Logistics productivity evaluation method and device, electronic equipment and storage medium

Abstract

The invention provides a logistics productivity evaluation method and device, electronic equipment and a storage medium. The method is applied to the field of logistics. The method comprises the steps of obtaining an order distribution data set of a target area, wherein the order distribution data set comprises multiple pieces of order distribution data; based on each piece of order distribution data, obtaining target performance duration of a plurality of orders in each piece of order distribution data; screening the plurality of order distribution data based on the plurality of target performance durations to obtain target order distribution data; and obtaining a logistics productivity evaluation result of the target area based on the target order distribution data. According to the method, the accuracy of logistics productivity evaluation can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of logistics, and more particularly, to a logistics capacity evaluation method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the rapid development of the takeout industry, logistics capacity evaluation has become an indispensable part of improving platform efficiency and service quality. Logistics capacity evaluation not only concerns the consumer experience, but also affects the operating costs of the platform.

[0003] However, logistics capacity evaluation is a relatively complex problem, and logistics capacity is affected by many factors such as transport allocation, consumer demand, order difficulty, and objective environment. For example, 100 orders within 3 kilometers and 100 orders within 1 kilometer, if the capacity is generally determined to be 100 orders, the workload of delivering 100 orders within 3 kilometers is significantly greater than that of delivering 100 orders within 1 kilometer. Therefore, how to improve the accuracy of logistics capacity evaluation has become a problem to be solved. SUMMARY

[0004] The present application provides a logistics capacity evaluation method, device, electronic device and storage medium, which can improve the accuracy of logistics capacity evaluation.

[0005] In a first aspect, a logistics capacity evaluation method is provided, the method comprising: obtaining an order distribution data set of a target area, the order distribution data set comprising a plurality of order distribution data; based on each order distribution data, obtaining a target fulfillment time length of a plurality of orders in each order distribution data; based on a plurality of target fulfillment time lengths, filtering a plurality of order distribution data to obtain target order distribution data; based on the target order distribution data, obtaining a logistics capacity evaluation result of the target area.

[0006] The above technical solution, based on each order distribution data in a plurality of order distribution data of a target area, obtains a target fulfillment time length of a plurality of orders in each order distribution data, filters a plurality of order distribution data based on a plurality of target fulfillment time lengths to obtain target order distribution data, and based on the target order distribution data, obtains a logistics capacity evaluation result of the target area; by using order distribution data of the target area to represent the capacity of the target area, the problem of ignoring order space flow and delivery difficulty when directly depicting the capacity of the target area with the number of orders can be avoided; on this basis, the target fulfillment time length is used to evaluate the fulfillment instruction of a plurality of order distribution data, and then the target order distribution data meeting the logistics fulfillment quality requirement is filtered to determine the logistics capacity evaluation result of the target area, thereby improving the accuracy of the logistics capacity evaluation of the target area.

[0007] In a possible implementation of the first aspect, the obtaining the order distribution dataset of the target region comprises: obtaining initial order distribution data of the target region in a target period, the initial order distribution data comprising historical order distribution data and / or predicted order distribution data; determining a target sub-region in a plurality of sub-regions in the target region based on the plurality of sub-regions and the initial order distribution data; and determining the order distribution dataset of the target period based on the target sub-region and the initial order distribution data.

[0008] The above technical solution determines a target sub-region in a plurality of sub-regions in a target region based on initial order distribution data of the target region in a target period and the plurality of sub-regions, and determines an order distribution dataset of the target period based on the target sub-region and the initial order distribution data. The target sub-region is determined by screening the plurality of sub-regions, which reduces the data processing amount. The order distribution dataset is determined based on the initial order distribution data and the target sub-region, which improves the authenticity and effectiveness of the order distribution dataset, and further improves the accuracy of the logistics capacity evaluation result.

[0009] In a possible implementation of the first aspect and the above implementation, the determining the order distribution dataset of the target period based on the target sub-region and the initial order distribution data comprises: determining an order quantity from a first sub-region to a second sub-region based on the initial order distribution data, the first sub-region and the second sub-region being any sub-region in the target sub-region; generating reference order distribution data based on a plurality of order quantities and the target sub-region, the reference order distribution data comprising order quantities between the target sub-regions; and obtaining the order distribution dataset based on the reference order distribution data.

[0010] The above technical solution determines an order quantity from a first sub-region to a second sub-region based on initial order distribution data, generates reference order distribution data based on a plurality of order quantities and a target sub-region, and obtains an order distribution dataset based on the reference order distribution data. The order quantity and the delivery distance of the order (determined by the distance between the target sub-regions) are determined by determining the order quantity from each first sub-region to a second sub-region in the initial order distribution data. Based on this, the reliability of the order distribution dataset data is ensured by determining the order distribution dataset according to the reference order distribution data.

[0011] In a possible implementation of the first aspect and the above implementation, the reference order distribution data is a single-quantity adjacency matrix, and a matrix element in the single-quantity adjacency matrix is used to indicate an order quantity between the target sub-regions.

[0012] The technical solution has the advantages that the reference order distribution data is represented by the single-quantity adjacency matrix, so that the order quantity between target sub-regions can be clearly determined; and the distance of each order can be determined based on the position information of the target sub-regions, thereby ensuring the accuracy of each order distribution data in the order distribution data set.

[0013] With reference to the first aspect and the above implementation manners, in some possible implementation manners, the obtaining of the order distribution data set based on the reference order distribution data comprises: adjusting the order quantity between target sub-regions in the reference order distribution data to obtain adjusted order distribution data; and obtaining the order distribution data set based on the adjusted order distribution data and the reference order distribution data.

[0014] The technical solution has the advantages that the order quantity between target sub-regions in the reference order distribution data is adjusted to obtain adjusted order distribution data, and the order distribution data set is obtained based on the adjusted order distribution data and the reference order distribution data; by adjusting the order data quantity in the reference order distribution data, the evaluation data can be expanded, and the positioning accuracy of the target order distribution data is improved, thereby improving the accuracy of the logistics capacity evaluation result of the target region.

[0015] With reference to the first aspect and the above implementation manners, in some possible implementation manners, the determining of the target sub-region in the plurality of sub-regions in the target region based on the plurality of sub-regions and the initial order distribution data comprises: determining, based on the initial order distribution data, a reference quantity of orders in each sub-region in the plurality of sub-regions as a delivery starting point and / or a delivery ending point; performing descending order sorting on the plurality of sub-regions based on the reference quantity to obtain a sorting sequence; and selecting, based on the sorting order, a preset quantity of sub-regions in the sorting sequence as the target sub-region, starting from a first position of the sorting sequence.

[0016] The technical solution has the advantages that the reference quantity of orders in each sub-region in the plurality of sub-regions as a delivery starting point and / or a delivery ending point is determined based on the initial order distribution data, the plurality of sub-regions are sorted in descending order based on the reference quantity to obtain a sorting sequence, and a preset quantity of sub-regions in the sorting sequence are selected as the target sub-region, starting from a first position of the sorting sequence; the plurality of sub-regions are selected based on the reference quantity of orders in each sub-region in the plurality of sub-regions, so that the most active target sub-region of logistics delivery orders can be intercepted, the data quantity of the order distribution data set is reduced, the efficiency of the logistics capacity evaluation result is improved, and the accuracy of the logistics capacity evaluation result is ensured.

[0017] In a possible implementation of the first aspect and the foregoing implementation, the logistics capacity evaluation result of the target region is obtained based on the target order distribution data, including: The candidate evaluation parameter of each target order distribution data is determined based on each target order distribution data in the target order distribution data, and the candidate evaluation parameter is the total order quantity or the transaction amount; and the logistics capacity evaluation result is determined based on the maximum value in the candidate evaluation parameter.

[0018] The above technical solution determines the candidate evaluation parameter of each target order distribution data based on each target order distribution data in the target order distribution data, and determines the logistics capacity evaluation result based on the maximum value in the candidate evaluation parameter; since the candidate evaluation parameter is the total order quantity or the transaction amount, the candidate evaluation parameter can evaluate the revenue of the order distribution data, and the maximum value in the candidate evaluation parameter can maximize the revenue, thereby improving the accuracy of the logistics capacity evaluation.

[0019] In a possible implementation of the first aspect and the foregoing implementation, the candidate evaluation parameter of each target order distribution data is determined based on each target order distribution data in the target order distribution data, including: The total order quantity corresponding to each target order distribution data is determined based on each target order distribution data; or the order amount of each order in each target order distribution data is obtained; and the transaction amount corresponding to each target order distribution data is obtained based on a plurality of orders in each target order distribution data and the order amount of each order in the plurality of orders.

[0020] The above technical solution determines the total order quantity in each target order distribution data based on each target order distribution data; or obtains the order amount of each order in each target order distribution data; and obtains the transaction amount corresponding to each target order distribution data based on a plurality of orders in each target order distribution data and the order amount of each order in the plurality of orders; by determining the total order quantity or the transaction amount in each target order distribution data, the revenue of the target region can be maximized, and the reliability of the logistics capacity evaluation result of the target region can be ensured.

[0021] In a possible implementation of the first aspect and the foregoing implementation, the target order distribution data is obtained based on each order distribution data, including: obtain rider information, historical order information and space-time information of the target area in a target period; input each order distribution data, the rider information, the historical order information and the space-time information into a target model to obtain the target delivery time length of multiple orders in each order distribution data, the target delivery time length being an average delivery time length of the multiple orders.

[0022] The technical solution inputs each order distribution data, rider information, historical order information and space-time information into a target model to obtain the target delivery time length of multiple orders in each order distribution data, the target delivery time length being an average delivery time length of the multiple orders; the target delivery time length of the multiple orders in each order distribution data is determined by combining multiple dimensions of data to evaluate each order distribution data, thereby ensuring the accuracy of the target delivery time length.

[0023] In combination with the first aspect and the above implementation manners, in some possible implementation manners, the screening of the multiple order distribution data based on the multiple target delivery time lengths to obtain target order distribution data includes: determining whether each target delivery time length in the multiple target delivery time lengths is less than or equal to a preset delivery time length; when the target delivery time length is less than or equal to the preset delivery time length, the order distribution data corresponding to the target delivery time length is determined as the target order distribution data.

[0024] The technical solution determines the order distribution data corresponding to the target delivery time length as the target order distribution data when the target delivery time length is less than or equal to the preset delivery time length; the order distribution data satisfying the delivery quality evaluation is determined by screening the multiple order distribution data based on the preset delivery time length, thereby determining the logistics capacity evaluation result of the target area, and the accuracy of the logistics capacity evaluation result can be ensured.

[0025] The second aspect provides a logistics capacity evaluation device, which includes: an acquisition module configured to acquire an order distribution data set of a target area, the order distribution data set including multiple order distribution data; a processing module configured to obtain target delivery time lengths of multiple orders in each order distribution data based on each order distribution data; the processing module is further configured to screen the multiple order distribution data based on the multiple target delivery time lengths to obtain target order distribution data; and the processing module is further configured to obtain a logistics capacity evaluation result of the target area based on the target order distribution data.

[0026] In combination with the second aspect, in some possible implementation manners, the acquisition module is specifically configured to: obtain initial order distribution data of the target region in a target period, the initial order distribution data comprising historical order distribution data and / or predicted order distribution data; determine a target sub-region in a plurality of sub-regions in the target region based on the plurality of sub-regions and the initial order distribution data; determine an order distribution data set of the target period based on the target sub-region and the initial order distribution data.

[0027] With reference to the second aspect and the preceding implementation manners, in a possible implementation manner, the obtaining module is configured to: determine an order quantity from a first sub-region to a second sub-region based on the initial order distribution data, the first sub-region and the second sub-region being any sub-region in the target sub-region; generate reference order distribution data based on a plurality of the order quantities and the target sub-region, the reference order distribution data comprising order quantities between target sub-regions; and obtain the order distribution data set based on the reference order distribution data.

[0028] With reference to the second aspect and the preceding implementation manners, in a possible implementation manner, the reference order distribution data is a single-quantity adjacency matrix, and a matrix element in the single-quantity adjacency matrix is used to indicate an order quantity between target sub-regions.

[0029] With reference to the second aspect and the preceding implementation manners, in a possible implementation manner, the obtaining module is configured to: adjust the order quantities between target sub-regions in the reference order distribution data to obtain adjusted order distribution data; and obtain the order distribution data set based on the adjusted order distribution data and the reference order distribution data.

[0030] With reference to the second aspect and the preceding implementation manners, in a possible implementation manner, the obtaining module is configured to: determine a reference quantity of orders with each sub-region in the plurality of sub-regions as a delivery starting point and / or a delivery ending point based on the initial order distribution data; sort the plurality of sub-regions in descending order based on the reference quantities to obtain a sorting sequence; and select a preset number of sub-regions in the sorting sequence as the target sub-region based on the sorting order and taking a first position of the sorting sequence as a starting point.

[0031] With reference to the second aspect and the preceding implementation manners, in a possible implementation manner, the processing module is configured to: determine a candidate evaluation parameter of each target order distribution data based on each target order distribution data in the target order distribution data, the candidate evaluation parameter being a total order quantity or a transaction amount; and determine the logistics capacity evaluation result based on a maximum value in the candidate evaluation parameter.

[0032] With reference to the second aspect and the preceding implementation manners, in some possible implementation manners, the processing module is specifically configured to: based on the target order distribution data, determine a total order quantity corresponding to the target order distribution data; or, obtain an order amount of each order in the target order distribution data; and based on a plurality of orders in the target order distribution data and the order amount of each order in the plurality of orders, obtain a transaction amount corresponding to the target order distribution data.

[0033] With reference to the second aspect and the preceding implementation manners, in some possible implementation manners, the processing module is specifically configured to: obtain rider information, historical order information, and spatio-temporal information of the target area in a target period; input the order distribution data, the rider information, the historical order information, and the spatio-temporal information into a target model to obtain the target performance time length of the plurality of orders in the order distribution data, the target performance time length being an average performance time length of the plurality of orders.

[0034] With reference to the second aspect and the preceding implementation manners, in some possible implementation manners, the processing module is specifically configured to: determine whether each target performance time length in the plurality of target performance time lengths is less than or equal to a preset performance time length; and when the target performance time length is less than or equal to the preset performance time length, determine the order distribution data corresponding to the target performance time length as the target order distribution data.

[0035] In a third aspect, an electronic device is provided, including a memory and a processor, the memory being configured to store executable program code, and the processor being configured to invoke and run the executable program code from the memory, so that the electronic device performs the logistics capacity evaluation method in the first aspect or any possible implementation manner of the first aspect.

[0036] In a fourth aspect, a computer-readable storage medium is provided, which stores computer program code, when the computer program code is run on a computer, the computer program code causes the computer to perform the logistics capacity evaluation method in the first aspect or any possible implementation manner of the first aspect.

[0037] In a fifth aspect, a computer program product is provided, which includes computer program code, when the computer program code is run on a computer, the computer program code causes the computer to perform the logistics capacity evaluation method in the first aspect or any possible implementation manner of the first aspect.

[0038] The technical scheme has the following beneficial effects: based on each order distribution data in the multiple order distribution data of the target region, the target fulfillment time length of the multiple orders in each order distribution data is obtained, the multiple order distribution data is filtered based on the multiple target fulfillment time lengths, the target order distribution data is obtained, and based on the target order distribution data, the logistics capacity evaluation result of the target region is obtained; the order distribution data of the target region is used to represent the capacity of the target region, so that the problem caused by neglecting the order space flow direction and the delivery difficulty when directly using the order quantity of the target region to describe the capacity can be avoided; on this basis, the multiple order distribution data is evaluated by the target fulfillment time length, and then the target order distribution data meeting the logistics fulfillment quality requirement is filtered out to determine the logistics capacity evaluation result of the target region, so that the accuracy of the logistics capacity evaluation of the target region is improved.

[0039] The technical scheme of the present application can be applied to the transaction and delivery service of an instant e-commerce platform, such as Taobao flash shopping, Taofxian, Eleme takeout and retail, etc. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 is a scene schematic diagram of a logistics capacity evaluation method provided by an embodiment of the present application; Figure 2 is a schematic flowchart of a logistics capacity evaluation method provided by an embodiment of the present application; Figure 3 is a schematic diagram of a single-quantity adjacency matrix provided by an embodiment of the present application; Figure 4 is a schematic flowchart of another logistics capacity evaluation method provided by an embodiment of the present application; Figure 5 is a schematic flowchart of still another logistics capacity evaluation method provided by an embodiment of the present application; Figure 6 is a structural schematic diagram of a logistics capacity evaluation device provided by an embodiment of the present application; Figure 7 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0041] The technical scheme in the present application will be described clearly and thoroughly in combination with the drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B: "and / or" in the text only represents a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone, and in the description of the embodiments of the present application, "multiple" means two or more than two.

[0042] The terms "first", "second", "third", etc. are used only for the purpose of description and do not connote or imply relative importance or a specific number of features. Thus, features defined with "first", "second" or "third" can explicitly or implicitly include one or more of the features.

[0043] Before introducing the scheme of the embodiments of the present application, the professional terms possibly involved in the embodiments of the present application are first explained and described.

[0044] Origin-Destination (OD): refers to a tuple composed of a merchant AOI (Area of Interest) and a user AOI. For example, in a logistics scenario, the merchant AOI is the origin of the shipping order, and the user AOI is the destination of the shipping order. The number of orders from the merchant AOI to the user AOI is the OD order quantity.

[0045] Logistics capacity: refers to the logistics capacity that can be stably carried and efficiently completed under certain time and certain constraints.

[0046] Before introducing the scheme of the embodiments of the present application, the application scenario of the embodiments of the present application is first introduced.

[0047] With the rapid development of the takeout industry, logistics capacity evaluation has become an indispensable part of improving platform efficiency and service quality. Logistics capacity evaluation not only concerns the consumer experience, but also affects the operating cost of the platform. However, logistics capacity evaluation is a relatively complex problem. Logistics capacity is affected by many factors such as transportation capacity allocation, consumer demand, order difficulty, and objective environment. When the number of orders (or shipping orders) is used to represent the logistics capacity, the difficulty information of the shipping orders is completely ignored.

[0048] For example, 100 orders of shipping orders within 3 kilometers and 100 orders of shipping orders within 1 kilometer, if the capacity is generally determined to be 100 orders, the workload of delivering 100 orders of shipping orders within 3 kilometers is significantly greater than that of delivering 100 orders of shipping orders within 1 kilometer.

[0049] The following will be combined Figure 1 The logistics capacity evaluation scenario is introduced.

[0050] Figure 1 is a scenario diagram of a logistics capacity evaluation method provided by the embodiments of the present application.

[0051] For example, Figure 1As shown, the target area 100 (such as a business district) includes 5 AOIs, such as AOI1 to AO2 have 50 delivery orders, AOI1 to AOI5 have 50 delivery orders, and AOI3 to AOI4 have 100 delivery orders. The capacity is determined by the number of orders, and the number of orders dispatched from AOI1 is the same as that from AOI3. However, since the distances between any two of the 5 AOIs are not the same, if only the number of orders is used to determine the capacity, the accuracy of the logistics capacity evaluation result in the target area 100 is seriously affected.

[0052] The real-time logistics capacity evaluation based on the number of orders that can be handled in the target area has limitations. First, only focusing on the number of orders ignores the difficulty information of the shipping order and the merging of the order in the instant delivery process, which greatly affects the carrying capacity of logistics. Second, the logistics capacity has a certain elasticity, and it is difficult to evaluate the true value of the capacity by only one order number. On this basis, there may be multiple feasible distributions of logistics capacity, and each feasible distribution may correspond to different order numbers, different benefits or user experience. It is difficult to assist the operation, planning, regulation and coordination between logistics by only a fixed order number.

[0053] In the logistics scenario, how to express and estimate the real-time capacity of logistics plays a key role in the operation, planning and regulation of logistics, as well as the coordination between logistics and business. For example, the shipping order distribution (or order distribution data) of a business district OD is evaluated by a fulfillment quality estimation model. If the fulfillment quality evaluation meets the quality standard, it is determined that the shipping order distribution of the business district OD is a feasible cloud top distribution. Then, a series of feasible shipping order distributions are obtained by iterative search or operational optimization, and one or more shipping order distributions are returned as the capacity evaluation result based on the optimization target in the actual scenario. In summary, the returned capacity evaluation result not only ensures the accuracy of the capacity evaluation result, but also clearly reflects the shipping order distribution information.

[0054] Therefore, the present application provides a logistics capacity evaluation method, device, electronic equipment and storage medium. The order distribution data of the target area is used to represent the capacity of the target area, which can avoid the problem caused by ignoring the order space flow and delivery difficulty when directly using the order number of the target area to describe the capacity. On this basis, the target fulfillment time is used to evaluate the fulfillment instructions of multiple order distribution data, and the target order distribution data that meets the logistics fulfillment quality requirement is selected to determine the logistics capacity evaluation result of the target area, thereby improving the accuracy of the logistics capacity evaluation of the target area.

[0055] The following will be combined Figures 2 to 5 The logistics capacity evaluation method is introduced.

[0056] Figure 2 is a schematic flowchart of a logistics capacity evaluation method provided by an embodiment of the present application.

[0057] Exemplarily, Figure 2 The logistics capacity evaluation method shown is applied to a server.

[0058] Exemplarily, as Figure 2 As shown, the logistics capacity evaluation method 200 includes the following steps S201-S204.

[0059] S201, obtaining an order distribution data set of a target region.

[0060] Exemplarily, the target region refers to a specific geographical region related to logistics activities, and the target region can be determined according to the place where the logistics capacity evaluation is needed. For example, the target region is A district of A city, the target region is C commercial circle of B district of A city, etc. It should be understood that the target region has clear geographical location information, such as the land location information of the target region being C commercial circle of B district of A city.

[0061] Exemplarily, the order distribution data set includes a plurality of order distribution data, each order distribution data including the number of orders in the target region and order information corresponding to each order, and the order information includes but is not limited to: delivery starting point, delivery ending point, delivery distance, etc. The order distribution data can be represented by a set, a graph, a matrix, a table, a vector, etc. The order distribution data can determine the delivery starting point, the delivery ending point, and the delivery distance of the order.

[0062] In addition, any two order distribution data in the plurality of order distribution data are different, that is, the number of orders of any two order distribution data can be different, and the number of orders of any two order distribution data is the same but the order delivery starting point or the order delivery ending point is different.

[0063] Exemplarily, the initial order distribution data of the target region in the target period is obtained, the initial order distribution data includes historical order distribution data and / or predicted order distribution data; based on a plurality of sub-regions in the target region and the initial order distribution data, a target sub-region in the plurality of sub-regions is determined; and based on the target sub-region and the initial order distribution data, an order distribution data set of the target period is determined.

[0064] It should be understood that the target time period is a future time period. By using historical order distribution data corresponding to the future time period and / or predicted order distribution data for the future time period, the initial order distribution data for the target area in the future time period can be determined. By evaluating the future time period, adjustments can be made in advance based on the logistics capacity assessment results to ensure that the order delivery rate can be maintained during logistics peaks, thereby improving both the user experience and the delivery personnel's experience.

[0065] Optionally, the initial order distribution data can be either historical order distribution data or predicted order distribution data; of course, the initial order distribution data can include both historical and predicted order distribution data, without specific limitations. It should be understood that historical order distribution data refers to the actual order data for the target region during the target time period, while predicted order distribution data is the predicted order data for the target region during the target time period, obtained through an order evaluation model. For example, if the target time period is Wednesday 5 PM to 7 PM and the target region is region B, then the historical order distribution data could be the order distribution data for region B during the previous Wednesday 5 PM to 7 PM, or the historical order distribution data could be the order distribution data for region B during the previous day 5 PM to 7 PM. The predicted order distribution data is the order distribution data for region B during Wednesday 5 PM to 7 PM, predicted through an order evaluation model.

[0066] Optionally, the order evaluation model is a trained model. The input data of the order evaluation model includes date, time period, weather information, and rider distribution information. The output of the order evaluation model is the predicted order distribution data for that date and time period.

[0067] Given the initial order distribution data for the target area during the target time period, the target area is divided into multiple Areas of Interest (AOIs). Each AOI represents a geographic entity in a specific region, such as a school, scenic spot, shopping mall, or office building. Each AOI has clearly defined boundary points, and there are no overlapping areas between AOIs.

[0068] Because the target region has a large number of sub-regions and the order distribution data is relatively discrete, the target sub-regions are identified by filtering these sub-regions. The number of target sub-regions is less than the number of sub-regions. By focusing on key sub-regions (target sub-regions), the data processing volume is simplified while improving the authenticity and effectiveness of the order distribution dataset. Furthermore, based on the initial order distribution data and the target sub-regions, the order distribution data corresponding to the target sub-regions is determined. When the initial order distribution data includes historical order distribution data and predicted order distribution data, the order distribution data of the target sub-regions corresponding to the historical order distribution data and the order distribution data of the target sub-regions corresponding to the predicted order distribution data can be determined based on the initial order distribution data and the target sub-regions. Finally, an order distribution dataset is obtained based on these multiple order distribution data.

[0069] It should be understood that because the target sub-region is obtained by filtering from multiple sub-regions, the order distribution data in the target time period's order distribution dataset may have fewer orders compared to the initial order distribution data. In other words, the initial order distribution data includes all orders in the target region, while the order distribution data in the order distribution dataset may include orders from a representative target sub-region.

[0070] The above technical solution determines the target sub-region within the target area based on the initial order distribution data of the target area during the target time period and multiple sub-regions within the target area. Based on the target sub-region and the initial order distribution data, it determines the order distribution dataset for the target time period. By filtering multiple sub-regions to determine the target sub-region, the amount of data processing can be reduced. Furthermore, by determining the order distribution dataset using the initial order distribution data and the target sub-region, the authenticity and validity of the order distribution dataset can be improved, thereby enhancing the accuracy of the logistics capacity assessment results.

[0071] Optionally, selecting a target sub-region from multiple sub-regions can be done by filtering based on geographic location information or by filtering based on the number of orders in each sub-region.

[0072] The following section will introduce how to filter target sub-regions based on the number of orders in each sub-region.

[0073] For example, the initial order distribution data of the target area during the target time period is obtained. Based on the initial order distribution data, the reference quantity of each sub-region as the delivery start point and / or delivery end point is determined. The multiple sub-regions are sorted in descending order based on the reference quantity to obtain a sorting sequence. Starting from the first position of the sorting sequence, a preset number of sub-regions in the sorting sequence are selected as the target sub-regions based on the sorting order.

[0074] Optionally, the initial order distribution data includes historical order distribution data, and may also include predicted order distribution data. Of course, the initial order distribution data can include both historical and predicted order distribution data. Preferably, the initial order distribution data includes both historical and predicted order distribution data.

[0075] For example, the reference quantity can be the number of orders originating from each sub-region within multiple sub-regions, or the number of orders ending in each sub-region within multiple sub-regions. Alternatively, the reference quantity can be the sum of the first number of orders ending in each sub-region within multiple sub-regions and the second number of orders ending in that sub-region. It should be understood that the delivery origin is the merchant's location, and the delivery destination is the customer's location.

[0076] Optionally, the preset quantity can be a fixed value or a dynamic value. When the preset quantity is a fixed value, it can be 20, 30, etc. When the preset quantity is a dynamic value, it can be determined based on the area of ​​the target region, and the preset quantity can be positively correlated with the area. The preset quantity can be determined according to the actual situation, and no specific limitation is made here.

[0077] For example, the total order volume of each sub-region as the delivery start and end point is determined from the initial order distribution data. Specifically, for each sub-region, the first order quantity as the delivery start point and the second order quantity as the delivery end point are determined, and the sum of the first and second order quantities is used as a reference quantity. The sub-regions are then sorted in descending order based on the reference quantities to obtain a sorted sequence, where the reference quantities of the sub-regions in the sorted sequence gradually decrease. Starting from the first position of the new sorted sequence, a predetermined number of sub-regions are selected as target sub-regions.

[0078] For example, multiple sub-regions include AOI1, AOI2, AOI3…AOI n. The number of first orders (the starting point for delivery) and the number of second orders (the ending point for delivery) are determined for each AOI. The sum of the first and second order quantities is used as a reference quantity. Based on these reference quantities, the multiple AOIs are sorted into the following sequence: AOI10, AOI2, AOI9, AOI6, AOI15, AOI7, AOI13…AOI n. If the preset quantity is 5, then the target sub-regions include AOI10, AOI2, AOI9, AOI6, and AOI15.

[0079] It should be understood that the above-described method is only one way to determine the target sub-region in practical applications, and does not limit the method or number of target sub-regions in practical applications. The method or number of target sub-regions can be determined according to the actual situation, and no specific limitation is made here.

[0080] The above technical solution, based on initial order distribution data, determines the reference quantity of orders in each of multiple sub-regions as the delivery start point and / or delivery destination. Based on the reference quantity, the multiple sub-regions are sorted in descending order to obtain a sorted sequence. Starting from the first position of the sorted sequence, a preset number of sub-regions are selected as target sub-regions based on the sorting order. By selecting multiple sub-regions based on the reference quantity of orders in each sub-region, the most active target sub-regions for logistics orders can be identified, reducing the data volume of the order distribution dataset. This improves the efficiency of logistics capacity assessment results while ensuring their accuracy.

[0081] Furthermore, in the case of identifying a target sub-region among multiple sub-regions, the order distribution dataset is determined by comparing the target sub-region with the initial order distribution data.

[0082] For example, based on the initial order distribution data, the number of orders from the first sub-region to the second sub-region is determined. The first sub-region and the second sub-region are any sub-regions within the target sub-region. Based on the multiple order quantities and the target sub-regions, reference order distribution data is generated. The reference order distribution data includes the number of orders between the target sub-regions. Based on the reference order distribution data, an order distribution dataset is obtained.

[0083] Optionally, the second sub-region can be a different sub-region from the first sub-region within the target sub-region, or it can be the same sub-region as the first sub-region within the target sub-region. When the second sub-region is a different sub-region from the first sub-region within the target sub-region, the order quantity from the first sub-region to the second sub-region refers to the order quantity between different target sub-regions. When the second sub-region is the same sub-region as the first sub-region within the target sub-region, the order quantity from the first sub-region to the second sub-region refers to the order quantity within the same target sub-region, meaning that this target sub-region is both the delivery origin and the delivery destination.

[0084] Optionally, the order distribution data can be used as a reference; alternatively, the order distribution data can be adjusted to generate the order distribution dataset. The method for generating the order distribution dataset can be determined based on the actual situation and is not specifically limited here.

[0085] It should be understood that the reference order distribution data may contain fewer orders than the initial order distribution data, because the initial order distribution data includes the number of orders from all sub-regions within the target region, while the reference order distribution data only includes the number of orders from the target sub-region within all sub-regions.

[0086] The above technical solution, based on initial order distribution data, determines the number of orders from the first sub-region to the second sub-region. Based on multiple order quantities and target sub-regions, it generates reference order distribution data and obtains an order distribution dataset based on the reference order distribution data. By determining the number of orders from each of the first and second sub-regions in the initial order distribution data, the reference order distribution data can be determined, thus determining the order quantity and the delivery distance of the orders (determined by the distance between the target sub-regions). Based on this, the order distribution dataset can be determined according to the reference order distribution data, ensuring the reliability of the order distribution dataset.

[0087] For example, reference order distribution data can be represented by a single-order adjacency matrix, where the matrix elements indicate the number of orders between target sub-regions. Representing reference order distribution data using a single-order adjacency matrix clearly determines the number of orders between target sub-regions; and the location information of the target sub-regions allows for the determination of the distance between each order, ensuring the accuracy of the order distribution data in the order distribution dataset.

[0088] It should be understood that since the initial order distribution data includes multiple order distribution data sets, the resulting reference order distribution data also consists of multiple reference order distribution data sets. Therefore, an order distribution dataset can be obtained through the reference order distribution data. To improve the comprehensiveness of the order distribution dataset, the number of orders in the reference order distribution data can be cropped or adjusted to enrich the data in the order distribution dataset.

[0089] For example, the number of orders between target sub-regions in the reference order distribution data is adjusted to obtain adjusted order distribution data, and an order distribution dataset is obtained based on the adjusted order distribution data and the reference order distribution data.

[0090] Specifically, adjusting the order quantity between target sub-regions may increase or decrease the order quantity between them. However, by adjusting the order quantity between target sub-regions, adjusted order distribution data can be obtained that differs from the reference order distribution data. Furthermore, the adjusted order distribution data and the reference order distribution data are combined to form the order distribution dataset.

[0091] For example, the reference order distribution data includes 10 different order distribution data. If the number of orders in each order distribution data in the reference order distribution data is adjusted, that is, if the number of orders in each order distribution data is increased or decreased, then each order distribution data corresponds to two adjusted order distribution data. The generated order distribution dataset includes the reference order distribution data and the adjusted order distribution data. The reference order distribution data includes 10 different order distribution data, while the adjusted order distribution data includes 20 different order distribution data, thus expanding the reference order distribution data.

[0092] Since the logistics capacity assessment results for the target area are used to make advance adjustments to manpower and resources, by adjusting the order distribution data to be closer to the true value, we can more accurately locate the logistics capacity assessment results that maximize revenue, thereby maximizing the logistics revenue of the target area.

[0093] The above technical solution adjusts the number of orders between target sub-regions in the reference order distribution data to obtain adjusted order distribution data, and obtains an order distribution dataset based on the adjusted order distribution data and the reference order distribution data. By adjusting the amount of order data in the reference order distribution data, the evaluation data can be expanded, thereby improving the positioning accuracy of the target order distribution data and thus improving the accuracy of the logistics capacity evaluation results of the target area.

[0094] Taking the determination of the order distribution dataset for business district A (target area) in the next 30 minutes (target time period) as an example, we need to determine the historical order distribution data of business district A for the corresponding historical time period of the previous day (or previous week) and the next 30 minutes, as well as the predicted order distribution data of business district A in the next 30 minutes predicted by the order evaluation model. It should be understood that both the historical order distribution data and the predicted order distribution data include the order volume of business district A and the delivery origin, delivery destination, and delivery distance for each order (the delivery distance is determined by the regions where the order's delivery origin and delivery destination are located).

[0095] The predicted order distribution data and historical order distribution data are used as the initial order distribution data. Based on each initial order distribution data, the reference number of orders for each sub-area AOI within multiple sub-area AOIs in business district A is determined. The reference number includes the sum of the first order volume from each sub-area AOI as the delivery starting point and the second order volume from each sub-area AOI as the delivery destination. The sub-area AOIs are then sorted in descending order based on their reference order numbers, resulting in a sorted sequence where the reference order number for each subsequent sub-area AOI is less than that for the preceding sub-area AOI. Starting from the first sub-area AOI in the descending sequence, the n (n is a positive integer greater than 2) sub-area AOIs with the largest order volumes are selected as the target sub-area AOIs.

[0096] Based on each initial order distribution data and its corresponding target sub-region AOI, the number of orders between any two target sub-region AOIs is determined, i.e., the OD order quantity (or the OD order quantity from the delivery start point to the delivery end point between any two target sub-region AOIs). An adjacency matrix (or reference order distribution data) is constructed based on the OD order quantity and the target sub-region AOIs.

[0097] Figure 3 This is a schematic diagram of a single adjacency matrix provided in an embodiment of this application.

[0098] For example, such as Figure 3 The single adjacency matrix shown has n target sub-regions (AOIs). This means that based on the reference quantities of multiple sub-regions (AOIs) within business district A, the target sub-regions (AOIs) with the highest reference quantities are selected. ij This represents the number of orders originating from AOIi (i.e., the i-th target sub-region) and ending at AOIj (the j-th target sub-region). Since the locations of different target sub-regions AOI are independent, meaning there is no overlap, the number of orders between target sub-regions AOI reflects the number of orders at different distances. For example, if the distance from AOI1 to AOI3 is 1 kilometer (e.g., the distance from the center of AOI1 to the center of AOI3 is 1 kilometer), then A... 13 This indicates the number of orders within 1 kilometer.

[0099] Furthermore, by adjusting the matrix elements in the single-order adjacency matrix, an adjusted single-order adjacency matrix is ​​obtained. Specifically, the matrix elements in the single-order adjacency matrix represent the number of orders at the destination (OD). Increasing or decreasing the number of orders at any OD generates the adjusted single-order adjacency matrix. An order distribution dataset is then generated based on the adjusted single-order adjacency matrix and the single-order adjacency matrix. This dataset includes multiple order distribution data points, represented by the adjacency matrix. The order distribution data includes the number of orders between target sub-areas (AOIs) within business district A, the delivery origin, delivery destination, and delivery distance (distance between different target sub-areas (AOIs)) for each order.

[0100] Optionally, during the adjustment of matrix elements in the single adjacency matrix, adjustments can be made based on the number of orders, the number of merchants in the target sub-region AOI, or the number of users in the target sub-region AOI.

[0101] S202, based on the distribution data of each order, obtain the target fulfillment time for multiple orders in the distribution data of each order.

[0102] For example, the target fulfillment time for multiple orders is the average fulfillment time for the multiple orders.

[0103] For example, multiple order distribution data of the target area during the target time period are obtained, as well as rider information, historical order information and spatiotemporal information of the target area during the target time period. The order distribution data, rider information, historical order information and spatiotemporal information are input into the target model to obtain the target fulfillment time of multiple orders in each order distribution data. The target fulfillment time is the average fulfillment time of multiple orders.

[0104] For example, spatiotemporal information refers to information at a specific time and location. Spatiotemporal information includes, but is not limited to: location information of target sub-regions within the target area, distances between different target sub-regions, environmental information within the target area, and statistics on uncompleted orders within the target area.

[0105] Historical order information refers to the actual logistics data of the target area during the target time period. Historical order information includes, but is not limited to: the average delivery time of historical orders, the number of historical order cancellations, etc.

[0106] Rider information includes rider details related to orders, as well as information reported by riders in real time. Order-related rider information includes, but is not limited to: the most recent preset waiting time at the store, the time a rider takes to accept an order, the total fulfillment time, and rider distribution. For example, rider distribution includes the number of riders in the business district, the number of empty riders, the rider tier ratio, and the number of riders who accepted orders but did not arrive at the store. Optionally, the preset duration can include a single duration, such as 10 minutes; or multiple durations, such as 10 minutes, 30 minutes, 60 minutes, etc. The preset duration can be determined based on actual circumstances and is not specifically limited here.

[0107] Optionally, the target model is used to predict the target fulfillment time for multiple orders in the order distribution data, i.e., the fulfillment quality prediction model. The target model is a prediction model that has been trained. As logistics information grows, the target model can be optimized accordingly, i.e., other information can be added to train the model. The training data for the target model includes rider information, historical order information, spatiotemporal information, and OD waybill distribution data (or training order distribution data) during the training period. Training the target model ensures the accuracy of the estimated fulfillment time.

[0108] It should be understood that the goal of the target model is to predict (evaluate) the overall fulfillment quality of the business district (such as delivery time, wave duration, etc.) given the OD order distribution (or order distribution data) of the business district.

[0109] The above technical solution inputs order distribution data, rider information, historical order information, and spatiotemporal information into the target model to obtain the target fulfillment time for multiple orders in each order distribution data. The target fulfillment time is the average fulfillment time of multiple orders. By combining multi-dimensional data to evaluate each order distribution data, the target fulfillment time for multiple orders in each order distribution data is determined, thereby ensuring the accuracy of the target fulfillment time.

[0110] For example, the order distribution dataset includes multiple order distribution data. By evaluating each order distribution data, the target fulfillment time of multiple orders in each order distribution data can be obtained, and the target fulfillment time corresponding to each order distribution data in the multiple order distribution data can be determined sequentially.

[0111] S203, based on multiple target fulfillment durations, filter multiple order distribution data to obtain target order distribution data.

[0112] For example, multiple order distribution data are filtered based on multiple target fulfillment times corresponding to multiple order distribution data to obtain target order distribution data. Since the target order distribution data is obtained from the multiple order distribution data, the number of target order distribution data is less than the number of multiple order distribution data. When representing order distribution data using adjacency matrices, if the multiple order distribution data includes x adjacency matrices, then the target order distribution data includes y adjacency matrices, where x is greater than or equal to y.

[0113] For example, it is determined whether each target fulfillment duration is less than or equal to a preset fulfillment duration; when the target fulfillment duration is less than or equal to the preset fulfillment duration, the order distribution data corresponding to the target fulfillment duration is determined as the target order distribution data.

[0114] Specifically, for multiple target fulfillment durations, these target fulfillment durations are sequentially designated as candidate fulfillment durations. It is then determined whether each candidate fulfillment duration is less than or equal to a preset fulfillment duration. When a candidate fulfillment duration is less than or equal to the preset fulfillment duration, the order distribution data corresponding to that candidate fulfillment duration is determined as the target order distribution data. When a candidate fulfillment duration is longer than the preset fulfillment duration, the order distribution data corresponding to that candidate fulfillment duration is discarded.

[0115] Optionally, the preset fulfillment time can be 30 minutes, 40 minutes, etc. The preset fulfillment time can be determined according to the actual situation, and no specific limit is made here.

[0116] For example, the filtering expression for target order distribution data is as follows: ; in, This represents order distribution data. Represents order distribution data The target fulfillment time is T, which is the preset fulfillment time. The order distribution data is filtered based on this preset time; when the target fulfillment time is less than or equal to T, the corresponding order distribution data... This is the target order distribution data.

[0117] The above technical solution determines the order distribution data corresponding to the target fulfillment time as the target order distribution data when the target fulfillment time is less than or equal to the preset fulfillment time. By filtering multiple order distribution data through the preset fulfillment time, the order distribution data that meets the fulfillment quality assessment is determined, thereby determining the logistics capacity assessment result of the target area, which can ensure the accuracy of the logistics capacity assessment result.

[0118] It should be noted that when the fulfillment time of multiple targets is greater than the preset fulfillment time, the order distribution data of multiple orders in the order distribution dataset can be adjusted to obtain an updated order distribution dataset, and the logistics capacity assessment can be repeated until the logistics capacity assessment result of the target area is obtained.

[0119] Optionally, the method for adjusting multiple order distribution data in the order distribution dataset can refer to the method for adjusting reference order distribution data in the aforementioned disclosed embodiments, and will not be repeated here.

[0120] S204, based on the target order distribution data, obtain the logistics capacity assessment results for the target area.

[0121] For example, multiple order distribution data for a target region are obtained. Based on each order distribution data, the target fulfillment time for multiple orders within each order distribution data is obtained. The multiple order distribution data are then filtered based on the multiple target fulfillment times to obtain target order distribution data. Finally, based on the target order distribution data, the logistics capacity assessment result for the target region is obtained. For example, the target order distribution data is determined as the logistics capacity assessment result for the target region.

[0122] Optionally, the logistics capacity assessment results for the target area are used to indicate the distribution data of orders that meet the fulfillment time requirements.

[0123] For example, based on the target order distribution data, candidate evaluation parameters for each target order distribution data are determined, where the candidate evaluation parameters are the total order volume or transaction amount; and the logistics capacity evaluation result is determined based on the maximum value among the candidate evaluation parameters.

[0124] For example, given the candidate evaluation parameters, the maximum value among the candidate evaluation parameters is determined, and the target order distribution data corresponding to the maximum value among the candidate evaluation parameters is determined as the logistics capacity evaluation result. For instance, when the candidate evaluation parameter is the total order volume, the target order distribution data corresponding to the maximum total order volume is determined as the logistics capacity evaluation result; when the candidate evaluation parameter is the transaction amount, the target order distribution data corresponding to the maximum transaction amount is determined as the logistics capacity evaluation result.

[0125] The above technical solution determines candidate evaluation parameters for each target order distribution data based on the target order distribution data, and determines the logistics capacity evaluation result based on the maximum value among the candidate evaluation parameters. Since the candidate evaluation parameters are the total order volume or transaction amount, the candidate evaluation parameters can evaluate the revenue of the order distribution data. By determining the logistics capacity evaluation result through the maximum value among the candidate evaluation parameters, the revenue can be maximized, thereby improving the accuracy of logistics capacity evaluation.

[0126] Optionally, candidate evaluation parameters are parameters used to measure the benefits brought by the production capacity of the target region. For example, candidate evaluation parameters can be the total number of orders in the order distribution data, or they can be the transaction amount in the order distribution data.

[0127] For example, based on the distribution data of each target order, determine the total number of orders corresponding to each target order distribution data; or, obtain the order amount of each order in each target order distribution data; based on multiple orders in each target order distribution data and the order amount of each order in the multiple orders, obtain the transaction amount corresponding to each target order distribution data.

[0128] For example, determine the number of delivery orders for each target sub-region in the target order distribution data, and sum the delivery order numbers to determine the total number of orders.

[0129] The above technical solution determines the total number of orders in each target order distribution data based on the distribution data of each target order; or, obtains the order amount of each order in each target order distribution data; and obtains the transaction amount corresponding to each target order distribution data based on multiple orders and the order amount of each order in multiple orders. By determining the total number of orders or the transaction amount in each target order distribution data, the revenue of the target area can be maximized and the reliability of the logistics capacity assessment results of the target area can be ensured.

[0130] In this embodiment, the order distribution data (or waybill distribution) is generated by adjusting the initial distribution data to form a large set of order distribution data to be evaluated (multiple order distribution data). Then, a fulfillment evaluation model is used for evaluation, that is, the evaluation model determines whether the target fulfillment time of the order distribution data to be evaluated exceeds the preset fulfillment time, thereby obtaining the target order distribution data that meets the fulfillment quality evaluation.

[0131] Since various order distribution data may meet the performance quality assessment conditions, an operational process needs to be introduced for the target order distribution data. The performance quality threshold (preset performance time) is only one of the constraints, and there needs to be an optimization target.

[0132] When the optimization objective is the number of orders, the order distribution data that maximizes the number of orders obtained through operations research can be understood as logistics capacity. For example, the expression for logistics capacity assessment can be represented as follows: ; in, Let I represent the number of orders from target sub-region i to target sub-region j, where I represents the set of target sub-regions where the order's delivery origin is located, and J represents the set of target sub-regions where the order's delivery destination is located. This represents the optimization objective, which can be the number of orders. The above expression can be used to find the order distribution data with the largest number of orders in the target order distribution data, and the order distribution data with the largest number of orders is determined as the logistics capacity assessment result of the target area.

[0133] If additional constraints are needed, or the optimization objective needs to be changed, other aspects of the logistics system can be identified. For example, the optimization objective could be to maximize Gross Merchandise Volume (GMV). The transaction amount corresponding to each order.

[0134] It should be understood that the logistics capacity assessment results for the target area are determined according to the aforementioned disclosed embodiments. Since the logistics capacity assessment results are feasible order distribution data, real-time control of logistics can be carried out through the logistics capacity assessment results, and coordination between logistics and commerce can also be carried out, thereby maximizing overall benefits under limited transportation capacity.

[0135] For example, logistics capacity assessment results can support precise rider scheduling (e.g., targeted energy replenishment, route planning), performance risk prediction (e.g., avoiding delays and order surges), and adjustment of order consolidation rules. Real-time logistics capacity assessment results can transform passively responding to order fluctuations into proactively matching resources and optimizing delivery efficiency, thereby achieving multi-dimensional improvements in capacity utilization, order fulfillment quality, delivery rider experience, and user (customer) experience.

[0136] The above technical solution, based on the order distribution data of multiple order distribution data in the target area, obtains the target fulfillment time of multiple orders in each order distribution data. Based on the multiple target fulfillment times, it filters the multiple order distribution data to obtain target order distribution data, and based on the target order distribution data, obtains the logistics capacity assessment result of the target area. Representing the capacity of the target area through order distribution data avoids the problems caused by ignoring the spatial flow of orders and delivery difficulties when directly describing capacity based on the number of orders in the target area. Furthermore, by evaluating the fulfillment instructions of multiple order distribution data through the target fulfillment time, it filters out the target order distribution data that meets the logistics fulfillment quality requirements to determine the logistics capacity assessment result of the target area, thus improving the accuracy of the logistics capacity assessment of the target area.

[0137] The methods in the following embodiments can be used as a basis for... Figure 2 A refinement of step S201 in the illustrated embodiment.

[0138] Figure 4 This is a schematic flowchart illustrating another logistics capacity assessment method provided in the embodiments of this application.

[0139] For example,Figure 4 The logistics capacity assessment method shown is applied to servers.

[0140] For example, such as Figure 4 As shown, the logistics capacity assessment method 400 includes the following steps S401-S408.

[0141] S401, Obtain the initial order distribution data for the target area during the target time period.

[0142] For example, if the target time period is a future time period, the initial order distribution data of the target area in the future time period can be determined by using the historical order distribution data corresponding to the future time period and the predicted order distribution data for the future time period.

[0143] Optionally, the initial order distribution data includes all order data for the target region during the target time period. Historical order distribution data consists of the actual order data for the target region during the corresponding historical time period, while the predicted order distribution data is the predicted order data for the target region during the target time period, obtained through an order evaluation model. For example, if the target time period is Wednesday 5 PM to 7 PM and the target region is region B, then the historical order distribution data could be the order distribution data for region B during the previous Wednesday 5 PM to 7 PM. The predicted order distribution data is the order distribution data for region B during the Wednesday 5 PM to 7 PM, predicted through an order evaluation model.

[0144] Optionally, the order evaluation model is a trained model. The input data of the order evaluation model includes date, time period, weather information, and rider distribution information. The output of the order evaluation model is the predicted order distribution data for that date and time period.

[0145] S402, based on the initial order distribution data, determine the reference number of orders in each of the multiple sub-regions that serve as the delivery start and end points.

[0146] For example, when the initial order distribution data includes multiple order distribution data, each order distribution data in the initial order distribution data is traversed in turn to obtain the adjusted adjacency matrix and the single adjacency matrix. Based on the adjusted adjacency matrix and the single adjacency matrix corresponding to each order distribution data in the initial order distribution data, the order distribution dataset is obtained.

[0147] For example, for each initial order distribution data, the total number of orders in each of the multiple sub-areas (AOIs) is determined as the delivery origin and destination. Specifically, for each sub-area, the number of first orders as the delivery origin and the number of second orders as the delivery destination in that sub-area are determined, and the sum of the first and second order quantities is determined as a reference quantity.

[0148] S403, sort multiple sub-regions in descending order based on the reference quantity to obtain the sorted sequence.

[0149] For example, given the reference number of orders in multiple sub-regions of the initial order distribution data, the multiple sub-regions are sorted in descending order according to the reference number to obtain a sorted sequence, and the reference number of multiple sub-regions in the sorted sequence gradually decreases.

[0150] S404, starting from the first position of the sorted sequence, selects a preset number of sub-regions in the sorted sequence as target sub-regions based on the sorting order.

[0151] For example, the reference number of multiple sub-regions in the sorting sequence of multiple sub-regions gradually decreases. Starting from the first position of the new sorting sequence, a preset number of sub-regions in the sorting sequence are selected as target sub-regions based on the sorting order, that is, the top-n (n is the preset number) sub-regions are selected as target sub-regions.

[0152] Optionally, the preset quantity can be a fixed value or a dynamic value. When the preset quantity is a fixed value, it can be 20, 30, etc. When the preset quantity is a dynamic value, it can be determined based on the area of ​​the target region. The preset quantity and the area can be positively correlated; the larger the area of ​​the target region, the larger the preset quantity, and the smaller the area of ​​the target region, the smaller the preset quantity. The preset quantity can be determined according to the actual situation and is not specifically limited here.

[0153] S405, based on the initial order distribution data, determine the number of orders from the first sub-region to the second sub-region.

[0154] For example, based on the initial order distribution data, the number of orders from the first sub-region to the second sub-region is determined, where the first sub-region and the second sub-region are any sub-regions within the target sub-region.

[0155] Optionally, the second sub-region can be a different sub-region from the first sub-region within the target sub-region, or it can be the same sub-region as the first sub-region within the target sub-region. When the second sub-region is a different sub-region from the first sub-region within the target sub-region, the order quantity from the first sub-region to the second sub-region refers to the order quantity between different target sub-regions. When the second sub-region is the same sub-region as the first sub-region within the target sub-region, the order quantity from the first sub-region to the second sub-region refers to the order quantity within the same target sub-region, meaning that this target sub-region is both the delivery origin and the delivery destination.

[0156] It should be understood that by determining the number of orders from the first sub-region to the second sub-region, the delivery origin and destination of the order can be located. That is, for an order, given the target sub-region where the delivery origin and destination are located, the delivery distance of the order can be represented by the distribution data.

[0157] S406 generates an adjacency matrix of order quantities based on multiple order quantities and target sub-regions.

[0158] For example, the matrix elements in the singular adjacency matrix refer to the number of orders between target sub-regions. Optionally, the representation of the singular adjacency matrix can refer to... Figure 3 The details will not be repeated here.

[0159] S407, adjust the number of orders between different target sub-regions in the single adjacency matrix to obtain the adjusted adjacency matrix.

[0160] For example, the matrix elements of the adjacency matrix refer to the number of orders between any two target sub-regions. By adjusting the values ​​of the matrix elements, the adjacency matrix can be dynamically adjusted to obtain the adjusted adjacency matrix.

[0161] S408, based on adjusting the adjacency matrix and the single adjacency matrix, obtains the order distribution dataset.

[0162] For example, since the initial order distribution data includes multiple order distribution data, each initial order distribution data is traversed sequentially to obtain the adjusted adjacency matrix and the single adjacency matrix corresponding to each initial order distribution data. Based on the adjusted adjacency matrix and the single adjacency matrix corresponding to each initial order distribution data, the order distribution dataset is obtained, which includes multiple order distribution data.

[0163] The above technical solution represents the capacity of the target area by using order distribution data, which avoids the problems caused by ignoring the spatial flow of orders and delivery difficulties when directly describing capacity based on the number of orders in the target area. Furthermore, by filtering multiple sub-regions to determine the target sub-region, the amount of data processing is reduced. Then, by using the initial order distribution data and the target sub-region to determine the order distribution dataset, the authenticity and validity of the order distribution dataset can be improved, thereby increasing the accuracy of the logistics capacity assessment results.

[0164] Figure 5 This is a schematic flowchart illustrating another logistics capacity assessment method provided in the embodiments of this application.

[0165] For example, Figure 5 The logistics capacity assessment method shown is applied to servers.

[0166] For example, such asFigure 5 As shown, the logistics capacity assessment method 500 includes the following steps S501-S506.

[0167] S501, obtain the order distribution dataset of the target area, rider information of the target area during the target time period, historical order information and spatiotemporal information.

[0168] For example, the target area refers to a specific geographical area related to logistics activities, which can be determined based on the location where logistics capacity assessment is needed.

[0169] For example, the order distribution dataset includes multiple order distribution data, each of which includes the number of orders in the target area and the order information corresponding to each order. The order information includes, but is not limited to, the order delivery origin, the order delivery destination, and the order delivery distance.

[0170] For example, spatiotemporal information refers to information at a specific time and location. Spatiotemporal information includes, but is not limited to: location information of target sub-regions within the target area, distances between different target sub-regions, environmental information within the target area, and statistics on uncompleted orders within the target area.

[0171] Historical order information refers to the actual logistics data of the target area during the target time period. Historical order information includes, but is not limited to: the average delivery time of historical orders, the number of historical order cancellations, etc.

[0172] Rider information includes rider details related to the order, as well as information reported by riders in real time. Rider information related to the order includes, but is not limited to: the rider's most recent preset waiting time at the store, the time the rider takes to accept the order, the total fulfillment time, and rider distribution.

[0173] S502, input the order distribution data, rider information, historical order information and spatiotemporal information into the target model to obtain the target fulfillment time of multiple orders in the order distribution data.

[0174] For example, the target model is used to predict the target fulfillment time of multiple orders in the order distribution data. The target model is a trained prediction model. As logistics information increases, the target model can be optimized accordingly, that is, other information can be added to train the model. The training data of the target model includes rider information, historical order information, spatiotemporal information, and OD waybill distribution data (or training order distribution data) during the training period. Training the target model ensures the accuracy of the estimated fulfillment time.

[0175] For example, multiple order distribution data of the target area during the target time period are obtained, as well as rider information, historical order information and spatiotemporal information of the target area during the target time period. The order distribution data, rider information, historical order information and spatiotemporal information are input into the target model to obtain the target fulfillment time of multiple orders in each order distribution data. The target fulfillment time is the average fulfillment time of multiple orders.

[0176] S503, determine whether the performance time of each target among multiple target performance times is less than or equal to the preset performance time.

[0177] Optionally, the preset fulfillment time can be 30 minutes, 40 minutes, etc. The preset fulfillment time can be determined according to the actual situation, and no specific limit is made here.

[0178] For example, multiple order distribution data are filtered based on multiple target fulfillment times corresponding to multiple order distribution data to obtain target order distribution data.

[0179] S504, when the target fulfillment time is less than the preset fulfillment time, the order distribution data corresponding to the target fulfillment time is determined as the target order distribution data.

[0180] For example, the target order distribution data is obtained by filtering from multiple order distribution data, so the number of target order distribution data is less than the number of multiple order distribution data.

[0181] For example, it is determined whether each target fulfillment duration is less than or equal to a preset fulfillment duration; when the target fulfillment duration is less than or equal to the preset fulfillment duration, the order distribution data corresponding to the target fulfillment duration is determined as the target order distribution data.

[0182] S505, Based on the target order distribution data in the target order distribution data, determine the candidate evaluation parameters for each target order distribution data.

[0183] For example, based on the target order distribution data, candidate evaluation parameters are determined for each target order distribution data. These candidate evaluation parameters can be either the total order volume or the transaction amount. Optionally, the candidate evaluation parameters can be parameters used to measure the benefits brought by the production capacity of the target region.

[0184] For example, based on the distribution data of each target order, the total number of orders corresponding to each target order distribution data is determined. For instance, the number of delivery orders for each target sub-region in the distribution data is determined, and the sum of these delivery order numbers is used to determine the total number of orders. Alternatively, the order amount of each order in the distribution data is obtained; based on multiple orders in the distribution data and the order amounts of each order within those multiple orders, the transaction amount corresponding to each target order distribution data is obtained.

[0185] S506, determine the logistics capacity assessment result based on the maximum value among the candidate assessment parameters.

[0186] For example, multiple order distribution data for a target region are obtained. Based on each order distribution data, the target fulfillment time for multiple orders in each order distribution data is obtained. Based on the multiple target fulfillment times, the multiple order distribution data are filtered to obtain target order distribution data. Then, based on the target order distribution data, the logistics capacity assessment result for the target region is obtained.

[0187] For example, when candidate evaluation parameters are determined, the maximum value among the candidate evaluation parameters is determined, and the target order distribution data corresponding to the maximum value among the candidate evaluation parameters is determined as the logistics capacity evaluation result.

[0188] The above technical solution, based on the order distribution data of multiple order distribution data in the target area, obtains the target fulfillment time of multiple orders in each order distribution data. Based on the multiple target fulfillment times, it filters the multiple order distribution data to obtain target order distribution data, and based on the target order distribution data, obtains the logistics capacity assessment result of the target area. Representing the capacity of the target area through order distribution data avoids the problems caused by ignoring the spatial flow of orders and delivery difficulties when directly describing capacity based on the number of orders in the target area. Furthermore, by evaluating the fulfillment instructions of multiple order distribution data through the target fulfillment time, it filters out the target order distribution data that meets the logistics fulfillment quality requirements to determine the logistics capacity assessment result of the target area, thus improving the accuracy of the logistics capacity assessment of the target area.

[0189] It should be understood that the above examples are provided to help those skilled in the art understand the embodiments of this application, and are not intended to limit the embodiments of this application to the specific values ​​or scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the above examples, and such modifications or changes also fall within the scope of the embodiments of this application.

[0190] The above text combined Figures 1 to 5 The logistics capacity assessment method provided in the embodiments of this application is described in detail below; the following will be combined with Figure 6 and Figure 7 This application provides a detailed description of embodiments of the logistics capacity assessment device. It should be understood that the logistics capacity assessment device in this application can execute various methods described in the foregoing embodiments of this application; that is, the specific working processes of the various products described below can be referred to the corresponding processes in the foregoing method embodiments.

[0191] Figure 6 This is a schematic diagram of the structure of a logistics capacity assessment device provided in an embodiment of this application.

[0192] For example, such as Figure 6 As shown, the logistics capacity assessment device 600 includes: The acquisition module 601 is used to acquire the order distribution dataset of the target area, which includes multiple order distribution data. Processing module 602 is used to obtain the target fulfillment time of multiple orders in each order distribution data based on the order distribution data; The processing module 602 is also used to filter multiple order distribution data based on multiple target fulfillment times to obtain target order distribution data; The processing module 602 is also used to obtain the logistics capacity assessment results of the target area based on the target order distribution data.

[0193] Optionally, as an embodiment, the acquisition module 601 is specifically used for: Obtain initial order distribution data for the target region during the target time period. The initial order distribution data includes historical order distribution data and / or predicted order distribution data. Based on multiple sub-regions within the target region and the initial order distribution data, determine the target sub-regions within the multiple sub-regions. Based on the target sub-regions and the initial order distribution data, determine the order distribution dataset for the target time period.

[0194] Optionally, as an embodiment, the acquisition module 601 is specifically used for: Based on the initial order distribution data, determine the number of orders from the first sub-region to the second sub-region, where the first and second sub-regions are any sub-regions within the target sub-regions; based on the multiple order quantities and the target sub-regions, generate reference order distribution data, which includes the number of orders between the target sub-regions; based on the reference order distribution data, obtain the order distribution dataset.

[0195] Optionally, as an example, the reference order distribution data is a single adjacency matrix, where the matrix elements are used to indicate the number of orders between target sub-regions.

[0196] Optionally, as an embodiment, the acquisition module 601 is specifically used for: Adjust the number of orders between target sub-regions in the reference order distribution data to obtain adjusted order distribution data; based on the adjusted order distribution data and the reference order distribution data, obtain the order distribution dataset.

[0197] Optionally, as an embodiment, the acquisition module 601 is specifically used for: Based on the initial order distribution data, determine the reference quantity of orders in each of the multiple sub-regions as the delivery start point and / or delivery destination; sort the multiple sub-regions in descending order based on the reference quantity to obtain a sorting sequence; starting from the first position of the sorting sequence, select a preset number of sub-regions in the sorting sequence as target sub-regions based on the sorting order.

[0198] Optionally, as an embodiment, the processing module 602 is specifically used for: Based on the target order distribution data, candidate evaluation parameters for each target order distribution data are determined. The candidate evaluation parameters are the total order volume or transaction amount. Based on the maximum value among the candidate evaluation parameters, the logistics capacity evaluation result is determined.

[0199] Optionally, as an embodiment, the processing module 602 is specifically used for: Based on the distribution data of each target order, determine the total number of orders corresponding to each target order distribution data; or, obtain the order amount of each order in each target order distribution data; based on multiple orders in each target order distribution data and the order amount of each order in multiple orders, obtain the transaction amount corresponding to each target order distribution data.

[0200] Optionally, as an embodiment, the processing module 602 is specifically used for: Obtain rider information, historical order information, and spatiotemporal information for the target area during the target time period; input the order distribution data, rider information, historical order information, and spatiotemporal information into the target model to obtain the target fulfillment time for multiple orders in each order distribution data. The target fulfillment time is the average fulfillment time for multiple orders.

[0201] Optionally, as an embodiment, the processing module 602 is specifically used for: Determine whether each target fulfillment duration is less than or equal to the preset fulfillment duration; when the target fulfillment duration is less than or equal to the preset fulfillment duration, determine the order distribution data corresponding to the target fulfillment duration as the target order distribution data.

[0202] It should be noted that the aforementioned logistics capacity assessment device 600 is embodied in the form of a functional unit. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0203] For example, a "module" can be a software program, a hardware circuit, or a combination of both that implements the above functions. The hardware circuit may include an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components that support the described functions.

[0204] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0205] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0206] For example, such as Figure 7 As shown, the electronic device 700 includes a memory 701 and a processor 702. The memory 701 stores executable program code 703, and the processor 702 is used to call and execute the executable program code 703 to perform a logistics capacity assessment method.

[0207] For example, memory 701 can be used to store related programs of the logistics capacity assessment method provided in the embodiments of this application; processor 702 can call the related programs of the logistics capacity assessment method stored in memory 701 to execute the logistics capacity assessment method of the embodiments of this application; for example, obtaining an order distribution dataset of a target area, the order distribution dataset including multiple order distribution data; based on each order distribution data, obtaining the target fulfillment time of multiple orders in each order distribution data; filtering the multiple order distribution data based on multiple target fulfillment times to obtain target order distribution data; and obtaining the logistics capacity assessment result of the target area based on the target order distribution data.

[0208] This embodiment can divide functional modules according to the above method example. For example, each module can correspond to a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0209] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0210] When using integrated units, the device may include a processing module and a storage module. The processing module may be a processor or a controller that can implement or execute various exemplary logic blocks, modules, and circuits shown in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0211] In addition, the device provided in the embodiments of this application may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute a logistics capacity assessment method provided in the above embodiments.

[0212] This application also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement the logistics capacity assessment method provided in the above embodiments. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, Digital Video Discs (DVDs), Compact Disc Read-Only Memory (CD-ROMs), microdrives, and magneto-optical disks, read-only memory (ROMs), random access memory (RAMs), erasable programmable read-only memory (EPROMs), electrically erasable programmable read-only memory (EEPROMs), dynamic random access memory (DRAMs), video random access memory (VRAMs), flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of media or device suitable for storing instructions and / or data.

[0213] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement the logistics capacity assessment method provided in the above embodiments.

[0214] The computer-readable storage medium, computer program product, or chip provided in this application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0215] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0216] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0217] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions 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 scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of assessing logistics capacity, characterized by, The method comprises: obtaining an order distribution data set of a target region, the order distribution data set comprising a plurality of order distribution data; based on each order distribution data, obtaining a target fulfillment time length of a plurality of orders in each order distribution data; based on a plurality of target fulfillment time lengths, screening the plurality of order distribution data to obtain target order distribution data; based on the target order distribution data, obtaining a logistics capacity evaluation result of the target region.

2. The method of claim 1, wherein, The order distribution data set of the target region comprises: obtaining initial order distribution data of the target region in a target period, the initial order distribution data comprising historical order distribution data and / or predicted order distribution data; based on a plurality of sub-regions in the target region and the initial order distribution data, determining a target sub-region in the plurality of sub-regions; based on the target sub-region and the initial order distribution data, determining an order distribution data set of the target period.

3. The method of claim 2, wherein, Based on the target sub-region and the initial order distribution data, the order distribution data set of the target period comprises: based on the initial order distribution data, determining the number of orders from a first sub-region to a second sub-region, the first sub-region and the second sub-region being any sub-region in the target sub-region; based on a plurality of order quantities and the target sub-region, generating reference order distribution data, the reference order distribution data comprising order quantities between the target sub-regions; based on the reference order distribution data, obtaining the order distribution data set.

4. The method of claim 3, wherein, The reference order distribution data is a single-quantity adjacency matrix, and the matrix elements in the single-quantity adjacency matrix are used to indicate the number of orders between target sub-regions.

5. The method of claim 3, wherein, Based on the reference order distribution data, the order distribution data set comprises: adjusting the number of orders between target sub-regions in the reference order distribution data to obtain adjusted order distribution data; based on the adjusted order distribution data and the reference order distribution data, obtaining the order distribution data set.

6. The method of claim 2, wherein, Based on the plurality of sub-regions in the target region and the initial order distribution data, the target sub-region in the plurality of sub-regions comprises: based on the initial order distribution data, determining a reference quantity of orders in each sub-region in the plurality of sub-regions as a distribution starting point and / or a distribution ending point; based on the reference quantity, sorting the plurality of sub-regions in descending order to obtain a sorting sequence; starting from the first position of the sorting sequence, selecting a preset number of sub-regions in the sorting sequence as the target sub-region based on the sorting order.

7. The method of claim 1, wherein, Based on the target order distribution data, the logistics capacity evaluation result of the target region comprises: based on each target order distribution data in the target order distribution data, determining a candidate evaluation parameter of each target order distribution data, the candidate evaluation parameter being a total order quantity or a transaction amount; based on the maximum value in the candidate evaluation parameter, determining the logistics capacity evaluation result.

8. A logistics capacity assessment apparatus, characterized by, The device comprises: An acquisition module is configured to acquire order distribution data sets of a target region, wherein each of the order distribution data sets comprises a plurality of order distribution data; A processing module is configured to obtain, based on each of the order distribution data, a target fulfillment duration of a plurality of orders in each of the order distribution data; The processing module is further configured to filter the plurality of order distribution data based on the target fulfillment durations to obtain target order distribution data; The processing module is further configured to obtain a logistics capacity evaluation result of the target region based on the target order distribution data.

9. An electronic device, comprising: The electronic device comprises: a memory configured to store executable program codes; a processor configured to call and run the executable program codes from the memory, so that the electronic device performs the logistics capacity evaluation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, when the computer program is executed, the logistics capacity evaluation method according to any one of claims 1 to 7 is realized.

Images