Method and device for determining order delivery time

Abstract

The present invention discloses a method and device for determining order delivery times. For any order at a target site, a corresponding on-time delivery rate determination model is determined based on the time period to which the order was placed. Each on-time delivery rate determination model is trained based on the target site's historical orders and on-time delivery rates within the same time period. For any preset overtime duration, the order and overtime duration are input into the corresponding on-time delivery rate determination model to obtain candidate on-time delivery rates corresponding to the overtime duration. Based on a standard on-time delivery rate set for the target site, a target on-time delivery rate that meets the set conditions with the standard on-time delivery rate is determined from the candidate on-time delivery rates. The order's delivery time is determined based on the overtime duration corresponding to the target on-time delivery rate. This solution can meet the on-time delivery rate requirements configured by the platform for distribution sites, thereby increasing user engagement with the distribution sites and the platform.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing, and in particular to a method and device for determining the delivery time of an order. Background Art

[0002] Currently, to increase user retention, online fresh food platforms will display information about the approximate delivery timeline for the purchased item after the user places an order, ensuring that users have a clear understanding of the items they purchased. However, due to objective factors that can cause delivery anomalies during the delivery process, delivery personnel may be unable to deliver orders within the scheduled timeframe. This can easily lead to a decrease in the on-time delivery rate at the purchase site, which directly impacts user trust in the purchase site and, ultimately, the platform itself. In other words, a low on-time delivery rate can easily lead to customer churn. Summary of the Invention

[0003] The present application provides a method and device for determining the delivery time of an order, which is used to accurately predict the overtime duration of an order, and thus deliver the order based on the accurately predicted overtime duration. This can meet the on-time delivery rate requirements configured by the platform for the delivery site, and increase the user's stickiness to the delivery site and the platform.

[0004] In the first aspect, an embodiment of the present application provides a method for determining the delivery time of an order, the method comprising: for any order of a target site, based on the time period to which the order placement time belongs, determining a delivery punctuality determination model corresponding to the order; any delivery punctuality determination model is trained based on historical orders and historical delivery punctuality of the target site in the same time period; for any preset overtime duration, inputting the order and the overtime duration into the delivery punctuality determination model corresponding to the order to obtain a candidate delivery punctuality corresponding to the overtime duration; according to the standard delivery punctuality set for the target site, determining a target delivery punctuality that meets the set conditions with the standard delivery punctuality from each candidate delivery punctuality; and determining the delivery time of the order based on the overtime duration corresponding to the target delivery punctuality.

[0005] In the above scheme, by configuring the site's orders with additional time periods, a set of information consisting of the order and each additional time period is input into the delivery on-time rate determination model corresponding to the order. Since the delivery on-time rate determination model is trained based on historical orders and historical delivery on-time rates in the same time period, the model can obtain candidate delivery on-time rates corresponding to each additional time period. Finally, based on the preset standard delivery on-time rate, a selection is made from the candidate delivery on-time rates, and the delivery time of the order is determined based on the additional time period corresponding to the selected candidate delivery on-time rate. The delivery time determined based on this method will be able to meet the standard delivery on-time rate designed for the site. Therefore, the delivery of goods in this way will be beneficial to the platform's maintenance of customers.

[0006] In one possible implementation method, the on-time delivery rate determination model of any one of the target sites is trained based on the historical orders and historical on-time delivery rates of the target site within the same time period, including: for any time period, determining the target historical orders belonging to different periods of the time period from the historical orders of the target site; for each period, obtaining the historical overtime duration corresponding to the target historical orders of the period and the historical on-time delivery rate corresponding to the target historical orders; for any target historical order, using the target historical order and the historical overtime duration corresponding to the target historical order as training samples, and using the on-time delivery rate corresponding to the target historical order as a label, to train the initial model, thereby obtaining the on-time delivery rate determination model.

[0007] The above scheme specifically describes the process of training the model for determining the on-time delivery rate for each time period. Since the model training is based on data from the same time period during the training process, the subsequent selection of the model for determining the on-time delivery rate for the corresponding time period according to the order time will make the determination of the candidate on-time delivery rate more accurate. In addition, during the training process, the historical overtime duration of historical orders and historical orders are used as training samples, and the on-time delivery rate corresponding to the historical orders is used as a label. The trained model can accurately capture the relationship between historical orders, the overtime duration of historical orders, and the on-time delivery rate. Therefore, based on the model obtained by the training, after the order and the overtime duration of the order are known, the order and the overtime duration of the order are input into the trained model, and the corresponding on-time delivery rate can be accurately output.

[0008] In a possible implementation method, each preset duration of the supplementary time is generated by sliding within a time window of a set size according to a set step size.

[0009] In the above scheme, by evenly dividing the time window of a set size, the length of each overtime is obtained, so that the distribution of each candidate delivery on-time rate determined based on each overtime length will also be relatively uniform, which will help to determine the target delivery on-time rate.

[0010] In one possible implementation method, determining a target on-time delivery rate that meets set conditions with the standard on-time delivery rate from each candidate on-time delivery rate includes: for each candidate on-time delivery rate, taking the candidate on-time delivery rate closest to the standard on-time delivery rate as the target on-time delivery rate.

[0011] In the above solution, by taking the candidate on-time delivery rate that is closest to the standard on-time delivery rate as the target on-time delivery rate, when subsequent deliveries are made based on this candidate on-time delivery rate, the delivery process will also be more likely to meet the standard on-time delivery rate set for the site, which will help maintain customer service.

[0012] In one possible implementation method, for any time period, target historical orders of different periods in the time period are determined from the historical orders of the target site, including: obtaining historical orders for the target site within a set time period closest to the order time; for any time period, target historical orders of different periods in the same time period as the time period are determined from the historical orders.

[0013] In the above scheme, since the historical orders within the set time period closest to the order placement time have a greater influence on the data processing of the current order to be processed, the model training by using the target historical orders determined in this way will be more timely.

[0014] In one possible implementation method, the delivery time of the order is determined based on the supplementary time corresponding to the target on-time delivery rate, including: determining the estimated delivery time of the order through a time estimation model based on the order time; and determining the delivery time of the order based on the supplementary time corresponding to the target on-time delivery rate and the estimated delivery time of the order.

[0015] In the above solution, after a customer places an order for a product, an estimated delivery time can be generated for the order through the time estimation model. Although this estimated delivery time cannot meet the standard on-time delivery rate, by adding the accurately determined supplementary time to the estimated delivery time, the standard on-time delivery rate set for the site can be met.

[0016] In one possible implementation method, any order delivery on-time rate determination model is updated daily.

[0017] In the above solution, by designing the delivery on-time rate determination model to be updated daily, it will have higher accuracy when predicting the candidate delivery on-time rates, and overall improve the accuracy of determining the order delivery time.

[0018] In a second aspect, an embodiment of the present application provides a device for determining the delivery time of an order, the device comprising: a delivery on-time rate determination model selection unit, for determining, for any order of a target site, a delivery on-time rate determination model corresponding to the order based on the time period to which the order placement time belongs; any delivery on-time rate determination model is trained based on historical orders and historical delivery on-time rates of the target site within the same time period; a candidate delivery on-time rate determination unit, for inputting the order and the supplementary time into the delivery on-time rate determination model corresponding to the order for any preset supplementary time duration, to obtain a candidate delivery on-time rate corresponding to the supplementary time duration; a target delivery on-time rate determination unit, for determining, according to the standard delivery on-time rate set for the target site, a target delivery on-time rate that meets the set conditions with the standard delivery on-time rate from each candidate delivery on-time rate; a delivery time determination unit, for determining the delivery time of the order based on the supplementary time duration corresponding to the target delivery on-time rate.

[0019] In a third aspect, an embodiment of the present application provides a computing device, including:

[0020] a memory for storing program instructions;

[0021] The processor is used to call the program instructions stored in the memory and execute any implementation method of the first aspect according to the obtained program.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute any implementation method of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0024] Figure 1 A schematic diagram of a method for determining order delivery time provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of a device for determining order delivery time provided in an embodiment of the present application;

[0026] Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of this application more clear, this application will be further described in detail below with reference to the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0028] When a site currently delivers goods ordered online by a user, the site's actual on-time delivery rate often fails to meet the standard on-time delivery rate pre-set by the platform. This standard on-time delivery rate can be understood as the minimum on-time delivery rate determined by the platform based on market research to maintain customer satisfaction. To address this issue, this application provides a method for determining order delivery times. Using this method, when a site delivers a user's order, its actual on-time delivery rate will meet the standard on-time delivery rate pre-set by the platform, helping the site and platform maintain user retention and increasing user engagement with the site and platform.

[0029] like Figure 1 FIG. 1 is a schematic diagram of a method for determining an order delivery time provided in an embodiment of the present application. The method can be executed by a device for determining an order delivery time. The method includes the following steps:

[0030] Step 101: For any order of a target site, a delivery on-time rate determination model corresponding to the order is determined based on the time period to which the order is placed.

[0031] Suppose there is an online fresh food platform that can design product delivery sites within a certain area based on its business scale. Before placing an order for the products they need from the platform, users can pre-select a delivery site. Based on the delivery site selected by the user, the products ordered from the platform will subsequently be delivered by the selected delivery site. Before the user selects a delivery site, the online fresh food platform may obtain the user's authorization information to obtain the user's geographic location information and proactively push several delivery sites to the user based on the user's geographic location information. The user can then select a delivery site from the pushed sites based on their actual situation.

[0032] It should be noted that the platform is not limited to the above-mentioned fresh food types, but can also be supermarket types and pharmaceutical types.

[0033] Based on the usage scenario of the technical solution described above, the target site can be any distribution site designed offline by the online fresh food platform. For the convenience of description, let the target site be recorded as site A. Then, for any order placed by the user from the online platform and designated to be delivered by site A, the order time of the user for the order can be obtained from the order. Among them, the time of the day is divided into time periods in advance in this application. As an example, the time periods are divided into half-hour periods starting from the hour in this application. For example, 0:00-0:30 every day will be a time period, and 0:31-1:00 every day will be a time period. In this way, each day can be divided into 48 time periods. Therefore, it can be assumed that the order time of the obtained order is 10:20. Then, for the order time, the time period of the day is matched, and the time period of 10:01-10:30 can be matched. Among them, in this application, based on the 48 time periods into which the time of the day is divided, a corresponding delivery punctuality determination model is trained for each time period. Therefore, an order placed by a user at 10:20 will be matched with a delivery on-time rate determination model corresponding to the time period of 10:01-10:30. Each delivery on-time rate determination model is trained based on the target station's historical orders and historical on-time delivery rates during the same time period.

[0034] Optionally, any one of the on-time delivery rate determination models is trained based on the historical orders and historical on-time delivery rates of the target site within the same time period, including: for any one time period, determining the target historical orders belonging to different periods of the time period from the historical orders of the target site; for each period, obtaining the historical overtime duration corresponding to each target historical order of the period and the historical on-time delivery rate corresponding to each target historical order; for any one of the target historical orders, using the target historical order and the historical overtime duration corresponding to the target historical order as training samples, and using the on-time delivery rate corresponding to the target historical order as a label, to train the initial model, thereby obtaining the on-time delivery rate determination model.

[0035] Next, this application uses the training of a delivery on-time rate determination model corresponding to the time period of 10:01-10:30, which matches an order placed by a user at 10:20 in the above example, as an example to illustrate the above solution. The content is as follows:

[0036] Step a: For the period of 10:01-10:30, target historical orders of different periods belonging to the period of 10:01-10:30 are determined from the historical orders of site A. The target historical orders can be obtained as follows:

[0037] In certain implementations of the present application, for any time period, target historical orders of different periods belonging to the time period are determined from the historical orders of the target site, including: obtaining historical orders for the target site within a set time period closest to the order time; for any time period, target historical orders of different periods that are the same time period as the time period are determined from the historical orders.

[0038] For example, if a user places an order at 10:20 AM during the 10:01-10:30 AM period and the order date is set to June 21, 2022, then you can retrieve all historical orders for Site A within a month before that order date. For example, you can retrieve all historical orders placed by the user on Site A for each of the 30 days from May 21, 2022, to June 20, 2022. That is, you can retrieve all historical orders placed by the user on Site A on May 21, 2022, and all historical orders placed by the user on Site A on May 22, 2022, and so on. And obtain the historical orders placed by the user for site A on June 20, 2022, and take the sum of the historical orders placed for site A on each day of the above 30 days as the historical orders for site A within the month most recent to the order placed by the user at 10:20 on June 21, 2022; then, for each historical order obtained above, according to the time period of 10:01-10:30 to which the order placed at 10:20 belongs, continue to select the historical orders within the time period from the historical orders, and these determined historical orders are the target historical orders. For example, for the historical orders placed by the user for site A on May 21, 2022, the historical orders placed by the user for site A during the period of 10:01-10:30 are selected; for the historical orders placed by the user for site A on May 22, 2022, the historical orders placed by the user for site A during the period of 10:01-10:30 are selected,... and for the historical orders placed by the user for site A on June 20, 2022, the historical orders placed by the user during the period of 10:01-10:30 are selected, and the sum of the historical orders placed by the user for site A during the period of 10:01-10:30 on each day of the above 30 days is taken as the target historical orders for site A within the month closest to the order placed by the user at 10:20 on June 21, 2022.

[0039] For the above example, the setting duration of this application is selected as 30 days, and the cycle is selected as 1 day.

[0040] Step b: for each period, obtain the historical overtime duration corresponding to each target historical order of the period and the historical on-time delivery rate corresponding to each target historical order.

[0041] For example, in combination with the above example, for each of the target historical orders placed by the user for site A during the period of 10:01-10:30 on May 21, 2022, the historical overtime duration and the corresponding historical on-time delivery rate of the target historical order can be obtained. Similarly, for each of the target historical orders placed by the user for site A during the period of 10:01-10:30 on May 22, 2022, and during the period of 10:01-10:30 on June 3, 2022, ... and for each of the target historical orders placed by the user for site A during the period of 10:01-10:30 on June 20, 2022, the action of obtaining the historical overtime duration and the historical delivery rate of the target historical order can be performed, thereby obtaining the historical overtime duration and the historical delivery rate of each target historical order.

[0042] After each order is delivered, the additional time for that order is recorded in the database based on the order number. Therefore, in this application, we only need to retrieve the corresponding additional time from the database based on the order number. The additional time is the additional time required for the final delivery of the order due to the fact that the platform cannot deliver the order in time after designing an estimated delivery time for the order.

[0043] In addition, before delivering each historical order, the platform will set a delivery punctuality rate for the site. The set delivery punctuality rate is used to indicate that in theory the site needs to complete the delivery of the order according to the set delivery punctuality rate. Therefore, the delivery punctuality rate set by the platform for the site can also be interpreted as the delivery punctuality rate set by the platform for each order that needs to be delivered. Therefore, the delivery punctuality rate of the order in this application can also be accurately obtained.

[0044] Step c: for any target historical order, the target historical order and the historical overtime duration corresponding to the target historical order are used as training samples, and the on-time delivery rate corresponding to the target historical order is used as a label to train the initial model, thereby obtaining the on-time delivery rate determination model.

[0045] For example, combined with the previous example, for each target historical order among the target historical orders placed by the user for site A during the period of 10:01-10:30 on May 21, 2022,... for each target historical order among the target historical orders placed by the user for site A during the period of 10:01-10:30 on June 20, 2022, the target historical order and the historical overtime duration of the target historical order can be formed into a training sample, and the on-time delivery rate of the target historical order can be used as a label to train the initial model. Through training, a regression model can be trained. Since any target historical order includes information about the site corresponding to the order and information about the order itself, the information about the site corresponding to the order includes information about the site, the number of delivery personnel at the site, and the current order volume at the site, while the information about the order itself includes information about the ordered goods and whether the ordered goods contain fragile items (such as live fish, ice cream, glassware, etc.), the trained regression model can be used to accurately capture the relationship between the target historical order, the time delay of the target historical order, and the on-time delivery rate. Subsequently, based on the trained model, after the order and the time delay of the order are known, by inputting the order and the time delay of the order into the trained model, the corresponding on-time delivery rate can be accurately output. This regression model is a model for determining the on-time delivery rate for site A during the period of 10:01-10:30, that is, the regression model can be used to determine the on-time delivery rate of orders placed by users at site A at 10:20.

[0046] It is noted that the initial model can be selected from models such as Xgboost model, LR model Logistic Regression, logistic regression model, GBDT model (Gradient Boosting Decision Tree, gradient descent tree), etc.

[0047] Step 102: For any preset overtime duration, the order and the overtime duration are input into a delivery on-time rate determination model corresponding to the order to obtain a candidate delivery on-time rate corresponding to the overtime duration.

[0048] In certain implementations of the present application, each preset duration of the supplementary time is generated by sliding within a time window of a set size according to a set step size.

[0049] For example, continuing with the previous example, for the order placed by the user at 10:20 on June 21, 2022 for site A, the delivery time of the order can be supplemented within a time window of 25 minutes. For example, the delivery time of the order can be supplemented in steps of 1 minute. Therefore, the supplementary time durations for the order placed by the user at 10:20 on June 21, 2022 will be 1 minute, 2 minutes, 3 minutes, ... 25 minutes respectively.

[0050] Therefore, taking the preset overtime duration of 1 minute as an example, the order placed by the user at 10:20 on June 21, 2022, and 1 minute can be input together into the on-time delivery rate determination model for Site A during the period of 10:01-10:30. Through processing by the on-time delivery rate determination model, an on-time delivery rate corresponding to the overtime duration can be obtained, that is, an on-time delivery rate corresponding to the overtime duration of 1 minute can be obtained, and this on-time delivery rate is a candidate on-time delivery rate. Similarly, for preset overtime durations of 2 minutes, 3 minutes, 4 minutes... and 25 minutes, through processing by the on-time delivery rate determination model, a corresponding candidate on-time delivery rate can be obtained.

[0051] Step 103 : According to the standard on-time delivery rate set by the target site, a target on-time delivery rate that meets the set conditions with the standard on-time delivery rate is determined from the candidate on-time delivery rates.

[0052] In this step, the target site's standard on-time delivery rate is set by the platform for that site. This standard on-time delivery rate is the minimum standard for maintaining customer satisfaction, determined by the platform based on the results of the delivery duration survey. This standard on-time delivery rate is an objective value and can be obtained.

[0053] In certain implementations of the present application, determining the target on-time delivery rate that meets the set conditions with the standard on-time delivery rate from each candidate on-time delivery rate includes: for each candidate on-time delivery rate, taking the candidate on-time delivery rate closest to the standard on-time delivery rate as the target on-time delivery rate.

[0054] For example, based on the previous example, for an order placed by a user at 10:20 AM on June 21, 2022, for Site A, the on-time delivery rate determination model for the period 10:01 AM to 10:30 AM yields 25 candidate on-time delivery rates. These 25 candidate on-time delivery rates can be expressed as follows: [1, 81%], [2, 82%], [5, 85%]... [10, 90%]... [15, 95%]... The first digit in [] represents the amount of overtime, and the second digit represents the candidate on-time delivery rate. For example, [1, 81%] means that, when the overtime is 1 minute, the candidate on-time delivery rate determined by the on-time delivery rate determination model is 81%.

[0055] Therefore, based on the obtained standard delivery punctuality rate, the standard delivery punctuality rate can be used to match the 25 candidate delivery punctuality rates determined by the delivery punctuality rate determination model. For example, in this application, the obtained standard delivery punctuality rate is 95%. Then, by matching 95% with the above 25 candidate delivery punctuality rates, it can be determined that the parameter [15,95%] meets the requirements, because [15,95%] can be interpreted as, when the overtime duration is 15 minutes, the candidate delivery punctuality rate determined by the delivery punctuality rate determination model is 95%. Obviously, this candidate delivery punctuality rate is closest to the standard delivery punctuality rate because the two are the same. Therefore, it can be determined that the candidate delivery punctuality rate of 95% in the parameter [15,95%] is used as the target delivery punctuality rate.

[0056] Step 104: Determine the delivery time of the order based on the additional time duration corresponding to the target on-time delivery rate.

[0057] For example, combining the previous example, after setting the candidate on-time delivery rate of 95% in the parameter [15, 95%] as the target on-time delivery rate, the 15-minute overtime duration in the parameter [15, 95%] can be obtained, and then the delivery time of the user's order placed at 10:20 can be determined based on the 15-minute overtime duration.

[0058] In the above scheme, by configuring the site's orders with additional time periods, a set of information consisting of the order and each additional time period is input into the delivery on-time rate determination model corresponding to the order. Since the delivery on-time rate determination model is trained based on historical orders and historical delivery on-time rates in the same time period, the model can obtain candidate delivery on-time rates corresponding to each additional time period. Finally, based on the preset standard delivery on-time rate, a selection is made from the candidate delivery on-time rates, and the delivery time of the order is determined based on the additional time period corresponding to the selected candidate delivery on-time rate. The delivery time determined based on this method will be able to meet the standard delivery on-time rate designed for the site. Therefore, the delivery of goods in this way will be beneficial to the platform's maintenance of customers.

[0059] In one implementation of the above-mentioned step 104, the delivery time of the order is determined based on the supplementary time corresponding to the target on-time delivery rate, including: determining the estimated delivery time of the order through a time estimation model based on the order time; and determining the delivery time of the order based on the supplementary time corresponding to the target on-time delivery rate and the estimated delivery time of the order.

[0060] For example, for an order placed by a user at 10:20 AM on June 21, 2022, for Station A, the estimated delivery time of the order can be determined using the time estimation model. Specifically, the time estimation model can be used to determine the approximate time it will take for the delivery driver to complete the delivery of the order. The time estimation model is not trained based on the standard on-time delivery rate set by the platform for the delivery station. Instead, the model is trained using real-time status data at the time of order generation and the delivery data of the station at the time of order delivery, thereby generating the time estimation model. The real-time status data of the order at the time of order generation may include the time of order generation, the weather at the time of order generation, the forward warehouse's transportation capacity at the time of order generation, the order backlog at the forward warehouse, and the specific status of sub-tasks such as sorting and packing within the forward warehouse. The delivery data at the time of order delivery is relatively fixed data associated with the forward warehouse, including, for example, the location of the forward warehouse, its storage capacity, the peak order hours for the forward warehouse, and the ease of delivery within the forward warehouse's jurisdiction.

[0061] After obtaining the estimated delivery time for the order, the order's delivery time can be obtained based on the additional time determined in this application. One possible implementation method is to add the estimated delivery time and the additional time to the order placement time to obtain the order's delivery time.

[0062] In certain implementations of the present application, any order delivery on-time rate determination model is updated daily.

[0063] For example, combined with the previous example, for the order placed by the user at 10:20 on June 21, 2022 for site A, this application can be based on the target historical orders in the period of 10:01-10:30 on May 21, 2022, the target historical orders in the period of 10:01-10:30 on May 22, 2022, ... and the target historical orders in the period of 10:01-10:30 on June 20, 2022 to obtain a delivery on-time rate determination model that can predict the candidate delivery on-time rate of the order placed by the user at 10:00 on June 22, 2022 for site A. If the candidate delivery punctuality rate is determined for orders placed at site A at any time point in the period from 10:01 to 10:30 on May 22, 2022, the target historical orders in the period from 10:01 to 10:30 on May 23, 2022, and ... the target historical orders in the period from 10:01 to 10:30 on June 21, 2022, are trained, thereby obtaining a delivery punctuality determination model that can predict the candidate delivery punctuality rate for orders placed at site A at any time point in the period from 110:01 to 10:30 on June 22, 2022.

[0064] Based on the same concept, the embodiment of the present application provides a device for determining the time of order delivery, such as Figure 2 , which is a schematic diagram of a device for determining order delivery time provided in an embodiment of the present application, comprising an order delivery on-time rate determination model selection unit 201, a candidate order delivery on-time rate determination unit 202, a target order delivery on-time rate determination unit 203, and a delivery time determination unit 204;

[0065] The on-time delivery rate determination model selection unit 201 is used to determine the on-time delivery rate determination model corresponding to any order of the target site based on the time period to which the order is placed; any on-time delivery rate determination model is trained based on the historical orders and historical on-time delivery rates of the target site in the same time period.

[0066] The candidate on-time delivery rate determination unit 202 is used to input the order and the supplementary time into the on-time delivery rate determination model corresponding to the order for any preset supplementary time duration, and obtain the candidate on-time delivery rate corresponding to the supplementary time duration.

[0067] The target on-time delivery rate determination unit 203 is configured to determine, according to the standard on-time delivery rate set by the target site, a target on-time delivery rate from among the candidate on-time delivery rates that meets the set conditions with the standard on-time delivery rate.

[0068] The delivery time determination unit 204 is configured to determine the delivery time of the order according to the additional time duration corresponding to the target on-time delivery rate.

[0069] Furthermore, the device also includes a delivery punctuality rate determination model training unit 205; the delivery punctuality rate determination model training unit 205 is used to: for any time period, determine the target historical orders belonging to different periods of the time period from the historical orders of the target site; for each period, obtain the historical overtime duration corresponding to each target historical order of the period and the historical delivery punctuality rate corresponding to each target historical order; for any target historical order, use the target historical order and the historical overtime duration corresponding to the target historical order as training samples, and use the delivery punctuality rate corresponding to the target historical order as a label to train the initial model, thereby obtaining the delivery punctuality rate determination model.

[0070] Furthermore, for this device, each preset duration of the supplementary time is generated by sliding within a time window of a set size according to a set step size.

[0071] Furthermore, for the device, the target on-time delivery rate determining unit 203 is specifically configured to: for each candidate on-time delivery rate, use the candidate on-time delivery rate closest to the standard on-time delivery rate as the target on-time delivery rate.

[0072] Furthermore, for the device, the delivery punctuality rate determination model training unit 205 is also used to: obtain each historical order for the target site and within the set time period closest to the order time; for any time period, determine each target historical order of each different period that is the same time period as the time period from each historical order.

[0073] Furthermore, for the device, the delivery time determination unit 204 is specifically used to: determine the expected delivery time of the order through a time estimation model based on the order placement time; and determine the delivery time of the order based on the supplementary time corresponding to the target on-time delivery rate and the expected delivery time of the order.

[0074] Furthermore, for this device, any order delivery on-time rate determination model is updated daily.

[0075] The present application also provides a computing device, which may be a desktop computer, a portable computer, a smart phone, a tablet computer, a personal digital assistant (PDA), etc. The computing device may include a central processing unit (CPU), a memory, input / output devices, etc. The input device may include a keyboard, a mouse, a touch screen, etc. The output device may include a display device, such as a liquid crystal display (LCD), a cathode ray tube (CRT), etc.

[0076] The memory may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor with program instructions and data stored in the memory. In an embodiment of the present application, the memory may be used to store program instructions for a method for determining the time of order delivery;

[0077] The processor is used to call the program instructions stored in the memory and execute the method for determining the order delivery time according to the obtained program.

[0078] like Figure 3 FIG. 1 is a schematic diagram of a computing device provided in an embodiment of the present application, wherein the computing device includes:

[0079] Processor 301, memory 302, transceiver 303, bus interface 304; wherein the processor 301, memory 302 and transceiver 303 are connected via bus 305;

[0080] The processor 301 is configured to read the program in the memory 302 and execute the above-mentioned method for determining the order delivery time;

[0081] The processor 301 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. It may also be a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0082] The memory 302 is used to store one or more executable programs and can store data used by the processor 301 when performing operations.

[0083] Specifically, the program may include program code, which includes computer operating instructions. Memory 302 may include volatile memory, such as random-access memory (RAM); memory 302 may also include non-volatile memory, such as flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); and memory 302 may also include a combination of the aforementioned types of memory.

[0084] The memory 302 stores the following elements, executable modules or data structures, or a subset or an extension thereof:

[0085] Operation instructions: include various operation instructions, used to implement various operations.

[0086] Operating system: includes various system programs used to implement various basic services and process hardware-based tasks.

[0087] The bus 305 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0088] The bus interface 304 may be a wired communication access port, a wireless bus interface, or a combination thereof. The wired bus interface may be, for example, an Ethernet interface. The Ethernet interface may be an optical interface, an electrical interface, or a combination thereof. The wireless bus interface may be a WLAN interface.

[0089] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute a method for determining the delivery time of an order.

[0090] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0094] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0095] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for determining order delivery time, characterized in that: include: For any order at the target site, a delivery on-time rate determination model corresponding to the order is determined based on the time period to which the order was placed. Each delivery on-time rate determination model is trained based on the target site's historical orders within the same time period, the corresponding historical overtime duration, and the historical delivery on-time rates. For any of the preset overtime durations, the order and the overtime duration are input into the on-time delivery rate determination model corresponding to the order, to obtain a candidate on-time delivery rate corresponding to the overtime duration; each preset overtime duration is generated by sliding within a time window of a set size according to a set step size; According to the standard delivery on-time rate set by the target site, a target delivery on-time rate that meets the set conditions is determined from the candidate delivery on-time rates corresponding to each additional time period; the standard delivery on-time rate is the minimum standard delivery on-time rate set by the platform for the target site; The delivery time of the order is determined according to the length of the overtime corresponding to the target on-time delivery rate.

2. The method according to claim 1, wherein The on-time delivery rate determination model is trained based on the target station's historical orders within the same time period, the historical overtime duration corresponding to the historical orders, and the historical on-time delivery rate, and includes: For any time period, determining target historical orders belonging to different periods of the time period from the historical orders of the target site; For each period, obtain the historical overtime duration corresponding to each target historical order in the period and the historical on-time delivery rate corresponding to each target historical order; For any target historical order, the target historical order and the historical overtime duration corresponding to the target historical order are used as training samples, and the on-time delivery rate corresponding to the target historical order is used as a label to train the initial model, thereby obtaining the on-time delivery rate determination model.

3. The method according to claim 1, wherein The step of determining a target on-time delivery rate that meets set conditions and the standard on-time delivery rate from the candidate on-time delivery rates corresponding to the respective overtime durations includes: For each candidate on-time delivery rate, the candidate on-time delivery rate closest to the standard on-time delivery rate is used as the target on-time delivery rate.

4. The method according to claim 2, wherein The step of determining, for any time period, target historical orders of different periods in the time period from the historical orders of the target site includes: Obtaining historical orders for the target site within a set time period closest to the order placement time; For any time period, target historical orders of different periods that are the same time period as the time period are determined from the historical orders.

5. The method according to claim 1, wherein Determining the delivery time of the order according to the additional time duration corresponding to the target on-time delivery rate includes: Determine the estimated delivery time of the order using a time estimation model based on the order placement time; The delivery time of the order is determined according to the additional time corresponding to the target on-time delivery rate and the estimated delivery time of the order.

6. The method according to claim 1, wherein Any delivery on-time rate determination model is updated daily.

7. A device for determining order delivery time, characterized in that: include: A delivery on-time rate determination model selection unit is configured to determine, for any order at a target site, a corresponding delivery on-time rate determination model based on the time period to which the order was placed; any delivery on-time rate determination model is trained based on historical orders of the target site within the same time period, the corresponding historical overtime duration, and the historical delivery on-time rates. a candidate on-time delivery rate determination unit, configured to input the order and the supplementary time duration into a corresponding on-time delivery rate determination model for any of the preset supplementary time durations, and obtain a candidate on-time delivery rate corresponding to the supplementary time duration; wherein each preset supplementary time duration is generated by sliding within a time window of a set size according to a set step size; a target on-time delivery rate determination unit configured to determine, according to a standard on-time delivery rate set by the target site, a target on-time delivery rate that meets the set conditions from the candidate on-time delivery rates corresponding to each additional time period; the standard on-time delivery rate is the minimum standard on-time delivery rate set by the platform for the target site; The delivery time determination unit is used to determine the delivery time of the order according to the additional time duration corresponding to the target on-time delivery rate.

8. A computer device, characterized in that: include: memory for storing computer programs; A processor is configured to call a computer program stored in the memory and execute the method according to any one of claims 1 to 6 according to the obtained program.

9. A computer-readable storage medium, characterized in that The storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

Images