An order delivery time estimation method and apparatus

Abstract

The specification discloses an order delivery time estimation method and device, which can determine a candidate time period after an initial delivery time of an order, and recall a plurality of candidate delivery capacities for delivering the order. Then, according to the order and allocated orders of each candidate delivery capacity, a probability and a change gain of each candidate delivery capacity for delivering the order according to each candidate delivery time in the candidate time period are determined. Finally, based on the probability and the change gain of each candidate delivery capacity for delivering the order according to each candidate delivery time, an expected gain corresponding to each candidate delivery time is determined, and then a predicted delivery time of the order is determined. By determining the expected gain of each candidate delivery capacity for additionally delivering the order at each candidate delivery time, and determining the predicted delivery time of the order based on the expected gain of each candidate delivery time, the predicted delivery time of the order is more accurate, and the experience of both the user and the delivery capacity is improved.

Description

Technical Field

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

[0002] In on-demand delivery services, delivery platforms typically display the estimated time of arrival (ETA) of an order to users before they place it. This allows users to plan their time accordingly, and it also helps delivery companies to schedule delivery times based on the order's ETA.

[0003] Currently, to determine the estimated delivery time of an order, the order information, the merchant's information, and the merchant's delivery area information are first obtained. The area information includes at least the number of orders and delivery capacity within the current area. Then, the order information, merchant information, and delivery area information are input into a pre-trained delivery time prediction model to determine the estimated delivery time. This delivery time prediction model is trained using the actual delivery times of historical orders as labels.

[0004] However, the above method for determining the estimated delivery time of orders does not fully take into account the current order allocation situation of each delivery capacity, resulting in inaccurate order delivery time estimates and affecting the experience of both users and delivery capacity. Summary of the Invention

[0005] This specification provides an order delivery time estimation method and apparatus to partially solve the problems in the prior art.

[0006] The embodiments in this specification adopt the following technical solutions:

[0007] This manual provides a method for estimating order delivery time, including:

[0008] Determine the initial delivery time of the order, and determine a preset time period after the initial delivery time as a candidate time period;

[0009] Based on the order information of the order, recall a number of potential delivery vehicles for the order;

[0010] For each candidate delivery time in the candidate time period, based on the order information of the order and the order information of the allocated orders of each candidate delivery capacity, determine the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change gain of each candidate delivery capacity delivering the order according to the candidate delivery time.

[0011] Based on the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change gain, the expected gain corresponding to the candidate delivery time is determined, and the estimated delivery time of the order is determined based on the expected gain corresponding to each candidate delivery time.

[0012] Optionally, based on the order information of the order, a number of potential delivery vehicles for delivering the order may be recalled, specifically including:

[0013] Based on the order information of the aforementioned orders, recall a number of potential delivery vehicles;

[0014] Based on the order information of the allocated orders of the recalled candidate delivery capacity, and the order information of the orders, determine the delivery probability of each candidate delivery capacity delivering the orders;

[0015] Based on the delivery probability of each candidate delivery capacity in delivering the order, select a number of candidate delivery capacities from the recalled candidate delivery capacities to deliver the order.

[0016] Optionally, based on the order information of the allocated orders of the recalled candidate delivery capacities and the order information of the orders, the delivery probability of each candidate delivery capacity delivering the order is determined, specifically including:

[0017] Based on the order information of the allocated orders of the recalled candidate delivery capacity, and the order information of the orders, determine the distance between the delivery start and end points of the allocated orders of each candidate delivery capacity and the delivery start and end points of the orders.

[0018] The delivery probability of each candidate delivery capacity for the order is determined based on the allocated order volume of each candidate delivery capacity, the order placement time of the order, and the distance between the delivery start and end points of the allocated orders of each candidate delivery capacity and the delivery start and end points of the order.

[0019] Optionally, based on the order information of the order and the order information of the allocated orders for each candidate delivery capacity, the probability of each candidate delivery capacity delivering the order according to the selected delivery time is determined, specifically including:

[0020] For each candidate delivery capacity, based on the delivery origin and destination of the assigned orders of the candidate delivery capacity, the estimated delivery time of the assigned orders, the delivery origin and destination of the orders, and the candidate delivery time, an updated path is determined for the candidate delivery capacity to additionally deliver the orders according to the candidate delivery time.

[0021] Based on the original routes of the selected delivery capacity for each assigned order, and the updated routes, the probability of the selected delivery capacity delivering additional orders is determined.

[0022] Optionally, determine the variation gain of each candidate delivery capacity in delivering the order according to the candidate delivery time, specifically including:

[0023] For each candidate delivery capacity, based on the delivery origin and destination of the assigned orders of the candidate delivery capacity, the estimated delivery time of the assigned orders, the delivery origin and destination of the orders, and the candidate delivery time, an updated path is determined for the candidate delivery capacity to additionally deliver the orders according to the candidate delivery time.

[0024] Based on the original path and the updated path of the candidate delivery capacity, determine the change gain of the candidate delivery capacity in delivering the order according to the candidate delivery time.

[0025] Optionally, based on the original path and the updated path of the candidate delivery capacity, the variation gain of delivering the order according to the candidate delivery time is determined, specifically including:

[0026] Based on the increase in timed-out orders resulting from the conversion of the candidate delivery capacity from the original route to the updated route, determine the change gain of the candidate delivery capacity in delivering the orders according to the candidate delivery time, wherein the change gain is negatively correlated with the increase in timed-out orders; and / or

[0027] Based on the on-time order increment generated when the candidate delivery capacity is converted from the original route to the updated route, determine the change gain of the candidate delivery capacity in delivering the orders according to the candidate delivery time, wherein the change gain is positively correlated with the on-time order increment; and / or

[0028] Based on the path increment of the candidate delivery capacity when it is converted from the original path to the updated path, the change gain of the candidate delivery capacity in delivering the order according to the candidate delivery time is determined, and the change gain is negatively correlated with the path increment.

[0029] Optionally, the method further includes:

[0030] Based on the order information and the preset compensation rules, determine the additional time for the order;

[0031] Based on the additional time allowance for the order, update the initial delivery time of the order, and determine a preset time period around the initial delivery time as a candidate time period.

[0032] This specification provides an order delivery time estimation device, including:

[0033] The first determining module is used to determine the initial delivery time of the order and to determine a preset time period after the initial delivery time as a candidate time period.

[0034] The recall module is used to recall several candidate delivery vehicles for delivering the order based on the order information of the order.

[0035] The second determining module is used to determine, for each candidate delivery time in the candidate time period, the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change gain of each candidate delivery capacity delivering the order according to the candidate delivery time, based on the order information of the order and the order information of the allocated orders of each candidate delivery capacity.

[0036] The third determining module is used to determine the expected gain corresponding to the selected delivery time based on the probability of each candidate delivery capacity delivering the order according to the selected delivery time and the change gain, and to determine the expected delivery time of the order based on the expected gain corresponding to each candidate delivery time.

[0037] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described order delivery time estimation method.

[0038] This specification provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the above-described order delivery time estimation method.

[0039] The above-described at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:

[0040] This specification first determines the initial delivery time of an order and then identifies the candidate time periods following that initial delivery time. Next, based on the order information, several candidate delivery capacities are recalled. For each candidate delivery time within the candidate time period, based on the order information and the order information of the assigned orders for each candidate delivery capacity, the probability and variability gain of each candidate delivery capacity delivering the order at that candidate delivery time are determined. Finally, based on the probability and variability gain of each candidate delivery capacity delivering the order at that candidate delivery time, the expected gain corresponding to that candidate delivery time is determined, and the estimated delivery time of the order is determined based on the expected gain corresponding to each candidate delivery time. By determining the expected gain of each candidate delivery capacity for additional order deliveries under different candidate delivery times, and determining the estimated delivery time of the order based on the expected gain of each candidate delivery time, the estimated delivery time of the order is made more accurate, improving the experience for both users and delivery capacities. Attached Figure Description

[0041] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0042] Figure 1 A flowchart illustrating an order delivery time estimation method provided in the embodiments of this specification;

[0043] Figure 2 This diagram illustrates the online application / offline training of the delivery time estimation model provided in the embodiments of this specification.

[0044] Figure 3 This is a schematic diagram of the structure of an order delivery time estimation device provided in the embodiments of this specification;

[0045] Figure 4 This is a schematic diagram of an electronic device used to implement the order delivery time estimation method provided in the embodiments of this specification. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0047] In on-demand delivery services, displaying users the Estimated Time of Arrival (ETA) not only improves the user experience and helps users plan their time accordingly, but also impacts the assessment of delivery capacity. A higher assessment score is awarded if delivery is completed within the ETA, and a lower score otherwise.

[0048] Furthermore, when allocating orders to various delivery capacities, the ETA (Earning Time To Accompaniment) of currently allocated orders for each delivery capacity is also referenced. For example, if allocating the order to any delivery capacity would result in a timeout, then no capacity will be allocated to that order during that dispatch cycle; that is, the order will be held back until the next dispatch cycle. Therefore, ETA is a crucial factor affecting user experience, delivery capacity assessment, and order allocation.

[0049] However, since the ETA of an order is shown to the user before the order is placed, and the delivery capacity assigned to the order has not yet been determined, the existing technology often ignores the impact of currently allocated orders on the order when estimating the delivery time of the order. This makes the determined ETA of the order inaccurate, which affects the user experience, delivery capacity assessment and order allocation.

[0050] In view of the above-mentioned problems, this specification provides a method for estimating order delivery time. The technical solutions provided by various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0051] Figure 1 This is a flowchart illustrating an order delivery time estimation method provided in an embodiment of this specification, which may specifically include the following steps:

[0052] S100: Determine the initial delivery time of the order, and determine a preset time period after the initial delivery time as a candidate time period.

[0053] The order delivery time estimation method provided in this manual is used to show users the estimated delivery time of their orders before they are placed, so that users can plan their time accordingly.

[0054] The order delivery time estimation method can be executed by the server of the instant delivery service platform, which can be a food delivery service, group buying service, etc. The server can be a single server or a system composed of multiple servers, such as a distributed server system. It can be a physical server device or a cloud server. This manual does not impose any restrictions and can be configured as needed.

[0055] Specifically, in order to more accurately estimate order delivery time, the server can first determine the initial delivery time of the order and then determine a preset time period after the initial delivery time as a candidate time period. Subsequent steps will then determine the accurate ETA from this candidate time period. This candidate time period can be 30 minutes after the initial delivery time, or it can be 15 to 30 minutes after the initial delivery time, depending on the specific requirements.

[0056] Furthermore, when determining the initial delivery time of an order, the initial delivery time can be roughly determined based on the user's location, the merchant's location, and the order's placement time in the order information.

[0057] Alternatively, in another embodiment, the order information, the merchant information of the ordering merchant, and the regional information of the delivery area to which the order belongs can also be obtained. The delivery area is pre-defined, and the area providing instant delivery service can be divided into several delivery areas. The delivery area where the merchant corresponding to the order is located is the delivery area to which the order belongs.

[0058] Next, the order information, merchant information, and regional information are input into a pre-trained delivery time prediction model to obtain the initial delivery time for the order. The order information includes at least the order's origin and destination (merchant and user locations), the types of goods in the order, and the order placement time. It may also include the merchant's identifier and whether delivery personnel are permitted to enter or leave the user's residential area. The merchant information includes at least the number of orders currently pending processing and the average recent pickup wait time for delivery personnel. The regional information includes at least the recent order volume and the number of delivery personnel within the region. The "recent" setting can be configured as needed, such as within 10 minutes of the current time.

[0059] Furthermore, when training this delivery time prediction model, order information from historical orders, merchant information of the ordering merchants, and regional information of the region can be used as training samples, and the actual delivery time of historical orders can be used as labels for model training.

[0060] like Figure 2 As shown, Figure 2 The upper half of the dashed line represents the offline training process of the model, using order information, merchant information, and regional information from historical orders as training samples, and the actual delivery time of historical orders as labels. Figure 2 The lower half of the dashed section represents the online application process of the model. It takes the order information, merchant information, and region information of the order to be estimated as input, and uses the trained delivery time estimation model to determine the estimated delivery time of the order. Subsequent order allocation to various delivery capacities is also based on the estimated delivery time of each order to ensure that the delivery capacity can complete the delivery of the order within the estimated delivery time. The orders already allocated to each delivery capacity also affect the actual delivery time of the current order.

[0061] In addition, to ensure the real-time performance of the delivery time prediction model, it typically needs to be updated periodically. Therefore, during the online application phase, the actual delivery time of each order is used as a label for the training samples to update the delivery time prediction model.

[0062] S102: Based on the order information of the order, recall a number of candidate delivery vehicles for the order.

[0063] In one or more embodiments of this specification, considering that other orders already allocated to a delivery capacity may affect the delivery time of the order after it is assigned to that capacity, the delivery capacity that the order may be assigned to can be determined to ascertain the impact of assigning the order to each delivery capacity. The delivery capacity may be a rider or a courier.

[0064] Specifically, based on the merchant's location in the order information, a number of delivery vehicles within a preset range centered on the merchant's location are recalled as potential delivery vehicles for the order.

[0065] Alternatively, in another embodiment, the delivery area to which the order belongs can be determined based on the order information, and delivery capacity within that delivery area can be recalled as a number of candidate delivery capacities for delivering the order. The number of orders allocated to each recalled candidate delivery cap shall not exceed a preset order delivery limit.

[0066] Furthermore, since the recalled delivery capacity may already be assigned orders that are not on the same route as this order, or the distance may be far, resulting in a large number of delivery turnsarounds, it is not suitable to deliver this order additionally. Therefore, the recalled delivery capacity can be initially screened.

[0067] Specifically, based on the order information of the allocated orders of the recalled candidate delivery capacity, and the order information of the order, the delivery probability of each candidate delivery capacity delivering the order is determined, and based on the delivery probability of each candidate delivery capacity delivering the order, the delivery capacity with a delivery probability greater than a first preset threshold is determined as the candidate delivery capacity for delivering the order.

[0068] Alternatively, a preset number of delivery capacities can be determined based on the ranking of the delivery probability of each candidate delivery capacity for that order, and used as the candidate delivery capacities for that order. Both the first preset threshold and the preset number can be set as needed.

[0069] Furthermore, when determining the delivery probability of each candidate delivery capacity for the order, for each candidate delivery capacity, based on the order information of the assigned orders for that candidate capacity and the order information of the current order, the distance between the delivery start and end points (merchant location and user location) of the assigned orders for each candidate delivery capacity and the delivery start and end points of the current order can be determined. Then, based on the order placement time (midday peak, evening peak, etc.), the current number of assigned orders for the candidate delivery capacity, and the distance between the delivery start and end points of the assigned orders for the candidate delivery capacity and the delivery start and end points of the current order, the delivery probability of the candidate delivery capacity for the order is determined using a pre-trained first capacity prediction model. The closer the distance between the current assigned order start and end points of the delivery capacity and the delivery start and end points of the current order, the higher the probability that the delivery capacity will deliver the order. This first capacity prediction model can be a tree model, such as Extreme Gradient Boosting Tree (XGBoost).

[0070] S104: For each candidate delivery time in the candidate time period, based on the order information of the order and the order information of the allocated orders of each candidate delivery capacity, determine the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change gain of each candidate delivery capacity delivering the order according to the candidate delivery time.

[0071] In one or more embodiments of this specification, after recalling each of the candidate delivery capacities for delivering the order, the impact of the allocated orders of each candidate delivery capacity on the delivery time of the order after the order is allocated to each candidate delivery capacity can be estimated based on the order information of the allocated orders of each candidate delivery capacity.

[0072] However, since the ETAs of these orders are different, the order in which the selected delivery capacity will be used to deliver the other orders will also be affected. For example, if the ETA of this order is earlier, while the ETAs of other orders for which the selected delivery capacity has already been allocated are later, then this order can be delivered first.

[0073] Therefore, in this specification, in order to avoid increasing order timeouts due to additional delivery of the order, for each selected delivery time in the selected time period, the amount of order timeout caused by additional delivery of the order by each delivery capacity when the ETA of the order is the selected delivery time can be determined, so as to determine the selected delivery time with the least amount of order timeout from all selected delivery times, and use it as the estimated delivery time of the order.

[0074] Specifically, for each potential delivery time within the selected time period, based on the order information of the order and the order information of the allocated orders of each potential delivery capacity, the probability of each potential delivery capacity delivering the order at the selected delivery time is determined, as well as the change gain resulting from the additional delivery of the order at the selected delivery time is determined. Each unit of time within the selected time period can be considered as a potential delivery time; for example, if the selected time period is 12:00 to 12:15, then the potential delivery time can be each minute within that selected time period.

[0075] Furthermore, when determining the probability that each candidate delivery capacity will deliver the order additionally according to the selected delivery time, for each candidate delivery capacity, an updated path can be determined based on the delivery origin and destination of the orders already assigned to that candidate delivery capacity, the ETA of each assigned order, the delivery origin and destination of the order, and the selected delivery time. Since the assigned orders have already been assigned to their corresponding delivery capacities, the order information for each assigned order includes the determined ETA.

[0076] Subsequently, based on the original routes of the selected delivery capacity for each allocated order and the updated routes for additional delivery of the order, a pre-trained second capacity prediction model is used to determine the probability that the selected delivery capacity will additionally deliver the order according to the selected delivery time. This second capacity prediction model can also be a tree model, using the original routes of the selected delivery capacity for each historical order and the updated routes after additional delivery of historical orders as training samples, and using the actual delivery capacity allocated to historical orders as labels for training.

[0077] When determining the change gain resulting from additional delivery of an order by each candidate delivery capacity according to the selected delivery time, specifically, for each candidate delivery capacity, based on the delivery origin and destination of the orders already assigned to that candidate delivery capacity, the ETA of each assigned order, the delivery origin and destination of the order, and the selected delivery time, an updated path for the additional delivery of the order by that candidate delivery capacity according to the selected delivery time can be determined. Then, based on the original path and the updated path of the candidate delivery capacity, the change gain resulting from switching from the original path delivery to the updated path delivery is determined; that is, the change gain of the candidate delivery capacity delivering the order according to the selected delivery time.

[0078] Furthermore, when determining the change gain of the candidate delivery capacity in delivering the order according to the candidate delivery time, at least one of the following can be used as the change gain of the candidate delivery capacity in delivering the order according to the candidate delivery time after the candidate delivery capacity is converted from the original route to the updated route: the increase in timed orders, the increase in on-time orders, and the increase in route. This change gain is negatively correlated with the increase in timed orders, positively correlated with the increase in on-time orders, and negatively correlated with the increase in route.

[0079] Of course, other business metrics can also be used to determine the gain of change, such as path similarity and the overall timeout of each order.

[0080] S106: Based on the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change gain, determine the expected gain corresponding to the candidate delivery time, and determine the estimated delivery time of the order based on the expected gain corresponding to each candidate delivery time.

[0081] In one or more embodiments of this specification, the probability of each available delivery capacity delivering the order, and the gain from additional delivery of the order, differ depending on the available delivery time. Therefore, the optimal estimated delivery time for the order can be determined from the available delivery times with the goal of maximizing the gain from additional delivery of the order.

[0082] Specifically, based on the probability and change gain of each candidate delivery capacity in delivering the order according to the candidate delivery time, the expected gain corresponding to the candidate delivery time is determined. Based on the expected gains corresponding to each candidate delivery time, the candidate delivery time with the largest expected gain is determined as the estimated delivery time corresponding to the order and sent to the user terminal for display.

[0083] Assume the desired delivery time is t, and the delivery capacity for each option is r. i (r1, r2...r) n The probability that each of the selected delivery capacities will deliver the order according to the selected delivery time is: The change in gain resulting from the additional delivery of this order by each of the candidate delivery capacities is: The expected gain corresponding to the selected delivery time is then... .

[0084] based on Figure 1 The order delivery time estimation method shown first determines the initial delivery time of an order and then identifies the candidate time periods following that initial delivery time. Next, based on the order information, several candidate delivery capacities are recalled. For each candidate delivery time within the candidate time periods, based on the order information of the order and the order information of the already allocated orders for each candidate delivery capacity, the probability and variability gain of each candidate delivery capacity delivering the order at that candidate delivery time are determined. Finally, based on the probability and variability gain of each candidate delivery capacity delivering the order at that candidate delivery time, the expected gain corresponding to that candidate delivery time is determined, and the estimated delivery time of the order is determined based on the expected gain corresponding to each candidate delivery time. By determining the expected gain of each candidate delivery capacity for additional order deliveries under different candidate delivery times, and determining the estimated delivery time of the order based on the expected gain of each candidate delivery time, the estimated delivery time of the order is made more accurate.

[0085] The order delivery time estimation method provided in this manual is based on the order information of the currently assigned orders of each delivery capacity. It fully considers the current order assignment situation of each candidate delivery capacity, presents users with more accurate order delivery times, and provides delivery capacity with more accurate time references. This makes the delivery time arrangement of delivery capacity more sufficient and reasonable, and improves the experience for both users and delivery capacity.

[0086] In addition, to improve user satisfaction, when displaying the estimated delivery time of an order to the user, an extra time is usually added to the calculated estimated delivery time, allowing delivery capacity to deliver the order a little earlier. For example, assuming the estimated delivery time of an order obtained through the delivery time estimation model is 11:57, an extra time can be added, and the estimated delivery time displayed to the user will be 12:00.

[0087] Therefore, in one embodiment of this specification, after determining the initial delivery time output by the delivery time estimation model, an additional delivery time can be determined based on the order information and preset compensation rules, and the initial delivery time of the order can be updated accordingly. The preset compensation rules can be set based on business indicators such as the order placement time and the number of available delivery capacity for the order. If the order placement time falls during peak dispatch periods, the additional delivery time will be longer. Similarly, if the number of available delivery capacity for recalled orders is small, the additional delivery time will be longer.

[0088] Furthermore, when determining the candidate time period, since the updated initial delivery time has already reserved the delay time for each delivery capacity, the preset time period around the initial delivery time can be determined as the candidate time period. For example, if the updated initial delivery time is 12 o'clock, then the time period from 11:45 to 12:15 can be determined as the candidate time period.

[0089] based on Figure 1 The present invention provides a method for estimating order delivery time. This specification also includes a corresponding schematic diagram of an order delivery time estimation device. Figure 3 As shown.

[0090] Figure 3 A schematic diagram of an order delivery time estimation device provided in the embodiments of this specification includes:

[0091] The first determining module 200 is used to determine the initial delivery time of the order and determine a preset time period after the initial delivery time as a candidate time period.

[0092] The recall module 202 is used to recall a number of candidate delivery vehicles for delivering the order based on the order information of the order.

[0093] The second determining module 204 is used to determine, for each candidate delivery time in the candidate time period, the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change gain of each candidate delivery capacity delivering the order according to the candidate delivery time, based on the order information of the order and the order information of the allocated orders of each candidate delivery capacity.

[0094] The third determining module 206 is used to determine the expected gain corresponding to the selected delivery time based on the probability of each candidate delivery capacity delivering the order according to the selected delivery time and the change gain, and to determine the expected delivery time of the order based on the expected gain corresponding to each candidate delivery time.

[0095] Optionally, the recall module 202 is specifically used to: recall a number of candidate delivery capacity based on the order information of the order; determine the delivery probability of each candidate delivery capacity delivering the order based on the order information of the allocated orders of the recalled candidate delivery capacity and the order information of the order; and select a number of candidate delivery capacity to deliver the order from the recalled candidate delivery capacity based on the delivery probability of each candidate delivery capacity delivering the order.

[0096] Optionally, the recall module 202 is specifically used to determine the distance between the delivery start and end points of the allocated orders of the recalled candidate delivery capacity and the delivery start and end points of the order based on the order information of the allocated orders of the recalled candidate delivery capacity and the order information of the order; and to determine the delivery probability of each candidate delivery capacity in delivering the order based on the allocated order volume of each candidate delivery capacity, the order placement time of the order, and the distance between the delivery start and end points of the allocated orders of each candidate delivery capacity and the delivery start and end points of the order.

[0097] Optionally, the second determining module 204 is specifically configured to, for each candidate delivery capacity, determine an updated path for the candidate delivery capacity to additionally deliver the orders according to the selected delivery time, based on the delivery start and end points of the assigned orders of the candidate delivery capacity, the estimated delivery time of the assigned orders, the delivery start and end points of the orders, and the selected delivery time; and determine the probability of the candidate delivery capacity to additionally deliver the orders based on the original path of the candidate delivery capacity to deliver each assigned order and the updated path.

[0098] Optionally, the second determining module 204 is specifically configured to, for each candidate delivery capacity, determine an updated path for the candidate delivery capacity to additionally deliver the orders according to the candidate delivery time, based on the delivery start and end points of the assigned orders of the candidate delivery capacity, the estimated delivery time of the assigned orders, the delivery start and end points of the orders, and the candidate delivery time; and determine the change gain of the candidate delivery capacity in delivering the orders according to the candidate delivery time, based on the original path of the candidate delivery capacity and the updated path.

[0099] Optionally, the second determining module 204 is specifically configured to: determine the change gain of the candidate delivery capacity in delivering the orders according to the candidate delivery time based on the timeout order increment generated when the candidate delivery capacity is converted from the original path to the updated path, wherein the change gain is negatively correlated with the timeout order increment; and / or determine the change gain of the candidate delivery capacity in delivering the orders according to the candidate delivery time based on the on-time order increment generated when the candidate delivery capacity is converted from the original path to the updated path, wherein the change gain is positively correlated with the on-time order increment; and / or determine the change gain of the candidate delivery capacity in delivering the orders according to the candidate delivery time based on the path increment when the candidate delivery capacity is converted from the original path to the updated path, wherein the change gain is negatively correlated with the path increment.

[0100] Optionally, the first determining module 200 is further configured to determine the additional time supplement for the order based on the order information of the order and the preset compensation rules, update the initial delivery time of the order based on the additional time supplement for the order, and determine a preset time period around the initial delivery time as a candidate time period.

[0101] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described embodiments. Figure 1 The provided method for estimating order delivery time.

[0102] according to Figure 1 The present invention provides a method for estimating order delivery time, and the embodiments of this specification also propose... Figure 4 The diagram shows a schematic structural representation of the electronic device. Figure 4 At the hardware level, this electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then executes it to achieve the above. Figure 1 The order delivery time estimation method shown.

[0103] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0104] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Moreover, nowadays, instead of manually generating integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0105] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0106] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0107] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0108] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0110] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0111] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0112] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0113] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0114] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0115] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0116] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0118] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0119] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for estimating order delivery time, characterized in that, include: Determine the initial delivery time of the order, and determine a preset time period after the initial delivery time as a candidate time period; Based on the order information of the order, recall a number of potential delivery vehicles for the order; For each candidate delivery time in the candidate time period, based on the order information of the order and the order information of the allocated orders of each candidate delivery capacity, the probability of each candidate delivery capacity delivering the order according to the candidate delivery time and the change in delivery efficiency of each candidate delivery capacity delivering the order according to the candidate delivery time are determined; wherein, the change in delivery efficiency is a quantitative value determined by the timed order increment, on-time order increment and / or path increment generated after the candidate delivery capacity is converted from the original path to an updated path for additional delivery of the order; Based on the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change in delivery efficiency, the expected gain corresponding to the candidate delivery time is determined, and the estimated delivery time of the order is determined based on the expected gain corresponding to each candidate delivery time.

2. The method as described in claim 1, characterized in that, Based on the order information of the aforementioned order, a number of potential delivery vehicles for delivering the order are recalled, specifically including: Based on the order information of the aforementioned orders, recall a number of potential delivery vehicles; Based on the order information of the allocated orders of the recalled candidate delivery capacity, and the order information of the orders, determine the delivery probability of each candidate delivery capacity delivering the orders; Based on the delivery probability of each candidate delivery capacity in delivering the order, select a number of candidate delivery capacities from the recalled candidate delivery capacities to deliver the order.

3. The method as described in claim 2, characterized in that, Based on the order information of the allocated orders of the recalled candidate delivery capacity, and the order information of the orders, the delivery probability of each candidate delivery capacity delivering the order is determined, specifically including: Based on the order information of the allocated orders of the recalled candidate delivery capacity, and the order information of the orders, determine the distance between the delivery start and end points of the allocated orders of each candidate delivery capacity and the delivery start and end points of the orders. The delivery probability of each candidate delivery capacity for the order is determined based on the allocated order volume of each candidate delivery capacity, the order placement time of the order, and the distance between the delivery start and end points of the allocated orders of each candidate delivery capacity and the delivery start and end points of the order.

4. The method as described in claim 1, characterized in that, Based on the order information of the aforementioned orders and the order information of the allocated orders for each candidate delivery capacity, the probability of each candidate delivery capacity delivering the order according to the selected delivery time is determined, specifically including: For each candidate delivery capacity, based on the delivery origin and destination of the assigned orders of the candidate delivery capacity, the estimated delivery time of the assigned orders, the delivery origin and destination of the orders, and the candidate delivery time, an updated path is determined for the candidate delivery capacity to additionally deliver the orders according to the candidate delivery time. Based on the original routes of the selected delivery capacity for each assigned order, and the updated routes, the probability of the selected delivery capacity delivering additional orders is determined.

5. The method as described in claim 1, characterized in that, Determine the change in delivery efficiency for each candidate delivery capacity according to the selected delivery time for the order, specifically including: For each candidate delivery capacity, based on the delivery origin and destination of the assigned orders of the candidate delivery capacity, the estimated delivery time of the assigned orders, the delivery origin and destination of the orders, and the candidate delivery time, an updated path is determined for the candidate delivery capacity to additionally deliver the orders according to the candidate delivery time. Based on the original path and the updated path of the candidate delivery capacity, the change in delivery efficiency of the candidate delivery capacity in delivering the order according to the candidate delivery time is determined.

6. The method as described in claim 5, characterized in that, Based on the original route and the updated route of the candidate delivery capacity, determine the change in delivery efficiency of the candidate delivery capacity for delivering the order according to the candidate delivery time, specifically including: Based on the increase in timed orders resulting from the conversion of the candidate delivery capacity from the original route to the updated route, determine the change in delivery efficiency of the candidate delivery capacity for delivering the orders according to the candidate delivery time, wherein the change in delivery efficiency is negatively correlated with the increase in timed orders; and / or Based on the increase in on-time orders resulting from the conversion of the candidate delivery capacity from the original route to the updated route, determine the change in delivery efficiency of the candidate delivery capacity for delivering the orders according to the candidate delivery time, wherein the change in delivery efficiency is positively correlated with the increase in on-time orders; and / or Based on the path increment of the candidate delivery capacity when it is converted from the original path to the updated path, the change in delivery efficiency of the candidate delivery capacity when delivering the order according to the candidate delivery time is determined, and the change in delivery efficiency is negatively correlated with the path increment.

7. The method as described in claim 1, characterized in that, The method further includes: Based on the order information and the preset compensation rules, determine the additional time for the order; Based on the additional time allowance for the order, update the initial delivery time of the order, and determine a preset time period around the initial delivery time as a candidate time period.

8. An order delivery time estimation device, characterized in that, include: The first determining module is used to determine the initial delivery time of the order and to determine a preset time period after the initial delivery time as a candidate time period. The recall module is used to recall several candidate delivery vehicles for delivering the order based on the order information of the order. The second determining module is used to determine, for each candidate delivery time in the candidate time period, the probability of each candidate delivery capacity delivering the order according to the candidate delivery time, and the change in delivery efficiency of each candidate delivery capacity delivering the order according to the candidate delivery time, based on the order information of the order and the order information of the allocated orders of each candidate delivery capacity; wherein, the change in delivery efficiency is a quantitative value determined by the timed order increment, on-time order increment and / or path increment generated after the candidate delivery capacity is converted from the original path to an updated path for additional delivery of the order; The third determining module is used to determine the expected gain corresponding to the selected delivery time based on the probability of each candidate delivery capacity delivering the order according to the selected delivery time and the change value of delivery efficiency, and to determine the expected delivery time of the order based on the expected gain corresponding to each candidate delivery time.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 7.

Images