Order estimated arrival time determination method and device, equipment and medium

Abstract

The invention provides an order estimated arrival time determination method and device, equipment and a medium. According to the invention, based on the delivery data of a plurality of historical orders completed by a target store in a first time period before the current time, the punctuality rate of the target store in the first time period and the expected punctuality rate threshold of the target store, the estimated delivery time length adjustment parameter at the current time is determined; therefore, after the estimated delivery duration of the current moment is determined through the delivery duration estimation model based on the number of first orders being delivered by the target store at the current moment, the number of second orders waiting to be delivered by the target store at the current moment and the number of available delivery personnel at the current moment, the parameters are adjusted based on the estimated delivery duration, and the delivery time of the target store is determined. And adjusting the pre-estimated delivery time, so as to determine the pre-estimated delivery time of the order at the current moment based on the adjusted pre-estimated delivery time, thereby improving the accuracy of the finally determined pre-estimated delivery time of the order.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular, to a method, apparatus, device, and medium for determining the estimated delivery time of an order. Background Art

[0002] With the diversification of consumer demands and the acceleration of people's life rhythms, instant delivery has become an important means to meet consumer demands. Instant delivery plays a positive role in meeting consumer demands, promoting commercial development, and enhancing user experience by quickly and efficiently delivering goods or services to consumers.

[0003] In instant delivery, the estimated delivery time plays an important role. For consumers, they can know when an order will be delivered through the estimated delivery time so as to make corresponding arrangements; for merchants, they can reasonably arrange the processing order of multiple orders according to the estimated delivery time to ensure that the goods or services can be delivered to consumers on time. Therefore, accurately estimating the delivery time is an urgent problem to be solved in the instant delivery process. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present application provides a method, apparatus, device, and medium for determining the estimated delivery time of an order.

[0005] According to the first aspect of the embodiments of the present application, a method for determining the estimated delivery time of an order is provided. The method includes:

[0006] Based on the delivery data of multiple historical orders completed by a target store within a first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, determine an adjustment parameter for the estimated delivery duration at the current moment, where the time interval between the first time period and the current moment is less than a preset threshold;

[0007] Based on the number of first orders being delivered by the target store at the current moment, the number of second orders waiting for delivery by the target store at the current moment, and the number of available delivery personnel at the current moment, determine the estimated delivery duration at the current moment through a delivery duration estimation model;

[0008] Based on the adjustment parameter for the estimated delivery duration, adjust the estimated delivery duration, and determine the estimated delivery time of the order at the current moment based on the adjusted estimated delivery duration.

[0009] According to the second aspect of the embodiments of the present application, a device for determining the estimated delivery time of an order is provided. The device includes:

[0010] A first determination module, configured to determine an estimated delivery duration adjustment parameter at the current moment based on the delivery data of multiple historical orders completed within a first time period before the current moment for the target store, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, where the time interval between the first time period and the current moment is less than a preset threshold;

[0011] A second determination module, configured to determine the estimated delivery duration at the current moment through a delivery duration estimation model based on the number of first orders being delivered at the current moment for the target store, the number of second orders waiting for delivery at the current moment for the target store, and the number of available delivery personnel at the current moment;

[0012] A third determination module, configured to adjust the estimated delivery duration based on the estimated delivery duration adjustment parameter, and determine the estimated order delivery time at the current moment based on the adjusted estimated delivery duration.

[0013] According to a third aspect of the embodiments of the present application, there is provided a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where, when the processor executes the computer program, the operations performed by the above method for determining the estimated order delivery time are implemented.

[0014] According to a fourth aspect of the embodiments of the present application, there is provided a computer-readable storage medium, on which a program is stored, and when the program is executed by the processor, the operations performed by the above method for determining the estimated order delivery time are implemented.

[0015] According to a fifth aspect of the embodiments of the present application, there is provided a computer program product, including a computer program, and when the computer program is executed by the processor, the operations performed by the above method for determining the estimated order delivery time are implemented.

[0016] The technical solutions provided by the embodiments of the present application may include the following beneficial effects:

[0017] Based on the delivery data of multiple historical orders completed by the target store within the first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, an estimated delivery duration adjustment parameter before the current moment is determined. So that after determining the estimated delivery duration before the current moment through a delivery duration estimation model based on the number of the first orders being delivered by the target store at the current moment, the number of the second orders waiting for delivery by the target store at the current moment, and the number of available delivery personnel at the current moment, the estimated delivery duration can be adjusted based on the estimated delivery duration adjustment parameter, and the estimated delivery time of the order before the current moment can be determined based on the adjusted estimated delivery duration. By introducing the estimated delivery duration adjustment parameter determined based on the historical orders within the first time period during the estimation process of the order delivery time, the estimated delivery duration adjustment parameter can help adjust the estimated delivery duration estimated by the model and improve the accuracy of the finally determined estimated delivery time.

[0018] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. Brief Description of the Drawings

[0019] The drawings herein are incorporated into the specification and constitute a part of this application, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0020] Figure 1 is a flowchart of a method for determining the estimated delivery time of an order shown according to an exemplary embodiment of this application.

[0021] Figure 2 is a schematic diagram of the value of an estimated delivery duration adjustment coefficient shown according to an exemplary embodiment of this application.

[0022] Figure 3 is a block diagram of a device for determining the estimated delivery time of an order shown according to an exemplary embodiment of this application.

[0023] Figure 4 is a schematic diagram of the structure of a computing device shown according to an exemplary embodiment of this application. Detailed Description of the Embodiments

[0024] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are only examples of devices and methods consistent with some aspects of this application as detailed in this application.

[0025] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a", "the", and "said" used in this application are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0026] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0027] This application provides a method for determining the estimated delivery time of an order, which is used to introduce an estimated delivery duration adjustment parameter determined based on recent historical orders during the process of determining the estimated delivery time of an order. Thus, after the estimated delivery time of the order is determined by the delivery duration estimation model, the estimated delivery time determined by the model is adjusted based on the estimated delivery duration adjustment parameter, so that the final estimated delivery time can more truly reflect the change in the order volume of the store on the same day and improve the accuracy of determining the estimated delivery time.

[0028] The method for determining the estimated delivery time of an order provided by this application can be applied to the takeaway business scenario. In the takeaway business scenario, a customer can place a takeaway order through a takeaway software. For a potential order (an order in which the customer has entered the meal ordering interface, selected the delivery address, but has not officially placed an order yet), when the customer has selected the takeaway delivery location before placing the takeaway order, the terminal can display the estimated delivery time of this order to inform the customer when the takeaway will be delivered to the customer's hands if the order is placed immediately at the current moment. Among them, the estimated delivery time of the order displayed by the terminal can be predicted by the method for determining the estimated delivery time of an order provided by this application.

[0029] Optionally, the estimated delivery time can also be referred to as the promised delivery time, indicating that it is promised to deliver the takeaway to the customer before this time.

[0030] The above method for determining the estimated delivery time of an order can be executed by a computing device. The computing device can be a server, such as a single server, multiple servers, a server cluster, a cloud computing platform, etc., but is not limited thereto. This application does not limit the device type and the number of devices of the computing device.

[0031] The above is only an exemplary description of the application scenarios of the present application, and does not constitute a limitation on the application scenarios of the present application. In more possible implementation manners, the present application can be applied to other scenarios that require predicting the order delivery time more.

[0032] After introducing the application scenarios of the present application, next, in combination with the embodiments of the present application, the method for determining the estimated delivery time of the order provided by the present application will be further described.

[0033] As Figure 1 shown, Figure 1 is a flowchart of a method for determining the estimated delivery time of an order shown according to an exemplary embodiment of the present application. The method includes the following steps:

[0034] Step 101: Based on the delivery data of multiple historical orders completed by the target store within the first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, determine the estimated delivery duration adjustment parameter at the current moment, where the time interval between the first time period and the current moment is less than a preset threshold.

[0035] Among them, the target store can be any store among multiple stores in the business scenario. The target store can be a restaurant, convenience store, supermarket, flower shop, dessert shop, etc. The present application does not limit the store type of the target store. Taking the business scenario as the takeaway business scenario as an example, the target store can be any restaurant in the takeaway business scenario.

[0036] The first time period can be the time period corresponding to the first preset duration before the current moment. The first preset duration can be a relatively short duration, and the time interval between the first time period and the current moment can be less than the preset threshold, so as to determine the estimated delivery duration adjustment parameter based on the historical orders within a relatively short period of time recently.

[0037] The delivery data can include various data related to the order delivery situation. The present application does not limit the data content included in the delivery data.

[0038] Optionally, when receiving a to-be-processed order that has just been placed, the determination of the estimated delivery duration adjustment parameter at the current moment can be triggered, and the order placement time of the to-be-processed order is the current moment. Or, the determination of the estimated delivery duration adjustment parameter can be performed periodically. Whenever the determination period of the estimated delivery duration adjustment parameter is reached, the determination of the estimated delivery duration adjustment parameter at the current moment is triggered.

[0039] It should be noted that the to-be-processed order can be a potential order, that is, an order in which the customer has entered the ordering interface, selected the delivery address, but has not officially placed an order yet. The generation time of the to-be-processed order can be the time when the customer selects the delivery address in the ordering interface.

[0040] The on-time rate of the target store in the first time period can be determined based on the order delivery situation of the target store in the first time period. For example, the on-time rate of the target store in the first time period can be the ratio of the number of orders delivered by the target store within the estimated delivery time to the total number of orders in the first time period.

[0041] The expected on-time rate threshold of the target store can be pre-set by the target store according to its own business goals, and the expected on-time rate threshold can include various types of threshold values.

[0042] The estimated delivery duration adjustment parameter can be used to indicate the duration value that needs to be adjusted based on the estimated delivery duration predicted by the model.

[0043] Step 102: Based on the number of the first orders being delivered by the target store at the current moment, the number of the second orders waiting for delivery by the target store at the current moment, and the number of available delivery personnel at the current moment, determine the estimated delivery duration at the current moment through the delivery duration estimation model.

[0044] Among them, the delivery duration estimation model can be any type of machine learning model. For example, the delivery duration estimation model can be a Support Vector Machine (SVM) model, but it is not limited to this. The delivery duration estimation model can also be other types of machine learning models. The application does not limit the model type of the delivery duration estimation model.

[0045] Step 103: Adjust the estimated delivery duration based on the estimated delivery duration adjustment parameter, and determine the estimated order delivery time at the current moment based on the adjusted estimated delivery duration.

[0046] In this application, based on the delivery data of multiple historical orders completed by the target store in the first time period before the current moment, the on-time rate of the target store in the first time period, and the expected on-time rate threshold of the target store, the estimated delivery duration adjustment parameter before the current moment is determined. So that after determining the estimated delivery duration before the current moment through the delivery duration estimation model based on the number of the first orders being delivered by the target store at the current moment, the number of the second orders waiting for delivery by the target store at the current moment, and the number of available delivery personnel at the current moment, the estimated delivery duration can be adjusted based on the estimated delivery duration adjustment parameter, and the estimated order delivery time before the current moment can be determined based on the adjusted estimated delivery duration. By introducing the estimated delivery duration adjustment parameter determined based on the historical orders in the first time period in the process of estimating the order delivery time, the estimated delivery duration adjustment parameter can help adjust the estimated delivery duration predicted by the model and improve the accuracy of the finally determined estimated delivery time.

[0047] After introducing the basic implementation process of the present application, various non-limiting implementation manners of the present application will be specifically introduced below.

[0048] In some embodiments, for step 101, based on the delivery data of multiple historical orders completed by the target store within the first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, to determine the estimated delivery duration adjustment parameter at the current moment, where when the time interval between the first time period and the current moment is less than the preset threshold, it can be implemented through the following steps:

[0049] Step 1011: Based on the on-time rate of the target store within the first time period and the expected on-time rate threshold of the target store, determine the estimated delivery duration adjustment coefficient at the current moment, and the estimated delivery duration adjustment coefficient is used to indicate the accuracy of the delivery duration estimation model for estimating the delivery duration.

[0050] It should be noted that the delivery on-time rate is not necessarily the higher the better, because a high on-time rate requires a large number of delivery personnel as a guarantee, and the increase in the number of delivery personnel will directly lead to an increase in the operating cost of the store. If this part of the cost increase is added to the delivery fee of the customer, it is very likely that the customer will not place an order at this store due to the high delivery fee; and if the delivery on-time rate is too low, it means that the orders of this store cannot be delivered to the customer within the estimated delivery duration, thus causing customer dissatisfaction and no longer placing an order at this store, resulting in customer loss. Therefore, for each store, it is necessary to set a corresponding threshold for the on-time rate (that is, the expected on-time rate threshold) to ensure that both customers can be retained and the delivery fee paid by the customer is not too high.

[0051] Optionally, the expected on-time rate threshold may include a first upper limit value, a first lower limit value, a second upper limit value, and a second lower limit value. The first upper limit value can be used to indicate the upper limit of the on-time rate that the target store expects to reach, the first lower limit value can be used to indicate the lower limit of the on-time rate that the target store expects to reach, the second upper limit value can be used to indicate the upper limit of the on-time rate that the target store can accept, and the second lower limit value can be used to indicate the lower limit of the on-time rate that the target store can accept, where the first upper limit value is less than the second upper limit value, and the first lower limit value is less than the second lower limit value.

[0052] Among them, the first lower limit value and the first upper limit value can form the target on-time rate interval of the target store. For example, denote the first upper limit value as p + , and denote the first lower limit value as p - , then the target on-time rate interval of the target store can be denoted as [p - , p +. The on-time rate range is a relatively reasonable on-time rate range that the target store expects to achieve. If the order on-time rate of the target store during a certain period is within the above range, it can be considered that the estimated delivery duration is relatively reasonable, and the delivery personnel can deliver the order to the customer within the estimated delivery duration; if the order on-time rate of the target store during a certain period is less than p - , it is considered that the on-time rate of the target store is poor, the estimated delivery duration is short, and the delivery personnel cannot deliver the order to the customer within the estimated delivery duration; if the order on-time rate of the target store during a certain period is greater than p + , it is considered that the number of delivery personnel in the target store is excessive, the delivery cost is high, and the estimated delivery duration is long. Not only can the delivery personnel deliver the order to the customer within the estimated delivery duration, but the actual delivery time is also much earlier than the estimated delivery time.

[0053] In addition, the second lower limit value and the second upper limit value can form the acceptable extreme on-time rate range of the target store. For example, if the second upper limit value is denoted as p max , and the second lower limit value is denoted as p min , then the extreme on-time rate range of the target store can be denoted as [p min , p max . The extreme on-time rate range is the acceptable extreme on-time rate range of the target store. If the order on-time rate of the target store during a certain period is within the above range, it can be considered that although the estimated delivery duration is not very reasonable, it is within the acceptable range of the target store; if the on-time rate is less than p min , the previous estimated delivery duration is short, and the target store simply cannot complete it, and the subsequent estimated delivery duration needs to be increased; if the on-time rate is greater than p max , the previous estimated delivery duration is long, resulting in customers being unwilling to place orders at this store, and the target store also cannot accept it, and the subsequent estimated delivery duration needs to be reduced.

[0054] Therefore, the estimated delivery duration adjustment coefficient can be determined based on the on-time rate of the target store in the first time period and the expected on-time rate threshold of the target store, so as to evaluate the reasonableness of the estimated delivery duration predicted by the model through the estimated delivery duration adjustment coefficient.

[0055] In a possible implementation manner, when the on-time rate of the target store is less than the second lower limit value, the estimated delivery duration adjustment coefficient is determined to be 1.

[0056] It should be noted that when the on-time rate (denoted as p) is less than the second lower limit value (that is, p < p min ), it indicates that the estimated delivery duration of the model is very unreasonable and has exceeded the on-time rate limit that the target store can accept. It is necessary to adjust the estimated delivery duration of the model to a large extent. Therefore, the estimated delivery duration adjustment coefficient can be set to 1.

[0057] In another possible implementation, when the on-time rate of the target store is greater than or equal to the second lower limit value and less than or equal to the first lower limit value, an estimated delivery duration adjustment coefficient is determined based on the on-time rate of the target store, the first lower limit value, and the second lower limit value.

[0058] It should be noted that when the on-time rate is greater than or equal to the second lower limit value and less than or equal to the first lower limit value (i.e., p ∈ [p min , p - ), the estimated delivery duration of the model is relatively unreasonable and is not within the target on-time rate range, but it does not exceed the on-time rate limit that the target store can accept. Therefore, an estimated delivery duration adjustment coefficient can be determined based on the first target value, the on-time rate of the target store, the first lower limit value, and the second lower limit value, so that the estimated delivery duration adjustment coefficient changes between 0 and 1. The closer the on-time rate is to p - , the closer the estimated delivery duration adjustment coefficient is to 0, indicating that the degree of adjustment required for the on-time rate is smaller; the closer the on-time rate is to p min , the closer the estimated delivery duration adjustment coefficient is to 1, indicating that the degree of adjustment required for the on-time rate is greater.

[0059] Optionally, when determining the estimated delivery duration adjustment coefficient based on the on-time rate of the target store, the first lower limit value, and the second lower limit value, a first difference can be determined based on the on-time rate of the target store and the second lower limit value; a second difference can be determined based on the first lower limit value and the second lower limit value; the ratio of the first difference and the second difference is determined as the first ratio; the difference between the first target value (i.e., 1) and the first ratio is determined as the estimated delivery duration adjustment coefficient.

[0060] For example, the following formula (1) can be used to determine the estimated delivery duration adjustment coefficient based on the on-time rate of the target store, the first lower limit value, and the second lower limit value:

[0061]

[0062] where adjust k represents the estimated delivery duration adjustment coefficient, p represents the on-time rate of the target store, p min represents the second lower limit value, and p - represents the first lower limit value.

[0063] In another possible implementation, when the on-time rate of the target store is greater than the first lower limit value and less than or equal to the first upper limit value, the estimated delivery duration adjustment coefficient is determined to be 0.

[0064] It should be noted that when the on-time rate is greater than the first lower limit value and less than or equal to the first upper limit value (i.e., p ∈ (p - , p +) When the estimated delivery duration of the model is reasonable and does not need to be adjusted, the estimated delivery duration adjustment coefficient can be set to 0.

[0065] In another possible implementation, when the on-time rate of the target store is greater than the first upper limit value and less than or equal to the second upper limit value, based on the on-time rate of the target store, the first upper limit value, and the second upper limit value, determine the estimated delivery duration adjustment coefficient.

[0066] It should be noted that when the on-time rate is greater than the first upper limit value and less than or equal to the second upper limit value (that is, p ∈ (p + , p max ), the estimated delivery duration of the model is relatively unreasonable and not within the target on-time rate range, but it does not exceed the on-time rate limit that the target store can accept. Therefore, based on the on-time rate of the target store, the first upper limit value, and the second upper limit value, determine the estimated delivery duration adjustment coefficient to set the estimated delivery duration adjustment coefficient to vary between 0 and 1. The closer the on-time rate is to p + , the closer the estimated delivery duration adjustment coefficient is to 0, indicating that the degree of adjustment required for the on-time rate is smaller; the closer the on-time rate is to p max , the closer the estimated delivery duration adjustment coefficient is to 1, indicating that the degree of adjustment required for the on-time rate is greater.

[0067] Optionally, when determining the estimated delivery duration adjustment coefficient based on the on-time rate of the target store, the first upper limit value, and the second upper limit value, the third difference can be determined based on the on-time rate of the target store and the first upper limit value; the fourth difference can be determined based on the second upper limit value and the first upper limit value; and the ratio of the third difference and the fourth difference is determined as the estimated delivery duration adjustment coefficient.

[0068] For example, according to the following formula (2), based on the on-time rate of the target store, the first upper limit value, and the second upper limit value, determine the estimated delivery duration adjustment coefficient:

[0069]

[0070] Among them, adjust k represents the estimated delivery duration adjustment coefficient, p represents the on-time rate of the target store, p max represents the second upper limit value, and p + represents the first upper limit value.

[0071] In another possible implementation, when the on-time rate of the target store is greater than the second upper limit value, the estimated delivery duration adjustment coefficient is determined to be 1.

[0072] It should be noted that when the on-time rate is greater than the second upper limit value (that is, p > p max) When it is the case, it indicates that the estimated delivery duration of the model is very unreasonable and has exceeded the limit of the on-time rate acceptable to the target store. It is necessary to adjust the estimated delivery duration of the model to a large extent. Therefore, the adjustment coefficient of the estimated delivery duration can be set to 1.

[0073] Optionally, the above five methods for determining the adjustment coefficient of the estimated delivery duration can be integrated into the following formula (3):

[0074]

[0075] Among them, adjust k represents the adjustment coefficient of the estimated delivery duration, p represents the on-time rate of the target store, p + represents the first upper limit value, p - represents the first lower limit value, p max represents the second upper limit value, p min represents the second lower limit value.

[0076] See Figure 2 , Figure 2 is a schematic diagram of the value of the adjustment coefficient of the estimated delivery duration shown according to an exemplary embodiment of the present application. As Figure 2 shown, when p ∈ (p - , p + , the adjustment coefficient of the estimated delivery duration is 0; when p < p min or p > p max , the adjustment coefficient of the estimated delivery duration is 1; when p ∈ (p min , p - or p ∈ (p + , p max , the adjustment coefficient of the estimated delivery duration varies between 0 and 1. The closer the on-time rate is to p - or p + , the closer the adjustment coefficient of the estimated delivery duration is to 0. The closer the on-time rate is to p min or p max , the closer the adjustment coefficient of the estimated delivery duration is to 1.

[0077] Step 1012: Based on the delivery data of multiple historical orders completed by the target store within the first time period, determine the adjustment span of the estimated delivery duration at the current moment. The adjustment span of the estimated delivery duration is used to indicate the difference between the estimated delivery duration and the actual delivery duration estimated by the delivery duration estimation model within the first time period.

[0078] Among them, the delivery data may include the historical order placement time, the historical actual delivery time, and the historical estimated delivery time, but is not limited thereto. The delivery data may also include other types of data.

[0079] In some embodiments, the above step 1012 may be implemented through the following steps:

[0080] Step 1012A: Based on the historical order placement times and historical actual delivery times of multiple historical orders, determine the historical average actual completion duration of the multiple historical orders.

[0081] In a possible implementation, the historical actual completion duration of each historical order may be determined based on the historical order placement time and historical actual delivery time of each historical order, and then the historical average actual completion duration of the multiple historical orders may be determined based on the historical actual completion duration of each historical order among the multiple historical orders.

[0082] Optionally, when determining the historical actual completion duration of each historical order based on the historical order placement time and historical actual delivery time of each historical order, the difference between the historical actual delivery time and the historical order placement time of each historical order may be determined as the historical actual completion duration of each historical order, that is, the historical actual completion duration of each historical order may be calculated in the manner of "historical actual completion duration = historical actual delivery time - historical order placement time".

[0083] Step 1012B: Based on the historical order placement times and historical estimated delivery times of multiple historical orders, determine the historical average estimated delivery duration of the multiple historical orders.

[0084] In a possible implementation, the historical estimated delivery duration of each historical order may be determined based on the historical order placement time and historical estimated delivery time of each historical order, and then the historical average estimated delivery duration of the multiple historical orders may be determined based on the historical estimated delivery duration of each historical order among the multiple historical orders.

[0085] Optionally, when determining the historical estimated delivery duration of each historical order based on the historical order placement time and historical estimated delivery time of each historical order, the difference between the historical estimated delivery time and the historical order placement time of each historical order may be determined as the historical estimated completion duration of each historical order, that is, the historical estimated completion duration of each historical order may be calculated in the manner of "historical estimated completion duration = historical estimated delivery time - historical order placement time".

[0086] Step 1012C: Determine the difference between the historical average estimated delivery duration and the historical average actual completion duration as the estimated delivery duration adjustment span.

[0087] It should be noted that the historical average actual completion time can reflect the actual delivery time of the completed orders within the first time period, and the historical average estimated delivery time can reflect the model-estimated delivery time of the completed orders within the first time period. After obtaining the historical average actual completion time and the historical average estimated delivery time, the estimated delivery time adjustment span at the current moment can be calculated according to the following formula (4):

[0088]

[0089] Among them, adjust span represents the estimated delivery time adjustment span, represents the historical average estimated delivery time, represents the historical average actual completion time.

[0090] It should be noted that the estimated delivery time adjustment span adjust span can reflect the difference between the model-estimated delivery time and the actual delivery time. If adjust span > 0, it indicates that the model has insufficient confidence in the target store and the delivery personnel, and the estimated delivery time determined by the model is relatively long. Therefore, it is necessary to adjust the estimated delivery time determined by the model in the direction of a shorter time; if adjust span < 0, it indicates that the model has excessive confidence in the target store and the delivery personnel, and the estimated delivery time determined by the model is relatively short. Therefore, it is necessary to adjust the estimated delivery time determined by the model in the direction of a longer time.

[0091] Step 1013: Determine the estimated delivery time adjustment parameter based on the estimated delivery time adjustment span and the estimated delivery time adjustment coefficient.

[0092] In a possible implementation manner, the product of the estimated delivery time adjustment span and the estimated delivery time adjustment coefficient can be determined as the estimated delivery time adjustment parameter at the current moment.

[0093] For example, the estimated delivery time adjustment parameter at the current moment can be determined according to the following formula (5):

[0094] adjust period = adjust k × adjust span (5)

[0095] Among them, adjust period represents the estimated delivery time adjustment parameter, adjust k represents the estimated delivery time adjustment coefficient, and adjust span represents the estimated delivery time adjustment span.

[0096] In some embodiments, the estimated delivery duration model may take the current delivery pressure value of the target store as the input and the estimated delivery duration as the output, so as to predict the estimated delivery time of the order based on the order placement time and the estimated delivery duration output by the model. Among them, the current delivery pressure value of the target store may be determined based on the number of the first orders being delivered by the target store currently, the number of the second orders waiting to be delivered by the target store currently, and the current number of available delivery personnel.

[0097] It should be noted that the orders being delivered by the target store currently may be the orders that the customers have placed and the delivery personnel have been assigned; the orders waiting to be delivered by the target store currently may be the orders that the customers have placed but the delivery personnel have not been assigned yet; the current available delivery personnel may be the delivery personnel in the process of delivery and / or the delivery personnel waiting to be assigned orders.

[0098] In some embodiments, for step 102, when determining the estimated delivery duration through the estimated delivery duration model based on the number of the first orders being delivered by the target store currently, the number of the second orders waiting to be delivered by the target store currently, and the current number of available delivery personnel, it may be achieved through the following steps:

[0099] Step 1021: Determine the current delivery pressure value of the target store based on the number of the first orders being delivered by the target store at the current moment, the number of the second orders waiting to be delivered by the target store at the current moment, and the current number of available delivery personnel.

[0100] In a possible implementation manner, the product of the number of the first orders being delivered by the target store at the current moment and a preset proportionality coefficient may be determined; the sum value of the product and the number of the second orders waiting to be delivered by the target store at the current moment may be determined; and the current delivery pressure value of the target store may be determined based on the sum value and the current number of available delivery personnel.

[0101] For example, the current delivery pressure value of the target store may be determined according to the following formula (6):

[0102]

[0103] Among them, press represents the current delivery pressure value of the target store, M1 represents the number of the first orders being delivered by the target store at the current moment, M2 represents the number of the second orders waiting to be delivered by the target store at the current moment, N represents the current number of available delivery personnel, and the preset proportionality coefficient is 0.5.

[0104] It should be noted that when calculating the ratio of the number of orders to the number of delivery personnel, the larger the ratio, the more orders the delivery personnel need to deliver, and the greater the current pressure on the target store; the smaller the ratio, the fewer orders the delivery personnel need to deliver, and the smaller the current pressure on the target store. Moreover, for the orders being delivered, since the status of such orders is unknown, for example, whether they have just left the target store or are about to be delivered to the customer, therefore, they can be converted according to a preset proportional coefficient. For example, the orders being delivered can be converted according to a preset proportional coefficient of 0.5, so as to regard them as 0.5 orders.

[0105] Step 1022: Based on the current delivery pressure value of the target store, determine the estimated delivery duration through the delivery duration estimation model.

[0106] It should be noted that the delivery duration estimation model can be pre-trained. For example, the delivery data of the historical orders completed within the second time period can be used as the training data to train the delivery duration estimation model. The time interval between the second time period and the current moment can be relatively long, and the second time period can be a relatively long time period to ensure that sufficient training data can be obtained, so as to improve the accuracy of the trained delivery duration estimation model as much as possible.

[0107] Optionally, the delivery duration estimation model can be an SVM model, but not limited to this. Other types of machine learning models can also be used as the delivery duration estimation model.

[0108] It should be noted that since the estimated delivery time needs to be displayed for the customer before they actually place an order, which means that the estimated delivery duration needs to be calculated for all potential customers who are interested in purchasing, resulting in a relatively large calculation scale. Therefore, the estimated delivery duration can be determined in advance through the delivery duration estimation model, and the determined estimated delivery duration can be used as the estimated delivery duration applicable to all potential orders within a certain period of time (such as within Δt1 time). Wherein, Δt1 can represent the effective duration of the determined estimated delivery duration, and the value of Δt1 can be 1 minute.

[0109] That is, at the current moment current time The calculated estimated delivery duration promise period Can be effective within the next Δt1 time. That is, if there is a potential order occurring within the [current time , current time +Δt1] time period, the estimated delivery duration of the potential order can be determined as the estimated delivery duration calculated at the current moment current time . Until current timeAt time +Δt1, calculate the estimated delivery duration of potential orders in the time period corresponding to the next Δt1 time (i.e., in the time period time +Δt1, current time +2Δt1]).

[0110] Optionally, based on the above settings of the method for determining the estimated delivery duration, the process of determining the estimated delivery duration adjustment parameter can also be periodic. For example, it can be set that the estimated delivery duration adjustment parameter adjust time calculated at the current moment current period will take effect within the next Δt2 time. Wherein, Δt2 can represent the effective duration of the determined estimated delivery duration adjustment parameter, and the value of Δt2 can be the same as the value of Δt1, or the value of Δt2 can be different from the value of Δt1. The present application does not limit the value of Δt2.

[0111] That is, the estimated delivery duration adjustment parameter adjust time calculated at the current moment current period can take effect within the next Δt2 time. That is, the estimated delivery duration adjustment parameter calculated at the current moment current time can be used as the estimated delivery duration adjustment parameter effective within the time period time current time +Δt2]. When reaching the moment current time +Δt2, calculate the estimated delivery duration adjustment parameter of potential orders in the time period corresponding to the next Δt2 time (i.e., in the time period time +Δt2, current time +2Δt2).

[0112] Alternatively, the estimated delivery duration adjustment parameter of each order can also be calculated in real time. For example, when receiving each potential order, determine the estimated delivery duration adjustment parameter corresponding to the potential order. The determined estimated delivery duration adjustment parameter only takes effect for the current potential order, thereby improving the real-time performance and effectiveness of the determined estimated delivery duration adjustment parameter.

[0113] In some embodiments, for step 103, when adjusting the estimated delivery duration based on the estimated delivery duration adjustment parameter and determining the estimated delivery time of the order at the current moment based on the adjusted estimated delivery duration, it can be implemented through the following steps:

[0114] Step 1031: Determine the difference between the estimated delivery duration and the estimated delivery duration adjustment parameter as the adjusted estimated delivery duration.

[0115] In a possible implementation, the adjusted estimated delivery duration can be calculated according to the following formula (6):

[0116] promise period =estimate model (perss)-asjust period (6)

[0117] Wherein, promise period represents the adjusted estimated delivery duration, estimate model (perss) represents the estimated delivery duration predicted by the model, and adjustk period represents the estimated delivery duration adjustment parameter.

[0118] Step 1032: Determine the estimated delivery time of the order at the current moment based on the adjusted estimated delivery duration.

[0119] Optionally, the adjusted estimated delivery time can be added to the current moment to obtain the estimated delivery time of the order at the current moment.

[0120] Through the method for determining the estimated delivery time of the order provided by this application, by introducing recently completed orders with shorter time, an estimated delivery duration adjustment parameter that can more truly reflect the change in the order delivery situation of the target store on the same day can be obtained, so as to adjust the prediction result of the delivery duration estimation model according to the estimated delivery duration adjustment parameter, so as to obtain a more accurate estimated promised delivery duration, and thus obtain a more accurate estimated delivery time of the order.

[0121] For ease of understanding, the following uses a specific example to further illustrate the method for determining the estimated delivery time of the order provided by this application.

[0122] For example, for a target store, it is known that the target on-time rate range of the target store is [88%, 92%], the upper limit of the acceptable extreme on-time rate of the target store is 100%, and the lower limit of the acceptable extreme on-time rate of the target store is 80%. That is, p - =88%, p + =92%, p min =80%, p max =100%.

[0123] The number of orders recently completed by the target store is 20. These 20 historical orders can be denoted as order1, order2, ……, order19, order20. Given the historical order placement time and historical estimated delivery duration of each historical order, the historical estimated delivery time of each historical order can be calculated. Moreover, since the orders have been completed, the historical actual completion time of each historical order can also be known, and thus the historical actual completion duration of each historical order can be calculated. The calculation results can be seen in Table 1 below:

[0124] Table 1

[0125]

[0126] Based on the delivery data of the 20 historical orders recently completed by the target store shown in Table 1 above, the on-time rate (i.e., p) of the orders recently completed by the target store can be statistically calculated as 96%.

[0127] Moreover, based on the delivery data of the 20 historical orders recently completed by the target store shown in Table 2, the estimated delivery duration adjustment coefficient adjust can be calculated k .

[0128] Since 96% ∈ (92%, 100%], that is, p ∈ (p + , p max , it indicates that the estimated delivery duration of the model is relatively unreasonable and not within the target on-time rate range, but it has not exceeded the on-time rate limit acceptable to the target store. Therefore, the estimated delivery duration adjustment coefficient adjust k needs to vary between 0 and 1. The closer the on-time rate is to p + (i.e., 92%), the closer adjust k is to 0, and the smaller the degree of adjustment required for the on-time rate; the closer the on-time rate is to p max (i.e., 100%), the closer adjust k is to 1, and the greater the degree of adjustment required for the on-time rate.

[0129] Therefore, the estimated delivery duration adjustment coefficient adjust can be calculated according to the following formula (7) k :

[0130]

[0131] Furthermore, based on the historical estimated delivery durations of these 20 historical orders, the historical average estimated delivery duration of these 20 historical orders can be determined as Moreover, based on the historical actual completion durations of these 20 historical orders, the historical average completion duration of these 20 historical orders can be determined as

[0132] Based on the above historical average estimated delivery duration and historical average completion duration, the adjustment span adjust of the estimated delivery duration can be determined according to the following formula (8) span :

[0133]

[0134] where adjust span = 4 > 0, indicating that the model has insufficient confidence in the target store and delivery personnel. The estimated delivery duration determined by the model is 4 minutes more than the actual completion duration. Therefore, it is necessary to adjust the estimated delivery duration determined by the model in the direction of shorter duration. That is, for new orders, the estimated delivery duration predicted by the subsequent model should be reduced.

[0135] Optionally, the adjustment parameter adjust of the estimated delivery duration can be determined according to the following formula (9) period :

[0136] adjust period = adjust k × adjust span = 0.5 × 4 = 2 (9)

[0137] Thus, after predicting the estimated delivery duration estimate based on the current pressure value (press) of the target store through the delivery duration prediction model model (perss), the estimated delivery duration predicted by the model can be adjusted according to the following formula (10) to obtain the adjusted estimated delivery duration promise period :

[0138]

[0139] That is, by adjusting the estimated delivery duration predicted by the model by reducing it by 2 minutes, the adjusted estimated delivery duration can be obtained.

[0140] Suppose there are two new orders (i.e., orders to be processed), new_order1 and new_order2, at the current moment. The estimated delivery duration model predicts that the estimated delivery duration of new_order1 is 38 minutes, and the estimated delivery duration of new_order2 is 41 minutes. Therefore, the estimated delivery duration predicted by the model can be adjusted by reducing 2 minutes to determine that the adjusted estimated delivery duration of new_order1 is 36 minutes and the adjusted estimated delivery duration of new_order2 is 39 minutes. Thus, based on the generation time of these two orders to be processed and the adjusted estimated delivery duration, the estimated delivery time of these two orders to be processed can be determined. The calculation results can be seen in Table 2 below:

[0141] Table 2

[0142]

[0143] Corresponding to the embodiments of the foregoing method, the present application also provides embodiments of a device and a computing device to which the device is applied.

[0144] As Figure 3 shown, Figure 3 is a block diagram of a device for determining the estimated delivery time of an order according to an exemplary embodiment of the present application. The device includes:

[0145] A first determination module 301, configured to determine an estimated delivery duration adjustment parameter at the current moment based on the delivery data of multiple historical orders completed by a target store within a first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, where the time interval between the first time period and the current moment is less than a preset threshold;

[0146] A second determination module 302, configured to determine the estimated delivery duration at the current moment through an estimated delivery duration model based on the number of first orders being delivered by the target store at the current moment, the number of second orders waiting to be delivered by the target store at the current moment, and the number of available delivery personnel at the current moment;

[0147] A third determination module 303, configured to adjust the estimated delivery duration based on the estimated delivery duration adjustment parameter, and determine the estimated delivery time of the order at the current moment based on the adjusted estimated delivery duration.

[0148] In some embodiments, the first determination module 301 is specifically configured to:

[0149] Based on the on-time rate of the target store within the first time period and the expected on-time rate threshold of the target store, determine the estimated delivery duration adjustment coefficient at the current moment. The estimated delivery duration adjustment coefficient is used to indicate the accuracy of the delivery duration estimation model for estimating the delivery duration;

[0150] Based on the delivery data of multiple historical orders completed by the target store within the first time period, determine the estimated delivery duration adjustment span at the current moment. The estimated delivery duration adjustment span is used to indicate the difference between the estimated delivery duration and the actual delivery duration estimated by the delivery duration estimation model within the first time period;

[0151] Based on the estimated delivery duration adjustment span and the estimated delivery duration adjustment coefficient, determine the estimated delivery duration adjustment parameter.

[0152] In some embodiments, the expected on-time rate threshold includes a first upper limit value, a first lower limit value, a second upper limit value, and a second lower limit value. The first upper limit value is used to indicate the upper limit of the on-time rate that the target store expects to achieve, the first lower limit value is used to indicate the lower limit of the on-time rate that the target store expects to achieve, the second upper limit value is used to indicate the upper limit of the on-time rate that the target store can accept, and the second lower limit value is used to indicate the lower limit of the on-time rate that the target store can accept. Among them, the first upper limit value is less than the second upper limit value, and the first lower limit value is less than the second lower limit value;

[0153] The first determination module 301 is specifically used to perform any one of the following:

[0154] When the on-time rate of the target store is less than the second lower limit value, determine the estimated delivery duration adjustment coefficient as 1;

[0155] When the on-time rate of the target store is greater than or equal to the second lower limit value and less than or equal to the first lower limit value, determine the estimated delivery duration adjustment coefficient based on the on-time rate of the target store, the first lower limit value, and the second lower limit value;

[0156] When the on-time rate of the target store is greater than the first lower limit value and less than or equal to the first upper limit value, determine the estimated delivery duration adjustment coefficient as 0;

[0157] When the on-time rate of the target store is greater than the first upper limit value and less than or equal to the second upper limit value, determine the estimated delivery duration adjustment coefficient based on the on-time rate of the target store, the first upper limit value, and the second upper limit value;

[0158] When the on-time rate of the target store is greater than the second upper limit value, determine the estimated delivery duration adjustment coefficient as 1.

[0159] In some embodiments, the delivery data includes the historical order placement time, the historical actual delivery time, and the historical estimated delivery time;

[0160] The first determination module 301 is specifically configured to:

[0161] Based on the historical order placement time and historical actual delivery time of multiple historical orders, determine the historical average actual completion duration of the multiple historical orders;

[0162] Based on the historical order placement time and historical estimated delivery time of multiple historical orders, determine the historical average estimated delivery duration of the multiple historical orders;

[0163] Determine the difference between the historical average estimated delivery duration and the historical average actual completion duration as the adjustment span of the estimated delivery duration.

[0164] In some embodiments, the first determination module 301 is specifically configured to:

[0165] Determine the product of the adjustment span of the estimated delivery duration and the adjustment coefficient of the estimated delivery duration as the adjustment parameter of the estimated delivery duration.

[0166] In some embodiments, the third determination module 303 is specifically configured to:

[0167] Determine the difference between the estimated delivery duration and the adjustment parameter of the estimated delivery duration as the adjusted estimated delivery duration;

[0168] Based on the adjusted estimated delivery duration, determine the estimated delivery time of the order at the current moment.

[0169] For the implementation processes of the functions and roles of each module in the above device, please refer to the implementation processes of the corresponding steps in the above method for details, which will not be elaborated here.

[0170] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial descriptions of the method embodiments. The device embodiments described above are only illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0171] This application also provides a computing device. Refer to Figure 4 , Figure 4 is a schematic structural diagram of a computing device shown by this application according to an exemplary embodiment. As Figure 4As shown, the computing device includes a processor 410, a memory 420, and a network interface 430. The memory 420 is used to store computer instructions that can run on the processor 410. The processor 410 is used to implement the method for determining the estimated delivery time of an order provided in any embodiment of the present application when executing the computer instructions. The network interface 430 is used to implement input and output functions. In more possible implementation manners, the computing device may further include other hardware, which is not limited in the present application.

[0172] The present application also provides a computer-readable storage medium. The computer-readable storage medium can be in various forms. For example, in different examples, the computer-readable storage medium can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or a combination thereof. Specifically, the computer-readable medium can also be paper or other suitable media capable of printing programs. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the method for determining the estimated delivery time of an order provided in any embodiment of the present application.

[0173] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the method for determining the estimated delivery time of an order provided in any embodiment of the present application.

[0174] Those skilled in the art should understand that one or more embodiments of the present application can be provided as a method, apparatus, computing device, computer-readable storage medium, or computer program product for determining the estimated delivery time of an order. Therefore, one or more embodiments of the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0175] The various embodiments in the present application are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiment corresponding to the computing device, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

[0176] The foregoing describes particular embodiments of the present application. Other embodiments are within the scope of the present application. In some cases, the acts or steps recited in this application can be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain implementations, multitasking and parallel processing are also possible or may be advantageous.

[0177] Embodiments of the subject matter and the functional operations described in this application can be implemented in: digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this application and their structural equivalents, or one or more of them in combination. Embodiments of the subject matter described in this application can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible non-transitory program carrier to be executed by, or to control the operation of, a data processing apparatus. Alternatively or additionally, the program instructions can be encoded on an artificially generated propagated signal, such as a machine-generated electrical, optical, or electromagnetic signal, generated to encode and transmit information to a suitable receiver apparatus for execution by the apparatus for determining the estimated time of arrival of an order. A computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0178] The processes and logical flows described in this application can be performed by one or more programmable computers executing one or more computer programs to perform the corresponding functions by operating on input data and generating output. The processes and logical flows can also be performed by, or the apparatus can be implemented as, special purpose logic circuitry, such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0179] Computers suitable for executing computer programs include, for example, general and / or special purpose microprocessors, or any other type of central processing unit. Generally, the central processing unit will receive instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, etc., or the computer will be operably coupled to such mass storage devices to receive data therefrom or transfer data thereto, or both. However, a computer is not necessarily required to have such devices. In addition, a computer may be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name just a few examples.

[0180] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as including semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0181] Although this application contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of what is claimed, but rather as mainly describing the features of specific embodiments of a particular invention. Certain features described in multiple embodiments in this application may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may operate in certain combinations as described above and are even initially claimed as such, one or more features from a claimed combination may in some cases be removed from that combination, and the claimed combination may be directed to a sub-combination or a variation of a sub-combination.

[0182] Similarly, although operations are depicted in the drawings in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or sequentially, or that all illustrated operations be performed, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0183] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the present application. In some cases, the acts recited in this application can be performed in a different order and still achieve the desired results. Additionally, the processes depicted in the figures are not necessarily in the particular order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0184] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include known common knowledge or conventional technical means in the technical field not claimed in this application. That is, this application is not limited to the exact structures described above and shown in the figures, and various modifications and changes can be made without departing from its scope.

[0185] The above are only alternative embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for determining the estimated delivery time of an order, characterized in that, The method includes: Determining an estimated delivery duration adjustment parameter at the current moment based on the delivery data of multiple historical orders completed by the target store within a first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, where the time interval between the first time period and the current moment is less than a preset threshold; Determining the estimated delivery duration at the current moment through a delivery duration estimation model based on the number of first orders being delivered by the target store at the current moment, the number of second orders waiting for delivery by the target store at the current moment, and the number of available delivery personnel at the current moment; Adjusting the estimated delivery duration based on the estimated delivery duration adjustment parameter, and determining the estimated order delivery time at the current moment based on the adjusted estimated delivery duration.

2. The method according to claim 1, wherein The determining of the estimated delivery duration adjustment parameter at the current moment based on the delivery data of multiple historical orders completed by the target store within a first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store includes: Determining an estimated delivery duration adjustment coefficient at the current moment based on the on-time rate of the target store within the first time period and the expected on-time rate threshold of the target store, where the estimated delivery duration adjustment coefficient is used to indicate the accuracy of the delivery duration estimation model in estimating the delivery duration; Determining an estimated delivery duration adjustment span at the current moment based on the delivery data of multiple historical orders completed by the target store within the first time period, where the estimated delivery duration adjustment span is used to indicate the difference between the estimated delivery duration and the actual delivery duration estimated by the delivery duration estimation model within the first time period; Determining the estimated delivery duration adjustment parameter based on the estimated delivery duration adjustment span and the estimated delivery duration adjustment coefficient.

3. The method according to claim 2, characterized in that, The expected on-time rate threshold includes a first upper limit value, a first lower limit value, a second upper limit value, and a second lower limit value. The first upper limit value is used to indicate the upper limit of the on-time rate that the target store expects to achieve, the first lower limit value is used to indicate the lower limit of the on-time rate that the target store expects to achieve, the second upper limit value is used to indicate the upper limit of the on-time rate that the target store can accept, and the second lower limit value is used to indicate the lower limit of the on-time rate that the target store can accept. Among them, the first upper limit value is less than the second upper limit value, and the first lower limit value is less than the second lower limit value; The determining of the estimated delivery duration adjustment coefficient at the current moment based on the on-time rate of the target store within the first time period and the expected on-time rate threshold of the target store includes any one of the following: When the on-time rate of the target store is less than the second lower limit value, determining the estimated delivery duration adjustment coefficient as 1; When the on-time rate of the target store is greater than or equal to the second lower limit value and less than or equal to the first lower limit value, determining the estimated delivery duration adjustment coefficient based on the on-time rate of the target store, the first lower limit value, and the second lower limit value; When the on-time rate of the target store is greater than the first lower limit value and less than or equal to the first upper limit value, the estimated delivery duration adjustment coefficient is determined to be 0; When the on-time rate of the target store is greater than the first upper limit value and less than or equal to the second upper limit value, based on the on-time rate of the target store, the first upper limit value, and the second upper limit value, the estimated delivery duration adjustment coefficient is determined; When the on-time rate of the target store is greater than the second upper limit value, the estimated delivery duration adjustment coefficient is determined to be 1.

4. The method according to claim 2, wherein The delivery data includes the historical order placement time, the historical actual delivery time, and the historical estimated delivery time; Determining the adjustment span of the estimated delivery duration at the current moment based on the delivery data of multiple historical orders completed by the target store within the first time period includes: Based on the historical order placement time and the historical actual delivery time of the multiple historical orders, determining the historical average actual completion duration of the multiple historical orders; Based on the historical order placement time and the historical estimated delivery time of the multiple historical orders, determining the historical average estimated delivery duration of the multiple historical orders; Taking the difference between the historical average estimated delivery duration and the historical average actual completion duration as the adjustment span of the estimated delivery duration.

5. The method according to claim 2, characterized in that, Determining the estimated delivery duration adjustment parameter based on the adjustment span of the estimated delivery duration and the estimated delivery duration adjustment coefficient includes: Taking the product of the adjustment span of the estimated delivery duration and the estimated delivery duration adjustment coefficient as the estimated delivery duration adjustment parameter.

6. The method according to claim 1, wherein Adjusting the estimated delivery duration based on the estimated delivery duration adjustment parameter, and determining the estimated delivery time of the order at the current moment based on the adjusted estimated delivery duration includes: Determining the difference between the estimated delivery duration and the estimated delivery duration adjustment parameter as the adjusted estimated delivery duration; Based on the adjusted estimated delivery duration, determining the estimated delivery time of the order at the current moment.

7. A device for determining the estimated delivery time of an order, characterized in that, The device includes: A first determination module, configured to determine the adjustment parameter of the estimated delivery duration at the current moment based on the delivery data of multiple historical orders completed by the target store within the first time period before the current moment, the on-time rate of the target store within the first time period, and the expected on-time rate threshold of the target store, where the time interval between the first time period and the current moment is less than a preset threshold; A second determination module, configured to determine the estimated delivery duration at the current moment through a delivery duration estimation model based on the number of the first orders being delivered by the target store at the current moment, the number of the second orders waiting for delivery by the target store at the current moment, and the number of available delivery personnel at the current moment; A third determination module, configured to adjust the estimated delivery duration based on the adjustment parameter of the estimated delivery duration, and determine the estimated delivery time of the order at the current moment based on the adjusted estimated delivery duration.

8. The device according to claim 7, wherein The first determination module is specifically configured to: Determine an estimated delivery duration adjustment coefficient at the current moment based on the on-time rate of the target store during the first time period and the expected on-time rate threshold of the target store, where the estimated delivery duration adjustment coefficient is used to indicate the accuracy of the delivery duration estimation model in estimating the delivery duration; Determine an estimated delivery duration adjustment span at the current moment based on the delivery data of multiple historical orders completed by the target store during the first time period, where the estimated delivery duration adjustment span is used to indicate the difference between the estimated delivery duration and the actual delivery duration estimated by the delivery duration estimation model during the first time period; Determine the estimated delivery duration adjustment parameter based on the estimated delivery duration adjustment span and the estimated delivery duration adjustment coefficient.

9. A computing device, characterized in that, The computing device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. Wherein, when the processor executes the program, it implements the operations performed by the method for determining the estimated delivery time of an order according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, A program is stored on the computer-readable storage medium, and the program is executed by the processor to perform the operations performed by the method for determining the estimated delivery time of an order according to any one of claims 1 to 6.

Images