Site selection method and device of service site, electronic equipment and storage medium

Abstract

The invention provides a site selection method and device of a service site, electronic equipment and a computer readable storage medium, and relates to the technical field of computers. The site selection method of the service site comprises the following steps: acquiring address information of all orders in a target area and business sites to which the orders belong; performing clustering processing on all the orders based on the address information and the business points to obtain a plurality of clustering arrays; obtaining associated data of each clustering array, and determining a site selection demand point of the service site from the clustering centers corresponding to the plurality of clustering arrays according to the associated data; the associated data comprises at least one of the number of waybills, the transportation distance, the waybill collection result and the site selection cost. The site selection of the service site can be accurately recommended, and convenience is provided for effective construction of the service site.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular to a service site location method, a service site location device, an electronic device and a computer readable storage medium. BACKGROUND

[0002] With the increasing emphasis on the logistics supply chain, it is usually necessary to select a suitable service site in the logistics industry to make the efficiency of goods transportation higher and the cost lower.

[0003] However, the current service site selection only selects from the existing sites, which cannot meet the demand for new service sites, and the location effect is poor, which affects the service experience to some extent. SUMMARY

[0004] The purpose of the present disclosure is to provide a service site location method, a service site location device, an electronic device and a computer readable storage medium, thereby at least to some extent, improving the accuracy of service site location and service effect, and reducing the construction cost.

[0005] According to a first aspect of the present disclosure, a service site location method is provided, comprising: obtaining address information of all orders in a target area and business points to which the orders belong; based on the address information and the business points, performing clustering processing on the all orders to obtain a plurality of clustering arrays; obtaining association data of each of the clustering arrays, and determining a service site location demand point from clustering centers corresponding to the plurality of clustering arrays according to the association data; the association data comprises at least one of the following: the number of waybills, the transportation distance, the waybill collection result and the location cost.

[0006] In an example embodiment of the present disclosure, based on the address information and the business points, the clustering processing is performed on the all orders to obtain a plurality of clustering arrays, comprising: determining the area range of each of the business points; for each of the business points, performing clustering processing on the orders within the area range of the business point based on the address information to obtain a clustering array; wherein each of the business points corresponds to at least one clustering array.

[0007] In an example embodiment of the present disclosure, before obtaining the association data of any of the clustering arrays, the method comprises: obtaining an area of interest (AOI) corresponding to the clustering array; determining a predicted site range corresponding to the clustering array according to the area of interest (AOI), so as to obtain the association data based on the predicted site range.

[0008] In an example embodiment of the present disclosure, the associated data of any of the cluster arrays is obtained, including: predicting the number of the shipping orders corresponding to the cluster array according to the number of historical pickup orders in the range of the predicted site; determining the pickup result of the shipping order based on the pickup result of the historical pickup order, the pickup result of the shipping order being used to represent the success rate of the historical pickup order; determining the transportation distance according to the distance between the cluster center corresponding to the cluster array and the sorting center; obtaining the house rental information in the range of the predicted site, and performing cost prediction by using the house rental information, the number of the historical pickup orders and the transportation distance to obtain the site selection cost.

[0009] In an example embodiment of the present disclosure, the prediction of the number of the shipping orders corresponding to the cluster array according to the number of the historical pickup orders in the range of the predicted site includes: performing shipping order quantity prediction according to the number of the historical pickup orders in the range of the predicted site in a preset period to obtain a to-be-corrected shipping order quantity; obtaining the number of AOI faces with merchants in the range of the predicted site and the distance between each merchant; determining a correction factor based on the number of AOI faces and the distance between each merchant; and adjusting the to-be-corrected shipping order quantity by using the correction factor to obtain the number of the shipping orders corresponding to the cluster array.

[0010] In an example embodiment of the present disclosure, the cost prediction by using the house rental information, the number of the historical pickup orders and the transportation distance to obtain the site selection cost includes: predicting a site cost based on the house rental information and the number of the historical pickup orders; predicting a station transmission cost according to the number of the historical pickup orders and the distance; and determining the site selection cost according to the site cost and the station transmission cost.

[0011] In an example embodiment of the present disclosure, the determination of the site selection demand point of the service site from the cluster centers corresponding to the plurality of cluster arrays according to the associated data includes: inputting the associated data into a site selection recommendation model to obtain a recommendation result for each of the cluster arrays, wherein the recommendation result is used to indicate whether the cluster center corresponding to the cluster array is determined as the site selection demand point of the service site.

[0012] In an example embodiment of the present disclosure, the process of obtaining the site selection recommendation model includes: extracting an associated data sample from the site associated data of the historical service site; training a to-be-trained model according to the associated data sample and a corresponding label to obtain the site selection recommendation model.

[0013] In an example embodiment of the present disclosure, after the associated data of each of the cluster arrays is obtained, and the site selection demand point of the service station is determined from the cluster centers corresponding to the plurality of cluster arrays according to the associated data, the method further comprises: after a target service station is configured at the site selection demand point, re-performing the clustering processing according to the address information of all orders in the target region and the business points to which the orders belong at intervals of a preset time to obtain updated cluster arrays; determining updated site selection demand points of the service station from the cluster centers corresponding to the updated cluster arrays according to the associated data of each of the updated cluster arrays; and switching the site selection of the service station in the target region based on the updated site selection demand points.

[0014] In an example embodiment of the present disclosure, the service station is a station providing supply of goods and delivery of goods.

[0015] According to a second aspect of the present disclosure, a site selection device of a service station is provided, comprising: an information acquisition module configured to acquire address information of all orders in a target region and business points to which the orders belong; a clustering processing module configured to perform clustering processing on the all orders based on the address information and the business points to obtain a plurality of cluster arrays; and a site selection determination module configured to obtain associated data of each of the cluster arrays, and determine a site selection demand point of the service station from cluster centers corresponding to the plurality of cluster arrays according to the associated data; the associated data comprising at least one of the following: number of shipments, shipping distance, shipment pickup result, and site selection cost.

[0016] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method described above.

[0017] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, when the computer program is executed by a processor, the method described above is implemented.

[0018] The site selection method of the service station provided by the embodiments of the present disclosure, on the one hand, clusters the orders based on the address information of all the orders in the target region and the business points to which the orders belong, to obtain a plurality of clustering arrays, and then determines the address demand point of the service station from the clustering centers corresponding to the clustering arrays according to the associated data of the clustering arrays, so that the selection range of the site selection demand point is further reduced to the clustering centers of the clustering arrays, and the site selection demand point can cover all the order services in the target region as much as possible, so that the site selection accuracy is high; on the other hand, the site selection demand point of the service station is determined from the clustering centers according to at least one of the number of waybills, the transportation distance, the waybill collection result and the site selection cost of each clustering array, so that the site selection demand point takes into account the cost factor, the distance factor and the waybill service factor, and can comprehensively evaluate whether the clustering center is suitable as the site selection demand point according to the multi-dimensional characteristic factors, and then balances the accuracy and service effect of the site selection of the service station, reduces the construction cost, and improves the user service experience.

[0019] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0020] The drawings incorporated into the specification and forming a part of the specification, show embodiments consistent with the present disclosure, and together with the specification, serve to explain the principles of the present disclosure. It is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained according to these drawings without creative labor for those skilled in the art. In the drawings:

[0021] Figure 1 A diagram schematically showing an application environment of an exemplary embodiment of the present disclosure;

[0022] Figure 2 A flowchart schematically showing a site selection method of a service station used in an exemplary embodiment of the present disclosure;

[0023] Figure 3 A flowchart schematically showing an implementation of obtaining a plurality of clustering arrays in an exemplary embodiment of the present disclosure;

[0024] Figure 4 A flowchart schematically showing a process of obtaining a clustering array corresponding to a certain business point in an exemplary embodiment of the present disclosure;

[0025] Figure 5 A diagram schematically showing data points of a business point and an order in a geographic position coordinate system in an exemplary embodiment of the present disclosure;

[0026] Figure 6A flowchart schematically showing a process of acquiring a predicted site range corresponding to a clustering number in an exemplary embodiment of the present disclosure;

[0027] Figure 7 A flowchart schematically showing an implementation of acquiring associated data of a clustering number in an exemplary embodiment of the present disclosure;

[0028] Figure 8 A flowchart schematically showing a process of acquiring a number of orders in an exemplary embodiment of the present disclosure;

[0029] Figure 9 A flowchart schematically showing a process of acquiring a site selection cost by using house rental information, a number of historical pickup orders, and a transportation distance for cost prediction in an exemplary embodiment of the present disclosure;

[0030] Figure 10 A flowchart schematically showing an implementation of switching a service site in an exemplary embodiment of the present disclosure;

[0031] Figure 11 A flowchart schematically showing a site selection process of a field operating point in an express delivery industry in an exemplary embodiment of the present disclosure;

[0032] Figure 12 A schematic diagram of a site selection device of a service site in an exemplary embodiment of the present disclosure;

[0033] Figure 13 A schematic diagram of an electronic device to which an embodiment of the present disclosure can be applied is shown. DETAILED DESCRIPTION

[0034] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example implementations to those skilled in the art. Features described in the description, structures, or characteristics may be combined in any suitable manner in one or more implementations.

[0035] In addition, the accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure, and together with the description serve to explain the principles of the present disclosure. Like reference numbers refer to like elements throughout the several views.

[0036] The embodiments of the present disclosure relate to artificial intelligence (AI) and machine learning technology, and are designed based on machine learning (ML) in artificial intelligence. Artificial intelligence is a theory, method, technology and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence.

[0037] Artificial intelligence is the study of the design principles and implementation methods of various intelligent machines, enabling machines to have perception, reasoning and decision-making functions. It mainly includes natural language processing technology, computer vision technology, and machine learning or deep learning. With the research and progress of artificial intelligence technology, artificial intelligence has been researched and applied in many fields, such as common smart home, intelligent customer service, virtual assistants, smart speakers, intelligent marketing, unmanned vehicles, autonomous driving, robots, intelligent medical care, etc. It is believed that with the development of technology, artificial intelligence will be applied in more fields and play an increasingly important role.

[0038] The inventors found in the process of implementing the present disclosure that the selection of service sites is currently evaluated among existing sites or the address is selected according to personal experience, but the coverage range of the service site selected in this way is low in rationality, the delivery stability is low, the construction cost of the service site is high, but the ideal benefit cannot be obtained, and to some extent, the service experience for users is affected, resulting in user loss.

[0039] Therefore, the embodiments of the present disclosure provide a service site location method, which clusters orders based on address information of all orders in a target area and business points to which the orders belong, to determine a location demand point from a cluster center based on a clustering result, in combination with at least one of a number of waybills, a transportation distance, a waybill collection result and a location cost, so as to recommend the location demand point, so that the location demand point takes into account cost factors, distance factors and waybill service factors, and thus balances the accuracy of service site location and service effect, reduces construction cost while improving user service experience, and is an effective automated address recommendation method.

[0040] In a possible embodiment, as Figure 1The service site location method provided by the embodiments of the present disclosure can be executed by the terminal device 101, wherein the terminal 101 communicates with the server 102 through a network. The data storage system can store data required to be processed by the server 102. The data storage system can be integrated on the server 102, or placed on a cloud or other network server. The terminal device 101 can obtain address information of all orders in a target area and business points to which the orders belong, and then perform clustering processing on all orders based on the address information and the business points to obtain a plurality of clustering arrays. Finally, the terminal device 101 obtains association data of each clustering array, and determines a location demand point of the service site from clustering centers corresponding to the plurality of clustering arrays according to the association data.

[0041] In this way, in the service site location method provided by the embodiments of the present disclosure, all steps can be executed by the terminal device 101.

[0042] The terminal device 101 in the embodiments of the present disclosure can be a mobile terminal, a fixed terminal or a portable terminal, for example, a mobile phone, a station, a unit, a device, a multimedia computer, a multimedia tablet, an Internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera or camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination thereof, including accessories and peripherals of these devices or any combination thereof.

[0043] Furthermore, the technical solutions provided by the embodiments of the present disclosure can also be executed by the server 102. Correspondingly, in this way executed by the server 102, the server 102 can execute the steps in the technical solutions of the embodiments of the present disclosure in response to a trigger order, wherein the trigger order can be sent by the terminal device 101 used by the user, or triggered locally by the server 102 in response to some automatic events.

[0044] The server 102 in the embodiments of the present disclosure can be a stand-alone physical server, or a server cluster or distributed system composed of multiple physical servers, or a plurality of cloud servers providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms in cloud service technology; the functions of the above-mentioned server 102 can be implemented by one or more cloud servers, and can also be implemented by one or more cloud server clusters, etc.

[0045] In addition, the technical solutions of the embodiments of the present disclosure can also be executed by the terminal device 101 and the server 102 in cooperation. In this way of executing in cooperation, some steps in the technical solutions provided by the embodiments of the present disclosure are executed by the terminal device 101, and the other steps are executed by the server 102. For example, the technical solutions provided by the embodiments of the present disclosure can be executed by the server 102 to acquire address information of all orders in a target area and a business point to which the orders belong, to perform clustering processing on all orders based on the address information and the business point, to obtain a plurality of clustering arrays, and to send the obtained clustering arrays to the terminal device 101, by which the terminal device 101 acquires associated data of each clustering array, and determines a site selection demand point of a service station from clustering centers corresponding to the plurality of clustering arrays according to the associated data.

[0046] It should be noted that in this way of executing in cooperation, the steps executed by the terminal device 101 and the server 102 can be dynamically adjusted according to actual conditions, and the embodiments of the present disclosure do not make special limitations on this.

[0047] Reference Figure 2 As shown in the figure, the site selection method of the service station of the embodiments of the present disclosure can include the following steps S210 to S230:

[0048] In step S210, address information of all orders in a target area and a business point to which the orders belong are acquired.

[0049] In the exemplary embodiments of the present disclosure, the target area is a region to be automatically recommended to build a service station, which can be a region corresponding to at least one administrative region, can be a self-defined region, and the like, and no special limitation is made on this. The range of the target area can be positioned to a geographic position coordinate system through a geographic position coordinate system.

[0050] The address information of the order can be acquired by acquiring the order, and the address information can be acquired by analyzing the order information. The address information is the address of the order, which can also be called the pickup address, and the address information can be displayed on the geographic position coordinate system in a specific identifier, for example, in the form of a small icon on the geographic position coordinate system. The small icon can be in the form of a dot, a square, and the like, and no special limitation is made on this. The geographic position coordinate system can be a platform for positioning the location of the order, for example, it can be a map APP. The target area can be a region to be automatically recommended to build a service station, which is previously circled in the geographic position coordinate system.

[0051] The business point to which the order belongs is determined according to the pickup information of the order, that is, the actual business point to which the pickup personnel belongs. Usually, the business point has a specified area range, and the specified area range of the business point can also be circled in a geographic position coordinate system. For example, the business range of each business point on the map is displayed through the division of an electronic area by an electronic fence system. The division method of the specified area range of the business point is not specially limited in the embodiments of the present disclosure.

[0052] The embodiments of the present disclosure can call an order data platform to obtain the address information of all orders in the target area and the business points to which the orders belong and related information. The order data platform can be a big data platform that stores all order information. The order information can also include order recipient and sender information, recipient address, order number information, etc.

[0053] In step S220, all orders are clustered based on the address information and the business points to obtain a plurality of cluster arrays.

[0054] In the exemplary embodiments of the present disclosure, the orders in the area range of each business point are clustered to obtain a cluster array, with the area range of the business point as the boundary. The clustering of the orders is actually clustering of the orders according to the address information of the orders, for example, clustering of the data points identified based on the address information of the orders on a geographic position coordinate system.

[0055] The clustering can be performed by using a Mean shift clustering algorithm, a k-means clustering algorithm, a density-based clustering method (DBSCAN), etc., which can be selected according to actual needs.

[0056] After clustering, at least one cluster array corresponding to each business point can be obtained, and the selection range of the site selection demand point of the service station can be further narrowed down to the cluster center of each cluster array, so that the site selection demand point can cover all order services in the target area as much as possible, and the site selection accuracy is high.

[0057] In step S230, the associated data of each cluster array is obtained, and the site selection demand point of the service station is determined from the cluster centers corresponding to the plurality of cluster arrays according to the associated data.

[0058] In the exemplary embodiments of the present disclosure, the associated data of each cluster array includes at least one of the number of shipments, the transportation distance, the pickup result of the shipment, and the site selection cost. The associated data of each cluster array can be determined according to the order information and pickup information of the orders in the cluster array, or a predicted station range can be determined according to the address information of the orders in the cluster array, and the associated data can be determined according to the order information and pickup information of the orders in the predicted station range, which will be described below.

[0059] wherein the transportation distance refers to the distance between the cluster center of the cluster array and the sorting center to which the cluster center belongs, the order collection result can be used to represent the success rate of order collection, so as to reflect the order collection stability, and the site selection cost refers to the predicted cost required for constructing the service site at the cluster center of the cluster array, such as including the site cost and the transfer station cost. The site cost is the construction cost required for constructing the service site at the cluster center, such as the house rental cost; the transfer station refers to the transfer process of the goods from the sorting center to the service site, and the transfer station cost refers to the transfer cost required in the transfer process.

[0060] The site selection demand point of the service site will be used to construct the service site, and the service site is a site for providing goods supply and goods distribution, such as a field operating point, a warehouse for storing or managing goods, etc. The field operating point can be a physical store or a service point, which can provide goods supply and distribution services. The goods can be life products, electronic products, mechanical products, etc. The site selection demand point refers to a location with a demand for adding a new service site, so as to provide more efficient logistics services and user experience by adding a new service site.

[0061] After determining the site selection demand point of the service site, the embodiment of the present disclosure recommends the site selection demand point as the location for constructing the service site.

[0062] The site selection method of the service site in the embodiment of the present disclosure clusters all orders in the target region based on the address information of the orders and the operating points to which the orders belong, so as to obtain a plurality of cluster arrays, and then determines the address demand point of the service site from the cluster centers corresponding to the plurality of cluster arrays according to the associated data of the cluster arrays. Through the clustering processing, the selection range of the site selection demand point can be further reduced to the cluster centers of the cluster arrays, so that the site selection demand point can cover all order services in the target region as much as possible, and the site selection accuracy is high. According to at least one of the order quantity, the transportation distance, the order collection result and the site selection cost of each cluster array, the site selection demand point of the service site is determined from the cluster centers, so that the site selection demand point takes into account the cost factor, the distance factor and the order service factor, and can comprehensively evaluate whether the cluster center is suitable as the site selection demand point by comprehensively evaluating the multi-dimensional characteristic factors, so as to balance the accuracy and service effect of the site selection of the service site, reduce the construction cost, and improve the user service experience.

[0063] In an exemplary embodiment, an implementation manner for obtaining a plurality of cluster arrays is provided. As shown in Figure 3 The clustering processing of all orders based on the address information and the operating points to obtain a plurality of cluster arrays can include steps S310 and S320:

[0064] Step S310: Determine the region range of each operating point.

[0065] The area range of the business point can refer to an area covered by a business range of the business point, or a preset range area set around the business point. For example, the area range is an area determined according to an electronic fence of the business point.

[0066] Step S320: For each business point, the orders in the area range of the business point are clustered based on the address information to obtain a cluster array.

[0067] For a certain business point, the orders in the area range of the business point are clustered based on the address information to obtain a cluster array corresponding to the business point. Similarly, other business points obtain their respective cluster arrays in a similar manner. Each business point corresponds to at least one cluster array.

[0068] As Figure 4 , the following takes the Mean shift clustering algorithm as an example to explain the process of obtaining a cluster array corresponding to a certain business point.

[0069] Step S410, the address information can be displayed on the geographic coordinate system with a specific identifier (such as a data point), and similarly, the area corresponding to the business point can also be marked on the geographic coordinate system. As Figure 5 shown, the circular dashed box represents the area range corresponding to the business point, which covers at least one order data point (solid circle). The following describes a certain business point (such as business point A).

[0070] Step S420, randomly select a point in the unclassified data points as the center, and set the radius as L, that is, the maximum order navigation distance that the center can reach, L can be set according to demand.

[0071] Step S430, taking the center as the starting point, the data points of the orders satisfying the maximum order navigation distance L are denoted as set M, and the average value of the vector from the center point to each data point in set M is calculated to obtain an offset vector.

[0072] Step S440, move the center point in the direction of the offset vector, and the moving distance is the modulus of the offset vector to obtain a new center.

[0073] Repeat steps S430 and S440 until the end condition is met, such as the center of the sphere does not change, then at least one cluster array is obtained.

[0074] Further, at least one cluster array corresponding to each business point can be obtained through the above process to obtain the clustering result of all orders based on all cluster arrays.

[0075] The embodiment of the present disclosure can further reduce the selection range of the site selection demand point to the cluster center of each cluster array by clustering the orders according to the address information, so that the site selection demand point can cover all order services in the target area as much as possible.

[0076] In an example embodiment, after determining the cluster array, the site range can also be predicted to make site selection recommendation based on the related data of the predicted site range corresponding to the cluster array for further determining the area of the site selection demand point. As shown in Figure 6 Before obtaining the related data of any cluster array, steps S610 and S620 are further included:

[0077] Step S610: Obtain the area of interest (AOI) corresponding to the cluster array.

[0078] AOI (area of interest), i.e., the area of interest, also known as the information surface, refers to the regional geographic entity in the map data. Since the address information of the orders in the cluster array is displayed on the geographic position coordinate system in a specific identifier (such as a data point), the AOI is further obtained and bound by the address information to obtain the AOI corresponding to the cluster array, and then the area covered by the cluster array can be determined according to the AOI.

[0079] Step S620: Determine the predicted site range corresponding to the cluster array according to the area of interest (AOI), and obtain the related data based on the predicted site range.

[0080] The embodiment of the present disclosure can bind the orders in the cluster array with the AOI to determine the predicted site range corresponding to the cluster array according to the obtained area, that is, if a service site is set at the cluster center corresponding to the cluster array, the predicted site range is the business area covered by the service site.

[0081] By binding the orders in the cluster array with the AOI, the data point form of the orders is expanded to the actual area range, and then the related data of the actual area range is used to predict whether the cluster center of the cluster array can be recommended as the site selection demand point, which enriches the data amount for determining the site selection demand point and improves the accuracy of the site selection demand point.

[0082] In an example embodiment, an implementation manner for obtaining the related data of the cluster array is provided. As shown in Figure 7 Obtaining the related data of any cluster array can include steps S710 to S740:

[0083] Step S710: Predict the number of delivery orders corresponding to the cluster array according to the number of historical pick-up orders in the predicted site range.

[0084] The embodiment of the present disclosure can obtain the historical pickup order quantity in the prediction site range in a preset period, such as the historical pickup order quantity in the past 3 months. Of course, the preset period can also be other periods, such as 2 months, 1 month, etc., and no special limitation is made to this.

[0085] Further, the number of shipments in the prediction site range can be predicted based on the number of historical pickup orders. The prediction processing can be performed based on time series, regression, machine learning, etc., and no special limitation is made to this. The number of shipments after the clustering center of the clustering data is set as the service site is reflected by the number of shipments corresponding to the clustering array.

[0086] In an optional embodiment, the service site should generally cover one or more merchants in one location. The more merchants, the more difficult the actual performance is, and therefore the number of shipments corresponding to the prediction site range can be further corrected to weaken the influence of the distance between merchants on the final recommended site demand point.

[0087] Specifically, as shown in Figure 8 The step S710 can further include steps S810 to S840:

[0088] Step S810: predicting the number of shipments based on the number of historical pickup orders in the prediction site range in a preset period to obtain the number of shipments to be corrected; step S820: obtaining the number of AOI faces with merchants in the prediction site range and the distance between each merchant. The distance between each merchant can be the shortest concatenated distance of merchant coordinates.

[0089] Step S830: determining a correction factor based on the number of AOI faces and the distance between each merchant.

[0090] After obtaining the number of AOI faces and the distance between each merchant, the correction factor is determined according to the number of AOI faces and the distance between each merchant.

[0091] Illustratively, the correction factor can be calculated by the following formula:

[0092]

[0093] where w is the merchant distance weight; n is the number of AOI faces with merchants; j is the correction coefficient, which is 1 / 2, or needs to be taken as the square root of 2, or 1, or remains unchanged, and is adjusted according to demand; Y is the shortest concatenated distance between merchant coordinates; y is the correction coefficient, which is adjusted according to demand, and k is a preset constant.

[0094] Step S840: adjusting the number of waybills to be corrected by using the correction factor to obtain the number of waybills corresponding to the clustering data.

[0095] After obtaining the correction factor and the number of waybills to be corrected, the number of waybills to be corrected is adjusted by using the correction factor to obtain the number of waybills corresponding to the clustering data. For example, the correction factor is multiplied by the number of waybills to be corrected to obtain the number of waybills corresponding to the clustering data.

[0096] Based on this, the influence of the number of waybills on the recommended site selection demand point can be corrected by using the merchant distance weight as the correction factor.

[0097] Step S720: determining a waybill collection result based on the collection results of the historical collection orders, the waybill collection result being used to represent the success rate of the historical collection orders.

[0098] The embodiments of the present disclosure can obtain the historical collection order results in a preset period, and calculate the waybill collection result to reflect the waybill collection success rate of the prediction site range. The preset period can be 1 week, 2 weeks, 1 month, etc., and no special limitation is made thereto.

[0099] The waybill collection success rate can be calculated according to the ratio of the number of successfully collected orders to the number of orders issued, and the mean value of the obtained waybill collection success rate is taken as the waybill collection result.

[0100] The order collection result in the prediction site range calculated by the embodiments of the present disclosure can reflect the collection stability of the prediction site range, and to some extent, reflect whether the service experience of the prediction site range is good.

[0101] In step S730, the transportation distance is determined according to the distance between the clustering center corresponding to the clustering data and the sorting center to which the clustering center belongs.

[0102] The embodiments of the present disclosure can obtain the sorting center to which the clustering center corresponding to the clustering data belongs, to obtain the distance from the clustering center to the sorting center. The distance can be a navigation distance, so as to conform to the transportation line of actual logistics distribution.

[0103] In step S740, the housing rental information of the prediction site range is obtained, and the cost prediction is performed by using the housing rental information, the number of historical collection orders and the transportation distance to obtain the site selection cost.

[0104] The housing rental information includes site area, unit price or rent, etc., and the site selection cost includes site cost and station transfer cost. The site selection cost is used to reflect the fixed cost expenditure after setting the service site.

[0105] For example, Figure 9As shown, the site selection cost can include:

[0106] At step S910, a site cost is predicted based on the house rental information and the number of historical pickup orders.

[0107] The site cost depends on the required site area and the actual expenditure price of the site area, and the required site area depends on the number of orders to be picked up, which is calculated based on the number of historical pickup orders calculated above.

[0108] For example, the site cost can be calculated by the following formula:

[0109]

[0110] wherein a is the site cost; A is the predicted number of historical pickup orders; a is an order conversion area coefficient, which can be adjusted as appropriate, is the estimated area required per order; and χ is the predicted rental price per square meter of the site range.

[0111] At step S920, a transmission station cost is predicted based on the number of historical pickup orders and the distance.

[0112] The transmission station cost depends on the transmission station cost per kilometer, the transportation distance, and the number of times the transmission station is required, and the number of times the transmission station is required depends on the number of orders to be picked up, which is calculated based on the number of historical pickup orders. The transmission station cost per kilometer can include transportation cost and labor cost, which are not specially limited.

[0113] For example, the transmission station cost can be calculated by the following formula:

[0114]

[0115] wherein β is the transmission station cost; ROUNDUP is the rounding up function; A is the predicted number of historical pickup orders; b is an order conversion transmission station number coefficient, which can be adjusted as appropriate, is the number of times the transmission station is required per order; and l is the navigation distance from the sorting center coordinates to the cluster center; is the transmission station cost per kilometer.

[0116] At step S930, a site selection cost is determined based on the site cost and the transmission station cost.

[0117] After obtaining the site cost and the transmission station cost, the site selection cost can be determined based on the site cost and the transmission station cost. Alternatively, the site cost and the transmission station cost can be directly summed to obtain the site selection cost; alternatively, the site cost and the transmission station cost can be weighted and summed according to a pre-set weight to obtain the site selection cost.

[0118] By determining the site selection cost of setting the service station at the cluster center, i.e., the fixed cost expenditure after the service station is stationed, the cost factor in subsequent site selection demand point recommendation can be increased, thereby providing a reference for reducing the cost.

[0119] In an example embodiment, an implementation manner of recommending a site selection demand point according to association data is also provided. Determining the site selection demand point of the service station from the cluster center corresponding to each cluster array according to the association data can include:

[0120] For each cluster array, the association data is input into the site recommendation model to obtain a recommendation result. The recommendation result is used to indicate whether the cluster center corresponding to the cluster array is determined as the site selection demand point of the service station.

[0121] Specifically, after obtaining the association data of each cluster array, for each cluster array, the number of waybills, the transportation distance, the waybill pickup result, and the site selection cost can be input into the address recommendation model to obtain the recommendation result of recommendation and non-recommendation.

[0122] The address recommendation model of the embodiment of the present disclosure can be an effective supervised learning classification method, including but not limited to KNN (K-Nearest Neighbor), CART (Classification And Regression Tree), Bayesian method, SVM (Support Vector Machine), neural network, etc. The machine learning method used in the embodiment of the present disclosure is not specially limited.

[0123] In an example embodiment, the process of obtaining the site recommendation model can include:

[0124] extracting association data samples from the site association data of the historical service station;

[0125] training the to-be-trained model according to the association data samples and the corresponding labels to obtain the site recommendation model.

[0126] The association data samples can be extracted from the site association data of the historical service station, such as the opening data of the historical service station, including the number of waybills, the transportation distance, the waybill pickup result, and the site selection cost, and the corresponding labels of the association data samples are obtained, and then the model is trained according to the association data samples and the labels until the training convergence condition is reached to obtain the site recommendation model.

[0127] Exemplarily, the training data set can be calibrated first, for example, {1|order quantity 1, transportation distance 1, order pickup result 1, site selection cost 1}, {2|order quantity 2, transportation distance 2, order pickup result 2, site selection cost 2}, wherein “1” and “2” are labels corresponding to the associated data samples, used to represent recommendation and non-recommendation, and of course other identifiers can also be used. Secondly, the training data in the training data set is normalized, and finally based on the normalized data, the SVC method is used, the Gaussian kernel (RBF Kernel) is selected to construct the model, and the training is performed to obtain the site selection recommendation model.

[0128] The embodiments of the present disclosure make full use of the site associated data of the historical service sites for model training, and use the trained model to recommend the site selection demand point, comprehensively considers the multi-factor affecting the site selection, and makes the site selection comprehensive multi-dimensional characteristics, so that the accuracy and efficiency requirements of the site selection demand point of the automatic recommendation service site are met, and the cost expenditure of setting the service site is reduced to a certain extent.

[0129] In an exemplary embodiment, in order to further accurately cover the required area by the service site and reduce the cost, an implementation manner of switching the service site is also provided. As shown in Figure 10 After obtaining the associated data of each clustering array and determining the site selection demand point of the service site from the clustering centers corresponding to the plurality of clustering arrays according to the associated data, steps S1010 to S1030 can be further included:

[0130] Step S1010: After the target service station is configured at the site selection demand point, the clustering processing is performed again according to the address information of all orders in the target area and the business points to which the orders belong at a preset interval, and the updated clustering array is obtained.

[0131] This step can refer to the clustering processing process of steps S310 and S320, but it is worth noting that the data based on which the processing process is performed is all the data obtained after the target service station is configured at the site selection demand point.

[0132] Step S1020: According to the associated data of each updated clustering array, the updated site selection demand point of the service site is determined from the clustering centers corresponding to the updated clustering array.

[0133] The process of calculating the associated data of the updated clustering array in this step can refer to steps 710 to S740, and the updated site selection demand point of the service site can be determined from the clustering centers corresponding to the updated clustering array by inputting the associated data corresponding to the updated clustering array into the site selection recommendation model to obtain the recommendation result, and then determining the updated site selection demand point according to the recommendation result. For the same or similar content as the above steps, it is not described here.

[0134] Step S1030: Switch the location of service sites within the target area based on the updated location requirements.

[0135] After obtaining the updated site selection requirements, if the updated site selection requirements are different from the existing service sites, the site selection of the service sites in the target area can be switched to the updated site selection requirements, so that the set service sites can provide better order services while reducing operating costs.

[0136] In some possible embodiments, the site selection update operation can be performed according to a preset cycle, such as every six months or every year, which can be set according to actual needs to improve the accuracy of service sites.

[0137] like Figure 11 The diagram shows the site selection process for on-site business points in the express delivery industry. The following description uses the B-end pickup business in the application scenario of the express delivery industry to illustrate the site selection method for service stations in this embodiment.

[0138] In step S1110, the waybill information and waybill collection information of all B-end orders in the target area are obtained, so as to extract the address information from the waybill information and extract the business point to which the order belongs from the waybill collection information.

[0139] This involves parsing B-end orders to a geographic coordinate system, such as a map, to obtain the data points corresponding to each order. Then, based on the defined geographical area of ​​each business location (e.g., an electronic fence), for each business location, orders within that area are clustered based on address information to obtain a cluster array.

[0140] In step S1120, the interest surface (AOI) corresponding to the cluster array is obtained, and the predicted site range corresponding to the cluster array is determined based on the interest surface (AOI) so as to obtain associated data based on the predicted site range.

[0141] The acquisition of related data includes predicting the number of waybills corresponding to the cluster array based on the number of historical pickup orders within the predicted site area, determining the waybill pickup result based on the pickup result of historical pickup orders, determining the transportation distance based on the distance between the cluster center corresponding to the cluster array and the sorting center, and using housing rental information, the number of historical pickup orders and transportation distance to predict costs and obtain site selection costs.

[0142] In step S1130, the location requirements of the on-site business points are determined from the cluster centers corresponding to multiple cluster arrays based on the associated data.

[0143] Specifically, for each cluster array, the associated data is input into the site selection recommendation model to obtain the recommendation result, and the cluster center corresponding to the cluster data is determined as the on-site business point based on the recommendation result.

[0144] Nearly 100 million B-end collection orders are concentrated collection every year, and the current still depends on the courier to undertake. In the case of the courier undertaking distribution and collection (C-end collection + B-end collection), the user experience is poor. If reasonable orders are collected through the on-site mode, the user experience will be effectively improved, and the cost expenditure will be further reduced. Therefore, accurately and low-cost setting of on-site business points has practical application value for solving the above problems.

[0145] It should be noted that the specific content involved in each of the above steps has been described in detail in the above method embodiments, which will not be repeated here.

[0146] The service site location method provided by the embodiment of the present disclosure, on the one hand, clusters the orders based on the address information of all orders in the target area and the business points to which the orders belong, to obtain a plurality of clustering arrays, and then determines the address demand point of the service site from the clustering centers corresponding to the clustering arrays according to the association data of the clustering arrays, so that the selection range of the location demand point is further narrowed to the clustering centers of the clustering arrays, and the location demand point can cover all order services in the target area as much as possible, so that the location accuracy is high; on the other hand, at least one of the number of waybills, the transportation distance, the order collection result and the location cost of each clustering array is determined from the clustering centers to determine the location demand point of the service site, so that the location demand point takes into account the cost factor, the distance factor and the waybill service factor, and can comprehensively evaluate whether the clustering center is suitable as a location demand point according to the multi-dimensional characteristic factors, and then balance the accuracy and service effect of the service site location, reduce the construction cost, and improve the user service experience.

[0147] It should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not for limiting purposes. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0148] Further, with reference to Figure 12 In the exemplary implementation of the present disclosure, a service site location device 1200 is provided, which includes an information acquisition module 1210, a clustering processing module 1220 and a location determination module 1230. Wherein:

[0149] The information acquisition module 1210 is configured to acquire the address information of all orders in the target area and the business points to which the orders belong;

[0150] The clustering processing module 1220 is configured to cluster the all orders based on the address information and the business points, to obtain a plurality of clustering arrays;

[0151] The site determination module 1230 is configured to obtain association data of each of the cluster arrays, and determine a site selection demand point of a service station from cluster centers corresponding to the cluster arrays according to the association data. The association data includes at least one of the number of orders, the transportation distance, the order pickup result, and the site selection cost. In an example embodiment, the first information processing module 1010 is configured to perform: obtaining voice call content of the user; converting the voice call content into call text; extracting at least two rounds of conversations from the call text to obtain the conversation information.

[0152] In an example embodiment, the clustering processing module 1220 is configured to perform: determining a regional range of each of the business points; for each of the business points, clustering orders within the regional range of the business point based on address information to obtain a cluster array; and wherein each of the business points corresponds to at least one cluster array.

[0153] In an example embodiment, the site determination module 1230 is further configured to perform: obtaining an area of interest (AOI) corresponding to the cluster array; determining a predicted site range corresponding to the cluster array according to the AOI, so as to obtain the association data based on the predicted site range.

[0154] In an example embodiment, the site determination module 1230 is configured to perform: predicting the number of orders corresponding to the cluster array according to a number of historical pickup orders within the predicted site range; determining the order pickup result based on pickup results of the historical pickup orders, the order pickup result being used to represent a success rate of the historical pickup orders; determining the transportation distance according to a distance between a cluster center corresponding to the cluster array and a sorting center; obtaining house rental information of the predicted site range, and performing cost prediction by using the house rental information, the number of historical pickup orders, and the transportation distance to obtain the site selection cost.

[0155] In an example embodiment, the site determination module 1230 is configured to perform: predicting the number of orders according to a number of historical pickup orders within the predicted site range in a preset period to obtain a to-be-corrected number of orders; obtaining an AOI face number of the predicted site range and distances between merchants; determining a correction factor based on the AOI face number and the distances between the merchants; and adjusting the to-be-corrected number of orders by using the correction factor to obtain the number of orders corresponding to the cluster array.

[0156] In an example embodiment, the site selection determining module 1230 is configured to perform: predicting a site cost based on the house rental information and the number of historical pickup orders; predicting a station cost according to the number of historical pickup orders and the distance; and determining the site selection cost according to the site cost and the station cost.

[0157] In an example embodiment, the site selection determining module 1230 is configured to perform: inputting the associated data into a site selection recommendation model to obtain a recommendation result for each of the cluster arrays; and wherein the recommendation result is used to indicate whether to determine the cluster center corresponding to the cluster array as a site selection demand point of a service station.

[0158] In an example embodiment, the device further comprises a model training module configured to perform: extracting associated data samples from site associated data of historical service stations; and training a to-be-trained model according to the associated data samples and corresponding labels to obtain the site selection recommendation model.

[0159] In an example embodiment, the device further comprises an address switching module configured to perform: after obtaining the associated data of each of the cluster arrays and determining the site selection demand point of a service station from the cluster centers corresponding to the cluster arrays according to the associated data, configuring a target service station at the site selection demand point, and then re-performing the clustering processing according to the address information of all orders in the target region and the business points to which the orders belong at a preset interval to obtain updated cluster arrays; determining updated site selection demand points of service stations from the cluster centers corresponding to the updated cluster arrays according to the associated data of each of the updated cluster arrays; and switching the site selection of the service stations in the target region based on the updated site selection demand points.

[0160] In an example embodiment, the service station is a station that provides goods supply and goods distribution.

[0161] The specific details of each module in the above device have been described in detail in the method part of the embodiments, and the undisclosed details can be referred to the embodiment content of the method part, and thus will not be described again.

[0162] Those skilled in the art can understand that each aspect of the present disclosure can be implemented as a system, a method or a program product. Therefore, each aspect of the present disclosure can be embodied as a whole hardware embodiment, a whole software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" herein.

[0163] In an example embodiment of the present disclosure, an electronic device for the above method is also provided, which can be the above image device or server. Generally, the electronic device at least includes a processor and a memory, the memory is used to store executable instructions of the processor, and the processor is configured to execute the above method by executing the executable instructions.

[0164] The structure of the electronic device in the embodiments of the present disclosure will be described below by way of example with reference to a mobile terminal 1300 in Figure 13 Those skilled in the art should understand that, in addition to the components specially used for mobile purposes, Figure 13 the structure in the mobile terminal 1300 can also be applied to devices of a fixed type. In other embodiments, the mobile terminal 1300 can include more or fewer components than shown, or combine certain components, or split certain components, or different arrangement of components. The components shown can be implemented in hardware, software, or a combination of software and hardware. The interface connection relationship between components is only schematically shown and does not constitute a limitation on the structure of the mobile terminal 1300. In other embodiments, the mobile terminal can also use different interface connection methods, or a combination of multiple interface connection methods. Figure 13

[0165] As shown in Figure 13 , the mobile terminal 1300 can specifically include a processor 1301, a memory 1302, a bus 1303, a mobile communication module 1304, an antenna 1, a wireless communication module 1305, an antenna 2, a display screen 1306, a camera module 1307, an audio module 1308, a power module 1309, and a sensor module 1310.

[0166] The processor 1301 can include one or more processing units, for example: the processor 1301 can include an AP (Application Processor, application processor), a modem processor, a GPU (Graphics Processing Unit, graphics processing unit), an ISP (Image Signal Processor, image signal processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor, digital signal processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit, neural network processor), etc.

[0167] ​An encoder can encode (i.e., compress) an image or video to reduce data size for storage or transmission. A decoder can decode (i.e., decompress) encoded data of an image or video to restore the image or video data. The mobile terminal 1300 can support one or more encoders and decoders, such as JPEG (Joint Photographic Experts Group), PNG (Portable Network Graphics), BMP (Bitmap), and the like for image formats, and MPEG (Moving Picture Experts Group) 1, MPEG 10, H.1063, H.1064, HEVC (High Efficiency Video Coding), and the like for video formats.

[0168] The processor 1301 can form a connection with the memory 1302 or other components through the bus 1303.

[0169] The memory 1302 can be used to store computer-executable program codes, which include instructions. The processor 1301 executes various functional applications and data processing of the mobile terminal 1300 by running the instructions stored in the memory 1302. The memory 1302 can also store application data, such as storing image, video, and the like.

[0170] The communication function of the mobile terminal 1300 can be implemented through the mobile communication module 1304, the antenna 1, the wireless communication module 1305, the antenna 2, the modem processor, and the baseband processor, and the like. The antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals. The mobile communication module 1304 can provide 3G, 4G, 5G, and the like mobile communication solutions applied on the mobile terminal 1300. The wireless communication module 1305 can provide wireless local area network, Bluetooth, near field communication, and the like wireless communication solutions applied on the mobile terminal 1300.

[0171] The display screen 1306 is used to realize display functions, such as displaying user interfaces, images, videos, and the like, and displaying abnormal prompt information. The camera module 1307 is used to realize a shooting function, such as shooting images, videos, and the like, to collect scene images. The audio module 1308 is used to realize audio functions, such as playing audio, collecting voice, and the like. The power module 1309 is used to realize power management functions, such as charging the battery, supplying power to the device, monitoring the battery state, and the like. The sensor module 1310 can include one or more sensors to realize corresponding sensing and detection functions.

[0172] In addition, the exemplary embodiments of the present disclosure also provide a computer readable storage medium, which stores a program product capable of implementing the method described above. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program codes for causing the terminal device to perform the steps described in the "Exemplary Method" section above according to various exemplary embodiments of the present disclosure when the program product is run on the terminal device.

[0173] It should be noted that the computer readable medium shown in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0174] In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program codes. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit the program for use by or in conjunction with an instruction execution system, device or apparatus. The program codes contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0175] Furthermore, the program code can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0176] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A method for selecting the location of a service site, characterized in that, The method includes: Obtain the address information and the branch office to which the order belongs for all orders within the target area; Based on the address information and the business location, all orders are clustered to obtain multiple cluster arrays; Obtain the association data of each of the clustering arrays, and determine the site selection requirement points of the service station from the cluster centers corresponding to the multiple clustering arrays based on the association data; the association data includes at least one of the following: number of waybills, transportation distance, waybill collection results, and site selection cost.

2. The method according to claim 1, characterized in that, Based on the address information and the business location, all orders are clustered to obtain multiple cluster arrays, including: Determine the geographical scope of each of the aforementioned business locations; For each of the aforementioned business locations, the orders within the area of ​​the business location are clustered based on address information to obtain a cluster array; Each of the aforementioned business locations corresponds to at least one clustering array.

3. The method according to claim 1 or 2, characterized in that, Before retrieving the associated data of any of the clustered arrays, the method includes: Obtain the interest surface (AOI) corresponding to the clustering array; The predicted site range corresponding to the cluster array is determined based on the interest surface (AOI), and the associated data is obtained based on the predicted site range.

4. The method according to claim 3, characterized in that, Obtain the associated data of any of the clustering arrays, including: Based on the number of historical pickup orders within the predicted site range, predict the number of waybills corresponding to the cluster array; Based on the pickup results of the historical pickup orders, the waybill pickup result is determined, and the waybill pickup result is used to characterize the success rate of the historical pickup orders; The transportation distance is determined based on the distance between the cluster center corresponding to the cluster array and the sorting center to which it belongs; Obtain housing rental information within the predicted site area, and use the housing rental information, the number of historical pickup orders, and the transportation distance to predict costs and obtain the site selection cost.

5. The method according to claim 4, characterized in that, The step of predicting the number of waybills corresponding to the cluster array based on the number of historical pickup orders within the predicted site range includes: Based on the number of historical pickup orders within the predicted site range within the preset period, the number of waybills is predicted to be corrected. Obtain the number of AOI faces with merchants within the predicted site range and the distance between each merchant; Based on the number of AOI faces and the distance between each merchant, a correction factor is determined; The number of waybills to be corrected is adjusted using the correction factor to obtain the number of waybills corresponding to the cluster array.

6. The method according to claim 4, characterized in that, The method of using the housing rental information, the number of historical pickup orders, and the transportation distance to predict costs and obtain the site selection cost includes: Based on the housing rental information and the number of historical collection orders, the site cost is predicted; Based on the number of historically collected orders and the distance, predict the transmission station cost; The site selection cost is determined based on the site cost and the transmission station cost.

7. The method according to claim 1 or 2, characterized in that, The step of determining the service site location requirement points from the cluster centers corresponding to the multiple clustering arrays based on the associated data includes: For each of the clustered arrays, the associated data is input into the location recommendation model to obtain the recommendation result; The recommendation result is used to indicate whether to determine the cluster center corresponding to the cluster array as the location requirement point for the service site.

8. The method according to claim 7, characterized in that, The process of obtaining the location recommendation model includes: Extract related data samples from the site association data of historical service sites; The location recommendation model is obtained by training the model to be trained based on the associated data samples and corresponding labels.

9. The method according to claim 1 or 2, characterized in that, After obtaining the association data of each of the clustering arrays and determining the location requirement points of the service site from the cluster centers corresponding to the plurality of clustering arrays based on the association data, the method further includes: After configuring the target service station at the location requirement point, the clustering process is re-performed at preset intervals based on the address information of all orders in the target area and the business point to which the orders belong, to obtain an updated cluster array; Based on the associated data of each updated cluster array, the update site selection requirement point of the service site is determined from the cluster center corresponding to the updated cluster array; Based on the updated site selection requirements, the site selection of service stations within the target area is switched.

10. The method according to claim 1 or 2, characterized in that, The service station is a station that provides the supply and delivery of goods.

11. A site selection device for a service station, characterized in that, The device includes: The information acquisition module is used to acquire the address information and the business location to which the order belongs for all orders within the target area; The clustering processing module is used to cluster all orders based on the address information and the business location to obtain multiple cluster arrays; The site selection determination module is used to obtain the association data of each of the cluster arrays, and determine the site selection requirement point of the service station from the cluster centers corresponding to the multiple cluster arrays based on the association data; the association data includes at least one of the following: number of waybills, transportation distance, waybill collection results, and site selection cost.

12. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 10 by executing the executable instructions.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 10.

Images