Method, device and equipment for determining delivery range and storage medium

Abstract

The application discloses a delivery range determination method and device, equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: obtaining the historical delivery track of a delivery personnel in a historical period in a set of delivery personnel; determining the number of target delivery personnel corresponding to a candidate delivery area of a merchant account, the historical delivery track of the target delivery personnel passing through the candidate delivery area and a region where a merchant corresponding to the merchant account is located at the same time; screening the candidate delivery area according to the number of the target delivery personnel to obtain a target area; and determining the delivery range of the merchant account according to the target area. The historical delivery track of the target delivery personnel passes through the region where the merchant is located and the candidate delivery area, that is, the target delivery personnel has the intention to deliver in the region where the merchant is located and the candidate delivery area. The candidate delivery area is screened according to the target delivery personnel, so that the situation that the willingness of a rider to accept an order is low can be avoided, and therefore the order acceptance rate can be improved, and the delivery efficiency can be improved.

Description

Technical Field

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

[0002] A merchant's delivery area is the set of geographical locations where the merchant provides services to users; specifically, it can be a polygonal geographical area. Users within a merchant's delivery area can select and place orders for the merchant's products through the food delivery app. Users outside a merchant's delivery area will not see the merchant displayed on the food delivery app when placing an order.

[0003] An Area of ​​Interest (AOI) is a bounded, real-world geographical area, such as a residential area, office building complex, or hospital. Based on the historical order volume of AOIs near a merchant within the desired delivery range, and the straight-line distance between the AOI and the merchant, the server scores and ranks the AOIs according to their scores. Then, the server selects a subset of the ranked AOIs based on constraints (such as delivery range area limits and delivery time limits) and determines the merchant's delivery range accordingly.

[0004] Using the delivery range determined in the above way may result in riders having a lower willingness to accept orders from merchants. For example, if the determined delivery range of a merchant crosses a river, orders generated on one side of the river may need to be delivered to the other side, resulting in an excessively long delivery route. This can lead to riders having a lower willingness to accept orders, which in turn can cause a decrease in the order acceptance rate and affect delivery efficiency. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and storage medium for determining delivery range, which can avoid situations where riders have a low willingness to accept orders, thereby increasing the order acceptance rate and improving delivery efficiency. The technical solution is as follows:

[0006] According to one aspect of this application, a method for determining a delivery range is provided, the method comprising:

[0007] Obtain the historical delivery trajectories of delivery personnel within a historical time period from the delivery personnel set;

[0008] Determine the number of target delivery personnel corresponding to the candidate delivery areas of the merchant account. The target delivery personnel are those whose historical delivery trajectories pass through both the candidate delivery areas and the area where the merchant account is located.

[0009] Based on the number of target delivery personnel, the candidate delivery areas are filtered to obtain the target areas;

[0010] The delivery range of the merchant account is determined based on the target area.

[0011] According to another aspect of this application, a delivery range determination device is provided, the device comprising:

[0012] The acquisition module is used to acquire the historical delivery trajectories of delivery personnel in the delivery personnel set within a historical time period;

[0013] The determination module is used to determine the number of target delivery personnel corresponding to the candidate delivery areas of a merchant account. The target delivery personnel are those whose historical delivery trajectories pass through both the candidate delivery areas and the area where the merchant account is located.

[0014] The filtering module is used to filter the candidate delivery areas to obtain the target area based on the number of target delivery personnel;

[0015] The determining module is also used to determine the delivery range of the merchant account based on the target area.

[0016] In an optional design, the determining module is used for:

[0017] The delivery area located within the target range centered on the merchant's location corresponding to the merchant account is determined as the candidate delivery area, where the merchant's location is the location of the merchant account within that merchant's area.

[0018] The first delivery person whose historical delivery trajectory passes through the area where the merchant is located is identified as the first set of delivery persons; and the second delivery person whose historical delivery trajectory passes through the candidate delivery area is identified as the second set of delivery persons in the candidate delivery area;

[0019] Determine the similarity between the first set of delivery personnel and the second set of delivery personnel for the candidate delivery area, wherein the similarity is positively correlated with the number of target delivery personnel corresponding to the candidate delivery area;

[0020] The filtering module is used for:

[0021] In response to a similarity score higher than a similarity threshold corresponding to the candidate delivery area, the candidate delivery area is determined as the target area.

[0022] In an optional design, the determining module is used for:

[0023] A first deliveryman vocabulary is determined based on the first deliveryman, and the first deliveryman vocabulary consists of the identifier of the first deliveryman;

[0024] A second deliveryman vocabulary for the candidate delivery area is determined based on the second deliveryman corresponding to the candidate delivery area. The second deliveryman vocabulary consists of the identifier of the second deliveryman.

[0025] Determine the similarity between the first deliveryman vocabulary and the second deliveryman vocabulary of the candidate delivery areas.

[0026] In an optional design, the device further includes:

[0027] The sorting module is used to sort the target area according to the correlation between the characteristics of the target area and the characteristics of the merchant account;

[0028] The determining module is used for:

[0029] The delivery range of the merchant account is determined based on the sorting results of the target region.

[0030] In an optional design, the sorting module is used for:

[0031] The features of the target area and the features of the merchant account are input into the first machine learning model to obtain a score for the target area.

[0032] The target regions are sorted according to their scores.

[0033] The score of the target region is used to reflect the correlation between the features of the target region and the features of the merchant account. The first machine learning model is trained by the features of the sample region, the features of the sample merchant account, and the label of the sample region. The label of the sample region is used to reflect whether the sample region is related to the sample merchant account.

[0034] In an optional design, the features of the sample region include a region range, which includes an original range and a modified range, wherein the modified range is a range obtained by modifying the original range;

[0035] The first machine learning model includes a linear model and a deep neural network, and the original range and the modified range form a feature pair during the training of the first machine learning model.

[0036] In an optional design, the determining module is used for:

[0037] Based on the sorting results of the target areas, the delivery range is generated according to the area limit;

[0038] The area limit is used to restrict the total area of ​​the delivery range generated by the selected target area to be less than the area threshold. The selected target area is obtained by filtering based on the sorting results of the target area.

[0039] In an optional design, the determining module is used for:

[0040] Based on the target area, determine multiple candidate delivery ranges for the merchant account;

[0041] Determine the estimated order volume for each of the plurality of candidate delivery ranges, the estimated order volume being used to predict the number of orders generated within the candidate delivery range;

[0042] Based on the candidate delivery ranges and estimated order volumes of each merchant account within the undetermined range, the delivery range of each merchant account is determined according to constraints.

[0043] The constraints include the following conditions:

[0044] The sum of the total order prices within the delivery range of each merchant account, determined based on the estimated order volume, is the maximum.

[0045] The sum of the delivery range areas of each merchant account is not greater than the product of the sum of the historical delivery range areas of each merchant account and the first parameter.

[0046] The delivery range of each merchant account is greater than or equal to a first historical area and less than or equal to a second historical area. The first historical area is the product of the historical delivery range of each merchant account and a second parameter. The second historical area is the product of the historical delivery range of each merchant account and a third parameter. The second parameter is not greater than the third parameter.

[0047] In an optional design, the determining module is used for:

[0048] The features of each delivery area within the candidate delivery range are input into the second machine learning model to obtain the estimated order volume for each delivery area.

[0049] The sum of the estimated order volumes for each of the delivery areas is determined as the estimated order volume for the candidate delivery range.

[0050] The second machine learning model is trained using features of the sample delivery range and labels of the sample delivery range, where the labels reflect the number of orders within the sample delivery range.

[0051] According to another aspect of this application, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or instruction set being loaded and executed by the processor to implement the method for determining the delivery range as described above.

[0052] According to another aspect of this application, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, code set, or instruction set is stored therein, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the method for determining the delivery range as described above.

[0053] According to another aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the distribution range determination method provided in various alternative implementations of the above aspects.

[0054] The beneficial effects of the technical solution provided in this application include at least the following:

[0055] By filtering candidate delivery areas for merchant accounts based on delivery riders' historical delivery routes, the system essentially selects candidate delivery areas based on rider behavior. Rider behavior reflects their willingness to deliver within the merchant's location and candidate delivery areas, indicating their intention to deliver within those areas. Filtering candidate delivery areas based on this rider behavior helps avoid situations where riders have low order acceptance rates, thereby increasing order acceptance rates and improving delivery efficiency. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0057] Figure 1 This is a schematic diagram illustrating the process of determining a merchant's delivery range as provided in an exemplary embodiment of this application;

[0058] Figure 2This is a flowchart illustrating a method for determining the delivery range provided in an exemplary embodiment of this application;

[0059] Figure 3 This is a schematic diagram of the target area provided in an exemplary embodiment of this application;

[0060] Figure 4 This is a flowchart illustrating a method for determining the delivery range provided in an exemplary embodiment of this application;

[0061] Figure 5 This is a schematic diagram illustrating a candidate delivery range provided in an exemplary embodiment of this application;

[0062] Figure 6 This is a schematic diagram of the structure of a delivery range determination device provided in an exemplary embodiment of this application;

[0063] Figure 7 This is a schematic diagram of the structure of a delivery range determination device provided in an exemplary embodiment of this application;

[0064] Figure 8 This is a schematic diagram of the structure of a computer device provided in an exemplary embodiment of this application.

[0065] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. Detailed Implementation

[0066] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0067] Figure 1 This is a schematic diagram illustrating the process of determining a merchant's delivery area according to an exemplary embodiment of this application. Figure 1 As shown, in step S1, the computer device acquires the historical delivery trajectories of delivery personnel in the delivery personnel set within a historical time period, and determines the candidate delivery area for the merchant account based on the distance between the delivery area and the location of the merchant corresponding to the merchant account. This candidate delivery area is a Point of Interest (POI). Then, based on the first delivery personnel whose historical delivery trajectories pass through the merchant area corresponding to the merchant account, a first delivery personnel set is determined; and based on the second delivery personnel whose historical delivery trajectories pass through the candidate delivery area, a second delivery personnel set for the candidate delivery area is determined. When the similarity between a second delivery personnel set and the first delivery personnel set is higher than a similarity threshold, the computer device determines the candidate delivery area corresponding to that second delivery personnel set as the target area.

[0068] In step S2, the computer device determines the score of the target area based on the correlation between the characteristics of the target area and the characteristics of the merchant account, and sorts the target areas according to the scores.

[0069] In step S3, the computer device generates multiple candidate delivery ranges for the merchant account based on the sorting results of the target areas and according to different area limits. The area limit is used to restrict the area of ​​the candidate delivery ranges generated from the selected target areas from being smaller than the area threshold corresponding to the area limit. The selected target areas are obtained based on the sorting results of the target areas.

[0070] In step S4, the computer device determines the estimated order volume for each of the multiple candidate delivery ranges for the merchant account. The estimated order volume is used to predict the number of orders generated within the candidate delivery range. In this process, the computer device first evaluates the estimated order volume for each delivery area within the candidate delivery range, and then determines the estimated order volume for the candidate delivery range based on the sum of the estimated order volumes for each delivery area.

[0071] In step S5, the computer device determines the candidate delivery range and estimated order volume for each merchant account within the range to be determined using the aforementioned method. Then, based on the determined information, the computer device determines the delivery range for each merchant account according to constraints. These constraints ensure that the delivery range of each merchant account within the range to be determined is greater than its historical delivery range, and that the total predicted order price is highest within the range to be determined based on the estimated order volume corresponding to each merchant account's delivery range.

[0072] The process involves filtering candidate delivery areas for merchant accounts based on delivery riders' historical delivery routes. This means selecting candidate delivery areas for merchant accounts based on rider behavior. Rider behavior reflects their intentions; if a rider's historical delivery route passes through both the merchant's location and candidate delivery areas, it indicates their willingness to deliver within those areas. Filtering candidate delivery areas based on this rider behavior avoids situations where riders have low order acceptance rates, thus increasing order acceptance rates and improving delivery efficiency. The process also involves sorting target areas to generate multiple candidate delivery ranges for merchant accounts. Then, the estimated order volume for each candidate delivery range is evaluated. Based on the candidate delivery ranges and estimated order volume for each merchant account within the target range, the optimal delivery area for each merchant account is jointly determined, maximizing both the delivery range and the order value. This approach maximizes delivery area while considering revenue, contributing to improved delivery efficiency.

[0073] Figure 2 This is a flowchart illustrating a method for determining a delivery range according to an exemplary embodiment of this application. This method can be used with a computer device. Figure 2As shown, the method includes:

[0074] Step 202: Obtain the historical delivery trajectories of the delivery personnel in the delivery personnel set within the historical time period.

[0075] The delivery personnel set is determined by computer equipment. Optionally, the computer equipment determines the location of the merchant corresponding to the merchant account within the delivery range as needed, and then determines the delivery personnel set accordingly. For example, based on the city where the merchant's location is located, the delivery personnel of that city are determined as the delivery personnel set. Based on the administrative region where the merchant's location is located, the delivery personnel of that administrative region are determined as the delivery personnel set.

[0076] Optionally, the delivery person refers to a food delivery rider. The historical time period includes the past n days, where n is a positive integer and can be set by computer equipment. The historical delivery trajectory is the movement trajectory of the delivery person during delivery tasks.

[0077] Step 204: Determine the number of target delivery personnel corresponding to the candidate delivery areas of the merchant account.

[0078] This merchant account refers to any merchant account on the computer device whose delivery area needs to be defined. This includes newly added merchant accounts whose delivery areas have not yet been defined, as well as merchant accounts whose delivery areas have been defined but need to be updated.

[0079] Optionally, the computer device determines the candidate delivery area based on the distance between the merchant's location corresponding to the merchant account and the delivery area. This delivery area is an Area of ​​Interest (AOI), which is a bounded, real-world geographical area, such as a residential area, office building complex, or hospital.

[0080] The target delivery riders are those whose historical delivery routes both pass through the candidate delivery areas and the region corresponding to the merchant account. Based on the riders' historical delivery routes, computer equipment can determine the number of target delivery riders corresponding to the candidate delivery areas.

[0081] Step 206: Based on the number of target delivery personnel, filter the candidate delivery areas to obtain the target area.

[0082] Optionally, the more target delivery personnel a candidate delivery area corresponds to, the higher the likelihood that the computer device will identify it as a target area. Conversely, the fewer target delivery personnel a candidate delivery area corresponds to, the lower the likelihood that the computer device will identify it as a target area. For example, when the number of target delivery personnel corresponding to a candidate delivery area reaches a certain threshold, the computer device will identify that candidate delivery area as the target area. This threshold is set by the computer device.

[0083] For example, Figure 3This is a schematic diagram of the target area provided in an exemplary embodiment of this application. For example... Figure 3 As shown, the candidate delivery areas determined by the computer device based on the merchant's location 301 of the merchant account include the delivery areas in the first area 302. Figure 3 The system identifies the candidate delivery areas in three regions: the first region 302 (closed shape), the second region 303 (delivery area), and the third region 304 (delivery area). The computer then determines the number of target delivery personnel corresponding to each candidate delivery area for the merchant account, thus filtering the candidate delivery areas to obtain the target areas. The number of target delivery personnel corresponding to the candidate delivery areas in the first region 302 is generally higher than that in the second region 303 (black candidate delivery areas represent areas with fewer target delivery personnel). The number of target delivery personnel corresponding to the candidate delivery areas in the second region 303 is generally higher than that in the third region 304. When filtering target areas, the computer will identify the candidate delivery areas in the first region 302 as the target areas. The first region 302 and the merchant's location 301 are on the same side of the river, while the second region 303 and the third region 304 are on opposite sides of the river. Identifying the candidate delivery areas in the first region 302 as the target areas avoids excessively long delivery routes due to cross-river deliveries, which could lead to lower rider willingness to accept orders, thereby improving delivery efficiency.

[0084] Step 208: Determine the delivery range of the merchant account based on the target area.

[0085] Optionally, the delivery range consists of all target areas corresponding to the merchant account. The computer equipment, through outsourcing, can determine the delivery range of the merchant account based on the target areas. This outsourcing method ensures that the determined delivery range of the merchant account covers all target areas, and the boundaries of the delivery range are tangent to the boundaries of the target areas within the delivery range.

[0086] Optionally, the computer device can also use a subset of target areas to determine the delivery range of a merchant account. For example, target areas can be sorted according to their relevance to the characteristics of the merchant account. Based on limiting rules, a subset of target areas can be selected from the sorted results to generate the delivery range for the merchant account. For instance, a delivery range can be generated based on an area limit, where the total area of ​​the delivery range generated from the selected target areas is less than an area threshold determined by the computer device.

[0087] In summary, the method provided in this embodiment filters candidate delivery areas for merchant accounts based on the delivery rider's historical delivery trajectory, that is, it filters candidate delivery areas for merchant accounts based on the delivery rider's behavior. The delivery rider's behavior reflects their intentions; if the delivery rider's historical delivery trajectory passes through both the merchant's location and candidate delivery areas, it means the delivery rider is willing to deliver within both the merchant's location and the candidate delivery areas. Filtering candidate delivery areas based on this delivery rider behavior can avoid situations where riders have a low willingness to accept orders, thereby increasing the order acceptance rate and improving delivery efficiency.

[0088] Figure 4 This is a flowchart illustrating a method for determining a delivery range according to an exemplary embodiment of this application. This method can be used with a computer device. Figure 4 As shown, the method includes:

[0089] Step 402: Obtain the historical delivery trajectories of delivery personnel in the delivery personnel set within the historical time period.

[0090] The set of delivery personnel is determined by computer equipment. Optionally, the computer equipment determines the location of the merchant corresponding to the merchant account within the delivery range as needed, and then determines the set of delivery personnel. "Delivery personnel" refers to the riders who deliver food. The historical time period includes the past n days, where n is a positive integer, and the specific duration can be set by the computer equipment. The historical delivery trajectory is the movement trajectory of the delivery personnel during their delivery tasks.

[0091] Step 404: Determine the number of target delivery personnel corresponding to the candidate delivery areas of the merchant account.

[0092] The merchant account is any merchant account on the computer device whose delivery range needs to be determined. The candidate delivery area is the Area of ​​Interest (AOI). The target delivery person is a delivery person whose historical delivery trajectory has passed through both the candidate delivery area and the area where the merchant account is located. The merchant's area is the AOI where the merchant account is located; the merchant's area may be the same as one of the candidate delivery areas corresponding to the merchant account.

[0093] Optionally, the computer device determines the delivery area within the target range centered on the location of the merchant corresponding to the merchant account as the candidate delivery area, and determines the first delivery person whose historical delivery trajectory passes through the merchant's location as the first delivery person set, and the second delivery person whose historical delivery trajectory passes through the candidate delivery area as the second delivery person set of the candidate delivery area, and then determines the similarity between the first delivery person set and the second delivery person set of the candidate delivery area.

[0094] Here, the merchant's location refers to the position of the merchant account within the merchant's designated area. The size of the target area is determined by the computer equipment; for example, if the target area is circular, the radius of the circle is controlled by the computer equipment. Based on historical delivery trajectories, the computer equipment can determine the first set of delivery personnel and the second set of delivery personnel. Each candidate delivery area corresponding to the merchant account corresponds to a second set of delivery personnel. The similarity between candidate delivery areas is positively correlated with the number of target delivery personnel corresponding to each candidate delivery area.

[0095] In determining the first set of delivery personnel and the second set of delivery personnel to calculate similarity, the computer device can determine a first delivery personnel vocabulary based on the first delivery personnel and a second delivery personnel vocabulary for the candidate delivery areas based on the second delivery personnel corresponding to the candidate delivery areas. The first delivery personnel vocabulary consists of the identifiers of the first delivery personnel, and the second delivery personnel vocabulary consists of the identifiers of the second delivery personnel. This identifier includes the delivery personnel's number in the computer device, their Identity Document (ID), their mobile phone number, and their user account, etc. The computer device then determines the similarity between the first delivery personnel vocabulary and the second delivery personnel vocabulary for the candidate delivery areas as the aforementioned similarity score. Optionally, the computer device can calculate the cosine similarity between the first and second delivery personnel vocabulary.

[0096] Step 406: Based on the number of target delivery personnel, filter the candidate delivery areas to obtain the target area.

[0097] The more target delivery personnel a candidate delivery area has, the higher the likelihood that the computer will designate it as the target area. Conversely, the fewer target delivery personnel a candidate delivery area has, the lower the likelihood that the computer will designate it as the target area. For example, when the number of target delivery personnel for a candidate delivery area reaches a certain threshold, the computer will designate that candidate delivery area as the target area. This threshold is set by the computer.

[0098] Optionally, after calculating the similarity between the first delivery personnel set and the second delivery personnel set in step 404, in response to a similarity score higher than a similarity threshold corresponding to a candidate delivery area, the computer device will identify the candidate delivery area as the target area. This similarity threshold is set by the computer device.

[0099] Step 408: Sort the target regions according to the correlation between the characteristics of the target regions and the characteristics of the merchant accounts.

[0100] The computer device inputs the features of the target area and the features of the merchant account into the first machine learning model, which can obtain a score for the target area, and then sort the target areas according to the score.

[0101] The characteristics of the target area include the distance between the target area and the merchant's location, the number of orders in the target area during historical periods, the distribution density of locations where orders were generated in the target area, whether the target area and the merchant's location cross a natural barrier, the number of orders for various types of goods in the target area, and the category of the target area (e.g., residential area, office building, school, etc.). The characteristics of the merchant account include the total number of orders for the merchant account, the merchant type of the merchant account (food merchant, dessert merchant, pharmaceutical merchant, etc.), whether the merchant account is a chain store, and whether the merchant account is a certified quality merchant.

[0102] The target region score reflects the correlation between the target region's features and the merchant account's features. The first machine learning model is trained using the features of the sample region, the features of the sample merchant account, and the label of the sample region. The label of the sample region reflects the correlation between the sample region and the sample merchant account. The sample region and the sample merchant account are determined by computer equipment, while the label of the sample region can be manually annotated.

[0103] Optionally, the features of the sample region include the region range, which includes the original range and the modified range. The modified range is the range obtained by modifying the original range, for example, by manual modification. The first machine learning model is a shallow deep model (wide-deep model). During the training of the first machine learning model, the original range and the modified range form feature pairs. The shallow deep model includes linear models and deep neural networks. Shallow can refer to a single layer. The wide-deep model has good learning and generalization capabilities for statistical and discrete features. Through the embedding layer in the wide-deep model, it has strong expressive power for category and ID features. Therefore, the wide-deep model can accurately evaluate the correlation between the features of the target region and the features of the merchant account, that is, the correlation between the target region and the merchant account.

[0104] Step 410: Determine multiple candidate delivery ranges for the merchant account based on the sorting results of the target region.

[0105] Computer equipment can filter different combinations of target areas based on the ranking results of the target areas, thereby determining multiple candidate delivery ranges for a merchant account. Then, the delivery range for the merchant account is determined based on these multiple candidate delivery ranges. The candidate delivery ranges are called Areas of Interest (AOIs).

[0106] Optionally, the computer device can directly generate the delivery range for a merchant account based on the sorting results of the target areas and according to area restrictions. When multiple area restrictions exist, the computer device can generate multiple candidate delivery ranges for the merchant account according to these restrictions. The area restriction is used to limit the total area of ​​the delivery ranges generated from the filtered target areas to less than an area threshold. The filtered target areas are obtained based on the sorting results of the target areas, and this area restriction is set by the computer device.

[0107] For example, the target areas are sorted as Area 1, Area 2, Area 3, Area 4, and Area 5. If the area of ​​the delivery range determined by Area 1, Area 2, and Area 3 is less than the area threshold, and the area of ​​the delivery range determined by Area 1, Area 2, Area 3, and Area 4 is greater than the area threshold, then the computer device will determine the delivery range of the merchant account based on Area 1, Area 2, and Area 3.

[0108] For example, Figure 5 This is a schematic diagram illustrating a candidate delivery range provided in an exemplary embodiment of this application. For example... Figure 5 As shown, after determining the target area, the computer equipment uses a 12km radius... 2 The candidate delivery range determined by the area limitation is range 501, based on 18km. 2 The candidate delivery range determined by the area limitation is range two 502, where the area of ​​range two 502 is larger than that of range one 501, and range one 501 is located within the range covered by range two 502.

[0109] Alternatively, the computer device can also directly determine the delivery range of a merchant account based on the sorting results of the target regions. For example, selecting the first m target regions can generate a delivery range for the merchant account.

[0110] In determining the delivery range of a merchant account, computer equipment can use an outsourcing method to ensure that the delivery range of the merchant account covers the entire target area, and that the boundary of the delivery range is tangent to the boundary of the target area within the delivery range.

[0111] Step 412: Determine the delivery range of each merchant account based on the candidate delivery ranges of each merchant account within the range to be determined.

[0112] When determining the delivery range of each merchant account within the scope to be determined, the computer equipment will determine the estimated order volume of each candidate delivery range among multiple candidate delivery ranges for each merchant account, and determine the delivery range of each merchant account based on the candidate delivery ranges and estimated order volumes of each merchant account within the scope to be determined, based on the constraints.

[0113] Optionally, the area to be determined is determined by computer equipment, such as a city, a specific administrative district within a city, or a manually defined area. The merchant accounts within the area to be determined are those whose locations are situated within that area. Multiple candidate delivery areas for a merchant account are determined based on the multiple area restrictions outlined in step 410 above. The estimated order volume is used to predict the number of orders generated within the candidate delivery areas.

[0114] The computer equipment inputs the features of each delivery area within the candidate delivery range into a second machine learning model, which can obtain the estimated order volume for each delivery area. The sum of the estimated order volumes for each delivery area is then used to determine the estimated order volume for the candidate delivery range. The second machine learning model is trained using the features and labels of the sample delivery ranges, with the labels reflecting the order quantity within each range. This second machine learning model can be an Extreme Gradient Boosting (XGBoost) model.

[0115] Optionally, the above constraints include the following conditions:

[0116] The maximum sum of the total order value within the delivery range of each merchant account, determined based on the estimated order volume;

[0117] The sum of the delivery range areas of each merchant account shall not exceed the product of the sum of the historical delivery range areas of each merchant account and the first parameter;

[0118] The delivery range of each merchant account is greater than or equal to the first historical area and less than or equal to the second historical area. The first historical area is the product of the historical delivery range of each merchant account and the second parameter. The second historical area is the product of the historical delivery range of each merchant account and the third parameter. The second parameter is not greater than the third parameter.

[0119] The total order price is determined based on the estimated order volume and the average order price. The average order price is the average price of orders within a specified historical period determined by the computer equipment. The merchant account's historical delivery range is the delivery range previously determined by the computer equipment. The first, second, and third parameters are set by the computer equipment.

[0120] For example, the expressions for the above three constraints are as follows:

[0121] Solution objective:

[0122] Solution constraints:

[0123] Solution constraints:

[0124] Wherein, Order in equation (1) p，a This represents the estimated order volume for merchant account p within the candidate delivery range a, Price. p C represents the average order value (or price). p，a The variable is a pair with values ​​of 0 and 1. If candidate delivery range a is selected, the value is 1; otherwise, it is 0. The Area in equation (2) p AreaHis indicates the delivery range of merchant account p. p This represents the historical delivery range of merchant account p, with k0 being the first parameter. k in equation (3) min k is the second parameter. max This is the third parameter.

[0125] Computer equipment can solve the above problem using the branch and bound algorithm. The branch and bound algorithm is a commonly used algorithm for solving planning problems. It is a search and iterative method that selects different branch variables (combinations of candidate delivery ranges from different merchant accounts) and subproblems (the aforementioned constraints) to branch. After each branch, for subsets whose boundaries exceed the known feasible solution values, the computer equipment stops further branching. Thus, many subsets of the determined solutions are disregarded, thereby narrowing the search range. The computer equipment executes this process until a feasible solution is found, whose value is no greater than the boundary of any subset. Therefore, the branch and bound algorithm can find the optimal solution.

[0126] In summary, the method provided in this embodiment filters candidate delivery areas for merchant accounts based on the delivery rider's historical delivery trajectory, that is, it filters candidate delivery areas for merchant accounts based on the delivery rider's behavior. The delivery rider's behavior reflects their intentions; if the delivery rider's historical delivery trajectory passes through both the merchant's location and candidate delivery areas, it means the delivery rider is willing to deliver within both the merchant's location and the candidate delivery areas. Filtering candidate delivery areas based on this type of delivery rider behavior can avoid situations where riders have a low willingness to accept orders, thereby increasing the order acceptance rate and improving delivery efficiency.

[0127] Furthermore, using the similarity between the first and second delivery person sets to reflect the number of target delivery persons corresponding to candidate delivery areas, and constructing first and second delivery person vocabularies to calculate similarity, reduces statistical complexity and improves calculation speed. Target areas are sorted to generate multiple candidate delivery ranges for merchant accounts. Then, the estimated order volume of each candidate delivery range is evaluated. Based on the candidate delivery ranges and estimated order volumes of each merchant account within the undetermined range, the optimal delivery area for each merchant account with the widest delivery range and the highest order price is jointly determined. This maximizes the delivery area while considering revenue, contributing to improved delivery efficiency.

[0128] It should be noted that the order of the method steps provided in the embodiments of this application can be appropriately adjusted, and the steps can also be added or removed as appropriate. Any method variations that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application, and therefore will not be elaborated further.

[0129] In a specific example, when it's necessary to evaluate or update the delivery range of a merchant account within a specific administrative district of a city, the computer equipment retrieves the historical delivery routes of delivery personnel registered within that district and identifies candidate Points of Interest (POIs) for merchant accounts within that district. Based on the historical delivery routes, a second delivery personnel vocabulary for each candidate POI and a first delivery personnel vocabulary for each merchant account are determined. Based on the similarity between the first and second delivery personnel vocabulary lists, the computer equipment identifies the target POIs for each merchant account. Then, based on the relevance between the target POIs and the merchant account, the target POIs are ranked, and based on different area constraints and the ranking results, candidate Areas of Interest (AOIs) are generated for each merchant account. Based on the estimated order volume of each POI in the evaluated candidate AOIs, the computer equipment determines the estimated order volume for each candidate AOI for each merchant account. The computer then aggregates the candidate AOIs and the estimated order volume corresponding to each candidate AOI for merchant accounts within the administrative region. Based on the constraint that the delivery range of each merchant account is greater than its historical delivery range and the estimated order volume corresponding to the delivery range of each merchant account determines the highest total price of the predicted orders within the administrative region, the delivery range of each merchant account is solved.

[0130] Figure 6 This is a schematic diagram of a delivery range determination device provided in an exemplary embodiment of this application. The device can be used with computer equipment. Figure 6 As shown, the device includes:

[0131] The acquisition module 601 is used to acquire the historical delivery trajectories of delivery personnel in the delivery personnel set within a historical time period.

[0132] The determination module 602 is used to determine the number of target delivery personnel corresponding to the candidate delivery areas of the merchant account. The target delivery personnel are delivery personnel whose historical delivery trajectories have passed through both the candidate delivery areas and the merchant area corresponding to the merchant account.

[0133] The filtering module 603 is used to filter candidate delivery areas to obtain the target area based on the number of target delivery personnel.

[0134] The determination module 602 is also used to determine the delivery range of a merchant account based on the target area.

[0135] In an optional design, module 602 is defined for:

[0136] The delivery area centered on the merchant's location corresponding to the merchant account is defined as the candidate delivery area. The merchant's location is the location of the merchant account within that area. The first delivery person whose historical delivery route passes through the merchant's location is defined as the first set of delivery persons. The second delivery person whose historical delivery route passes through the candidate delivery area is defined as the second set of delivery persons in the candidate delivery area. The similarity between the first set of delivery persons and the second set of delivery persons in the candidate delivery areas is determined, and the similarity is positively correlated with the number of target delivery persons corresponding to the candidate delivery area.

[0137] Filtering module 603 is used for:

[0138] If the similarity of the candidate delivery area is higher than the similarity threshold, the candidate delivery area is identified as the target area.

[0139] In an optional design, module 602 is defined for:

[0140] A first delivery person vocabulary is determined based on the first delivery person, and this vocabulary consists of the first delivery person's identifier. A second delivery person vocabulary is determined based on the second delivery person corresponding to the candidate delivery area, and this vocabulary consists of the second delivery person's identifier. The similarity between the first delivery person vocabulary and the second delivery person vocabulary of the candidate delivery areas is then determined.

[0141] In an optional design, such as Figure 7 As shown, the device also includes:

[0142] The sorting module 604 is used to sort the target area based on the correlation between the characteristics of the target area and the characteristics of the merchant account.

[0143] Determine module 602, used for:

[0144] The delivery range of a merchant account is determined based on the sorting results of the target region.

[0145] In an optional design, sorting module 604 is used for:

[0146] The features of the target region and the features of the merchant account are input into the first machine learning model to obtain a score for the target region. The target regions are then sorted according to their scores.

[0147] The target region score reflects the correlation between the target region's features and the merchant account's features. The first machine learning model is trained using the features of the sample region, the features of the sample merchant account, and the label of the sample region. The label of the sample region reflects whether the sample region and the sample merchant account are related.

[0148] In an optional design, the features of the sample region include the region extent, which comprises the original extent and the modified extent, where the modified extent is the extent obtained by modifying the original extent. The first machine learning model includes linear models and deep neural networks, and during the training of the first machine learning model, the original extent and the modified extent form feature pairs.

[0149] In an optional design, module 602 is defined for:

[0150] Based on the sorting results of the target regions, delivery ranges are generated according to area restrictions. The area restriction limits the total area of ​​the generated delivery ranges from the selected target regions to a threshold value. The selected target regions are determined based on the sorting results of the target regions.

[0151] In an optional design, module 602 is defined for:

[0152] Multiple candidate delivery ranges are determined for each merchant account based on the target region. The estimated order volume for each candidate delivery range is then determined; this estimated volume is used to predict the number of orders generated within that candidate delivery range. Based on the candidate delivery ranges and estimated order volumes for each merchant account within the target region, the delivery range for each merchant account is determined according to constraints.

[0153] The constraints include the following conditions:

[0154] The maximum sum of the total order value within the delivery range of each merchant account, determined based on the estimated order volume;

[0155] The sum of the delivery range areas of each merchant account shall not exceed the product of the sum of the historical delivery range areas of each merchant account and the first parameter;

[0156] The delivery range of each merchant account is greater than or equal to the first historical area and less than or equal to the second historical area. The first historical area is the product of the historical delivery range of each merchant account and the second parameter. The second historical area is the product of the historical delivery range of each merchant account and the third parameter. The second parameter is not greater than the third parameter.

[0157] In an optional design, module 602 is defined for:

[0158] The features of each delivery area within the candidate delivery range are input into the second machine learning model to obtain the estimated order volume for each delivery area. The sum of the estimated order volumes for each delivery area is determined as the estimated order volume for the candidate delivery range. The second machine learning model is trained using the features and labels of the sample delivery ranges, with the labels reflecting the number of orders within each sample delivery range.

[0159] It should be noted that the delivery range determination device provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the delivery range determination device and the delivery range determination method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0160] Embodiments of this application also provide a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the method for determining the delivery range provided in the above-described method embodiments.

[0161] Alternatively, the computer device is a server. For example, Figure 8 This is a schematic diagram of the structure of a computer device provided in an exemplary embodiment of this application.

[0162] The computer device 800 includes a central processing unit (CPU) 801, a system memory 804 including random access memory (RAM) 802 and read-only memory (ROM) 803, and a system bus 805 connecting the system memory 804 and the CPU 801. The computer device 800 also includes a basic input / output system (I / O system) 806 to facilitate information transfer between various components within the computer device, and a mass storage device 807 for storing the operating system 813, application programs 814, and other program modules 815.

[0163] The basic input / output system 806 includes a display 808 for displaying information and an input device 809 for user input, such as a mouse or keyboard. Both the display 808 and the input device 809 are connected to the central processing unit 801 via an input / output controller 810 connected to the system bus 805. The basic input / output system 806 may also include the input / output controller 810 for receiving and processing input from multiple other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 810 also provides output to a display screen, printer, or other types of output devices.

[0164] The mass storage device 807 is connected to the central processing unit 801 via a mass storage controller (not shown) connected to the system bus 805. The mass storage device 807 and its associated computer-readable storage media provide non-volatile storage for the computer device 800. That is, the mass storage device 807 may include computer-readable storage media (not shown), such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0165] Without loss of generality, the computer-readable storage medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable storage instructions, data structures, program modules, or other data. Computer storage media include RAM, ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other solid-state storage devices, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic tape cassettes, magnetic tape, disk storage, or other magnetic storage devices. Of course, those skilled in the art will recognize that the computer storage medium is not limited to the above-mentioned types. The system memory 804 and mass storage device 807 described above can be collectively referred to as memory.

[0166] The memory stores one or more programs, which are configured to be executed by one or more central processing units 801. The one or more programs contain instructions for implementing the above method embodiments, and the central processing unit 801 executes the one or more programs to implement the methods provided by the above method embodiments.

[0167] According to various embodiments of this application, the computer device 800 can also be connected to a remote computer device on a network, such as the Internet. That is, the computer device 800 can be connected to a network 812 via a network interface unit 811 connected to the system bus 805, or the network interface unit 811 can be used to connect to other types of networks or remote computer device systems (not shown).

[0168] The memory further includes one or more programs stored in the memory, and the one or more programs include steps performed by a computer device in the methods provided in the embodiments of this application.

[0169] This application also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set. When the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor of a computer device, the method for determining the delivery range provided in the above-described method embodiments is implemented.

[0170] This application also provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the distribution range determination method provided in the above-described method embodiments.

[0171] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0172] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent switching, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining a delivery range, characterized in that, The method includes: Obtain the historical delivery trajectories of delivery personnel within a historical time period from the delivery personnel set; Determine the number of target delivery personnel corresponding to the candidate delivery areas of the merchant account. The target delivery personnel are those whose historical delivery trajectories pass through both the candidate delivery areas and the area where the merchant account is located. Based on the number of target delivery personnel, the candidate delivery areas are filtered to obtain the target areas; Determining the delivery range of the merchant account based on the target area includes: Based on the target area, determine multiple candidate delivery ranges for the merchant account; Determine the estimated order volume for each of the plurality of candidate delivery ranges, the estimated order volume being used to predict the number of orders generated within the candidate delivery range; Based on the candidate delivery ranges and estimated order volumes of each merchant account within the undetermined range, the delivery range of each merchant account is determined according to constraints. The constraints include the following conditions: The sum of the total order prices within the delivery range of each merchant account, determined based on the estimated order volume, is the maximum. The sum of the delivery range areas of each merchant account is not greater than the product of the sum of the historical delivery range areas of each merchant account and the first parameter. The delivery range of each merchant account is greater than or equal to a first historical area and less than or equal to a second historical area. The first historical area is the product of the historical delivery range of each merchant account and a second parameter. The second historical area is the product of the historical delivery range of each merchant account and a third parameter. The second parameter is not greater than the third parameter.

2. The method according to claim 1, characterized in that, The determination of the number of target delivery personnel corresponding to the candidate delivery areas of the merchant account includes: The delivery area within the target range centered on the location of the merchant corresponding to the merchant account is determined as the candidate delivery area, where the merchant location is the location of the merchant account in the merchant location area; The first delivery person whose historical delivery route passes through the area where the merchant is located is identified as the first set of delivery persons. And the second delivery person whose historical delivery trajectory passes through the candidate delivery area is identified as the second set of delivery persons for the candidate delivery area; Determine the similarity between the first set of delivery personnel and the second set of delivery personnel for the candidate delivery area, wherein the similarity is positively correlated with the number of target delivery personnel corresponding to the candidate delivery area; The step of filtering the candidate delivery areas to obtain the target area based on the number of target delivery personnel includes: In response to a similarity score higher than a similarity threshold corresponding to the candidate delivery area, the candidate delivery area is determined as the target area.

3. The method according to claim 2, characterized in that, The step of identifying the first delivery person whose historical delivery trajectory passes through the area where the merchant is located as the first set of delivery persons includes: A first deliveryman vocabulary is determined based on the first deliveryman, and the first deliveryman vocabulary consists of the identifier of the first deliveryman; The step of identifying the second delivery personnel whose historical delivery trajectories pass through the candidate delivery area as the second set of delivery personnel for the candidate delivery area includes: A second deliveryman vocabulary for the candidate delivery area is determined based on the second deliveryman corresponding to the candidate delivery area. The second deliveryman vocabulary consists of the identifier of the second deliveryman. Determining the similarity between the first set of delivery personnel and the second set of delivery personnel for the candidate delivery areas includes: Determine the similarity between the first deliveryman vocabulary and the second deliveryman vocabulary of the candidate delivery areas.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: The target regions are sorted according to the correlation between the characteristics of the target regions and the characteristics of the merchant accounts; Determining the delivery range of the merchant account based on the target area includes: The delivery range of the merchant account is determined based on the sorting results of the target region.

5. The method according to claim 4, characterized in that, The step of sorting the target region based on the correlation between the characteristics of the target region and the characteristics of the merchant account includes: The features of the target area and the features of the merchant account are input into the first machine learning model to obtain a score for the target area. The target regions are sorted according to their scores. The score of the target region is used to reflect the correlation between the features of the target region and the features of the merchant account. The first machine learning model is trained by the features of the sample region, the features of the sample merchant account, and the label of the sample region. The label of the sample region is used to reflect whether the sample region is related to the sample merchant account.

6. The method according to claim 5, characterized in that, The features of the sample region include the region range, which includes the original range and the modified range, and the modified range is the range obtained by modifying the original range; The first machine learning model includes a linear model and a deep neural network, and the original range and the modified range form a feature pair during the training of the first machine learning model.

7. The method according to claim 4, characterized in that, Determining the delivery range of the merchant account based on the sorting results of the target area includes: Based on the sorting results of the target areas, the delivery range is generated according to the area limit; The area limit is used to restrict the total area of ​​the delivery range generated by the selected target area to be less than the area threshold. The selected target area is obtained by filtering based on the sorting results of the target area.

8. The method according to claim 1, characterized in that, Determining the estimated order volume for each of the plurality of candidate delivery ranges includes: The features of each delivery area within the candidate delivery range are input into the second machine learning model to obtain the estimated order volume for each delivery area. The sum of the estimated order volumes for each of the delivery areas is determined as the estimated order volume for the candidate delivery range. The second machine learning model is trained using features of the sample delivery range and labels of the sample delivery range, where the labels reflect the number of orders within the sample delivery range.

9. A device for determining a delivery range, characterized in that, The device includes: The acquisition module is used to acquire the historical delivery trajectories of delivery personnel in the delivery personnel set within a historical time period; The determination module is used to determine the number of target delivery personnel corresponding to the candidate delivery areas of a merchant account. The target delivery personnel are those whose historical delivery trajectories pass through both the candidate delivery areas and the area where the merchant account is located. The filtering module is used to filter the candidate delivery areas to obtain the target area based on the number of target delivery personnel; The determining module is further configured to determine the delivery range of the merchant account based on the target area, including: Based on the target area, determine multiple candidate delivery ranges for the merchant account; Determine the estimated order volume for each of the plurality of candidate delivery ranges, the estimated order volume being used to predict the number of orders generated within the candidate delivery range; Based on the candidate delivery ranges and estimated order volumes of each merchant account within the undetermined range, the delivery range of each merchant account is determined according to constraints. The constraints include the following conditions: The sum of the total order prices within the delivery range of each merchant account, determined based on the estimated order volume, is the maximum. The sum of the delivery range areas of each merchant account is not greater than the product of the sum of the historical delivery range areas of each merchant account and the first parameter. The delivery range of each merchant account is greater than or equal to a first historical area and less than or equal to a second historical area. The first historical area is the product of the historical delivery range of each merchant account and a second parameter. The second historical area is the product of the historical delivery range of each merchant account and a third parameter. The second parameter is not greater than the third parameter.

10. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one instruction, at least one program, a code set, or an instruction set, the at least one instruction, the at least one program, the code set, or the instruction set being loaded and executed by the processor to implement the method for determining the delivery range as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The readable storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the method for determining the delivery range as described in any one of claims 1 to 8.

Images