Method, apparatus and device for determining estimated time of arrival

Abstract

The application discloses a method, device and equipment for determining a predicted delivery time, and belongs to the technical field of computers. The method comprises the following steps: acquiring a lower limit of a predicted order time length and an upper limit of the predicted order time length corresponding to a target order, and acquiring a predicted distribution time length corresponding to the target order; determining a lower limit of the predicted delivery time based on the lower limit of the predicted order time length, the predicted distribution time length and a generation time of the target order; determining an upper limit of the predicted delivery time based on the upper limit of the predicted order time length, the predicted distribution time length and the generation time; and determining an intervalized predicted delivery time based on the lower limit of the predicted delivery time and the upper limit of the predicted delivery time. In this way, the reliability of the predicted delivery time can be improved, the deviation between an actual delivery time and the predicted delivery time can be reduced, the on-time rate can be improved, the rate of negative comments can be reduced, the user experience can be improved, and the application scenario is relatively wide.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, and device for determining the expected delivery time. Background Technology

[0002] As delivery services develop, there are increasingly more applications for determining the estimated delivery time of orders. After determining the estimated delivery time, this time can be communicated to the user.

[0003] Among them, orders include those that require merchants to manually place orders with the delivery platform (i.e., non-automatic order placement). For these orders, the estimated delivery time is usually set manually. The reliability of the estimated delivery time is low, and there is a tendency for the actual delivery time to deviate significantly from the estimated delivery time. This makes it difficult to guarantee on-time delivery, increases the rate of negative reviews, and reduces the user experience. Summary of the Invention

[0004] This application provides a method, apparatus, and device for determining the estimated delivery time, which can be used to solve the problem of low reliability of estimated delivery time in related technologies. The technical solution is as follows:

[0005] On one hand, embodiments of this application provide a method for determining the estimated delivery time, the method comprising:

[0006] Obtain the lower limit and upper limit of the estimated order delivery time for the target order, and obtain the estimated delivery time for the target order;

[0007] Based on the lower limit of the estimated order placement time, the estimated delivery time, and the creation time of the target order, a lower limit of the estimated delivery time is determined; based on the upper limit of the estimated order placement time, the estimated delivery time, and the creation time, an upper limit of the estimated delivery time is determined.

[0008] Based on the lower limit of the estimated delivery time and the upper limit of the estimated delivery time, an intervalized estimated delivery time is determined.

[0009] In one possible implementation, obtaining the lower limit and upper limit of the estimated order placement time corresponding to the target order includes:

[0010] Obtain the first target information corresponding to the target order for estimating the probability distribution of order delivery duration;

[0011] Input the first target information into the first prediction model to obtain the reference order placement duration probability distribution output by the first prediction model;

[0012] Based on the reference order placement duration probability distribution, determine the order placement duration interval that meets the target confidence level; based on the order placement duration interval, obtain the lower limit of the expected order placement duration and the upper limit of the expected order placement duration.

[0013] In one possible implementation, obtaining the lower limit of the expected order placement duration and the upper limit of the expected order placement duration based on the order placement duration range includes:

[0014] Obtain the lower limit threshold and the upper limit threshold of the order placement duration, wherein the lower limit threshold is less than the upper limit threshold;

[0015] The maximum value between the lower limit of the order placement duration range and the lower limit threshold of the order placement duration is taken as the expected lower limit of the order placement duration; the minimum value between the upper limit of the order placement duration range and the upper limit threshold of the order placement duration is taken as the expected upper limit of the order placement duration.

[0016] In one possible implementation, obtaining the lower threshold and upper threshold of the order placement duration includes:

[0017] Obtain multiple actual order placement durations corresponding to multiple reference orders, wherein the reference orders are orders that have been completed and placed;

[0018] Based on the multiple actual order durations and the first quantity, the lower limit threshold for order duration is determined, where the first quantity is the number of actual order durations among the multiple actual order durations that are less than the lower limit threshold for order duration.

[0019] Based on the multiple actual order durations and the second quantity, the upper limit threshold for order duration is determined, where the second quantity is the number of actual order durations among the multiple actual order durations that are less than the upper limit threshold for order duration, and the second quantity is greater than the first quantity.

[0020] In one possible implementation, obtaining the estimated delivery time corresponding to the target order includes:

[0021] Obtain the second target information corresponding to the target order for estimating delivery time;

[0022] Input the second target information into the second prediction model to obtain the reference delivery time output by the second prediction model;

[0023] Based on the reference delivery time, the estimated delivery time is obtained.

[0024] In one possible implementation, after obtaining the estimated delivery time corresponding to the target order, the method further includes:

[0025] The assessment period for the target delivery object that will accept the target order will be determined based on the estimated delivery time.

[0026] The assessment duration is fed back to the terminal of the target delivery object, and the terminal of the target delivery object is used to display the assessment duration.

[0027] In one possible implementation, determining the assessment period for the target delivery recipient to accept the target order based on the estimated delivery time includes:

[0028] The sum of the estimated delivery time and the delivery buffer time is taken as the assessment time.

[0029] In one possible implementation, after determining the intervalized estimated delivery time, the method further includes:

[0030] The estimated delivery time of the interval is fed back to the terminal of the first object that generated the target order, and the terminal of the first object is used to display the estimated delivery time of the interval;

[0031] In response to the fact that the target order has been placed, an updated delivery time is determined based on the actual placement time of the target order and the estimated delivery time.

[0032] The updated delivery time is fed back to the terminal of the first object, and the terminal of the first object is used to update the displayed intervalized estimated delivery time to the updated delivery time.

[0033] On the other hand, an apparatus for determining an estimated delivery time is provided, the apparatus comprising:

[0034] The acquisition module is used to acquire the lower limit of the estimated order placement time and the upper limit of the estimated order placement time corresponding to the target order, as well as the estimated delivery time corresponding to the target order;

[0035] The determining module is used to determine the lower limit of the estimated delivery time based on the lower limit of the estimated order placement time, the estimated delivery time, and the generation time of the target order; and to determine the upper limit of the estimated delivery time based on the upper limit of the estimated order placement time, the estimated delivery time, and the generation time.

[0036] The determining module is further configured to determine an intervalized estimated delivery time based on the lower limit of the estimated delivery time and the upper limit of the estimated delivery time.

[0037] In one possible implementation, the acquisition module is configured to acquire first target information corresponding to the target order for estimating the probability distribution of order delivery duration; input the first target information into a first estimation model to obtain a reference order delivery duration probability distribution output by the first estimation model; determine the order delivery duration interval that satisfies the target confidence level based on the reference order delivery duration probability distribution; and acquire the lower limit of the expected order delivery duration and the upper limit of the expected order delivery duration based on the order delivery duration interval.

[0038] In one possible implementation, the acquisition module is configured to acquire a lower limit threshold for order placement duration and an upper limit threshold for order placement duration, wherein the lower limit threshold for order placement duration is less than the upper limit threshold for order placement duration; the maximum value between the lower limit of the order placement duration interval and the lower limit threshold for order placement duration is used as the expected lower limit for order placement duration; and the minimum value between the upper limit of the order placement duration interval and the upper limit threshold for order placement duration is used as the expected upper limit for order placement duration.

[0039] In one possible implementation, the acquisition module is configured to acquire multiple actual order placement durations corresponding to multiple reference orders, wherein the reference orders are orders that have been completed; determine a lower limit threshold for order placement duration based on the multiple actual order placement durations and a first quantity, wherein the first quantity is the number of actual order placement durations less than the lower limit threshold among the multiple actual order placement durations; and determine an upper limit threshold for order placement duration based on the multiple actual order placement durations and a second quantity, wherein the second quantity is the number of actual order placement durations less than the upper limit threshold among the multiple actual order placement durations, and the second quantity is greater than the first quantity.

[0040] In one possible implementation, the acquisition module is configured to acquire second target information corresponding to the target order for estimating delivery time; input the second target information into a second estimation model to obtain a reference delivery time output by the second estimation model; and acquire the expected delivery time based on the reference delivery time.

[0041] In one possible implementation, the determining module is further configured to determine the assessment period for the target delivery object that will accept the target order based on the estimated delivery time;

[0042] The device further includes:

[0043] The feedback module is used to provide feedback on the assessment duration to the terminal of the target delivery object, and the terminal of the target delivery object is used to display the assessment duration.

[0044] In one possible implementation, the determining module is further configured to use the sum of the expected delivery time and the delivery buffer time as the assessment time.

[0045] In one possible implementation, the feedback module is further configured to provide feedback of the intervalized estimated delivery time to the terminal of the first object that generated the target order, and the terminal of the first object is configured to display the intervalized estimated delivery time.

[0046] The determining module is further configured to, in response to the fact that the target order has been placed, determine an updated delivery time based on the actual placement time of the target order and the estimated delivery time;

[0047] The feedback module is further configured to provide feedback of the updated delivery time to the terminal of the first object, and the terminal of the first object is configured to update the displayed intervalized estimated delivery time to the updated delivery time.

[0048] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to enable the computer device to implement any of the above-described methods for determining the estimated delivery time.

[0049] On the other hand, a computer-readable storage medium is also provided, wherein at least one computer program is stored therein, the at least one computer program being loaded and executed by a processor to enable a computer to implement any of the above-described methods for determining the estimated delivery time.

[0050] On the other hand, a computer program product is also provided, the computer program product comprising a computer program or computer instructions, the computer program or computer instructions being loaded and executed by a processor to enable a computer to implement any of the above-described methods for determining the estimated delivery time.

[0051] The technical solution provided in this application has at least the following beneficial effects:

[0052] The technical solution provided in this application comprehensively considers both the estimated time for order placement and the estimated time for delivery in determining the estimated delivery time. This improves the reliability of the estimated delivery time, reduces the deviation between the actual delivery time and the estimated delivery time, increases the on-time rate, reduces the negative review rate, and enhances the user experience. Furthermore, the estimated time for order placement includes a lower limit and an upper limit, resulting in a range-bound estimated delivery time. This range-bound estimated delivery time can mitigate the uncertainties caused by non-automatic order placement to a certain extent and is also applicable to orders without automatic order placement, making it suitable for a wide range of scenarios. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a schematic diagram illustrating the implementation environment of a method for determining the estimated delivery time provided in an embodiment of this application;

[0055] Figure 2 This is a flowchart illustrating a method for determining an estimated delivery time, as provided in an embodiment of this application.

[0056] Figure 3 This is a schematic diagram illustrating a process for determining an estimated delivery time provided in an embodiment of this application;

[0057] Figure 4 This is a schematic diagram of the overall processing procedure of a computer device provided in an embodiment of this application;

[0058] Figure 5 This is a schematic diagram of an interaction process provided in an embodiment of this application;

[0059] Figure 6 This is a schematic diagram of an apparatus for determining an estimated delivery time provided in an embodiment of this application;

[0060] Figure 7 This is a schematic diagram of the structure of a server provided in an embodiment of this application;

[0061] Figure 8 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0063] It should be noted that the terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0064] This application provides a method for determining the estimated delivery time. Please refer to [the relevant documentation]. Figure 1 This diagram illustrates an implementation environment for the method for determining the estimated delivery time provided in this application embodiment. This implementation environment may include: computer equipment 11.

[0065] Computer device 11 can be any device capable of determining the Estimated Time of Arrival (ETA) of the target order. For example, computer device 11 can be a terminal, such as the terminal of the merchant corresponding to the target order; computer device 11 can also be a server, such as the server corresponding to the platform that generated the target order.

[0066] Optionally, the terminal can be any electronic product that allows human-computer interaction with the user through one or more methods such as a keyboard, touchpad, touchscreen, remote control, voice interaction, or handwriting device, such as a PC (Personal Computer), mobile phone, smartphone, PDA (Personal Digital Assistant), wearable device, PPC (Pocket PC), tablet computer, smart car system, smart TV, smart speaker, in-vehicle terminal, etc. The server can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center.

[0067] Those skilled in the art should understand that the computer device 11 described above is merely an example, and other existing or future computer devices that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0068] Based on the above Figure 1 The implementation environment shown in this application embodiment provides a method for determining the estimated delivery time. Taking the application of this method to computer device 11 as an example, the computer device 11 can be a terminal or a server; this application embodiment does not limit this. Figure 2 As shown, the method for determining the estimated delivery time provided in this application embodiment may include the following steps 201 to 203.

[0069] In step 201, the lower limit and upper limit of the estimated order placement time corresponding to the target order are obtained, as well as the estimated delivery time corresponding to the target order.

[0070] A target order is any order for which the estimated delivery time is yet to be determined. This application embodiment does not limit the type of items to be purchased in the target order, and may include, but is not limited to, food, medicine, clothing, and electrical appliances. Exemplarily, the object that generates the target order is referred to as the first object, and exemplarily, the first object can refer to any user.

[0071] For example, a target order is an order that is not automatically sent to the delivery platform; that is, a target order is an order that needs to be manually sent to the delivery platform by the merchant. Sending an order to the delivery platform means connecting the order information to the delivery platform so that the delivery platform can automatically specify the delivery recipient or the delivery recipient can choose whether to accept the order. For example, for a target order, the merchant can manually send an order to one or more delivery platforms, which can be selected by the merchant, and this application embodiment does not limit this. For example, the delivery recipients corresponding to different delivery platforms may be the same or different. Of course, in some embodiments, a target order can also be an order that is automatically sent to the delivery platform.

[0072] In this embodiment, the computer device obtains the lower limit of the estimated order placement time, the upper limit of the estimated order placement time, and the estimated delivery time corresponding to the target order, and then obtains the estimated delivery time based on a comprehensive consideration of the lower limit of the estimated order placement time, the upper limit of the estimated order placement time, and the estimated delivery time. The lower limit of the estimated order placement time is the minimum estimated time from the time the target order is generated to the time the merchant corresponding to the target order places the order with the delivery platform; the upper limit of the estimated order placement time is the maximum estimated time from the time the target order is generated to the time the merchant corresponding to the target order places the order with the delivery platform; the estimated delivery time is the estimated time from the time the merchant corresponding to the target order places the order with the delivery platform to the actual delivery time of the target order.

[0073] The lower and upper limits of the estimated order placement time constitute the estimated order placement time range. These limits can mitigate the uncertainty of manually placing orders by merchants to some extent, and are also applicable to real-world scenarios where order placement time is highly random. Determining the estimated delivery time by comprehensively considering the lower and upper limits of the estimated order placement time, along with the estimated delivery time, improves the reliability of the estimated delivery time, reduces the deviation between the actual and estimated delivery times, increases the on-time delivery rate of target orders, reduces the likelihood of negative reviews from the first customer, and ultimately lowers the negative review rate, improving the first customer's experience.

[0074] For example, the computer device can be any device capable of determining the estimated delivery time of the target order. For instance, the computer device can be the terminal of the merchant corresponding to the target order, or it can be the server corresponding to the platform that generated the target order.

[0075] For example, obtaining the lower limit and upper limit of the estimated order dispatch time for a target order can be considered as estimating the relevant duration of the order dispatch stage, and obtaining the estimated delivery time for a target order can be considered as estimating the relevant duration of the delivery stage. By obtaining the lower limit and upper limit of the estimated order dispatch time for a target order, and the estimated delivery time for a target order, the relevant durations of the two stages can be estimated respectively. These two stages are the stages that need to be considered from order generation to delivery, thereby ensuring the reliability and accuracy of the estimated delivery time.

[0076] In one possible implementation, the process of obtaining the lower limit and upper limit of the expected order placement time corresponding to the target order includes the following steps 1 to 3.

[0077] Step 1: Obtain the first target information corresponding to the target order for estimating the probability distribution of order delivery time.

[0078] The order duration probability distribution indicates the probabilistic pattern of the random variable of order duration. Based on the order duration probability distribution, the probability that the random variable of order duration falls within a certain interval can be calculated. Each order corresponds to information used to estimate the order duration probability distribution. The information used to estimate the order duration probability distribution for different orders may be different. The information used to estimate the order duration probability distribution for the target order is used as the first target information.

[0079] The content of the first target information can be set based on experience or flexibly adjusted according to the actual application scenario, and this application embodiment does not limit it in this way. In an exemplary embodiment, the first target information includes the first merchant information corresponding to the target order and the first environment information corresponding to the target order. The first merchant information refers to information related to the merchant corresponding to the target order for estimating the probability distribution of order placement duration, and the first environment information refers to information related to the environment corresponding to the time the target order was generated for estimating the probability distribution of order placement duration.

[0080] For example, the information of the first merchant may include the historical average order processing time of the merchant corresponding to the target order, so that the first prediction model can predict the probability distribution of the order processing time corresponding to the target order by referring to the historical average order processing time, thereby improving the prediction accuracy. For example, the information of the first merchant may also include at least one of the following: the historical average food preparation time of the merchant corresponding to the target order, the geographical location of the merchant corresponding to the target order, the historical average delivery time of the merchant corresponding to the target order, the type of goods sold by the merchant corresponding to the target order, and the qualifications of the merchant corresponding to the target order.

[0081] For example, the first environmental information may include at least one of the following: the distribution of delivery objects corresponding to the time the target order was generated, the overall load of delivery objects corresponding to the time the target order was generated, the weather conditions corresponding to the time the target order was generated, and the road congestion conditions corresponding to the time the target order was generated. For example, the distribution of delivery objects corresponding to the time the target order was generated and the overall load of delivery objects corresponding to the time the target order was generated can reflect the overall supply and demand situation corresponding to the time the target order was generated.

[0082] The first target information corresponding to the target order can be obtained by the computer device through analysis based on the target order, or by the computer device through communication with other devices, or by obtaining it from the network, etc. This application embodiment does not limit this.

[0083] Step 2: Input the first target information into the first prediction model to obtain the reference order duration probability distribution output by the first prediction model.

[0084] The first prediction model is a trained model that can output a corresponding order duration probability distribution based on the input information. This application does not limit the model structure of the first prediction model; it can be a neural network model. For example, the first prediction model can also be called an order duration probability distribution prediction model.

[0085] After inputting the first target information into the first prediction model, the first prediction model can make a prediction based on the first target information and then output the order placement duration probability distribution corresponding to the target order. This order placement duration probability distribution output by the first prediction model is called the reference order placement duration probability distribution. The reference order placement duration probability distribution refers to the probabilistic pattern of the random variable of order placement duration under the constraint of the target order. This application does not limit the representation of the reference order placement duration probability distribution. For example, the reference order placement duration probability distribution can be represented using a distribution function (e.g., a normal distribution function).

[0086] Before using the first prediction model to predict the probability distribution of the reference order delivery duration corresponding to the target order, the first prediction model needs to be trained first. In an exemplary embodiment, the first prediction model is trained based on the first sample information used to predict the probability distribution of order delivery duration corresponding to the first sample order and the actual order delivery duration corresponding to the first sample order. Exemplarily, the process of training the first prediction model includes: obtaining the first sample information used to predict the probability distribution of order delivery duration corresponding to the first sample order and the actual order delivery duration corresponding to the first sample order; inputting the first sample information into the first initial prediction model to obtain the sample order delivery duration probability distribution output by the first initial prediction model; determining the first loss based on the sample order delivery duration probability distribution and the actual order delivery duration corresponding to the first sample order; and updating the model parameters of the first initial prediction model using the first loss to obtain the first prediction model.

[0087] The first sample order refers to an order whose actual order placement time is known. For example, the type of the first sample order is one that is not automatically placed with the delivery platform, and the actual order placement time corresponding to the first sample order is the time spent by the merchant manually placing the order with the delivery platform. The number of first sample orders can be one or more, and this application embodiment does not limit this.

[0088] The actual order delivery time corresponding to the first sample order is used to provide supervisory information for the sample order delivery time probability distribution output by the first initial prediction model. In an exemplary embodiment, the process of determining the first loss based on the sample order delivery time probability distribution and the actual order delivery time corresponding to the first sample order includes: determining a reference interval centered on the actual order delivery time corresponding to the first sample order; determining the probability that the random variable of order delivery time falls within the reference interval based on the sample order delivery time probability distribution; and obtaining the first loss based on the first difference between the probability that the random variable of order delivery time falls within the reference interval and probability 1. Exemplarily, the first loss is positively correlated with the first difference.

[0089] For example, the reference interval centered on the actual order placement time corresponding to the first sample order can be an interval whose lower limit is the difference between the actual order placement time and the reference duration, and whose upper limit is the sum of the actual order placement time and the reference duration. The reference duration is set based on experience or can be flexibly adjusted according to the application scenario. For example, the reference duration is a relatively short duration to ensure the model training effect.

[0090] By using this first loss to update the model parameters of the first initial prediction model, the model parameters of the first initial prediction model can be updated in the direction of reducing the first difference. By reducing the first difference, the probability that the random variable of order placement duration, determined by the probability distribution of the output order placement duration, falls within the reference interval can be made close to 1, thereby improving the reliability of the output order placement duration probability distribution and improving the model training effect.

[0091] For example, the process of updating the model parameters of the first initial prediction model using the first loss to obtain the first prediction model is an iterative process. Each time the model parameters of the first initial prediction model are updated using the first loss, it is determined whether the current training process meets the first training termination condition. If the current training process meets the first training termination condition, the prediction model obtained by the current training is taken as the first prediction model. If the current training process does not meet the first training termination condition, training continues until the current training process meets the first training termination condition, and the prediction model obtained when the first training termination condition is met is taken as the first prediction model.

[0092] The current training process may satisfy the first training termination condition based on experience or be flexibly adjusted according to the application scenario; this application embodiment does not limit this. For example, the current training process satisfying the first training termination condition may include, but is not limited to, any of the following conditions: the first loss obtained in the current training process converges; the first loss obtained in the current training process is less than a first loss threshold; or the total number of iterations corresponding to the current training process reaches a first number threshold. The first loss threshold and the first number threshold may be set based on experience or be flexibly adjusted according to the application scenario; this application embodiment does not limit this.

[0093] Step 3: Based on the probability distribution of the reference order placement duration, determine the order placement duration interval that meets the target confidence level; based on the lower limit and upper limit of the order placement duration interval, obtain the lower limit and upper limit of the expected order placement duration.

[0094] The order placement duration interval that satisfies the target confidence level refers to the interval within which the true value of the random variable, order placement duration, is likely to have the target confidence level. The target confidence level is set empirically or adjusted flexibly according to the application scenario; this application does not limit this. For example, the target confidence level can be 0.95, or it can be 0.98, etc. The higher the target confidence level, the larger the range of the order placement duration interval.

[0095] In an exemplary embodiment, determining the order placement duration interval that satisfies the target confidence level based on the reference order placement duration probability distribution includes: determining, based on the reference order placement duration probability distribution, an interval in which the probability of the order placement duration random variable falling is equal to the target confidence level; and determining the order placement duration interval that satisfies the target confidence level based on this interval. For example, if there is only one interval in which the probability of the order placement duration random variable falling is equal to the target confidence level, then this single interval can be used as the order placement duration interval that satisfies the target confidence level. If there are multiple intervals in which the probability of the order placement duration random variable falling is equal to the target confidence level, then one of these multiple intervals can be selected as the order placement duration interval that satisfies the target confidence level.

[0096] This application does not limit the implementation method of selecting one interval from the plurality of intervals as the order placement duration interval that meets the target confidence level. For example, an interval may be randomly selected from the plurality of intervals as the order placement duration interval that meets the target confidence level. For example, an interval with the smallest or largest interval length may be selected from the plurality of intervals as the order placement duration interval that meets the target confidence level, etc.

[0097] After determining the order placement duration range that meets the target confidence level, the lower limit and upper limit of the expected order placement duration are obtained based on the order placement duration range. In an exemplary embodiment, obtaining the lower limit and upper limit of the expected order placement duration based on the order placement duration range can be achieved by using the lower limit of the order placement duration range as the lower limit of the expected order placement duration and the upper limit of the order placement duration range as the upper limit of the expected order placement duration. For example, the order placement duration range corresponds to an order placement duration range, the lower limit of the order placement duration range is the minimum order placement duration within the corresponding order placement duration range, and the upper limit of the order placement duration range is the maximum order placement duration within the corresponding order placement duration range. For instance, if the order placement duration range is [1, 5] (in minutes), then the order placement duration range corresponding to the order placement duration range is from 1 minute to 5 minutes, the lower limit of the order placement duration range is 1 minute, and the upper limit of the order placement duration range is 5 minutes.

[0098] In an exemplary embodiment, the method for obtaining the lower limit and upper limit of the expected order placement duration based on the order placement duration range can also be as follows: obtain the lower limit threshold and the upper limit threshold of the order placement duration, wherein the lower limit threshold is less than the upper limit threshold; take the maximum value between the lower limit of the order placement duration range and the lower limit threshold as the lower limit of the expected order placement duration; and take the minimum value between the lower limit of the order placement duration range and the upper limit threshold as the lower limit of the expected order placement duration.

[0099] The lower limit threshold for order delivery time is used to constrain the minimum value of the expected order delivery time, while the upper limit threshold for order delivery time is used to constrain the maximum value of the expected order delivery time. By using the maximum value between the lower limit of the order delivery time interval and the lower limit threshold as the expected order delivery time lower limit, and the minimum value between the lower limit of the order delivery time interval and the upper limit threshold as the expected order delivery time lower limit, the lower limit threshold can be used to provide a safety net for the expected order delivery time, preventing it from being too small. Similarly, the upper limit threshold can be used to provide a safety net for the expected order delivery time upper limit, preventing it from being too large. This avoids extreme or abnormal situations, improves the reliability of the expected order delivery time lower and upper limits, and ultimately improves the reliability of the expected delivery time.

[0100] In an exemplary embodiment, the lower limit threshold and the upper limit threshold of order placement duration can be set based on experience or flexibly adjusted according to the application scenario.

[0101] In an exemplary embodiment, the lower limit threshold and the upper limit threshold of order placement duration can be determined based on the actual order placement duration corresponding to the reference order. For example, the process of obtaining the lower limit threshold and the upper limit threshold of order placement duration based on the actual order placement duration corresponding to the reference order includes: obtaining multiple actual order placement durations corresponding to multiple reference orders; determining the lower limit threshold of order placement duration based on the multiple actual order placement durations and a first quantity; and determining the upper limit threshold of order placement duration based on the multiple actual order placement durations and a second quantity.

[0102] In this context, reference orders are those that have already been placed. Since each reference order is a completed order, it corresponds to an actual placement duration. The actual placement durations for multiple reference orders are obtained, resulting in multiple actual placement durations. This embodiment does not limit the number of reference orders, as long as each reference order is a completed order.

[0103] For example, if the computer device is the terminal of the merchant corresponding to the target order, the multiple reference orders can be orders historically received by the terminal of the merchant corresponding to the target order. In this case, the merchants corresponding to the multiple reference orders are the same as the merchants corresponding to the target order. However, the platforms that generate the multiple reference orders may be the same as or different from the platforms that generate the target order.

[0104] For example, if the computer device is the server corresponding to the platform that generated the target order, then the multiple reference orders can be orders historically received by the server corresponding to the platform that generated the target order. In this case, the platform that generated the multiple reference orders is the same as the platform that generated the target order. However, the merchants corresponding to the multiple reference orders may be the same as the merchants corresponding to the target order, or they may be different.

[0105] The first quantity is less than the number of actual order durations. This first quantity can be set based on experience or adjusted flexibly according to the application scenario; this embodiment does not limit this. For example, the first quantity is obtained by rounding down the product of the number of actual order durations and the first ratio. The first ratio can be set based on experience or adjusted flexibly according to the application scenario; for example, the first ratio could be 20%, or 25%, etc. For example, rounding down the product of the number of actual order durations and the first ratio can be done by rounding down, rounding up, or rounding to the nearest integer; this embodiment does not limit this.

[0106] After determining the first quantity, a lower limit threshold for order placement duration can be determined based on multiple actual order placement durations and the first quantity. This application does not limit the implementation method of determining the lower limit threshold for order placement duration based on multiple actual order placement durations and the first quantity, as long as a first relationship is maintained between the multiple actual order placement durations, the first quantity, and the lower limit threshold for order placement duration. This first relationship refers to the following: the first quantity is the number of actual order placement durations among the multiple actual order placement durations that are less than the lower limit threshold for order placement duration.

[0107] In an exemplary embodiment, the process of determining the lower limit threshold of order placement duration based on multiple actual order placement durations and a first quantity can be as follows: multiple actual order placement durations are arranged in ascending order, and the first actual order placement duration in the first position is taken as the lower limit threshold of order placement duration, wherein the first position is the position where there is a first quantity of actual order placement durations before it.

[0108] In an exemplary embodiment, the process of determining the lower limit threshold for order placement duration based on multiple actual order placement durations and a first quantity can also be as follows: arranging multiple actual order placement durations in ascending order, and determining the lower limit threshold for order placement duration based on the first actual order placement duration in the first position and the second actual order placement duration preceding the first actual order placement duration.

[0109] The embodiments of this application do not limit the implementation method of determining the lower limit threshold of order placement time based on the first actual order placement time and the second actual order placement time, as long as the lower limit threshold of order placement time is not less than the second actual order placement time and not greater than the first actual order placement time, so as to ensure that the number of actual order placement times less than the lower limit threshold of order placement time among multiple actual order placement times is the first quantity.

[0110] For example, a weighted sum of the first and second actual order placement times is performed to obtain a lower limit threshold for order placement time. During this weighted summation, the weights corresponding to the first and second actual order placement times can be set empirically or adjusted flexibly according to the application scenario, as long as the lower limit threshold obtained by the weighted summation is not less than the second actual order placement time and not greater than the first actual order placement time. For example, the weights corresponding to the first and second actual order placement times are both values ​​between 0 and 1, and the sum of the weights corresponding to the first and second actual order placement times is 1. For instance, if both the weights corresponding to the first and second actual order placement times are 0.5, the lower limit threshold for order placement time is the average of the first and second actual order placement times.

[0111] For example, the difference between the second actual order placement time and the first actual order placement time is used as the first time difference. The product of the first time difference and the reference weight is calculated, and the sum of the calculated product and the first actual order placement time is used as the lower limit threshold for order placement time. The first reference weight is set based on experience or flexibly adjusted according to the application scenario. For example, the first reference weight is a value between 0 and 1 to ensure that the lower limit threshold for order placement time is not less than the second actual order placement time and not greater than the first actual order placement time.

[0112] For example, taking the first quantity as determined based on the first ratio, and the first ratio as 20%, the lower limit threshold of the order placement time determined based on multiple actual order placement times and the first quantity can be considered as the time corresponding to the 2 quantile of multiple actual order placement times.

[0113] The second quantity is greater than the first quantity and less than the number of actual order placement durations. The second quantity can be set based on experience or flexibly adjusted according to the application scenario; this embodiment does not limit this. For example, the second quantity is obtained by rounding down the product of the number of actual order placement durations and the second ratio. The second ratio is greater than the first ratio, and the second ratio can be set based on experience or flexibly adjusted according to the application scenario; for example, the second ratio may be 80% or 85%. For example, the method of rounding down the product of the number of actual order placement durations and the second ratio can be rounding down, rounding up, or rounding to the nearest integer; this embodiment does not limit this.

[0114] After determining the second quantity, the upper limit threshold for order placement duration can be determined based on multiple actual order placement durations and the second quantity. This application does not limit the implementation method of determining the upper limit threshold for order placement duration based on multiple actual order placement durations and the second quantity, as long as a second relationship is ensured between the multiple actual order placement durations, the second quantity, and the upper limit threshold for order placement duration. This second relationship refers to the following: the second quantity is the number of actual order placement durations among the multiple actual order placement durations that are less than the upper limit threshold for order placement duration.

[0115] In an exemplary embodiment, the process of determining the upper limit threshold of order placement duration based on multiple actual order placement durations and a second number can be as follows: the multiple actual order placement durations are arranged in ascending order, and the third actual order placement duration in the second position is taken as the upper limit threshold of order placement duration, wherein the second position is the position where there are a second number of actual order placement durations before it.

[0116] In an exemplary embodiment, the process of determining the upper limit threshold for order placement duration based on multiple actual order placement durations and a second quantity can also be as follows: the multiple actual order placement durations are arranged in ascending order, and the upper limit threshold for order placement duration is determined based on the third actual order placement duration in the second position and the fourth actual order placement duration located one position before the third actual order placement duration.

[0117] The embodiments of this application do not limit the implementation method of determining the upper limit threshold of order placement time based on the third actual order placement time and the fourth actual order placement time, as long as the upper limit threshold of order placement time is not less than the fourth actual order placement time and not greater than the third actual order placement time, so as to ensure that the number of actual order placement times less than the upper limit threshold of order placement time among multiple actual order placement times is the second quantity.

[0118] For example, the third and fourth actual order placement times are weighted and summed to obtain the upper limit threshold for order placement time. In the process of weighted summing the third and fourth actual order placement times, the weights corresponding to the third and fourth actual order placement times can be set empirically or flexibly adjusted according to the application scenario, as long as the upper limit threshold for order placement time obtained by weighted summation is not less than the fourth actual order placement time and not greater than the third actual order placement time. For example, the weights corresponding to the third and fourth actual order placement times are both values ​​between 0 and 1, and the sum of the weights corresponding to the third and fourth actual order placement times is 1. For instance, if the weights corresponding to the third and fourth actual order placement times are both 0.5, in this case, the upper limit threshold for order placement time is the average of the third and fourth actual order placement times.

[0119] For example, the difference between the fourth and third actual order placement times is used as the second time difference. The product of the second time difference and the second reference weight is calculated, and the sum of this product and the third actual order placement time is used as the upper limit threshold for order placement time. The second reference weight is set based on experience or adjusted flexibly according to the application scenario. For example, the second reference weight is a value between 0 and 1 to ensure that the upper limit threshold for order placement time is not less than the fourth actual order placement time and not greater than the third actual order placement time. It should be noted that the second reference weight can be the same as or different from the first reference weight.

[0120] For example, taking the second quantity as determined by the second ratio, and the second ratio as 20%, the upper limit threshold of the order placement time determined based on multiple actual order placement times and the second quantity can be considered as the time corresponding to the 8th percentile of multiple actual order placement times.

[0121] In one possible implementation, the process of obtaining the estimated delivery time for the target order includes the following steps A through C.

[0122] Step A: Obtain the second target information corresponding to the target order for estimating delivery time.

[0123] Delivery time refers to the time between the actual order placement time and the actual delivery time. Each order has corresponding information for estimated delivery time, and the information for estimated delivery time may differ between different orders. The information for estimated delivery time corresponding to the target order is used as the secondary target information.

[0124] The content of the second target information can be set based on experience or flexibly adjusted according to the actual application scenario, and this application embodiment does not limit it in this way. In an exemplary embodiment, the second target information includes second merchant information corresponding to the target order, target delivery address information corresponding to the target order, and second environmental information corresponding to the target order. The second merchant information refers to information related to the merchant corresponding to the target order for estimating delivery time. The second merchant information can be the same as or different from the first merchant information. The second environmental information refers to information related to the environment corresponding to the time the target order was generated for estimating delivery time. The second environmental information can be the same as or different from the first environmental information. The target delivery address information refers to information related to the delivery address of the target order for estimating delivery time. For example, the delivery address of the target order can also be referred to as the delivery location of the target order.

[0125] For example, the second merchant information may include the historical average delivery time of the merchant corresponding to the target order, so that the second prediction model can predict the delivery time of the target order by referring to the historical average delivery time, thereby improving the prediction accuracy. For example, the second merchant information may also include at least one of the following: the historical average food preparation time of the merchant corresponding to the target order, the geographical location of the merchant corresponding to the target order, the historical average order placement time of the merchant corresponding to the target order, the type of goods sold by the merchant corresponding to the target order, and the qualifications of the merchant corresponding to the target order.

[0126] For example, the second environmental information may include at least one of the following: the distribution of delivery objects corresponding to the time the target order was generated, the overall load of delivery objects corresponding to the time the target order was generated, the weather conditions corresponding to the time the target order was generated, and the road congestion conditions corresponding to the time the target order was generated.

[0127] For example, the target delivery address information may include at least one of the following: the distance between the delivery address of the target order and the location of the merchant corresponding to the target order, the floor information of the delivery address of the target order, and the road conditions around the delivery address of the target order.

[0128] The second target information corresponding to the target order can be obtained by the computer device through analysis based on the target order, or by the computer device through communication with other devices, or by obtaining it from the network, etc. This application embodiment does not limit this.

[0129] Step B: Input the second target information into the second prediction model to obtain the delivery time parameter output by the second prediction model.

[0130] The second prediction model is a trained model that can output the corresponding delivery time based on the input information. This application embodiment does not limit the model structure of the second prediction model; it can be a neural network model. For example, the second prediction model can also be called a delivery time prediction model.

[0131] After the second target information is input into the second prediction model, the second prediction model can make a prediction based on the second target information and then output the delivery time corresponding to the target order. The delivery time corresponding to the target order output by the second prediction model is called the reference delivery time.

[0132] Before using the second prediction model to estimate the reference delivery time corresponding to the target order, the second prediction model needs to be trained first. In an exemplary embodiment, the second prediction model is trained based on the second sample information for estimating the delivery time corresponding to the second sample order and the actual delivery time corresponding to the second sample order. Exemplarily, the process of training the second prediction model includes: obtaining the second sample information for estimating the delivery time corresponding to the second sample order and the actual delivery time corresponding to the second sample order; inputting the second sample information into the second initial prediction model to obtain the sample delivery time output by the second initial prediction model; determining a second loss based on the second difference between the sample delivery time and the actual delivery time corresponding to the second sample order; and updating the model parameters of the second initial prediction model using the second loss to obtain the second prediction model.

[0133] The second sample order refers to an order with a known actual delivery time. For example, the type of the second sample order can be either an order that is automatically sent to the delivery platform or an order that is not automatically sent to the delivery platform. The number of second sample orders can be one or more, and this application embodiment does not limit this.

[0134] The actual delivery time corresponding to the second sample order is used to provide supervision information for the sample delivery time output by the second initial prediction model. For example, the second loss is positively correlated with the second difference. Updating the model parameters of the second initial prediction model using this second loss allows the model parameters to be updated in the direction of reducing the second difference. By reducing the second difference, the output delivery time can be made closer to the actual delivery time, thereby improving the reliability of the output delivery time and enhancing the model training effect.

[0135] For example, the process of updating the model parameters of the second initial prediction model using the second loss to obtain the second prediction model is an iterative process. Each time the model parameters of the second initial prediction model are updated using the second loss, it is determined whether the current training process meets the second training termination condition. If the current training process meets the second training termination condition, the prediction model obtained by the current training is used as the second prediction model; if the current training process does not meet the second training termination condition, training continues until the current training process meets the second training termination condition, and the prediction model obtained when the second training termination condition is met is used as the second prediction model.

[0136] The current training process may satisfy the second training termination condition based on experience or be flexibly adjusted according to the application scenario; this application embodiment does not limit this. For example, the current training process satisfying the second training termination condition may include, but is not limited to, any of the following conditions: the second loss obtained in the current training process converges; the second loss obtained in the current training process is less than the second loss threshold; or the total number of iterations corresponding to the current training process reaches the second number threshold. The second loss threshold and the second number threshold may be set based on experience or be flexibly adjusted according to the application scenario; this application embodiment does not limit this.

[0137] Step C: Obtain the estimated delivery time based on the reference delivery time.

[0138] After obtaining the reference delivery time, the estimated delivery time is obtained based on the reference delivery time. The reference delivery time is a relatively accurate delivery time for the target order estimated by the second estimation model. Obtaining the estimated delivery time based on the reference delivery time helps to ensure the reliability of the estimated delivery time.

[0139] In an exemplary embodiment, the method of obtaining the estimated delivery time based on the reference delivery time includes: using the reference delivery time as the estimated delivery time.

[0140] In an exemplary embodiment, obtaining the estimated delivery time based on a reference delivery time includes: adjusting the reference delivery time by adding time to obtain the estimated delivery time. Adjusting the reference delivery time by adding time improves reliability, thereby better handling abnormal situations. The process of adjusting the reference delivery time by adding time can be set based on experience or flexibly adjusted according to the actual application scenario; this embodiment does not limit this process. For example, if the navigation route from the location of the merchant corresponding to the target order to the delivery address of the target order is highly congested, a first time supplement can be added to the reference delivery time. The first time supplement can be set based on experience or flexibly adjusted according to the congestion of the navigation route.

[0141] For example, if the weather conditions are severe when the target order is generated (e.g., rain, snow, strong winds, etc.), a second supplementary time can be added to the reference delivery time. The second supplementary time can be set based on experience or flexibly adjusted according to the actual weather conditions.

[0142] In an exemplary embodiment, after obtaining the estimated delivery time corresponding to the target order, the computer device can further determine the assessment time for the target delivery object that will accept the target order based on the estimated delivery time; and feed back the assessment time to the terminal of the target delivery object. The terminal of the target delivery object is used to display the assessment time.

[0143] The target delivery recipient is the delivery recipient that accepts the target order; that is, the delivery recipient that delivers the target order to the first recipient. The assessment time for the target delivery recipient refers to the maximum time between the time the target delivery recipient accepts the target order and the time the target delivery recipient delivers the target order to its delivery address. Linking the assessment time to the estimated delivery time helps reduce discrepancies between the time used by the first recipient to judge on-time delivery and the time used by the target delivery recipient, thus reducing the likelihood of negative reviews from the first recipient due to late delivery and lowering the negative review rate.

[0144] For example, the implementation method for determining the assessment duration of the target delivery object based on the estimated delivery time can be: using the estimated delivery time as the assessment duration of the target delivery object.

[0145] For example, another way to determine the assessment time for the target delivery object based on the estimated delivery time is to use the sum of the estimated delivery time and the delivery buffer time as the assessment time. The delivery buffer time can be set based on experience or flexibly adjusted according to the application scenario, and this application embodiment does not limit this. For example, the delivery buffer time can be 8 minutes or 10 minutes, etc. By setting the delivery buffer time, a certain buffer time can be provided for the delivery process of the target delivery object, thereby improving the delivery experience of the target delivery object.

[0146] For example, the computer device can provide feedback on the assessment duration to the target delivery recipient's terminal either by directly providing the assessment duration or by providing the assessment time corresponding to the assessment duration. This application embodiment does not limit this approach. The assessment time corresponding to the assessment duration refers to the time obtained by subtracting the assessment duration from the time the target delivery recipient accepts the target order.

[0147] For example, when the computer device directly feeds back the assessment duration to the target delivery recipient's terminal, the target delivery recipient's terminal directly displays the assessment duration, which decreases in real time during the delivery process. When the computer device feeds back the assessment time corresponding to the assessment duration to the target delivery recipient's terminal, the target delivery recipient's terminal displays the assessment time corresponding to the assessment duration, and the assessment duration corresponding to the assessment time remains unchanged during the delivery process.

[0148] For example, the computer device may provide feedback on the assessment duration to the target delivery recipient's terminal via at least one of SMS reminders and application reminders. The target delivery recipient's terminal may display the assessment duration on at least one of an SMS display interface and an application display interface. For example, the application referred to herein may be an application installed on the target delivery recipient's terminal for accepting orders.

[0149] In step 202, the lower limit of the estimated delivery time is determined based on the lower limit of the estimated order placement time, the estimated delivery time, and the time when the target order was generated; the upper limit of the estimated order placement time, the estimated delivery time, and the time when the order was generated are determined.

[0150] The lower limit of the estimated delivery time is the earliest estimated delivery time for the target order, and the upper limit of the estimated delivery time is the latest estimated delivery time for the target order. The creation time of the target order is the time when the first object generates the target order.

[0151] For example, the method of determining the lower limit of the expected delivery time based on the lower limit of the expected order placement time, the expected delivery time, and the generation time of the target order includes: taking the sum of the lower limit of the expected order placement time and the expected delivery time as the first duration, and taking the time obtained by pushing the first duration backward from the generation time of the target order as the upper limit of the expected delivery time.

[0152] For example, the method of determining the upper limit of the estimated delivery time based on the upper limit of the estimated order placement time, the estimated delivery time, and the generation time of the target order includes: taking the sum of the upper limit of the estimated order placement time and the estimated delivery time as the second time, and taking the time obtained by pushing the second time backward from the generation time of the target order as the upper limit of the estimated delivery time.

[0153] For example, if the estimated order placement time is 2 minutes at the lower limit, 4 minutes at the upper limit, and 20 minutes at the upper limit, and the target order is generated at 9:00, then the first time is 22 minutes, the second time is 24 minutes, the estimated delivery time is 9:22 at the lower limit, and the estimated delivery time is 9:24 at the upper limit.

[0154] In step 203, the intervalized estimated delivery time is determined based on the lower limit of the estimated delivery time and the upper limit of the estimated delivery time.

[0155] A range-based estimated delivery time is an estimated delivery time expressed as a time range (or time period). It is determined by comprehensively considering the lower limit of the estimated order placement time, the upper limit of the estimated order placement time, and the delivery time. This approach can mitigate the uncertainties associated with non-automatic order placement to some extent, resulting in higher reliability. It reduces the deviation between the actual and estimated delivery times, improves on-time delivery rates, and lowers negative feedback rates. This range-based estimated delivery time is applicable to both automated and non-automated order placement scenarios, making it suitable for a wide range of applications.

[0156] In an exemplary embodiment, the method for determining the intervalized expected delivery time based on the lower limit of the expected delivery time and the upper limit of the expected delivery time includes: using the interval formed by the lower limit of the expected delivery time and the upper limit of the expected delivery time as the intervalized expected delivery time.

[0157] In an exemplary embodiment, the method for determining the intervalized estimated delivery time based on the lower limit and upper limit of the estimated delivery time includes: taking the interval formed by the lower limit and upper limit of the estimated delivery time as a first interval, and expanding the first interval to obtain the intervalized estimated delivery time. For example, expanding the first interval may mean decreasing the lower limit of the first interval by a first adjustment period and increasing the upper limit of the first interval by a second adjustment period. The first and second adjustment periods are set based on experience or flexibly adjusted according to the application scenario; this embodiment does not limit this. The range of estimated delivery times determined in this way is wider, which is beneficial for further increasing the probability that the actual delivery time falls within the intervalized estimated delivery time, thereby improving the on-time delivery rate.

[0158] For example, the process of determining the expected delivery time can be as follows: Figure 3 As shown. In the order placement duration estimation stage, the first merchant information and the first environment information are obtained; the first merchant information and the first environment information are input into the first estimation model to obtain the reference order placement duration probability distribution corresponding to the target order; based on the reference order placement duration probability distribution, the order placement duration interval that meets the target confidence level is determined; the lower limit threshold and the upper limit threshold of the order placement duration determined based on multiple actual order placement durations are used as a fallback to obtain the expected lower limit and the expected upper limit of the order placement duration.

[0159] In the delivery time estimation stage, second merchant information, target delivery address information, and second environmental information are obtained. These information are then input into a second estimation model to obtain a reference delivery time for the target order. The reference delivery time is adjusted by adding time to obtain the estimated delivery time. Based on the lower limit of the estimated order placement time, the upper limit of the estimated order placement time, the estimated delivery time, and the time the target order was generated, a range of estimated delivery times is determined.

[0160] In one possible implementation, after determining the interval-based estimated delivery time, the computer device can further feed back the interval-based estimated delivery time to the terminal of the first object that generated the target order, the terminal of the first object being used to display the interval-based estimated delivery time. Exemplarily, the computer device can feed back the interval-based estimated delivery time to the terminal of the first object via at least one of SMS reminders and application reminders. Exemplarily, the terminal of the first object can display the interval-based estimated delivery time on at least one of an SMS display interface and an application display interface. Exemplarily, the application involved here can refer to an application installed on the terminal of the first object for the first object to generate the target order.

[0161] In one possible implementation, after feeding back the intervalized estimated delivery time to the terminal of the first object, the computer device may further, in response to the fact that the target order has been placed, determine an updated delivery time based on the actual placement time and estimated delivery time of the target order; and feed back the updated delivery time to the terminal of the first object, which is used to update the displayed intervalized estimated delivery time to the updated delivery time.

[0162] Because the interval-based estimated delivery time is determined based on the upper and lower limits of the estimated order placement time, while the updated delivery time is determined based on the actual order placement time, which is determined within the actual order placement time, the updated delivery time is more accurate than the interval-based estimated delivery time. This process better manages the expectations of the first-party customer and improves their experience. For example, the updated delivery time is highly likely to be one of the interval-based estimated delivery times. Using a more accurate delivery time to interact with the first-party customer after order placement further avoids inconsistencies in performance evaluation between the first-party customer and the target delivery customer.

[0163] For example, determining the updated delivery time based on the actual order placement time and the estimated delivery time of the target order can be achieved by subtracting the estimated delivery time from the actual order placement time as the updated delivery time. The computer device can then provide this updated delivery time to the terminal of the first object via at least one of SMS alerts and application notifications.

[0164] For example, under the method for determining the estimated delivery time provided in the embodiments of this application, the overall processing procedure of the computer device is as follows: Figure 4 As shown. After the first object generates a target order, the computer device obtains the estimated delivery time for the corresponding time interval of the target order; after the target order is placed, it determines the updated delivery time based on the actual placement time and the estimated delivery time; after the target delivery object accepts the target order, it determines the assessment time for the target delivery object based on the estimated delivery time; it feeds back the updated delivery time to the terminal of the first object; and it feeds back the assessment time to the terminal of the target delivery object.

[0165] The method for determining the estimated delivery time provided in this application can be applied to errand-running services, a rapidly developing business with daily order volume exceeding 1 million orders and peak order volume exceeding 2 million orders. Many errand-running merchants are self-delivering businesses, choosing to use multiple delivery platforms, leading to significant uncertainty in order placement time. This application avoids this uncertainty by estimating order placement time and using interval-based estimated delivery times. Furthermore, it manages user expectations by updating the actual estimated delivery time via push notifications after order placement. This reduces difficulties in setting estimated delivery times and assessment times, preventing inconsistencies between user and delivery recipient assessment times, and reducing conflicts between users and delivery recipients (or riders), thereby lowering order reminder rates and negative review rates.

[0166] The estimated delivery time and assessment duration (or assessment time) determined by the method provided in this application are more reasonable, which can improve the on-time rate of errand services to 91.4%. In addition, the problem of inconsistency between user and rider assessments is significantly alleviated, with user order reminder rate decreasing by 14.82%, user negative review rate decreasing by 50.66%, rider penalty rate decreasing by 32.65%, and user complaint rate decreasing by 27.66%.

[0167] The method for determining the estimated delivery time provided in this application comprehensively considers both the estimated time for order placement and the estimated time for delivery. This improves the reliability of the estimated delivery time, reduces the deviation between the actual delivery time and the estimated delivery time, increases the on-time rate, reduces the negative review rate, and enhances the user experience. Furthermore, the estimated time for order placement includes a lower limit and an upper limit, resulting in a range-bound estimated delivery time. This range-bound estimated delivery time can mitigate the uncertainties caused by non-automatic order placement to some extent and is applicable to orders without automatic placement, making it suitable for a wide range of scenarios.

[0168] In an exemplary embodiment, under the method for determining the estimated delivery time provided in this application embodiment, the interaction process between the computer device, the terminal of the first object, and the terminal of the target delivery object is as follows: Figure 5 Steps 501 to 508 are shown in the diagram.

[0169] Step 501: The computer device obtains the lower limit and upper limit of the estimated order placement time for the target order, as well as the estimated delivery time for the target order.

[0170] Step 502: The computer equipment determines the interval-based estimated delivery time based on the lower limit of the estimated order placement time, the upper limit of the estimated order placement time, the estimated delivery time, and the generation time of the target order.

[0171] Step 503: The computer device feeds back the intervalized estimated delivery time to the terminal of the first object.

[0172] The first object is the object that generates the target order.

[0173] Step 504: The terminal of the first object displays the estimated delivery time in intervals.

[0174] Step 505: In response to the fact that the target order has been placed, the computer device determines the updated delivery time based on the actual order placement time and the estimated delivery time of the target order; and sends the updated delivery time back to the terminal of the first object.

[0175] Step 506: The final displayed ranged estimated delivery time of the first object is updated to the updated delivery time.

[0176] Step 507: The computer equipment determines the assessment time for the target delivery object based on the estimated delivery time; and feeds back the assessment time to the terminal of the target delivery object.

[0177] The target delivery recipient is the recipient of the target order.

[0178] Step 508: The terminal of the target delivery object displays the assessment time.

[0179] See Figure 6 This application provides an apparatus for determining the estimated delivery time, the apparatus comprising:

[0180] The acquisition module 601 is used to acquire the lower limit and upper limit of the estimated order delivery time corresponding to the target order, as well as the estimated delivery time corresponding to the target order;

[0181] The determination module 602 is used to determine the lower limit of the estimated delivery time based on the lower limit of the estimated order placement time, the estimated delivery time, and the generation time of the target order; and to determine the upper limit of the estimated delivery time based on the upper limit of the estimated order placement time, the estimated delivery time, and the generation time.

[0182] The determination module 602 is also used to determine the intervalized estimated delivery time based on the lower limit of the estimated delivery time and the upper limit of the estimated delivery time.

[0183] In one possible implementation, the acquisition module 601 is used to acquire first target information corresponding to the target order for estimating the probability distribution of order delivery duration; input the first target information into the first estimation model to obtain the reference order delivery duration probability distribution output by the first estimation model; determine the order delivery duration interval that meets the target confidence level based on the reference order delivery duration probability distribution; and obtain the lower limit and upper limit of the expected order delivery duration based on the order delivery duration interval.

[0184] In one possible implementation, the acquisition module 601 is used to acquire the lower limit threshold and the upper limit threshold of the order placement duration, wherein the lower limit threshold is less than the upper limit threshold; the maximum value between the lower limit of the order placement duration interval and the lower limit threshold is used as the expected lower limit of the order placement duration; and the minimum value between the upper limit of the order placement duration interval and the upper limit threshold is used as the expected upper limit of the order placement duration.

[0185] In one possible implementation, the acquisition module 601 is used to acquire multiple actual order placement durations corresponding to multiple reference orders, where the reference orders are orders that have been completed; based on the multiple actual order placement durations and a first quantity, a lower limit threshold for order placement duration is determined, where the first quantity is the number of actual order placement durations less than the lower limit threshold; based on the multiple actual order placement durations and a second quantity, an upper limit threshold for order placement duration is determined, where the second quantity is the number of actual order placement durations less than the upper limit threshold and the second quantity is greater than the first quantity.

[0186] In one possible implementation, the acquisition module 601 is used to acquire second target information corresponding to the target order for estimating delivery time; input the second target information into the second estimation model to obtain the reference delivery time output by the second estimation model; and obtain the expected delivery time based on the reference delivery time.

[0187] In one possible implementation, the determining module 602 is further configured to determine the assessment duration of the target delivery object accepting the target order based on the estimated delivery duration;

[0188] The device also includes:

[0189] The feedback module is used to provide feedback on the assessment duration to the target delivery recipient's terminal, which is then used to display the assessment duration.

[0190] In one possible implementation, the determining module 602 is further used to use the sum of the expected delivery time and the delivery buffer time as the assessment time.

[0191] In one possible implementation, the feedback module is further configured to provide a ranged estimated delivery time to the terminal of the first object that generated the target order, and the terminal of the first object is configured to display the ranged estimated delivery time.

[0192] The determination module 602 is also used to determine the updated delivery time in response to the fact that the target order has been dispatched, based on the actual dispatch time and the estimated delivery time of the target order;

[0193] The feedback module is also used to provide the updated delivery time to the terminal of the first object, and the terminal of the first object is used to update the displayed intervalized estimated delivery time to the updated delivery time.

[0194] The estimated delivery time determination device provided in this application comprehensively considers both the estimated time for order placement and the estimated time for delivery, thereby improving the reliability of the estimated delivery time, reducing the deviation between the actual delivery time and the estimated delivery time, increasing the on-time rate, reducing the negative review rate, and enhancing the user experience. Furthermore, the estimated time for order placement includes a lower limit and an upper limit, resulting in a range-based estimated delivery time. This range-based estimated delivery time can mitigate the uncertainties caused by non-automatic order placement to a certain extent, and it is also applicable to orders without automatic order placement, making it suitable for a wide range of scenarios.

[0195] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0196] In an exemplary embodiment, a computer device is also provided, comprising a processor and a memory storing at least one computer program. The at least one computer program is loaded and executed by one or more processors to enable the computer device to implement any of the methods for determining the estimated delivery time described above. The computer device can be a server or a terminal. The structures of servers and terminals will be described below.

[0197] Figure 7 This is a schematic diagram of a server structure provided in an embodiment of this application. The server can vary significantly due to differences in configuration or performance. It may include one or more Central Processing Units (CPUs) 701 and one or more memories 702. The one or more memories 702 store at least one computer program, which is loaded and executed by the one or more processors 701 to enable the server to implement the estimated delivery time determination method provided in the various method embodiments described above. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated upon here.

[0198] Figure 8 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. The terminal can be: a PC, mobile phone, smartphone, PDA, wearable device, handheld portable gaming device, PPC, tablet computer, smart car system, smart TV, smart speaker, or in-vehicle terminal. The terminal may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other names.

[0199] Typically, a terminal includes a processor 1201 and a memory 1202.

[0200] Processor 1201 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1201 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1201 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1201 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, processor 1201 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0201] The memory 1202 may include one or more computer-readable storage media, which may be non-transitory. The memory 1202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1202 are used to store at least one instruction, which is executed by the processor 1201 to cause the terminal to implement the estimated delivery time determination method provided in the method embodiments of this application.

[0202] In some embodiments, the terminal may also optionally include: a peripheral device interface 1203 and at least one peripheral device. The processor 1201, memory 1202, and peripheral device interface 1203 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1203 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of: a radio frequency circuit 1204, a display screen 1205, a camera assembly 1206, an audio circuit 1207, a positioning assembly 1208, and a power supply 1209.

[0203] Peripheral device interface 1203 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1201 and memory 1202. In some embodiments, processor 1201, memory 1202 and peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1201, memory 1202 and peripheral device interface 1203 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0204] The radio frequency (RF) circuit 1204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1204 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals.

[0205] Display screen 1205 is used to display a user interface (UI). This UI may include graphics, text, icons, video, and any combination thereof. When display screen 1205 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1201 for processing. In this case, display screen 1205 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard.

[0206] The camera assembly 1206 is used to acquire images or videos. Optionally, the camera assembly 1206 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions.

[0207] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1201 for processing, or input to the radio frequency circuit 1204 to achieve voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert the electrical signals from the processor 1201 or the radio frequency circuit 1204 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker.

[0208] The positioning component 1208 is used to determine the current geographic location of the terminal in order to enable navigation or LBS (Location Based Service). The positioning component 1208 can be a positioning component based on the US GPS (Global Positioning System), China's BeiDou system, Russia's Granas system, or the EU's Galileo system.

[0209] The power supply 1209 is used to power the various components in the terminal. The power supply 1209 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When the power supply 1209 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0210] In some embodiments, the terminal further includes one or more sensors 1210. The one or more sensors 1210 include, but are not limited to: an accelerometer 1211, a gyroscope 1212, a pressure sensor 1213, a fingerprint sensor 1214, an optical sensor 1215, and a proximity sensor 1216.

[0211] Accelerometer 1211 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by the terminal. For example, accelerometer 1211 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1201 can control display screen 1205 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1211. Accelerometer 1211 can also be used for games or for acquiring user motion data.

[0212] The gyroscope sensor 1212 can detect the terminal's orientation and rotation angle. The gyroscope sensor 1212 can work in conjunction with the accelerometer sensor 1211 to collect the user's 3D movements on the terminal. Based on the data collected by the gyroscope sensor 1212, the processor 1201 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0213] The pressure sensor 1213 can be disposed on the side bezel of the terminal and / or the lower layer of the display screen 1205. When the pressure sensor 1213 is disposed on the side bezel of the terminal, it can detect the user's grip signal on the terminal, and the processor 1201 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1213. When the pressure sensor 1213 is disposed on the lower layer of the display screen 1205, the processor 1201 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1205. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0214] The fingerprint sensor 1214 is used to collect a user's fingerprint. The processor 1201 identifies the user's identity based on the fingerprint collected by the fingerprint sensor 1214, or the fingerprint sensor 1214 identifies the user's identity based on the collected fingerprint. When the user's identity is identified as trusted, the processor 1201 authorizes the user to perform relevant sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, making payments, and changing settings. The fingerprint sensor 1214 can be located on the front, back, or side of the terminal. When the terminal has physical buttons or a manufacturer's logo, the fingerprint sensor 1214 can be integrated with the physical buttons or manufacturer's logo.

[0215] The optical sensor 1215 is used to collect ambient light intensity. In one embodiment, the processor 1201 can control the display brightness of the display screen 1205 based on the ambient light intensity collected by the optical sensor 1215. Specifically, when the ambient light intensity is high, the display brightness of the display screen 1205 is increased; when the ambient light intensity is low, the display brightness of the display screen 1205 is decreased. In another embodiment, the processor 1201 can also dynamically adjust the shooting parameters of the camera assembly 1206 based on the ambient light intensity collected by the optical sensor 1215.

[0216] The proximity sensor 1216, also known as a distance sensor, is typically installed on the front panel of the terminal. The proximity sensor 1216 is used to detect the distance between the user and the front of the terminal. In one embodiment, when the proximity sensor 1216 detects that the distance between the user and the front of the terminal is gradually decreasing, the processor 1201 controls the display screen 1205 to switch from a screen-on state to a screen-off state; when the proximity sensor 1216 detects that the distance between the user and the front of the terminal is gradually increasing, the processor 1201 controls the display screen 1205 to switch from a screen-off state to a screen-on state.

[0217] Those skilled in the art will understand that Figure 8 The structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0218] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one computer program that is loaded and executed by a processor of a computer device to enable the computer to implement any of the methods for determining the expected delivery time described above.

[0219] In one possible implementation, the aforementioned computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0220] In an exemplary embodiment, a computer program product is also provided, comprising a computer program or computer instructions that are loaded and executed by a processor to enable a computer to implement any of the methods for determining the expected delivery time described above.

[0221] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application are authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the target orders, first target information, and second target information generated by the first object involved in this application were all obtained with full authorization.

[0222] It should be understood that "multiple" as used in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0223] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining the estimated delivery time, characterized in that, The method includes: Obtain the first target information corresponding to the target order for estimating the probability distribution of order delivery duration; Input the first target information into the first prediction model to obtain the reference order placement duration probability distribution output by the first prediction model; Based on the reference order duration probability distribution, determine the order duration interval that meets the target confidence level; Based on the order placement time range, obtain the lower limit and upper limit of the expected order placement time corresponding to the target order; Obtain the estimated delivery time for the target order; Based on the lower limit of the estimated order placement time, the estimated delivery time, and the generation time of the target order, the lower limit of the estimated delivery time is determined; Based on the estimated order placement time limit, the estimated delivery time, and the generation time, the estimated delivery time limit is determined; Based on the lower limit of the estimated delivery time and the upper limit of the estimated delivery time, an intervalized estimated delivery time is determined.

2. The method according to claim 1, characterized in that, The step of obtaining the lower limit of the expected order placement time and the upper limit of the expected order placement time corresponding to the target order based on the order placement time range includes: Obtain the lower limit threshold and the upper limit threshold of the order placement duration, wherein the lower limit threshold is less than the upper limit threshold; The maximum value between the lower limit of the order placement duration range and the lower limit threshold of the order placement duration is taken as the expected lower limit of the order placement duration. The minimum value between the upper limit of the order placement duration range and the upper limit threshold of the order placement duration is taken as the expected upper limit of the order placement duration.

3. The method according to claim 2, characterized in that, The process of obtaining the lower threshold and upper threshold of order placement duration includes: Obtain multiple actual order placement durations corresponding to multiple reference orders, wherein the reference orders are orders that have been completed and placed; Based on the multiple actual order durations and the first quantity, the lower limit threshold for order duration is determined, where the first quantity is the number of actual order durations among the multiple actual order durations that are less than the lower limit threshold for order duration. Based on the multiple actual order durations and the second quantity, the upper limit threshold for order duration is determined, where the second quantity is the number of actual order durations among the multiple actual order durations that are less than the upper limit threshold for order duration, and the second quantity is greater than the first quantity.

4. The method according to claim 1, characterized in that, The step of obtaining the estimated delivery time corresponding to the target order includes: Obtain the second target information corresponding to the target order for estimating delivery time; Input the second target information into the second prediction model to obtain the reference delivery time output by the second prediction model; Based on the reference delivery time, the estimated delivery time is obtained.

5. The method according to any one of claims 1–4, characterized in that, After obtaining the estimated delivery time corresponding to the target order, the method further includes: The assessment period for the target delivery object that will accept the target order will be determined based on the estimated delivery time. The assessment duration is fed back to the terminal of the target delivery object, and the terminal of the target delivery object is used to display the assessment duration.

6. The method according to claim 5, characterized in that, The process of determining the assessment period for the target delivery object to accept the target order based on the estimated delivery time includes: The sum of the estimated delivery time and the delivery buffer time is taken as the assessment time.

7. The method according to any one of claims 1–4, characterized in that, After determining the intervalized estimated delivery time, the method further includes: The estimated delivery time of the interval is fed back to the terminal of the first object that generated the target order, and the terminal of the first object is used to display the estimated delivery time of the interval; In response to the fact that the target order has been placed, an updated delivery time is determined based on the actual placement time of the target order and the estimated delivery time; The updated delivery time is fed back to the terminal of the first object, and the terminal of the first object is used to update the displayed intervalized estimated delivery time to the updated delivery time.

8. A device for determining an estimated delivery time, characterized in that, The device includes: The acquisition module is used to acquire the first target information corresponding to the target order for estimating the probability distribution of the order delivery time. Input the first target information into the first prediction model to obtain the reference order placement duration probability distribution output by the first prediction model; Based on the reference order duration probability distribution, determine the order duration interval that meets the target confidence level; Based on the order placement time range, obtain the lower limit and upper limit of the expected order placement time corresponding to the target order; And obtain the estimated delivery time corresponding to the target order; The determination module is used to determine the lower limit of the estimated delivery time based on the lower limit of the estimated order placement time, the estimated delivery time, and the generation time of the target order; Based on the estimated order placement time limit, the estimated delivery time, and the generation time, the estimated delivery time limit is determined; The determining module is further configured to determine an intervalized estimated delivery time based on the lower limit of the estimated delivery time and the upper limit of the estimated delivery time.

9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to enable the computer device to implement the method for determining the estimated delivery time as described in any one of claims 1 to 7.

Images