A method and device for predicting delivery timeliness

Abstract

The present application discloses a method and device for predicting delivery time. The present application obtains user order information, wherein the user order information includes destination information, determines the order path based on the destination information, uses the multi-quantile method to determine the predicted delivery time of each section node in the order path, and adds the delivery time of each section node to obtain the predicted delivery time corresponding to the user order information. The method provided in the embodiment of the present application can confirm the order path through user order information, that is, the path of the goods from the merchant warehouse to the destination specified by the user, use the quantile to determine the predicted delivery time of each section node in the order path, implement the predicted delivery time of each section, and then add the predicted delivery time of each section node to obtain the predicted delivery time of the entire user order, thereby improving the accuracy of the predicted delivery time.

Description

Technical Field

[0001] The present application relates to the field of physical technology, and in particular to a method and device for predicting delivery timeliness. Background Art

[0002] With the development of Internet technology, more and more people choose to shop online, and the express delivery and logistics industries have developed rapidly. Merchants send goods to all parts of the country through express delivery and logistics. In order to let users know when their goods will arrive in their hands, there will be an estimated arrival time for the goods when the user submits a purchase order.

[0003] However, in the traditional logistics field, the estimated delivery time of goods is usually determined by merchants configuring loose time limits on their own and then correcting the time limits after the track is generated. In addition, the delivery time is based on the statement that the goods will be shipped within 48 hours, which makes the estimated delivery time of the entire product not accurate enough. How to obtain the estimated delivery time of goods more accurately is a problem that people are concerned about. Summary of the invention

[0004] In view of this, the present application provides a method and device for predicting delivery timeliness to improve the accuracy of estimated delivery timeliness.

[0005] In order to achieve the above objectives, the proposed solution is as follows:

[0006] A method for predicting delivery time, comprising:

[0007] Acquire user order information, wherein the user order information includes destination information;

[0008] determining an order path based on the destination information;

[0009] Obtain the historical delivery time efficiency data of each node in the order path within the preset time period;

[0010] For each road section node, the corresponding target quantile is determined using the historical delivery time efficiency data of the road section node and the preset standard delivery time efficiency;

[0011] Determine the predicted delivery time of the node of the road section in the order path by using the target quantile;

[0012] The predicted delivery time of each road section node is added together to obtain the predicted delivery time of the user order information.

[0013] Optionally, the historical delivery time efficiency data includes delivery time efficiency of multiple orders, and for each road section node, determining a corresponding target quantile using the historical delivery time efficiency data of the road section node and a preset standard delivery time efficiency includes:

[0014] Dividing the historical delivery time efficiency data into multiple order delivery time efficiency collections according to cycle time;

[0015] Determine the on-time rate, delay rate and early rate of the order delivery time collection according to the preset standard delivery time collection corresponding to the order delivery time collection;

[0016] The preset standard delivery time is determined according to the delivery time dimension of the corresponding road section node;

[0017] Based on the on-time rate, delay rate and early rate of the order delivery time collection, according to the set optimal standard delivery time selection rule, select the target order delivery time collection corresponding to the optimal standard delivery time;

[0018] Calculate the quantile of the standard delivery time described in the target order delivery time collection to obtain the target quantile.

[0019] Optionally, the determining the predicted delivery time of the section node in the order path by using the target quantile includes:

[0020] Obtain the historical delivery time efficiency data of the road section node in the previous historical period closest to the time of the user order information as the target historical delivery time efficiency data;

[0021] The predicted delivery time efficiency of the road section node is determined based on the target quantile and the target historical delivery time efficiency data.

[0022] Optionally, based on the on-time rate, delay rate and early rate of the order delivery time collection, according to the set optimal standard delivery time selection rule, selecting the target order delivery time collection corresponding to the optimal standard delivery time includes:

[0023] Calculate a first ratio of the on-time rate to the delayed rate, and a second ratio of the on-time rate to the early rate for each of the order delivery time collections;

[0024] From each of the order delivery time collections, select the order delivery time collection corresponding to the largest first ratio and second ratio as the target order delivery time collection.

[0025] Optionally, the target order delivery time collection is one, and the calculating the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile includes:

[0026] The quantile corresponding to the standard delivery time in the target order delivery time collection is calculated as the target quantile.

[0027] Optionally, the target order delivery time collection is more than two, and the calculating the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile includes:

[0028] Calculate the quantile of the corresponding standard delivery time in the delivery time set of each target order;

[0029] Determine the target quantile based on the quantile of the delivery time set of each target order.

[0030] Optionally, the preset time period includes a first time period or a second time period, the first time period is greater than the second time period, and the acquiring of historical delivery time efficiency data within the preset time period of each section node in the order path includes:

[0031] Determine whether a special event occurs at the road section node, wherein the special event includes natural disasters, man-made disasters and force majeure;

[0032] If not, obtain the historical delivery time efficiency data of each node in the order path within the first time period;

[0033] If yes, then obtain the historical delivery time efficiency data of each section node in the order path within the second time period.

[0034] Optionally, also include:

[0035] The predicted delivery time and the obtained predicted delivery time of each road section node are sent to the client for display by the client.

[0036] Optionally, the section nodes include supplier warehouses, self-operated warehouses, distribution nodes and transport sections.

[0037] A device for predicting delivery timeliness, comprising:

[0038] An order acquisition unit, used to acquire user order information, wherein the user order information includes destination information;

[0039] a path determination unit, configured to determine an order path based on the destination information;

[0040] A historical data acquisition unit, used to acquire historical delivery time efficiency data within a preset time period of each section node in the order path;

[0041] A quantile determination unit, for determining, for each road section node, a corresponding target quantile using the historical delivery time efficiency data of the road section node and a preset standard delivery time efficiency;

[0042] A delivery time efficiency prediction unit, used to determine the predicted delivery time efficiency of the road section node in the order path by using the target quantile;

[0043] An order time efficiency prediction unit is used to add the predicted delivery time efficiency of each road section node to obtain the predicted delivery time efficiency of the user order information.

[0044] It can be seen from the above technical solutions that the method for predicting delivery time provided by the embodiment of the present application obtains user order information, the user order information includes destination information, determines the order path based on the destination information, uses the multi-quantile method to determine the predicted delivery time of each section node in the order path, and adds the delivery time of each section node to obtain the predicted delivery time corresponding to the user order information. The method provided by the embodiment of the present application can confirm the order path through user order information, that is, the path of the goods from the merchant warehouse to the destination specified by the user, and use quantiles to determine the predicted delivery time of each section node in the order path, so that the delivery time of each section can be predicted, making the predicted delivery time of each section node more compact, and then adding the predicted delivery time of each section node to obtain the predicted delivery time of the entire user order, thereby improving the accuracy of the predicted delivery time. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0046] Figure 1 A system architecture diagram for implementing the prediction of delivery time provided in an embodiment of the present application;

[0047] Figure 2 A flow chart of a method for predicting delivery timeliness provided in an embodiment of the present application;

[0048] Figure 3 A flow chart for determining a target quantile provided in an embodiment of the present application;

[0049] Figure 4 A scenario flow chart of an embodiment provided for an embodiment of the present application;

[0050] Figure 5 A schematic diagram of the structure of a device for predicting delivery timeliness provided in an embodiment of the present application;

[0051] Figure 6 This is a hardware structure block diagram of a device for predicting delivery timeliness disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] In order to make the technical solution of this application clearer, Figure 1 An optional system architecture for implementing the prediction of delivery time provided in the embodiment of the present application is as follows: Figure 1 As shown, the system architecture may include: a client 10 and a server 20.

[0054] The server 20 may be a service device disposed on the network side. The server 20 and the client 10 exchange data through the network. The server 20 may be implemented as a single server or as a server cluster composed of multiple servers. The server 20 may be a server provided by a supplier of predicted delivery time. In the embodiment of the present application, the server 20 can obtain the user's order path, obtain the matching predicted delivery time based on the order path, and send the predicted delivery time to the client.

[0055] The client 10 may be a terminal device such as a mobile phone, a computer, etc. The client 10 can support the sending of user order information and the display of predicted delivery time, so that the user can view the predicted delivery time and operate the user order information.

[0056] The embodiment of the present application can receive the user order information sent by the client 10 through the server 20, and determine the order path based on the destination information in the user order information, match the historical delivery time efficiency data of each section node in the corresponding order path within a preset time period in the database, and use quantiles based on these historical delivery time efficiency data to determine the predicted delivery time efficiency of the user order, thereby removing redundant predicted time efficiency, making the delivery time efficiency between each section node more compact, and achieving the purpose of improving the accuracy of the predicted delivery time efficiency.

[0057] based on Figure 1 The system architecture shown, Figure 2 A flow chart of a method for predicting delivery time provided by an embodiment of the present application is shown. The following describes a method for predicting delivery time of the present solution from the perspective of the server 20. Figure 2 , the process may include:

[0058] Step S100: Obtain user order information, wherein the user order information includes destination information.

[0059] Specifically, the server 20 receives the user order information sent by the client 10. The user order information may include destination information, and the destination information here may include a destination specified by the user.

[0060] Step S110: determine the order path based on the destination information.

[0061] Specifically, the server 20 may determine the shipping warehouse closest to the destination based on the destination information, thereby determining the order path from the shipping warehouse to the destination.

[0062] Step S120: Obtain historical delivery time efficiency data within a preset time period for each section node in the order path.

[0063] Specifically, the server 20 may split the order path into various road section nodes. Within a preset time, the historical delivery time efficiency data of each road section node may be different. The server 20 may obtain the historical delivery time efficiency data of each road section node from the database.

[0064] Step S130: for each road section node, determine the corresponding target quantile using the historical delivery time efficiency data of the road section node and the preset standard delivery time efficiency.

[0065] Specifically, there are actual delivery times of multiple user orders in the historical delivery time data. In each road section node, a standard delivery time can be pre-set as the standard for delivery time, and the actual delivery times of these multiple user orders are sorted from small to large. Based on the preset standard delivery time, the target percentile corresponding to the road section node can be determined.

[0066] Step S140: using the target quantile to determine the predicted delivery time of the road section node in the order path.

[0067] Specifically, the predicted delivery time of the road section node is the time that the server 20 predicts the user order will take at the road section node, and the predicted delivery time of the road section node can be determined based on the determined target quantile.

[0068] Step S150: Add the predicted delivery time of each road section node to obtain the predicted delivery time of the user order information.

[0069] Specifically, the predicted delivery time of each road section node may be different according to the actual situation of each road section node. The server 20 can obtain the predicted delivery time of the user order information by adding the predicted delivery time of each road section node.

[0070] The predicted delivery time scheme provided in this embodiment can confirm the order path through user order information, that is, the path of the goods from the merchant warehouse to the user's specified destination, and use quantiles to determine the predicted delivery time of each section node in the order path, and implement the predicted delivery time of each section, so that the delivery time between each section node is more compact, and then the predicted delivery time of each section node is added together to obtain the predicted delivery time of the entire user order, thereby improving the accuracy of the predicted delivery time.

[0071] Furthermore, since the goods in the embodiment of the present application have different order paths and delivery time limits for the entire process from shipment from the warehouse to delivery to the destination specified by the user, in order to facilitate the calculation of the delivery time limits of different order paths, the order path can be split into different road section nodes, and the delivery time limits corresponding to different road section nodes can be different, and the delivery time limits of the same road section node can be regarded as the same within the same time period. Therefore, in the order path of the embodiment of the present application, each road section node can be divided into a supplier warehouse, a self-operated warehouse, a distribution node, and a transportation section.

[0072] In some embodiments of the present application, the historical delivery time efficiency data may include the delivery time efficiency of multiple orders. The following is an introduction to the above step S130, for each road segment node, using the historical delivery time efficiency data of the road segment node and the preset standard delivery time efficiency to determine the corresponding target quantile. This process can refer to Figure 3 , the specific process is as follows:

[0073] Step S131: Divide the historical delivery time efficiency data into multiple order delivery time efficiency collections according to cycle time.

[0074] Specifically, the cycle time may be one day or other time units, and the historical delivery time efficiency data may be actual delivery time efficiency data of one week or one month. The server 20 may divide the historical delivery time efficiency data into multiple order delivery time efficiency collections according to the cycle time. An order delivery time efficiency collection may include the actual delivery time efficiency of all orders in one day or other time units.

[0075] Step S132: Determine the on-time rate, delay rate and early rate of the order delivery time collection.

[0076] Among them, according to the preset standard delivery time corresponding to the order delivery time collection, the on-time rate, delay rate and early rate of the order delivery time collection are determined.

[0077] The preset standard delivery time is determined according to the delivery time dimension of the corresponding road section node.

[0078] Specifically, each standard delivery time corresponding to the order delivery time collection can be pre-set according to the delivery time dimension of the corresponding road section node. The delivery time dimension may include the shipping city, the first-level delivery address, the second-level delivery address, the third-level delivery address, the delivery time of the carrier, and the order time period, and the time limit within the shipping warehouse. Necessary time dimensions may also be added according to different internal business models. The standard delivery time corresponding to different delivery time dimensions may be different. The standard delivery time can be used to compare the delivery time of multiple orders in the order delivery time collection to determine the punctuality rate, delay rate and early delivery rate of the order delivery time collection.

[0079] Step S133: According to the set optimal standard delivery time selection rule, a target order delivery time collection corresponding to the optimal standard delivery time is selected.

[0080] Among them, based on the punctuality rate, delay rate and early rate of the order delivery time collection, according to the set optimal standard delivery time selection rule, the target order delivery time collection corresponding to the optimal standard delivery time is selected.

[0081] Specifically, in order to achieve the most reasonable standard delivery time in the selected road section node, the optimal standard delivery time selection rule can be set according to the user's needs. The specific selection process of this step is as follows:

[0082] Step 1331, calculate a first ratio of the on-time rate to the delay rate, and a second ratio of the on-time rate to the early rate for each of the order delivery time sets.

[0083] Specifically, the punctuality rate, delay rate and advance rate of different order delivery time collections may be the same. In order to obtain the standard delivery time that minimizes the difference between the actual delivery time and the expected delivery time, the first ratio of the punctuality rate to the delay rate and the second ratio of the punctuality rate to the advance rate of the order delivery time collection can be calculated respectively by ratio.

[0084] Step 1332: From each of the order delivery time sets, select the order delivery time set corresponding to the largest first ratio and second ratio as the target order delivery time set.

[0085] Specifically, in order to minimize the error between the actual delivery time and the expected delivery time, the order delivery time limit collection corresponding to the largest first ratio and second ratio can be selected as the target order delivery time limit collection. Because the punctuality rate, delay rate and early rate of different order delivery time limit collections may be the same, there can be one or more target order delivery time limit collections selected.

[0086] Step S134: Calculate the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile.

[0087] Specifically, the quantile of the target order delivery time collection can be determined according to the standard delivery time corresponding to the selected target order delivery time collection. Since there can be one or more target order delivery time collections, multiple target order delivery time collections can be discussed in different situations:

[0088] When the target order delivery time collection is one, the process of calculating the quantile of the standard delivery time in the target order delivery time collection in step S134 to obtain the target quantile may be as follows:

[0089] The quantile corresponding to the standard delivery time in the target order delivery time collection is calculated as the target quantile.

[0090] Specifically, the quantile corresponding to the standard delivery time in the target order delivery time collection is used as the target quantile.

[0091] When there are more than two target order delivery time collections, the process of calculating the quantile of the standard delivery time in the target order delivery time collection in step S134 to obtain the target quantile may be as follows:

[0092] Step S1341, calculate the quantile of the corresponding standard delivery time in each target order delivery time set.

[0093] Specifically, the quantile corresponding to the standard delivery time in the target order delivery time collection of each target order delivery time collection is calculated respectively to obtain a plurality of quantiles.

[0094] Step S1342: Determine the target quantile according to the quantiles of the delivery time efficiency set of each target order.

[0095] Specifically, the quantiles of the multiple target order delivery time sets can be averaged by calculating the average value, and the average value can be used as the target quantile. According to needs, the maximum or minimum quantile can be selected from the quantiles of each target order delivery time set as the target quantile.

[0096] The above steps comprehensively consider the collection of one or more different target order delivery time effects, and finally determine a target quantile as the representative quantile of the road section node, so as to use the target quantile to determine the predicted delivery time effect of the next order.

[0097] Since each section node is mainly responsible for the transportation of goods, there is uncertainty. Some sudden special events such as natural disasters and man-made disasters will cause the actual delivery time to be prolonged, resulting in drastic fluctuations in the historical delivery time data. In order to reduce the impact of such data fluctuations on the predicted delivery time, the embodiment of the present application introduces the above step S120, an optional implementation process for obtaining the historical delivery time data within a preset time period of each section node in the order path, which may specifically include:

[0098] Step S121, determine whether a special event occurs at the road section node, the special event includes natural disasters, man-made disasters and force majeure, if not, execute step S122, if a special event occurs, execute step S123.

[0099] Specifically, when a special event occurs at the road section node, the technician can promptly report the relevant information of the special event in the system, and explain the specific reasons that will cause the actual delivery time to be prolonged. When the server 20 does not usually receive the relevant information of the special event, the operation of step S122 can be executed. When the server 20 receives the relevant information of the special event reported by the technician, the operation of step S123 can be executed.

[0100] Step S122: Obtain historical delivery time efficiency data for each section node in the order path within the first time period.

[0101] Specifically, the first time period may be set to 60 days. When the server 20 does not receive relevant information about a special event, the historical delivery timeliness data of each section node in the order path may be obtained in a cycle of 60 days.

[0102] Step S123: Obtain historical delivery time efficiency data for each section node in the order path within the second time period.

[0103] Specifically, the second time period can be set to 7 days. When the server 20 receives relevant information about a special event, the historical delivery time efficiency data of each section node in the order path can be obtained in a cycle of 7 days, and the 7 days include the time period when the special event occurs.

[0104] The first time period is greater than the second time period.

[0105] In order to eliminate the fluctuations in historical delivery time data caused by special events and consider the possible impact of special events on the delivery time of orders in the surrounding time period, the above steps give priority to selecting historical delivery time data in the shorter second time period as the basis for predicting delivery time.

[0106] In some embodiments of the present application, the process of determining the predicted delivery time of the road segment node in the order path by using the target quantile in step S140 is introduced below. The process may specifically include:

[0107] Step S141, obtaining the historical delivery time efficiency data of the road section node in the previous historical period closest to the time of the user order information as the target historical delivery time efficiency data.

[0108] Specifically, after determining the target percentile, in order to reduce the probability of a large deviation in the predicted delivery time due to the occurrence of special events, the historical delivery time data corresponding to the most recent historical cycle time that is closest to the time of the user order information may be preferentially selected. The historical delivery time data of the road section node may be the historical delivery time data of the road section node obtained one day before receiving the user order information. The most recent previous historical cycle time here may be set according to demand.

[0109] Step S142: determining the predicted delivery time efficiency of the road section node based on the target quantile and the target historical delivery time efficiency data.

[0110] Specifically, after determining the target percentile and the target historical delivery time data, the delivery time of each order in the target historical delivery time data can be sorted from small to large, and then the delivery time in the target historical delivery time data can be determined according to the target percentile as the predicted delivery time of the road section node.

[0111] In order to facilitate users to view the predicted delivery time, the embodiment of the present application can also send the predicted delivery time and the obtained predicted delivery time of each road section node to the client 10. The client 10 can display the predicted delivery time of each road section node in the order from the shipping warehouse to the destination, and display the predicted delivery time of the total order path based on the user's order information.

[0112] The present application embodiment provides an optional flow chart for predicting the delivery timeliness scenario, such as Figure 4 As shown in the figure, W1-W6 represent the predicted operation time of each distribution node, D1-D5 represent the predicted delivery time of each distribution section, where W1 corresponds to the supplier warehouse, W6 corresponds to the courier delivery / receipt point, and W2-W5 corresponds to the distribution transfer warehouse that may be passed through. The predicted delivery time of the entire user order

[0113] PT=W1+W2+W3+W4+W5+W6+D1+D2+D3+D4+D5.

[0114] Taking W1 as an example, we first select the historical order delivery time efficiency data of the supplier warehouse in the past 60 days. The historical order delivery time efficiency data in the past 60 days can be divided into 60 groups of data with one day as a cycle, and the daily on-time rate, delay rate and early rate are calculated according to the preset standard delivery time every day. The standard delivery time here can be set based on the comprehensive consideration of the technical staff on the environment, personnel, equipment and other dimensions of the current road section node.

[0115] From the 60 sets of data corresponding to the on-time rate, delay rate and advance rate, we can select the set of data with the lowest delay rate and advance rate and the highest on-time rate as the target order delivery time collection according to demand.

[0116] Assume that this set of data is [2, 2, 2, 3, 3.1, 3.2, 3.2, 3.5, 3.5, 4], calculate the 8th quantile of the standard delivery time of 3.5 days set for the day as the target quantile, and then select the historical order delivery time data of the most recent cycle of this user order [3, 3, 3, 3, 3, 3, 3, 3, 3.5] as the target historical delivery time data, and use the 8th quantile to determine from the target historical delivery time data that the predicted operation time for this user order in the supplier warehouse is 3 days.

[0117] A device for predicting delivery timeliness provided in an embodiment of the present application is described below. The device for predicting delivery timeliness described below and the method for predicting delivery timeliness described above can refer to each other.

[0118] like Figure 5 As shown, it discloses a structural schematic diagram of a device for predicting delivery timeliness, which may include:

[0119] An order acquisition unit 11 is used to acquire user order information, wherein the user order information includes destination information;

[0120] A path determination unit 12, configured to determine an order path based on the destination information;

[0121] The historical data acquisition unit 13 is used to acquire the historical delivery time efficiency data of each section node in the order path within a preset time period;

[0122] The quantile determination unit 14 is used to determine the corresponding target quantile for each road section node by using the historical delivery time efficiency data of the road section node and the preset standard delivery time efficiency;

[0123] A delivery time efficiency prediction unit 15, used to determine the predicted delivery time efficiency of the road segment node in the order path by using the target quantile;

[0124] The order time efficiency prediction unit 16 is used to add the predicted delivery time efficiency of each road section node to obtain the predicted delivery time efficiency of the user order information.

[0125] Optionally, the historical delivery time efficiency data includes delivery time efficiency of multiple orders, and the quantile determination unit 14 may include:

[0126] A cycle time division unit, used to divide the historical delivery time efficiency data into a plurality of order delivery time efficiency collections according to the cycle time;

[0127] A probability determination unit, configured to determine the on-time rate, delay rate and early rate of the set of order delivery time limits according to a preset standard delivery time limit corresponding to the set of order delivery time limits;

[0128] The preset standard delivery time is determined according to the delivery time dimension of the corresponding road section node;

[0129] An optimal standard delivery time selection unit, configured to select a target order delivery time collection corresponding to the optimal standard delivery time collection based on the on-time rate, delay rate and early rate of the order delivery time collection and according to the set optimal standard delivery time selection rule;

[0130] The target quantile acquisition unit is used to calculate the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile.

[0131] Optionally, the probability determination unit may include:

[0132] A ratio calculation unit, used to calculate a first ratio of the on-time rate to the delayed rate, and a second ratio of the on-time rate to the early rate of each order delivery time collection;

[0133] The target order delivery time efficiency collection selection unit is used to select the order delivery time efficiency collection corresponding to the largest first ratio and second ratio from each of the order delivery time efficiency collections as the target order delivery time efficiency collection.

[0134] Optionally, the target quantile acquisition unit may include a first target quantile determination unit;

[0135] The first target quantile determination unit is used to calculate the quantile corresponding to the standard delivery time in the target order delivery time collection as the target quantile when the target order delivery time collection is one.

[0136] Optionally, the target quantile acquisition unit may include a second target quantile determination unit, which is used to calculate the quantile of the corresponding standard delivery time in each target order delivery time set when there are more than two target order delivery time sets; and determine the target quantile based on the quantiles of each target order delivery time set.

[0137] Optionally, the historical data acquisition unit 13 may include:

[0138] A special event judgment unit, used to judge whether a special event occurs at the road section node, wherein the special event includes natural disasters, man-made disasters and force majeure;

[0139] A first historical delivery time efficiency data acquisition unit, configured to acquire historical delivery time efficiency data within a first time period of each section node in the order path when the special event determination unit determines that no special event has occurred;

[0140] The second historical delivery time efficiency data acquisition unit is used to execute the acquisition of historical delivery time efficiency data within a second time period of each section node in the order path when the special event judgment unit determines that a special event has occurred, wherein the first time period is greater than the second time period.

[0141] Optionally, the delivery time efficiency prediction unit 15 may include:

[0142] A target historical delivery time efficiency data acquisition unit, used to acquire the historical delivery time efficiency data of the road segment node within the previous historical period closest to the time of the user order information as the target historical delivery time efficiency data;

[0143] A predicted delivery time determination unit is used to determine the predicted delivery time of the road section node based on the target quantile and the target historical delivery time data.

[0144] Optionally, the device of the solution of the present application further includes a predicted delivery time sending unit, which is used to send the predicted delivery time and the acquired predicted delivery time of each road section node to the client for display by the client.

[0145] The device for predicting delivery time provided in the embodiment of the present application can be applied to a device for predicting delivery time. The device for obtaining the predicted delivery time can be the server 20. Figure 6 The hardware structure diagram of the delivery time prediction device is shown. Figure 6 , the hardware structure of the delivery time prediction device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0146] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0147] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0148] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0149] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:

[0150] Acquire user order information, wherein the user order information includes destination information;

[0151] determining an order path based on the destination information;

[0152] Obtain the historical delivery time efficiency data of each node in the order path within the preset time period;

[0153] For each road section node, the corresponding target quantile is determined using the historical delivery time efficiency data of the road section node and the preset standard delivery time efficiency;

[0154] Determine the predicted delivery time of the node of the road section in the order path by using the target quantile;

[0155] The predicted delivery time of each road section node is added together to obtain the predicted delivery time of the user order information.

[0156] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0157] The embodiment of the present application further provides a storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0158] Acquire user order information, wherein the user order information includes destination information;

[0159] determining an order path based on the destination information;

[0160] Obtain the historical delivery time efficiency data of each node in the order path within the preset time period;

[0161] For each road section node, the corresponding target quantile is determined using the historical delivery time efficiency data of the road section node and the preset standard delivery time efficiency;

[0162] Determine the predicted delivery time of the node of the road section in the order path by using the target quantile;

[0163] The predicted delivery time of each road section node is added together to obtain the predicted delivery time of the user order information.

[0164] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0165] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0166] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined with each other, and the same or similar parts can be referenced to each other.

[0167] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting delivery time, characterized in that: include: Acquire user order information, wherein the user order information includes destination information; determining an order path based on the destination information; Obtain the historical delivery time efficiency data of each node in the order path within the preset time period; For each road section node, the corresponding target quantile is determined using the historical delivery time efficiency data of the road section node and the preset standard delivery time efficiency; Determine the predicted delivery time of the node of the road section in the order path by using the target quantile; Adding the predicted delivery time of each road section node to obtain the predicted delivery time of the user order information; The historical delivery time efficiency data includes the delivery time efficiency of multiple orders. For each road segment node, the corresponding target quantile is determined by using the historical delivery time efficiency data of the road segment node and the preset standard delivery time efficiency, including: Dividing the historical delivery time efficiency data into multiple order delivery time efficiency collections according to cycle time; Determine the on-time rate, delay rate and early rate of the order delivery time collection according to the preset standard delivery time collection corresponding to the order delivery time collection; The preset standard delivery time is determined according to the delivery time dimension of the corresponding road section node; Based on the on-time rate, delay rate and early rate of the order delivery time collection, according to the set optimal standard delivery time selection rule, select the target order delivery time collection corresponding to the optimal standard delivery time; Calculate the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile; The method of using the target quantile to determine the predicted delivery time of the road section node in the order path includes: Obtain the historical delivery time efficiency data of the road section node in the previous historical period closest to the time of the user order information as the target historical delivery time efficiency data; Determining the predicted delivery time efficiency of the road section node based on the target quantile and the target historical delivery time efficiency data; The on-time rate, delay rate and early rate of the order delivery time collection are based on the set optimal standard delivery time selection rule, and the target order delivery time collection corresponding to the optimal standard delivery time is selected, including: Calculate a first ratio of the on-time rate to the delayed rate, and a second ratio of the on-time rate to the early rate for each of the order delivery time collections; From each of the order delivery time collections, select the order delivery time collection corresponding to the largest first ratio and second ratio as the target order delivery time collection; The step of determining the predicted delivery time efficiency of the road section node based on the target quantile and the target historical delivery time efficiency data specifically includes: After determining the target percentile and the target historical delivery time data, the delivery time of each order in the target historical delivery time data can be sorted from small to large, and then the delivery time in the target historical delivery time data can be determined according to the target percentile as the predicted delivery time of the road section node.

2. The method according to claim 1, characterized in that The target order delivery time collection is one, and the calculation of the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile includes: The quantile corresponding to the standard delivery time in the target order delivery time collection is calculated as the target quantile.

3. The method according to claim 1, characterized in that The target order delivery time collection is more than two, and the step of calculating the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile includes: Calculate the quantile of the corresponding standard delivery time in the delivery time set of each target order; Determine the target quantile based on the quantile of the delivery time set of each target order.

4. The method according to claim 1, characterized in that: The preset time period includes a first time period or a second time period, the first time period is greater than the second time period, and the acquiring of historical delivery time efficiency data within the preset time period of each section node in the order path includes: Determine whether a special event occurs at the road section node, wherein the special event includes natural disasters, man-made disasters and force majeure; If not, obtain the historical delivery time efficiency data of each node in the order path within the first time period; If yes, then obtain the historical delivery time efficiency data of each section node in the order path within the second time period.

5. The method according to claim 1, characterized in that Also includes: The predicted delivery time and the obtained predicted delivery time of each road section node are sent to the client for display by the client.

6. The method according to any one of claims 1 to 5, characterized in that: The road section nodes include supplier warehouses, self-operated warehouses, distribution nodes and transportation sections.

7. A device for predicting delivery time, characterized in that: include: An order acquisition unit, used to acquire user order information, wherein the user order information includes destination information; a path determination unit, configured to determine an order path based on the destination information; A historical data acquisition unit, used to acquire historical delivery time efficiency data within a preset time period of each section node in the order path; A quantile determination unit, for determining, for each road section node, a corresponding target quantile using the historical delivery time efficiency data of the road section node and a preset standard delivery time efficiency; A delivery time efficiency prediction unit, used to determine the predicted delivery time efficiency of the road section node in the order path by using the target quantile; An order time efficiency prediction unit, configured to add the predicted delivery time efficiency of each road section node to obtain the predicted delivery time efficiency of the user order information; The quantile determination unit includes: a cycle time division unit, which is used to divide the historical delivery time data into multiple order delivery time collections according to the cycle time; a probability determination unit, which is used to determine the punctuality rate, delay rate and early rate of the order delivery time collection according to the preset standard delivery time corresponding to the order delivery time collection; wherein the preset standard delivery time is determined according to the distribution time dimension of the corresponding road section node; an optimal standard delivery time selection unit, which is used to select the target order delivery time collection corresponding to the optimal standard delivery time based on the punctuality rate, delay rate and early rate of the order delivery time collection and according to the set optimal standard delivery time selection rule; a target quantile acquisition unit, which is used to calculate the quantile of the standard delivery time in the target order delivery time collection to obtain the target quantile; The probability determination unit includes: a ratio calculation unit, which is used to calculate a first ratio of the on-time rate to the delay rate, and a second ratio of the on-time rate to the early rate of each of the order delivery time efficiency collections; a target order delivery time efficiency collection selection unit, which is used to select the order delivery time efficiency collection corresponding to the largest first ratio and second ratio from each of the order delivery time efficiency collections as the target order delivery time efficiency collection; The delivery time prediction unit includes: a target historical delivery time data acquisition unit, which is used to acquire the historical delivery time data of the road section node in the previous historical period closest to the time of the user order information as the target historical delivery time data; a predicted delivery time determination unit, which is used to determine the predicted delivery time of the road section node based on the target quantile and the target historical delivery time data.

Images