computer-readable storage medium storing a computer program, which, when executed, implements the delivery range determination method disclosed in this application.

[0114] This invention also provides a computer program product, including a computer program or computer instructions, which, when executed by a processor, implement the delivery range determination method disclosed in the embodiments of this application.

[0115] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0116] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, electronic devices, and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0118] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0120] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0121] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0122] The above provides a detailed description of the delivery range determination method, apparatus, electronic device, and storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of determining a delivery range, characterized by, The method includes: Based on the geographical location of the target merchant, multiple candidate areas for the target merchant are obtained; wherein, obtaining multiple candidate areas for the target merchant includes: Centered on the geographical location of the target merchant, a region of preset area is defined, the preset area being larger than the merchant's delivery range area; Multiple zones within the region are identified as multiple candidate zones for the target merchant; The characteristics of the target merchant are compared with the characteristics of each merchant to determine the similar merchants of the target merchant and the corresponding similarity. Based on the historical orders of each user in the multiple candidate areas from the similar merchants, the correlation between each of the multiple candidate areas and the similar merchants is determined. Based on the similarity of the similar merchants and the correlation between each of the multiple candidate areas and the similar merchants, the correlation between each of the multiple candidate areas and the target merchant is determined. Based on the geographical locations of the multiple candidate areas and the geographical location of the target merchant, the geographical location scores of the multiple candidate areas are determined; Based on the correlation between each of the multiple candidate areas and the target merchant, a set of target areas is determined, including: The target area set is determined based on the geographical location of each of the multiple candidate areas and their correlation with the target merchants; The delivery range of the target merchant is obtained by splicing together the various target areas included in the target area set.

2. The method of claim 1, wherein, The characteristics of the target merchant are compared with the characteristics of various merchants to determine similar merchants and their corresponding similarity scores, including: Based on the characteristics of the target merchant and the characteristics of each merchant, a representation vector for the target merchant and a representation vector for each merchant are generated respectively. Calculate the distance between the representation vector of the target merchant and the representation vectors of each of the other merchants to obtain the similar merchants of the target merchant and the corresponding similarity.

3. The method of claim 1, wherein, Based on the historical orders of each user in the multiple candidate areas from the similar merchants, the correlation between each of the multiple candidate areas and the similar merchants is determined, including: The historical orders of each user in the multiple candidate areas from similar merchants are analyzed from multiple dimensions to obtain data from multiple dimensions; Based on data from multiple dimensions for each candidate area, the correlation between each candidate area and the similar merchants is determined.

4. The method according to any one of claims 1 to 3, characterized in that, Based on the geographical location scores of the multiple candidate areas and their relevance to the target merchants, the target area set is determined, including: Candidate regions are selected sequentially from highest to lowest relevance and added to the target region set until all target regions in the target region set satisfy the constraints, which include: The delivery range obtained according to the target area set exceeds the preset range and / or the product delivery time is greater than the preset time.

5. A delivery range determination device, characterized in that, The device includes: A candidate area acquisition module is used to acquire multiple candidate areas for a target merchant based on the target merchant's geographical location; wherein, the candidate area acquisition module includes: A region division unit is used to divide a region of preset area centered on the geographical location of the target merchant, wherein the preset area is larger than the merchant's delivery range area; The candidate area determination unit is used to determine multiple areas included in the region as multiple candidate areas for the target merchant; The similar merchant determination module is used to compare the features of the target merchant with the features of each merchant to determine the similar merchants of the target merchant and the corresponding similarity. The first correlation determination module is used to determine the correlation between each of the multiple candidate areas and the similar merchants based on the historical orders of each user in the multiple candidate areas. The second correlation determination module is used to determine the correlation between each of the multiple candidate areas and the target merchant based on the similarity corresponding to the similar merchants and the correlation between each of the multiple candidate areas and the similar merchants. The geographic location score determination module is used to determine the geographic location score of the multiple candidate areas based on the geographic location of the multiple candidate areas and the geographic location of the target merchant; The area set determination module is used to determine the target area set based on the geographical location of each of the multiple candidate areas and their correlation with the target merchant; The delivery range determination module is used to stitch together the various target areas included in the target area set to obtain the delivery range of the target merchant.

6. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the delivery range determination method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the delivery range determination method as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program or computer instructions, characterized in that, When the computer program or computer instructions are executed by the processor, the delivery range determination method as described in any one of claims 1 to 4 is implemented.

Images