Appointment arrival time adjustment method and device, electronic equipment and readable storage medium

Abstract

Embodiments of the present application provide a kind of agreed time of arrival adjustment method, device, electronic equipment and readable storage medium, it is related to computer technical field.The present application embodiment obtains the label information of target order after, according to the label information of target order, determine the target confidence degree and target quantile number corresponding to target order, according to target confidence degree, calculate the expected delay duration of each order in target order, according to target quantile number and each expected delay duration, determine the overtime value of target order, according to overtime value, the agreed time of arrival of target order is adjusted.So, more accurate agreed time of arrival can be obtained, improve the accuracy of agreed time of arrival.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method, apparatus, electronic device, and readable storage medium for adjusting agreed arrival times. Background Technology

[0002] With the development of internet technology, e-commerce platforms are proliferating. Consequently, the logistics industry is also experiencing rapid growth.

[0003] In the logistics industry, most logistics companies have multiple logistics stations located in different places, with staff at these stations working together to complete the transportation and delivery of goods. When goods begin transportation, an agreed-upon arrival time is generated, which is the estimated time when the goods will be delivered to the customer. However, when logistics stations experience abnormalities, such as backlogs, capacity adjustments, or peak holidays, delivery times can change, making it impossible to deliver goods to customers within the agreed-upon time, thus impacting customer experience.

[0004] Currently, adjustments to the agreed arrival time rely on reports from local personnel or historical statistical calculations, but this method has a low accuracy rate. Summary of the Invention

[0005] Based on the above research, the present invention provides a method, apparatus, electronic device, and readable storage medium for adjusting agreed arrival times, which can improve the accuracy of agreed arrival times.

[0006] Embodiments of the present invention can be implemented in the following ways:

[0007] In a first aspect, embodiments of the present invention provide a method for adjusting an agreed arrival time, the method comprising:

[0008] Obtain the tag information of the target order, and determine the target confidence level and target quantile corresponding to the target order based on the tag information;

[0009] Based on the target confidence level, calculate the expected delay time for each order in the target order;

[0010] The overtime value for the target order is determined based on the target quantile and each of the expected delay durations.

[0011] The agreed arrival time of the target order is adjusted based on the added time value.

[0012] In an optional implementation, before determining the target confidence level and target quantile corresponding to the target order based on the tag information, the method further includes:

[0013] Historical orders are grouped by defined tags to obtain multiple tag groups and the flow direction of each tag group;

[0014] Calculate the initial time increment value for each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles;

[0015] Based on the initial time-added values ​​of each flow direction in each of the label groups at different confidence levels and different quantiles, the first confidence level, the first quantile, and the first time-added value corresponding to each of the label groups are determined.

[0016] In an optional implementation, the step of calculating the initial time-added value for each flow direction in each of the labeled groups at different confidence levels and different quantiles includes:

[0017] For each flow direction in each tag group, the estimated delay time of each order in that flow direction is calculated at different confidence levels based on a preset probability model;

[0018] The estimated delay times of each order in the flow are sorted at the same confidence level, and the target estimated delay times corresponding to different quantiles are determined from the estimated delay times sorted at the same confidence level. The target delay times are set as the initial time-addition value.

[0019] In an optional implementation, the step of determining the first confidence level, first quantile, and first time-added value corresponding to each of the label groups based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and different quantiles includes:

[0020] Based on the initial time-added values ​​of each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles, the achievement rate of each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles is determined;

[0021] Based on the achievement rate of each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles, calculate the accuracy and coverage of each of the aforementioned label groups at different confidence levels and different quantiles;

[0022] Based on the accuracy and coverage of each label group at different confidence levels and different quantiles, the first confidence level, the first quantile, and the first time-addition value corresponding to each label group are determined.

[0023] In an optional implementation, the step of determining the achievement rate of each flow direction in each label group at different confidence levels and different quantiles based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and different quantiles includes:

[0024] Obtain the agreed arrival time and actual arrival time of orders corresponding to each flow direction in each of the aforementioned tag groups;

[0025] Based on the agreed arrival time and the initial time increments at different confidence levels and quantiles, the target arrival times of orders corresponding to each flow direction in each of the aforementioned tag groups are determined at different confidence levels and quantiles.

[0026] For each flow direction in each of the aforementioned tag groups, the achievement rate of that flow direction at different confidence levels and different quantiles is obtained based on the target arrival time and actual arrival time of the corresponding order at different confidence levels and different quantiles.

[0027] In an optional implementation, the step of calculating the accuracy and coverage of each label group at different confidence levels and different quantiles based on the achievement rate of each flow direction in each label group at different confidence levels and different quantiles includes:

[0028] Based on the achievement rate of each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles, the number of abnormal but not timed flows, the number of timed but not abnormal flows, and the number of abnormal and timed flows are obtained for each of the aforementioned label groups at different confidence levels and different quantiles.

[0029] Based on the number of abnormal but not timed flows, the number of timed but not abnormal flows, and the number of abnormal flows with timed flows at different confidence levels and different quantiles for each of the aforementioned label groups, the accuracy and coverage of each of the aforementioned label groups at different confidence levels and different quantiles are calculated.

[0030] In an optional implementation, the step of determining the first confidence level, first quantile, and first time-added value corresponding to each of the label groups based on the accuracy and coverage of each label group at different confidence levels and different quantiles includes:

[0031] For each of the label groups, the accuracy of the label group at different confidence levels and different quantiles is filtered according to the set accuracy threshold to obtain a target accuracy greater than the accuracy threshold;

[0032] From the coverage corresponding to each of the target accuracy rates, the maximum coverage rate is determined, the confidence level corresponding to the maximum coverage rate is set as the first confidence level corresponding to the label group, the quantile corresponding to the maximum coverage rate is set as the first quantile corresponding to the label group, and the first quantile and the initial time-addition value corresponding to the first confidence level are set as the first time-addition value corresponding to the label group.

[0033] In an optional implementation, the step of determining the target confidence level and target quantile corresponding to the target order based on the tag information includes:

[0034] The tag information is compared with the tags of each tag group in the pre-stored tag database to obtain the target tag group whose tags are the same as the tag information;

[0035] The first confidence level and the first quantile corresponding to the target label group are set as the target confidence level and the target quantile corresponding to the target order; the label database stores the labels of each label group and the first confidence level and the first quantile corresponding to each label group.

[0036] In an optional implementation, the step of adjusting the agreed arrival time of the target order based on the added time value includes:

[0037] The tag information is compared with the tags of each tag group in the pre-stored tag database to obtain the target tag group whose tags are the same as the tag information;

[0038] Compare the first time-added value corresponding to the target tag group with the time-added value of the target order;

[0039] If the time-addition value of the target order is not less than the first time-addition value corresponding to the target tag group, then the agreed arrival time of the target order is adjusted according to the time-addition value of the target order;

[0040] If the time increment of the target order is less than the first time increment corresponding to the target tag group, then the agreed arrival time of the target order is maintained.

[0041] In an optional implementation, the step of calculating the expected delay time of each order in the target order based on the target confidence level includes:

[0042] Based on a preset probability model, the estimated arrival time of each order in the target order at the target confidence level is calculated;

[0043] Based on the agreed arrival time of the target order and the estimated arrival time of each order in the target order at the target confidence level, the estimated delay time of each order in the target order is obtained.

[0044] In an optional implementation, the step of determining the overtime value of the target order based on the target quantile and each of the expected delay durations includes:

[0045] The estimated delay durations are sorted according to the set conditions to obtain the sorted estimated delay durations;

[0046] Based on the target quantile, the target estimated delay time is determined from the sorted estimated delay times, and the target estimated delay time is set as the added time value.

[0047] Secondly, embodiments of the present invention provide a pre-arranged arrival time adjustment device, the pre-arranged arrival time adjustment device comprising:

[0048] The data acquisition module is used to acquire the tag information of the target order, and determine the target confidence level and target quantile corresponding to the target order based on the tag information;

[0049] The duration calculation module is used to calculate the estimated delay duration of each order in the target order based on the target confidence level;

[0050] The time calculation module is used to determine the time value of the target order based on the target quantile and each of the expected delay durations;

[0051] The time adjustment module is used to adjust the agreed arrival time of the target order based on the added time value.

[0052] Thirdly, embodiments of the present invention provide 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 computer program, it implements the agreed arrival time adjustment method described in any of the foregoing embodiments.

[0053] Fourthly, embodiments of the present invention provide a readable storage medium, the readable storage medium including a computer program, wherein the computer program, when running, controls the electronic device where the readable storage medium is located to execute the agreed arrival time adjustment method described in any of the foregoing embodiments.

[0054] The agreed arrival time adjustment method, apparatus, electronic device, and readable storage medium provided in this invention, after obtaining the tag information of a target order, determine the target confidence level and target quantile corresponding to the target order based on the tag information. Based on the target confidence level, the estimated delay time of each order in the target order is calculated. Based on the target quantile and each estimated delay time, an additional time value is determined for the target order. The agreed arrival time of the target order is then adjusted based on the additional time value. This results in a more accurate agreed arrival time and improves the accuracy of the agreed arrival time. Attached Figure Description

[0055] The technical solution and other beneficial effects of the present invention will become apparent from the following detailed description of specific embodiments of the invention, in conjunction with the accompanying drawings.

[0056] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0057] Figure 2This is a schematic flowchart of a pre-arranged arrival time adjustment method provided in an embodiment of the present invention.

[0058] Figure 3 This is another flowchart illustrating the agreed arrival time adjustment method provided in an embodiment of the present invention.

[0059] Figure 4 This is a parameter table diagram of tag grouping provided in an embodiment of the present invention.

[0060] Figure 5 This is a block diagram of a pre-arranged arrival time adjustment device provided in an embodiment of the present invention.

[0061] Icons: 100 - Electronic device; 10 - Agreed arrival time adjustment device; 11 - Data acquisition module; 12 - Duration calculation module; 13 - Addition time calculation module; 14 - Time adjustment module; 20 - Memory; 30 - Processor; 40 - Communication unit. Detailed Implementation

[0062] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0063] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0064] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows for communication; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0065] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0066] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0067] As described in the background section, currently, adjustments to agreed arrival times rely on reports from local personnel or historical statistical calculations. Relying on reports from local personnel lacks supporting evidence, and the values ​​requiring adjustment also lack a basis, resulting in low accuracy and coverage, and a lack of comprehensive evaluation for focused sites. While historical statistical calculations are relatively lagging, they smooth out anomalies, making them unsuitable for capturing abnormal events and thus failing to identify anomalies in a timely manner.

[0068] Based on the above research, embodiments of the present invention provide a method, apparatus, electronic device, and readable storage medium for adjusting agreed arrival times. After obtaining the tag information of a target order, the method determines the target confidence level and target quantile corresponding to the target order based on the tag information. Based on the target confidence level, the estimated delay time for each order within the target order is calculated. Based on the target quantile and each estimated delay time, an additional time value is determined for the target order. Based on the additional time value, the agreed arrival time of the target order is adjusted. This allows for timely adjustment of the agreed arrival time of orders with high accuracy.

[0069] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of the electronic device provided in this embodiment. Figure 1 As shown, the electronic device 100 includes a time-of-arrival adjustment device 10, a memory 20, a processor 30, and a communication unit 40. The memory 20, processor 30, and communication unit 40 are electrically connected directly or indirectly to each other to achieve signal transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0070] In this embodiment, the agreed arrival time adjustment device 10 includes at least one software functional module that can be stored in the memory 20 in the form of software or firmware. The processor 30 is used to execute the executable module (e.g., the software functional module or computer program included in the agreed arrival time adjustment device 10) stored in the memory 20. When the electronic device 100 is running, the processor 30 communicates with the memory 20 via a bus, and the processor 30 executes the executable module or computer program to implement the agreed arrival time adjustment method described in this embodiment.

[0071] The memory 20 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0072] Processor 30 is used to perform one or more functions described in this embodiment. In some embodiments, processor 30 may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). By way of example only, processor 30 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computing (RISC) computer, or a microprocessor, or any combination thereof.

[0073] For ease of explanation, only one processor is described in the electronic device 100. However, it should be noted that the electronic device 100 in this embodiment may also include multiple processors, and therefore the steps performed by one processor as described in this embodiment may also be performed jointly or individually by multiple processors. For example, if the processor of the electronic device performs steps A and B, it should be understood that steps A and B may also be performed jointly by two different processors or individually by one processor. For example, one processor performs step A, and a second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0074] In this embodiment, the process definition method disclosed in any implementation can be applied to the processor 30, or implemented by the processor 30.

[0075] The communication unit 40 is used to establish a communication connection between the electronic device 100 and other devices via a network, and to send and receive data via the network.

[0076] In some implementations, the network can be any type of wired or wireless network, or a combination thereof. By way of example only, the network may include wired networks, wireless networks, fiber optic networks, telecommunications networks, intranets, the Internet, local area networks (LANs), wide area networks (WANs), wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth networks, ZigBee networks, or near field communication (NFC) networks, or any combination thereof.

[0077] In this embodiment, the electronic device can be a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a physical server, or other devices. This embodiment does not impose any restrictions on the specific type of electronic device.

[0078] Understandably, Figure 1 The structure shown is for illustrative purposes only. Electronic devices may also have more advanced features. Figure 1 Showing more or fewer components, or having with Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0079] based on Figure 1 The implementation architecture of this embodiment provides a method for adjusting the agreed arrival time, which is... Figure 1 The electronic device shown executes the following detailed explanation of the steps of the agreed arrival time adjustment method provided in this embodiment. Please refer to the reference below. Figure 2 The agreed arrival time adjustment method provided in this embodiment includes steps S101 to S104.

[0080] Step S101: Obtain the tag information of the target order, and determine the target confidence level and target quantile corresponding to the target order based on the tag information.

[0081] The target order can be any batch of orders whose agreed arrival time needs to be adjusted. In this embodiment, the target order refers to orders belonging to the same batch. It is understood that the target order can include orders from different customers, and the number of orders from different customers can be different. That is, in this embodiment, the target order includes multiple orders, and these multiple orders can belong to different customers.

[0082] Optionally, the tag information of the target order can be obtained in real time, or it can be obtained at regular intervals. In this embodiment, the tag information of the target order can be obtained every K hours, that is, the agreed arrival time is checked every K hours to see if it needs to be adjusted, where K is a positive number.

[0083] In this embodiment, the tag information of the target order, i.e., the attribute information of the target order, may include the product code, transportation process, and the time when the tag information of the target order was obtained. After obtaining the tag information of the target order, the target confidence level and target quantile corresponding to the target order can be determined based on the tag information.

[0084] In this embodiment, a correspondence between label information, confidence level, and quantile is pre-established. Therefore, after obtaining the label information of the target order, the corresponding target confidence level and target quantile can be found based on the correspondence.

[0085] It should be noted that in this embodiment, the information types included in the label information of each batch of orders are the same. For example, if the label information of a certain batch of orders includes three pieces of information: product code, transportation process, and information acquisition time, then the label information of other batches of orders will also include the same three pieces of information. This ensures the consistency of the correspondence established when establishing the correspondence between label information and confidence levels and quantiles. That is, each correspondence is a correspondence between confidence level, quantile, and product code, transportation process, and information acquisition time in the label information. Furthermore, after establishing the correspondence, when determining the target confidence level and target quantile of the target order, the corresponding confidence level and quantile of the label information (product code, transportation process, and information acquisition time) of the target order can be found in the correspondence based on the correspondence, and then the found confidence level and quantile are set as the target confidence level and target quantile.

[0086] Step S102: Calculate the estimated delay time for each order in the target order based on the target confidence level.

[0087] Once the corresponding target confidence level is found, the expected delay time for each order in the target order can be calculated at the target confidence level.

[0088] In this embodiment, each order, when generated, has a promised arrival time, i.e., an agreed arrival time. During transportation, when each order leaves the current location for the next location, a probability model is triggered to calculate the estimated arrival time of each order at the next location. Therefore, in this embodiment, based on the probability model and the current target confidence level, the estimated arrival time of each order included in the target order can be calculated. Then, based on the calculated estimated arrival times of each order and the agreed arrival time, the estimated delay time of each order can be obtained.

[0089] It should be noted that, in this embodiment, when the estimated delay time of each order is obtained based on the calculated estimated arrival time and agreed arrival time of each order, if the estimated arrival time of the order is earlier than the agreed arrival time, the estimated delay time of the order can be set to zero.

[0090] Step S103: Determine the overtime value for the target order based on the target quantile and the estimated delay duration.

[0091] In this embodiment, the estimated delay time for each order represents the time by which each order will arrive later than the agreed arrival time. When the arrival time of any order in the batch of orders, i.e., the target order, is delayed, the agreed arrival time of the target order will also be delayed. Therefore, the agreed arrival time of the target order needs to be adjusted. Based on this, after obtaining the estimated delay time for each order, the added time value for the target order is determined from each estimated delay time using the target quantile corresponding to the target order.

[0092] In this embodiment, when determining the added time value for a target order based on the target quantile for each estimated delay duration, the estimated delay durations can be sorted first. Then, the added time value can be directly determined from the sorted estimated delay durations based on the target quantile. For example, assuming the target quantile is 1 / 4 and there are 100 estimated delay durations, the 25th estimated delay duration is used as the added time value after sorting. Alternatively, the sorted estimated delay durations can be proportionally divided into two delay duration groups based on the target quantile. The larger delay duration group is then selected as the target delay duration group, and the average value within the target delay duration group is calculated. This average value is then used as the added time value corresponding to the target quantile. This embodiment determines the added time value from the estimated delay duration of each order using the quantile. By adjusting the agreed arrival time using the added time value, the requirement for most orders to arrive within the adjusted agreed arrival time can be met, improving the user experience.

[0093] Step S104: Adjust the agreed arrival time of the target order according to the time increment.

[0094] Once the overtime value for the target order is determined, the agreed arrival time of the target order and the overtime value are added together to adjust the agreed arrival time of the target order, resulting in an adjusted agreed arrival time. Based on this adjusted agreed arrival time and the customer's promised delivery deadline, the system can meet the demand for most orders to arrive within the promised delivery period, effectively improving customer experience.

[0095] In this embodiment, when adjusting the agreed arrival time of the target order based on the time increment, the agreed arrival time of batch orders with the same tag information as the target order within a future valid timeframe can also be adjusted based on the time increment. The valid timeframe can be determined according to business needs, such as within the next 3 days, the next 2 days, or the next day, etc.

[0096] The agreed arrival time adjustment method provided in this embodiment, after obtaining the tag information of the target order, determines the target confidence level and target quantile corresponding to the target order based on the tag information. Based on the target confidence level, it calculates the estimated delay time for each order within the target order. Based on the target quantile and each estimated delay time, it determines the additional time value for the target order. Based on the additional time value, it adjusts the agreed arrival time of the target order. In this way, the agreed arrival time of orders can be adjusted in a timely manner with high accuracy, meeting the needs of most orders to arrive within the promised delivery period and effectively improving customer experience.

[0097] To accurately assess the impact on timeliness in the event of anomalies at any stage of cargo transportation, it is necessary to ensure the accuracy of the confidence level and quantiles for batch orders. To guarantee the accuracy of these confidence levels and quantiles, this embodiment establishes the relationship between confidence levels, quantiles, and batch orders using extensive historical order data. Therefore, please refer to [the relevant documentation / reference]. Figure 3 Before determining the target confidence level and target quantile corresponding to the target order based on the tag information of the target order, the method provided in this embodiment further includes steps S201 to S203.

[0098] Step S201: Group historical orders by set tags to obtain multiple tag groups and the flow of each tag group.

[0099] The historical orders can be selected from orders delivered within any historical time period prior to the target order. Optionally, in this embodiment, historical orders from week T-1 are grouped together, that is, individual orders delivered within the week prior to the target order are selected for grouping.

[0100] After obtaining historical orders, these orders can be grouped by set tags to obtain multiple tag groups and the flow of each tag group.

[0101] In this embodiment, when grouping historical orders with set tags, the set tags include the product code, transportation process, and time corresponding to the order. For example, in this embodiment, the set tags are the product code, transportation process, and time corresponding to the order, so the tags corresponding to each tag group are (product code, transportation process, and time).

[0102] In this context, the product code corresponding to an order represents the type of product; products of the same type share the same product code. The transportation stage corresponding to an order indicates its transportation status, including transit, receiving, and delivery stages. In this embodiment, the time corresponding to an order represents the moment when the agreed arrival time needs adjustment. For example, if the agreed arrival time is checked every K hours, and T1 is the first time this is checked, T1+K is the second time, T1+2k is the third time, and so on, with T1+nk being the (n-1)th time, then the time corresponding to an order can be represented as {T1, T1+K, T1+2K, ..., T1+nk}.

[0103] Understandably, in this embodiment, each order may correspond to multiple transportation links and multiple times. When grouping according to transportation links and times, each order may be assigned to different groups at the same time.

[0104] The flow direction represents the origin and destination of an order's transportation. For example, an order transported from Shanghai to Guangzhou has a flow direction of Shanghai to Guangzhou. In this embodiment, the flow direction of orders at different stages is expressed in different ways. For example, for orders in the receiving stage, the flow direction can be recorded as "site code to all, zoncode-all"; for orders in transit, the flow direction can be recorded as "city to city, city1-city2"; and for orders in the delivery stage, the flow direction can be recorded as "all to site code, all-zonecode". That is, the flow direction in the receiving and delivery stages starts with the site code, and the flow direction in the transit stage starts with the city code.

[0105] After grouping historical orders with defined tags, multiple tag groups are obtained. Each tag group includes the flow of each order; therefore, by statistically analyzing the flow of orders included in each tag group, the flow corresponding to each tag group can be obtained.

[0106] Step S202: Calculate the initial time increment for each flow direction in each label group at different confidence levels and quantiles.

[0107] Once the label groups and their flow directions are obtained, the initial time increments for each flow direction in each label group at different confidence levels and quantiles can be calculated.

[0108] In this embodiment, the initial time increment values ​​for each flow direction in each tag group at different confidence levels and quantiles can be calculated through the following steps:

[0109] (1) For each flow direction in each tag group, calculate the expected delay time of each order in that flow direction under different confidence levels based on the preset probability model.

[0110] (2) Sort the expected delay time of each order in the flow under the same confidence level, and determine the target expected delay time corresponding to each quantile from the expected delay time sorted under the same confidence level, and set the target expected delay time as the initial time value.

[0111] Specifically, for each flow direction in each tag group, the expected delay time of each order in that flow direction at different confidence levels can be calculated using a probability model.

[0112] Accordingly, when calculating the estimated delay time of each order in this flow under different confidence levels, the estimated arrival time of each order can also be calculated according to the probability model under different confidence levels, thus obtaining the estimated arrival time of each order under different confidence levels. For example: assuming that under the condition of satisfying a t-distribution (or other types of distribution), the probability of an order being delivered before time T0 is (1-p0), then the estimated arrival time of this order under confidence level P1 is T11, under confidence level P2 is T12, under confidence level P3 is T13, and so on, with the estimated arrival time under confidence level PM being T1M. The estimated arrival time of each order under different confidence levels can be expressed as p:<p1,p2,...,pM> And T1:<T11,T12,...,T1M> , where p is the confidence level and T1 is the estimated arrival time. It should be noted that in this embodiment, the confidence level can be set according to actual needs and is not specifically limited.

[0113] After obtaining the estimated arrival time of each order at different confidence levels, the estimated delay time of each order at different confidence levels can be obtained based on the agreed arrival time of each order and the estimated arrival time at different confidence levels.

[0114] Each order, when generated, has an agreed arrival time with the customer. For each order, based on the agreed arrival time and the estimated arrival time at different confidence levels, the estimated delay time for that order at different confidence levels is calculated. The agreed arrival time is then compared with the estimated arrival time at each confidence level, and the difference between the agreed arrival time and the estimated arrival time at each confidence level gives the estimated delay time for each order at each confidence level. It should be noted that if the estimated arrival time of an order is earlier than the agreed arrival time, the estimated delay time for that order can be set to zero.

[0115] For example, for a certain order, assuming the agreed arrival time is t1 and the expected arrival time at confidence level A is T1, then the expected delay time at confidence level A is T1-t1.

[0116] Through the above process, the estimated delay time of each order in each flow direction at different confidence levels can be obtained. After obtaining the estimated delay time of each order in each flow direction at different confidence levels, for each flow direction, the estimated delay time of each order in that flow direction at the same confidence level is sorted. Then, the target estimated delay time corresponding to different quantiles is determined from the estimated delay time sorted at the same confidence level. The target estimated delay time is set as the initial time increment, thereby obtaining the initial time increment value of that flow direction at different confidence levels and different quantiles.

[0117] When sorting the expected delay time of each order in the same flow at the same confidence level, they can be sorted in ascending order. For example, for a certain flow direction, there are expected delay times at confidence levels A and B. Sort the expected delay times at confidence level A from smallest to largest to obtain ta1, ta2, ta3, ta4. Sort the expected delay times at confidence level B from smallest to largest to obtain tb1, tb2, tb3, tb4. Assuming quantiles are 50% and 75%, then at confidence level A, based on the sorted expected delay times ta1, ta2, ta3, ta4, we need to determine the target expected delay time corresponding to the 50th quantile and the target expected delay time corresponding to the 75th quantile. At confidence level B, based on the sorted expected delay times tb1, tb2, tb3, tb4, we need to determine the target expected delay time corresponding to the 50th quantile and the target expected delay time corresponding to the 75th quantile.

[0118] In this embodiment, when determining the target estimated delay time corresponding to different quantiles from the estimated delay times sorted under the same confidence level, for each quantile, the target estimated delay time can be directly determined from the estimated delay times sorted under the same confidence level based on that quantile. For example, if the sorted estimated delay times ta1, ta2, ta3, and ta4 have a quantile of 50%, then the target estimated delay time corresponding to the 50% quantile is determined to be ta2. Alternatively, based on this quantile, the estimated delay times sorted under the same confidence level can be divided proportionally to obtain two delay time groups. Then, the larger delay time group among the two delay time groups is selected as the target delay time group. The average value of the target delay time group is calculated, and the calculated average value is used as the target estimated delay time corresponding to that quantile. For example, the sorted expected delay times ta1, ta2, ta3, and ta4 have a quantile of 50%. When dividing the delays proportionally based on the 50% quantile, ta1 and ta2 can be used as the first delay time group, and ta3 and ta4 can be used as the second delay time group. Since the values ​​of ta3 and ta4 are greater than the values ​​of ta1 and ta2, the second delay time group is used as the target delay time group. The average value of the expected delay times in the target delay time group is calculated, that is, the average value of ta3 and ta4 is calculated, and the average value is used as the target expected delay time corresponding to 50%.

[0119] After determining the target estimated delay time corresponding to each quantile from the estimated delay times sorted at the same confidence level, the determined target estimated delay time can be used as the initial time increment, thereby obtaining the initial time increment value of the flow under different confidence levels and different quantiles.

[0120] Understandably, the same process can be used for the flow of other label groups to obtain the initial time increments at different confidence levels and different quantiles.

[0121] Step S203: Based on the initial time values ​​of each flow direction in each label group under different confidence levels and different quantiles, determine the first confidence level, first quantile, and first time value corresponding to each label group.

[0122] In this process, after obtaining the initial time values ​​of each flow direction in each label group under different confidence levels and different quantiles, the first confidence level, first quantile, and first time value corresponding to each label group can be determined based on the initial time values ​​of each flow direction in each label group under different confidence levels and different quantiles.

[0123] Optionally, in this embodiment, the step of determining the first confidence level, first quantile, and first time-added value corresponding to each label group based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and different quantiles includes:

[0124] (1) Based on the initial time values ​​of each flow direction in each label group at different confidence levels and different quantiles, the achievement rate of each flow direction in each label group at different confidence levels and different quantiles is determined.

[0125] (2) Based on the achievement rate of each flow in each label group at different confidence levels and different quantiles, calculate the accuracy and coverage of each label group at different confidence levels and different quantiles.

[0126] (3) Based on the accuracy and coverage of each label group at different confidence levels and different quantiles, determine the first confidence level, first quantile and first time value corresponding to each label group.

[0127] The achievement rate for each delivery route refers to the percentage of orders successfully delivered within the agreed arrival time for that route. For example, if a delivery route includes 100 orders, and 80 orders are successfully delivered within the agreed arrival time, then the achievement rate for that route is 80%.

[0128] Optionally, in this embodiment, the step of determining the achievement rate of each flow direction in each label group at different confidence levels and different quantiles based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and different quantiles may include:

[0129] Get the agreed arrival time and actual arrival time of orders corresponding to each flow direction in each tag group.

[0130] Based on the agreed arrival time and the initial time increments at different confidence levels and quantiles, the target arrival times for orders corresponding to each flow direction in each tag group are determined at different confidence levels and quantiles.

[0131] For each flow direction in each tag group, the achievement rate of that flow direction at different confidence levels and different quantiles is obtained based on the target arrival time and actual arrival time of the corresponding order at different confidence levels and different quantiles.

[0132] In this embodiment, for each flow direction within each tag group, the agreed arrival time and actual arrival time of each order corresponding to that flow direction are first obtained; that is, the agreed arrival time and actual arrival time of each order in that flow direction are obtained. After obtaining the agreed arrival time and actual arrival time of each order in each flow direction, for each order in each flow direction, the target arrival time of the order at different confidence levels and different quantiles can be obtained based on the initial time increment value of that flow direction at different confidence levels and different quantiles, and the agreed arrival time of the order.

[0133] Specifically, when determining the target arrival time of an order at different confidence levels and quantiles based on the initial time increments for the flow direction at different confidence levels and quantiles, and the agreed arrival time of the order, the agreed arrival time of the order is added to the initial time increments for the flow direction at different confidence levels and quantiles to obtain the target arrival time of the order at different confidence levels and quantiles. For example, if the initial time increment for a flow direction is t1 at confidence level A and quantile a, and the initial time increment is t2 at confidence level B and quantile b, and the agreed arrival time of an order in this flow direction is T1, then the target arrival time of the order at confidence level A and quantile a is T1+t1, and the target arrival time at confidence level B and quantile b is T1+t2.

[0134] Through the above process, the target arrival time of orders corresponding to each flow direction in each tag group under different confidence levels and different quantiles can be obtained. After obtaining the target arrival time of orders corresponding to each flow direction in each tag group under different confidence levels and different quantiles, the achievement rate of that flow direction under different confidence levels and different quantiles can be obtained for each flow direction in each tag group, that is, based on the target arrival time and actual arrival time of the orders corresponding to that flow direction under different confidence levels and different quantiles.

[0135] In this embodiment, when obtaining the achievement rate of the flow direction at different confidence levels and different quantiles based on the target arrival time and actual arrival time of the orders corresponding to the flow direction at different confidence levels and different quantiles, the number of orders successfully delivered to the flow direction at different confidence levels and different quantiles is first calculated based on the target arrival time and actual arrival time of the orders corresponding to the flow direction at different confidence levels and different quantiles. Then, based on the number of orders successfully delivered at different confidence levels and different quantiles, the achievement rate of the flow direction at different confidence levels and different quantiles is obtained.

[0136] Specifically, when calculating the number of successfully delivered orders for a given flow direction at different confidence levels and quantiles based on the target arrival time and actual arrival time of the corresponding orders at different confidence levels and quantiles, for each order in that flow direction, if the target arrival time of the order at different confidence levels and quantiles is greater than or equal to the actual arrival time of the order, the order is considered successfully delivered and marked as successfully delivered. For example, for an order with a target arrival time of T1 at confidence level A and quantile a, and an actual arrival time of T2, if the target arrival time T1 is greater than or equal to the actual arrival time T2, the order is considered successfully delivered within the target arrival time and marked as successfully delivered; if the target arrival time T1 is less than the actual arrival time T2, the order is considered unsuccessfully delivered within the target arrival time and marked as unsuccessfully delivered.

[0137] Through the above process, we can obtain the number of orders successfully delivered for each flow direction at different confidence levels and quantiles. Counting these successfully delivered orders yields the total number of orders successfully delivered for each flow direction at different confidence levels and quantiles. After obtaining the number of successfully delivered orders for each flow direction at different confidence levels and quantiles, we can calculate the percentage of successfully delivered orders for that flow direction at different confidence levels and quantiles relative to the total number of orders for that flow direction. This gives us the achievement rate for that flow direction at different confidence levels and quantiles.

[0138] After obtaining the achievement rate of each flow in each label group at different confidence levels and quantiles, the first confidence level, first quantile, and first time-addition value corresponding to each label group can be determined based on the accuracy and coverage of each label group at different confidence levels and quantiles.

[0139] Optionally, in this embodiment, the step of calculating the accuracy and coverage of each label group at different confidence levels and quantiles based on the achievement rate of each flow direction in each label group at different confidence levels and quantiles may include:

[0140] Based on the achievement rate of each flow direction in each label group at different confidence levels and different quantiles, the number of abnormal but not timed flows, the number of timed but not abnormal flows, and the number of abnormal and timed flows are obtained for each label group at different confidence levels and different quantiles.

[0141] Based on the number of abnormal but not timed flows, timed but not abnormal flows, and abnormal and timed flows for each label group at different confidence levels and quantiles, the accuracy and coverage of each label group at different confidence levels and quantiles are calculated.

[0142] In calculating the accuracy and coverage of each label group at different confidence levels and quantiles based on the achievement rate of each flow direction in each label group at different confidence levels and quantiles, the number of abnormal flows in each label group at different confidence levels and quantiles can be obtained first based on the achievement rate of each flow direction in each label group at different confidence levels and quantiles.

[0143] When obtaining the number of abnormal flows in each label group at different confidence levels and quantiles based on the achievement rate of each flow in each label group at different confidence levels and quantiles, for each flow in each label group, the achievement rate of that flow can be compared with a set achievement rate threshold. If the achievement rate of that flow is less than the achievement rate threshold, then that flow is determined to be an abnormal flow. In this way, abnormal flows in the label group are identified, thereby obtaining the number of abnormal flows in the label group at different confidence levels and quantiles.

[0144] To accurately identify the number of abnormal flows in each tag group, in an optional implementation, an abnormal flow can be detected based on its achievement rate and deterioration rate. The deterioration rate refers to the degree of deterioration in the current achievement rate compared to the previous achievement rate. For each flow, it can be determined whether its achievement rate is less than an achievement rate threshold and whether its deterioration rate is greater than a set deterioration rate threshold. If the achievement rate is less than the achievement rate threshold and the deterioration rate is greater than the deterioration rate threshold, the flow is determined to be abnormal. Conversely, if the achievement rate is not less than the achievement rate threshold, or the deterioration rate is not greater than the deterioration rate threshold, the flow is determined not to be abnormal.

[0145] In this embodiment, after determining that the flow direction is an abnormal flow direction, the abnormal flow direction can be marked to obtain the abnormal flow direction of each label group under different confidence levels and different quantiles.

[0146] After obtaining the abnormal flow direction of each label group under different confidence levels and different quantiles, the number of abnormal flow directions of each label group under different confidence levels and different quantiles can be obtained by statistically analyzing the abnormal flow direction of each label group under different confidence levels and different quantiles.

[0147] In this embodiment, for each flow direction of each tag group, the flow direction can be detected as a time-added flow direction based on the agreed arrival time and actual arrival time at different confidence levels and quantiles. If the actual arrival time is greater than the agreed arrival time, the flow direction is a time-added flow direction and is marked. If the actual arrival time is not greater than the agreed arrival time, the flow direction is not a time-added flow direction. By statistically analyzing the time-added flow directions of each tag group at different confidence levels and quantiles, the number of time-added flow directions for each tag group at different confidence levels and quantiles can be obtained.

[0148] After obtaining the number of time-added flows and the number of abnormal flows for each label group at different confidence levels and different quantiles, we can analyze and statistically analyze the number of time-added flows and the number of abnormal flows for each label group at different confidence levels and different quantiles to obtain the number of abnormal flows with time-added, the number of flows with time-added but not abnormal, and the number of abnormal flows without time-added for each label group at different confidence levels and different quantiles.

[0149] After obtaining the number of abnormal but not timed flows, timed but not abnormal flows, and abnormal and timed flows for each label group at different confidence levels and quantiles, the accuracy and coverage of each label group at different confidence levels and quantiles can be calculated based on these numbers.

[0150] In this embodiment, as shown in Table 1, the number of abnormal flows with added time is N1, the number of abnormal flows without added time is N2, the number of flows with added time but not abnormal is N3, and the number of flows without abnormality and without added time is N4. Coverage COV and accuracy ACC are defined, then coverage COV = N1 / (N1+N2), and accuracy ACC = N1 / (N1+N3).

[0151] Table 1

[0152]

[0153] Based on the number of outliers, the number of outliers with added time, and the number of outliers with added time for each label group at different confidence levels and quantiles, the accuracy and coverage of each label group at different confidence levels and quantiles can be calculated using the above formula.

[0154] After obtaining the accuracy and coverage of each label group at different confidence levels and quantiles, the first confidence level, first quantile, and first time increment value corresponding to each label group can be determined based on the accuracy and coverage of each label group at different confidence levels and quantiles.

[0155] Optionally, for each label group, the confidence level and quantile with the highest accuracy can be selected as the first confidence level and first quantile for that label group. Then, the initial time-addition value obtained by determining the first confidence level and first quantile is used as the first time-addition value for that label group. Alternatively, the confidence level and quantile with the highest coverage can be selected as the first confidence level and first quantile for that label group. Finally, the initial time-addition value obtained by determining the first confidence level and first quantile is used as the first time-addition value for that label group. Or, the average coverage and accuracy at different confidence levels and different quantiles can be calculated, and the confidence level and quantile with the highest average can be selected as the first confidence level and first quantile for that label group. Then, the initial time-addition value obtained by determining the first confidence level and first quantile is used as the first time-addition value for that label group.

[0156] To achieve the highest coverage while ensuring accuracy, and to promptly identify abnormal flow directions, in this embodiment, the step of determining the first confidence level, first quantile, and first time-added value corresponding to each label group based on the accuracy and coverage of each label group at different confidence levels and quantiles may include:

[0157] For each label group, based on the set accuracy threshold, the accuracy of the label group at different confidence levels and different quantiles is filtered to obtain a target accuracy greater than the accuracy threshold.

[0158] From the coverage corresponding to the accuracy of each target, the maximum coverage is determined, and the confidence level corresponding to the maximum coverage is set as the first confidence level corresponding to the label group. The quantile corresponding to the maximum coverage is set as the first quantile corresponding to the label group. The first quantile and the initial time value corresponding to the first confidence are set as the first time value corresponding to the label group.

[0159] Each label group has multiple confidence levels and multiple quantiles. Each confidence level and each quantile corresponds to a coverage and accuracy. For example, for label group L1 with M confidence levels and L quantiles, this label group can yield M*L combinations of coverage and accuracy. Each combination corresponds to one confidence level and one quantile.

[0160] Based on this, when determining the first confidence level and first quantile for each label group, the accuracy of the label group at different confidence levels and quantiles can be filtered according to the set accuracy threshold to obtain a target accuracy greater than the accuracy threshold. After obtaining the target accuracy greater than the accuracy threshold, the maximum coverage can be determined from the coverage corresponding to each target accuracy. The confidence level corresponding to the combination with the maximum coverage is used as the first confidence level for the label group, and the quantile corresponding to the combination with the maximum coverage is used as the first quantile for the label group. The initial time-added value corresponding to the first quantile and the first confidence level is set as the first time-added value for the label group. For example, for label group L1, the coverage and accuracy at confidence level A and quantile a are (COV1, ACC1), the coverage and accuracy at confidence level A and quantile b are (COV2, ACC2), and the coverage and accuracy at confidence level B and quantile b are (COV3, ACC3). Based on the set accuracy threshold, the accuracy of label group L1 at different confidence levels and quantiles is filtered to obtain target accuracy rates ACC1 and ACC2 that are greater than the accuracy threshold. Then, from the coverage rate COV1 corresponding to the target accuracy rate ACC1 and the coverage rate COV2 corresponding to the target accuracy rate ACC2, the maximum coverage rate COV2 is determined. The confidence level A corresponding to (COV2, ACC2) is used as the first confidence level of label group L1, the quantile b corresponding to (COV2, ACC2) is used as the first quantile of label group L1, and the initial time-added value calculated at confidence level A and quantile b is used as the first time-added value of label group L1.

[0161] In this embodiment, the first confidence level, first quantile, and first time-added value corresponding to each label group are the optimal confidence level, optimal quantile, and optimal time-added value for each label group. Therefore, after obtaining the first confidence level, first quantile, and first time-added value corresponding to each label group, each label group and its corresponding first confidence level, first quantile, and first time-added value are stored. Figure 4 As shown, Figure 4 The diagram shows the parameters for label grouping, where each row represents a label group. Figure 4 The overtime point in the table represents both the moment when the agreed arrival time needs adjustment and the moment when tag information is acquired. After obtaining the parameter table diagram of the tag grouping, it is possible to detect whether the agreed arrival time of an order in transit needs adjustment based on the parameter table, and to calculate the overtime value that needs to be adjusted.

[0162] Based on this, in this embodiment, the steps of determining the target confidence level and target quantile corresponding to the target order according to the tag information include:

[0163] The tag information is compared with the tags of each tag group in the pre-stored tag database to obtain the target tag group whose tags are the same as the tag information.

[0164] Set the first confidence level and first quantile corresponding to the target label group as the target confidence level and target quantile corresponding to the target order.

[0165] After obtaining the tag information of the target order, the tag information of the target order can be compared with the tags of each tag group included in the parameter table in the tag database to obtain the target tag group whose tags are the same as the tag information. Then, the first confidence level and the first quantile corresponding to the target tag group in the parameter table are set as the target confidence level and the target quantile corresponding to the target order.

[0166] After obtaining the target confidence level and target quantile for the target order, the time-addition value for the target order can be calculated based on the target confidence level and target quantile. In this embodiment, the expected delay time of each order in the target order can be calculated first based on the target confidence level, and then the time-addition value of the target order can be determined from each expected delay time based on the target quantile.

[0167] The steps for calculating the expected delay time of each order in the target order at the target confidence level may include:

[0168] Based on a pre-defined probability model, the estimated arrival time of each order in the target order is calculated at the target confidence level.

[0169] Based on the agreed arrival time of the target order and the estimated arrival time of each order in the target order at the target confidence level, the estimated delay time of each order in the target order is obtained.

[0170] When an order is generated, a promised arrival time is set. When an order is transported from the current location to the next location, a probability model is triggered to calculate the estimated arrival time of each order at the next location.

[0171] It should be noted that in this embodiment, since the final destinations (e.g., community addresses) of each order in a batch of orders, i.e., the target orders, are different, when a batch of orders is in the delivery stage, some orders in that batch may have already been delivered to their final destination and received by the customer, while some orders are still at the station and have not yet been delivered. Given the short time between the delivery stage and delivery completion, when the target order is in the delivery stage, for orders already being delivered, the target confidence level is set to null, and the actual delivery time is used instead of the estimated arrival time to reduce prediction error. For orders not yet delivered, the estimated arrival time under the target confidence level is still calculated using a probability model.

[0172] After obtaining the estimated arrival time of each order in the target order at the target confidence level, the estimated delay time of each order in the target order can be obtained based on the agreed arrival time of the target order and the estimated arrival time of each order in the target order at the target confidence level. The agreed arrival time of the target order is the static commitment time of the target order, which is generated when the target order is created and is independent of the intermediate state of the target order.

[0173] When calculating the estimated delay time of each order in the target order based on the agreed arrival time of the target order and the estimated arrival time of each order in the target order at the target confidence level, for each order in the target order, the difference between the estimated arrival time and the agreed arrival time of the order is calculated, and the estimated delay time of the order is obtained based on the difference.

[0174] In this embodiment, when the difference is greater than 0, the difference is directly used as the expected delay time of the order; when the difference is less than or equal to 0, 0 is used as the expected delay time of the order, that is, expected delay time = max{0, T1-T2}, where T1 is the expected arrival time and T2 is the agreed arrival time.

[0175] Once the estimated delay time for each order in the target order is obtained, the additional time value for the target order can be determined based on the target quantile and the estimated delay time for each order.

[0176] Optionally, in this embodiment, the step of determining the overtime value of the target order based on the target quantile and each expected delay duration may include:

[0177] The estimated delay durations are sorted according to the set conditions to obtain the sorted estimated delay durations.

[0178] Based on the target quantile, the target estimated delay time is determined from the sorted estimated delay times, and the target estimated delay time is set as the time increment.

[0179] The estimated delay durations are sorted according to set conditions. This can be done by sorting from largest to smallest or from smallest to largest. In this embodiment, the estimated delay durations are sorted in ascending order to obtain the sorted estimated delay durations.

[0180] Once the sorted estimated delay times are obtained, the target estimated delay time can be directly determined from the sorted estimated delay times based on the target quantile, and then set as the time increment. For example, assuming the target quantile is 1 / 4 and there are 100 estimated delay times, the estimated delay times are sorted from smallest to largest, and the 25th estimated delay time is used as the target estimated delay time, with the target estimated delay time value used as the time increment.

[0181] After obtaining the overtime value for the target order, the agreed arrival time of the target order can be adjusted based on the overtime value. To improve accuracy, in this embodiment, considering the degree of impact on timeliness, after obtaining the overtime value, it is also necessary to check whether the agreed arrival time needs to be adjusted based on the overtime value. Therefore, in this embodiment, the step of adjusting the agreed arrival time of the target order based on the overtime value may include:

[0182] The tag information is compared with the tags of each tag group in the pre-stored tag database to obtain the target tag group whose tags are the same as the tag information.

[0183] Compare the first time-over value corresponding to the target tag group with the time-over value of the target order.

[0184] If the time surcharge value of the target order is not less than the first time surcharge value corresponding to the target tag group, the agreed arrival time of the target order will be adjusted according to the time surcharge value of the target order.

[0185] If the time increment for the target order is less than the first time increment corresponding to the target tag group, then the agreed arrival time for the target order is maintained.

[0186] After obtaining the tag information of the target order, this information is compared with the tags of each tag group included in the parameter table. Target tag groups with tags matching the tag information are identified. The first overtime value corresponding to each target tag group in the parameter table is then used as the overtime standard to assess the impact on delivery time. If the overtime value of the target order is not less than the first overtime value corresponding to the target tag group, the delivery time is considered significantly affected, and the agreed arrival time of the target order needs to be adjusted accordingly. Specifically, the overtime value is added to the agreed arrival time to obtain the adjusted agreed arrival time. If the overtime value of the target order is less than the first overtime value corresponding to the target tag group, the delivery time is considered less affected, and no adjustment to the agreed arrival time is required; the agreed arrival time remains unchanged.

[0187] The above process allows for adjustments to the agreed arrival time of the entire batch of orders. In practical applications, since the agreed arrival times of individual orders within a batch may differ, after obtaining the overtime value for the batch order (i.e., the target order), the agreed arrival time of each order within that target order can be adjusted individually to achieve the adjustment of the agreed arrival time for a single order.

[0188] It should be noted that, in this embodiment, for a single order, if it is determined that additional time is required in multiple stages such as receiving, transit, and delivery during the transportation process, the largest additional time value will be selected as the final additional time value for that single order. For example, for an order, if it is determined that additional time is required in the receiving, transit, and delivery stages, with durations of respectively...<T1,T2,T3> Then the final added time T = max{T1, T2, T3}.

[0189] The agreed arrival time adjustment method provided in this embodiment can collect order tag information in real time, thereby quickly calculating the degree of order delay. By aggregating orders with the same destination but different venues at each time point, and adjusting the agreed arrival time for batch orders, the results can be more accurate, avoiding the impact of occasional events at individual venues and reducing erroneous time additions.

[0190] The agreed arrival time adjustment method provided in this embodiment can cover most abnormal scenarios in terms of parameter training and strategy selection. It is highly controllable and flexible, and can avoid erroneous time additions caused by large differences in delay performance at different times, stages, and flow directions. For example, if there is a delay in the receiving stage, but the timeliness can still be salvaged in subsequent stages, the probability of erroneous time addition is high if time is added in this case.

[0191] The agreed arrival time adjustment method provided in this embodiment, after obtaining the tag information of the target order, determines the target confidence level and target quantile corresponding to the target order based on the tag information. Based on the target confidence level, it calculates the estimated delay time for each order within the target order. Based on the target quantile and each estimated delay time, it determines the additional time value for the target order. Based on the additional time value, it adjusts the agreed arrival time of the target order. This results in a more accurate agreed arrival time, improves customer experience, and effectively reduces the risk of customer complaints.

[0192] Based on the same inventive concept, please refer to the following: Figure 5 This embodiment provides a pre-arranged arrival time adjustment device 10, which is applied to... Figure 1 The electronic devices shown, such as Figure 5 As shown, the agreed arrival time adjustment device 10 provided in this embodiment includes a data acquisition module 11, a duration calculation module 12, an addition calculation module 13, and a time adjustment module 14.

[0193] The data acquisition module 11 is used to acquire the tag information of the target order and determine the target confidence level and target quantile of the target order based on the tag information of the target order.

[0194] The duration calculation module 12 is used to calculate the estimated delay duration of each order in the target order based on the target confidence level;

[0195] The time calculation module 13 is used to determine the time value of the target order based on the target quantile and the expected delay duration.

[0196] The time adjustment module 14 is used to adjust the agreed arrival time of the target order based on the time increment.

[0197] In an optional implementation, the agreed arrival time adjustment device includes a data processing module. Before determining the target confidence level and target quantile corresponding to the target order based on the tag information, the data processing module is used to:

[0198] Historical orders are grouped by set tags to obtain multiple tag groups and the flow of each tag group.

[0199] Calculate the initial time increment for each flow direction in each label group at different confidence levels and quantiles.

[0200] Based on the initial time values ​​of each flow direction in each label group at different confidence levels and quantiles, the first confidence level, first quantile, and first time value corresponding to each label group are determined.

[0201] In an optional implementation, the data processing module is used for:

[0202] For each flow direction in each tag group, the estimated delay time of each order in that flow direction is calculated at different confidence levels based on a preset probability model.

[0203] The estimated delay times of each order in the flow are sorted at the same confidence level, and the target estimated delay times corresponding to different quantiles are determined from the estimated delay times sorted at the same confidence level. The target estimated delay times are set as the initial time-addition value.

[0204] In an optional implementation, the data processing module is used for:

[0205] Based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and quantiles, the achievement rate of each flow direction in each label group at different confidence levels and quantiles is determined.

[0206] Based on the achievement rate of each flow in each label group at different confidence levels and quantiles, calculate the accuracy and coverage of each label group at different confidence levels and quantiles.

[0207] Based on the accuracy and coverage of each label group at different confidence levels and quantiles, the first confidence level, first quantile, and first time-addition value corresponding to each label group are determined.

[0208] In an optional implementation, the data processing module is used for:

[0209] Get the agreed arrival time and actual arrival time of orders corresponding to each flow direction in each tag group.

[0210] Based on the agreed arrival time and the initial time increments at different confidence levels and quantiles, the target arrival times for orders corresponding to each flow direction in each tag group are determined at different confidence levels and quantiles.

[0211] For each flow direction in each tag group, the achievement rate of that flow direction at different confidence levels and different quantiles is obtained based on the target arrival time and actual arrival time of the corresponding order at different confidence levels and different quantiles.

[0212] In an optional implementation, the data processing module is used for:

[0213] Based on the achievement rate of each flow direction in each label group at different confidence levels and different quantiles, the number of abnormal but not timed flows, the number of timed but not abnormal flows, and the number of abnormal and timed flows are obtained for each label group at different confidence levels and different quantiles.

[0214] Based on the number of abnormal but not timed flows, timed but not abnormal flows, and abnormal and timed flows for each label group at different confidence levels and quantiles, the accuracy and coverage of each label group at different confidence levels and quantiles are calculated.

[0215] In an optional implementation, the data processing module is used for:

[0216] For each label group, based on the set accuracy threshold, the accuracy of the label group at different confidence levels and different quantiles is filtered to obtain a target accuracy greater than the accuracy threshold.

[0217] From the coverage corresponding to the accuracy of each target, the maximum coverage is determined, the confidence level corresponding to the maximum coverage is set as the first confidence level corresponding to the label group, the quantile corresponding to the maximum coverage is set as the first quantile corresponding to the label group, and the initial time value corresponding to the first quantile and the first confidence level is set as the first time value corresponding to the label group.

[0218] In an optional implementation, the data acquisition module 11 is used for:

[0219] The tag information is compared with the tags of each tag group in the pre-stored tag database to obtain the target tag group whose tags are the same as the tag information.

[0220] Set the first confidence level and first quantile corresponding to the target label group as the target confidence level and target quantile corresponding to the target order; the label database stores the labels of each label group and the first confidence level and first quantile corresponding to each label group.

[0221] In an optional implementation, the time adjustment module 14 is used for:

[0222] The tag information is compared with the tags of each tag group in the pre-stored tag database to obtain the target tag group whose tags are the same as the tag information.

[0223] Compare the first time-over value corresponding to the target tag group with the time-over value of the target order.

[0224] If the time surcharge value of the target order is not less than the first time surcharge value corresponding to the target tag group, the agreed arrival time of the target order will be adjusted according to the time surcharge value of the target order.

[0225] If the time increment for the target order is less than the first time increment corresponding to the target tag group, then the agreed arrival time for the target order is maintained.

[0226] In an optional implementation, the duration calculation module 12 is used for:

[0227] Based on a pre-defined probability model, the estimated arrival time of each order in the target order is calculated at the target confidence level.

[0228] Based on the agreed arrival time of the target order and the estimated arrival time of each order in the target order at the target confidence level, the estimated delay time of each order in the target order is obtained.

[0229] In an optional implementation, the time calculation module 13 is used for:

[0230] The estimated delay durations are sorted according to the set conditions to obtain the sorted estimated delay durations.

[0231] Based on the target quantile, the target estimated delay time is determined from the sorted estimated delay times, and the target estimated delay time is set as the time increment.

[0232] The agreed arrival time adjustment device provided in this embodiment, after obtaining the tag information of the target order, determines the target confidence level and target quantile corresponding to the target order based on the tag information. Based on the target confidence level, it calculates the estimated delay time for each order within the target order. Based on the target quantile and each estimated delay time, it determines the additional time value for the target order. Based on the additional time value, it adjusts the agreed arrival time of the target order. In this way, a more accurate agreed arrival time can be obtained, improving the accuracy of the agreed arrival time.

[0233] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the agreed arrival time adjustment device 10 described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0234] Based on the above, this embodiment also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the agreed arrival time adjustment method described in any of the foregoing embodiments.

[0235] The readable storage medium can be, but is not limited to, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code.

[0236] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the readable storage medium described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0237] In summary, the agreed arrival time adjustment method, apparatus, electronic device, and readable storage medium provided in this embodiment, after obtaining the tag information of the target order, determine the target confidence level and target quantile corresponding to the target order based on the tag information. Based on the target confidence level, the estimated delay time of each order in the target order is calculated. Based on the target quantile and each estimated delay time, the added time value of the target order is determined. Based on the added time value, the agreed arrival time of the target order is adjusted. In this way, a more accurate agreed arrival time can be obtained, improving the accuracy of the agreed arrival time.

[0238] The foregoing has provided a detailed description of the agreed arrival time adjustment method, apparatus, electronic device, and readable storage medium provided in the embodiments of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the technical solutions and core ideas of the present invention. Those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for adjusting an agreed arrival time, characterized in that, The method includes: Based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and different quantiles, the achievement rate of each flow direction in each label group at different confidence levels and different quantiles is determined. Based on the achievement rate of each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles, calculate the accuracy and coverage of each of the aforementioned label groups at different confidence levels and different quantiles; Based on the accuracy and coverage of each label group at different confidence levels and different quantiles, target accuracy greater than the accuracy threshold is obtained by filtering. From the coverage corresponding to each target accuracy, the maximum coverage is determined. The confidence level corresponding to the maximum coverage is set as the first confidence level corresponding to the label group. The quantile corresponding to the maximum coverage is set as the first quantile corresponding to the label group. The first quantile and the initial time-addition value corresponding to the first confidence level are set as the first time-addition value corresponding to the label group. Obtain the tag information of the target order, compare the tag information with the tags of each tag group in the pre-stored tag database, and obtain the target tag group whose tags are the same as the tag information; set the first confidence level and the first quantile corresponding to the target tag group as the target confidence level and the target quantile corresponding to the target order. Based on the target confidence level, calculate the expected delay time for each order in the target order; The overtime value for the target order is determined based on the target quantile and each of the expected delay durations. The agreed arrival time of the target order is adjusted based on the added time value.

2. The agreed arrival time adjustment method according to claim 1, characterized in that, Before determining the target confidence level and target quantile corresponding to the target order based on the tag information, the method further includes: Historical orders are grouped by set tags to obtain multiple tag groups and the flow direction of each tag group; Calculate the initial time increment for each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles.

3. The agreed arrival time adjustment method according to claim 2, characterized in that, The steps for calculating the initial time-added value of each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles include: For each flow direction in each tag group, the estimated delay time of each order in that flow direction is calculated at different confidence levels based on a preset probability model; The estimated delay times of each order in the flow are sorted at the same confidence level, and the target estimated delay times corresponding to different quantiles are determined from the estimated delay times sorted at the same confidence level. The target estimated delay times are set as the initial time-addition value.

4. The method for adjusting the agreed arrival time according to claim 1, characterized in that, The step of determining the achievement rate of each flow direction in each label group at different confidence levels and different quantiles based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and different quantiles includes: Obtain the agreed arrival time and actual arrival time of orders corresponding to each flow direction in each of the aforementioned tag groups; Based on the agreed arrival time and the initial time increments at different confidence levels and quantiles, the target arrival times of orders corresponding to each flow direction in each of the aforementioned tag groups are determined at different confidence levels and quantiles. For each flow direction in each of the aforementioned tag groups, the achievement rate of that flow direction at different confidence levels and different quantiles is obtained based on the target arrival time and actual arrival time of the corresponding order at different confidence levels and different quantiles.

5. The method for adjusting the agreed arrival time according to claim 1, characterized in that, The step of calculating the accuracy and coverage of each label group at different confidence levels and different quantiles based on the achievement rate of each flow direction in each label group at different confidence levels and different quantiles includes: Based on the achievement rate of each flow direction in each of the aforementioned label groups at different confidence levels and different quantiles, the number of abnormal but not timed flows, the number of timed but not abnormal flows, and the number of abnormal and timed flows are obtained for each of the aforementioned label groups at different confidence levels and different quantiles. Based on the number of abnormal but not timed flows, the number of timed but not abnormal flows, and the number of abnormal flows with timed flows at different confidence levels and different quantiles for each of the aforementioned label groups, the accuracy and coverage of each of the aforementioned label groups at different confidence levels and different quantiles are calculated.

6. The agreed arrival time adjustment method according to claim 1, characterized in that, The step of filtering for a target accuracy greater than the accuracy threshold based on the accuracy and coverage of each label group at different confidence levels and different quantiles includes: For each of the label groups, the accuracy of the label group at different confidence levels and different quantiles is filtered according to the set accuracy threshold to obtain a target accuracy greater than the accuracy threshold.

7. The agreed arrival time adjustment method according to any one of claims 1-6, wherein the tag database stores the tags of each tag group and the first confidence level and first quantile corresponding to each tag group.

8. The method for adjusting the agreed arrival time according to any one of claims 1-6, characterized in that, The step of adjusting the agreed arrival time of the target order based on the added time value includes: The tag information is compared with the tags of each tag group in the pre-stored tag database to obtain the target tag group whose tags are the same as the tag information; Compare the first time-added value corresponding to the target tag group with the time-added value of the target order; If the time-addition value of the target order is not less than the first time-addition value corresponding to the target tag group, then the agreed arrival time of the target order is adjusted according to the time-addition value of the target order; If the time increment of the target order is less than the first time increment corresponding to the target tag group, then the agreed arrival time of the target order is maintained.

9. The method for adjusting the agreed arrival time according to claim 1, characterized in that, The step of calculating the expected delay time of each order in the target order based on the target confidence level includes: Based on a preset probability model, the estimated arrival time of each order in the target order at the target confidence level is calculated; Based on the agreed arrival time of the target order and the estimated arrival time of each order in the target order at the target confidence level, the estimated delay time of each order in the target order is obtained.

10. The method for adjusting the agreed arrival time according to claim 1, characterized in that, The step of determining the overtime value of the target order based on the target quantile and each of the expected delay durations includes: The estimated delay durations are sorted according to the set conditions to obtain the sorted estimated delay durations; Based on the target quantile, the target estimated delay time is determined from the sorted estimated delay times, and the target estimated delay time is set as the added time value.

11. A pre-arranged arrival time adjustment device, characterized in that, The agreed arrival time adjustment device includes: The data processing module is used to determine the achievement rate of each flow direction in each label group at different confidence levels and quantiles based on the initial time-added values ​​of each flow direction in each label group at different confidence levels and quantiles; calculate the accuracy and coverage of each label group at different confidence levels and quantiles based on the achievement rate of each flow direction in each label group at different confidence levels and quantiles; filter out target accuracy rates greater than the accuracy threshold based on the accuracy and coverage of each label group at different confidence levels and quantiles; determine the maximum coverage rate from the coverage rates corresponding to each target accuracy rate; set the confidence level corresponding to the maximum coverage rate as the first confidence level corresponding to the label group; set the quantile corresponding to the maximum coverage rate as the first quantile corresponding to the label group; and set the first quantile and the initial time-added value corresponding to the first confidence level as the first time-added value corresponding to the label group. The data acquisition module is used to acquire the tag information of the target order, compare the tag information with the tags of each tag group in the pre-stored tag database, obtain the target tag group whose tags are the same as the tag information, and set the first confidence level and the first quantile corresponding to the target tag group as the target confidence level and the target quantile corresponding to the target order. The duration calculation module is used to calculate the estimated delay duration of each order in the target order based on the target confidence level; The time calculation module is used to determine the time value of the target order based on the target quantile and each of the expected delay durations; The time adjustment module is used to adjust the agreed arrival time of the target order based on the added time value.

12. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the agreed arrival time adjustment method according to any one of claims 1 to 10.

13. A readable storage medium, characterized in that, The readable storage medium includes a computer program, which, when executed, controls the electronic device containing the readable storage medium to perform the agreed arrival time adjustment method as described in any one of claims 1 to 10.

Images