Logistics timeliness prediction method and device, equipment and storage medium

Abstract

The application provides a logistics time limit prediction method, device and equipment, and a storage medium. A rule configuration method of the logistics time limit prediction method comprises the following steps: acquiring a confidence degree of historical time limit prediction of a to-be-predicted waybill; judging whether the confidence degree is greater than a set confidence threshold; if yes, providing a first predicted waybill time limit according to the to-be-predicted waybill; and if no, providing a second predicted waybill time limit according to the to-be-predicted waybill, wherein the second predicted waybill time limit is later than the first predicted waybill time limit. The application predicts the logistics time limit, thereby avoiding the situation that the predicted time limit is inaccurate due to the difference in prediction accuracy of waybills of different lines, and further improving user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer application, and in particular, to a logistics time limit prediction method and device, equipment and storage medium. BACKGROUND

[0002] In logistics time limit prediction, the predicted delivery time of a shipment is usually obtained through a model prediction based on the pickup data of historical shipments. In some scenarios, the prediction of the logistics time limit can be accurate to the hour. After predicting the logistics time limit, the prediction result can be transmitted to the client, the merchant end, and the customer service end, so that the user or the customer service has an expectation of the pickup time limit of the express. However, the actual prediction accuracy of shipments of different routes currently differs greatly, and inaccurate prediction of the time limit of the shipments causes unnecessary trouble to the user and affects the user experience.

[0003] Therefore, how to optimize the prediction of the logistics time limit to avoid the inaccurate prediction of the time limit due to the difference in the prediction accuracy of shipments of different routes and to further improve the user experience is a technical problem to be solved in the field. SUMMARY

[0004] In order to overcome the defects of the related art, the present application provides a logistics time limit prediction method, device, equipment and storage medium, thereby optimizing the prediction of the logistics time limit to avoid the inaccurate prediction of the time limit due to the difference in the prediction accuracy of shipments of different routes and to further improve the user experience.

[0005] According to one aspect of the present application, a logistics time limit prediction method is provided, comprising:

[0006] obtaining the confidence of the historical time limit prediction of a to-be-predicted shipment;

[0007] determining whether the confidence is greater than a set confidence threshold;

[0008] if yes, providing a first predicted shipment time limit according to the to-be-predicted shipment;

[0009] if no, providing a second predicted shipment time limit according to the to-be-predicted shipment,

[0010] wherein the second predicted shipment time limit is later than the first predicted shipment time limit.

[0011] In some embodiments of the present application, the obtaining of the confidence of the historical time limit prediction of the to-be-predicted shipment comprises:

[0012] querying the confidence of the historical time limit prediction of the historical trajectory data having at least one same attribute as the to-be-predicted shipment; or

[0013] a confidence level of a historical time limit prediction of the to-be-predicted shipping order.

[0014] In some embodiments of the present application, the attribute comprises one or more of a combination of a logistics service provider, a sender address, a receiver address, a pickup node, a pickup city, a delivery node, a delivery city, and a transfer node.

[0015] In some embodiments of the present application, the first predicted shipping order time limit and the second predicted shipping order time limit are obtained by using the same time limit prediction model.

[0016] In some embodiments of the present application, the first predicted shipping order time limit is the most probable shipping order time limit output by the time limit prediction model, and the second predicted shipping order time limit is the latest shipping order time limit output by the time limit prediction model.

[0017] In some embodiments of the present application, the first predicted shipping order time limit and the second predicted shipping order time limit are obtained by using different time limit prediction models.

[0018] In some embodiments of the present application, the confidence level of the historical time limit prediction of the to-be-predicted shipping order is:

[0019] The time limit prediction model used to predict the first predicted shipping order time limit is used to predict the accuracy rate of the historical time limit prediction of the to-be-predicted shipping order.

[0020] In some embodiments of the present application, the accuracy rate of the historical time limit prediction of the to-be-predicted shipping order is calculated according to the following steps:

[0021] The number of historical shipping orders with the same route and the same predicted shipping order time limit as the to-be-predicted shipping order within a preset time period is taken as a first number.

[0022] The number of historical shipping orders with the same route and the same predicted shipping order time limit as the to-be-predicted shipping order within a preset time period is taken as a first number.

[0023] The ratio of the second number to the first number is taken as the accuracy rate of the historical time limit prediction of the to-be-predicted shipping order.

[0024] According to another aspect of the present application, a logistics time limit prediction device is also provided, comprising:

[0025] An acquisition module configured to acquire a confidence level of a historical time limit prediction of a to-be-predicted shipping order.

[0026] A judgment device configured to judge whether the confidence level is greater than a set confidence threshold.

[0027] The first providing device is configured to provide a first predicted delivery time limit according to the to-be-predicted delivery order when the judging device judges yes.

[0028] The second providing device is configured to provide a second predicted delivery time limit according to the to-be-predicted delivery order when the judging device judges no.

[0029] The second predicted delivery time limit is later than the first predicted delivery time limit.

[0030] According to still another aspect of the present application, there is also provided an electronic device comprising a processor, and a storage medium having a computer program stored thereon, the computer program being executed by the processor to perform the steps as described above.

[0031] According to still another aspect of the present application, there is also provided a storage medium having a computer program stored thereon, the computer program being executed by a processor to perform the steps as described above.

[0032] Compared with the prior art, the present application has the following advantages:

[0033] The present application obtains the confidence of the historical time limit prediction of the to-be-predicted delivery order, and then judges whether to provide the first predicted time limit or the second predicted delivery time limit to the user based on the comparison between the confidence and a set confidence threshold, and makes the second predicted delivery time limit later than the first predicted delivery time limit, so that the second predicted delivery time limit has a larger time limit range than the first predicted delivery time limit, reduces the possibility of time limit prediction error, and improves the user's logistics time limit experience. BRIEF DESCRIPTION OF DRAWINGS

[0034] The above and other features and advantages of the present application will become more apparent by describing in detail its example embodiments with reference to the attached drawings.

[0035] Figure 1 A flow chart of a logistics time limit prediction method according to an embodiment of the present application is shown.

[0036] Figure 2 A flow chart of the accuracy of the historical time limit prediction of the to-be-predicted delivery order according to an embodiment of the present application is shown.

[0037] Figure 3 A flow chart of a logistics time limit prediction method according to a specific embodiment of the present application is shown.

[0038] Figure 4 A module diagram of a logistics time limit prediction device according to an embodiment of the present application is shown.

[0039] Figure 5 A schematic diagram of a computer readable storage medium in an example embodiment of the present application is shown.

[0040] Figure 6 Fig. 1 schematically shows a schematic diagram of an electronic device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0041] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the example implementations to those skilled in the art. The described features, structures, or characteristics can be combined in one or more implementations.

[0042] In addition, the accompanying drawings are included to provide a further understanding of the present application, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present application and, as such, a change in the drawings can be made for clarity of explanation and emphasis. In the drawings:

[0043] The flowchart shown in the accompanying drawings is only an exemplary illustration, and does not necessarily include all the steps. For example, some steps can be further divided, and some steps can be combined or partially combined, so the actual execution order can be changed according to the actual situation.

[0044] In various embodiments of the present application, the logistics time limit prediction method provided by the present application can be applied to a logistics platform, an e-commerce platform, or any third-party platform that needs to realize logistics time limit prediction, but the application scenarios of the present application are not limited to this, and will not be described here.

[0045] Figure 1 A flowchart of a logistics time limit prediction method according to an embodiment of the present application is shown. The logistics time limit prediction method includes the following steps:

[0046] Step S110: Obtain the confidence of the historical time limit prediction of the to-be-predicted shipping order.

[0047] Specifically, the confidence of the historical time limit prediction of the to-be-predicted waybill can be the confidence of the historical time limit prediction of the historical trajectory data having at least one same attribute as the to-be-predicted waybill. The attribute can include one or a combination of the following: a logistics service provider, a sending address, a receiving address, a pickup node, a pickup city, a delivery node, a delivery city, and a transfer node. For example, the confidence of the historical time limit prediction of the to-be-predicted waybill can be the confidence of the historical time limit prediction of the historical trajectory data having the same pickup node and the same delivery node as the to-be-predicted waybill. For another example, the confidence of the historical time limit prediction of the to-be-predicted waybill can be the confidence of the historical time limit prediction of the historical trajectory data having the same pickup city and the same delivery city as the to-be-predicted waybill. For yet another example, the confidence of the historical time limit prediction of the to-be-predicted waybill can be the confidence of the historical time limit prediction of the historical trajectory data having the same pickup city, the same delivery city, and the same logistics service provider as the to-be-predicted waybill. The above are only illustrative examples of the confidence of the historical time limit prediction of the to-be-predicted waybill, and the present application is not limited thereto.

[0048] Specifically, in some embodiments, the confidence of the historical time limit prediction of the different combinations of attributes described above can be pre-calculated and stored in a database. Thus, step S110 can query the confidence of the historical time limit prediction of the to-be-predicted waybill by attribute query. In this embodiment, step S110 can be implemented by querying the confidence of the historical time limit prediction of the historical trajectory data having at least one same attribute as the to-be-predicted waybill. In addition, in this embodiment, the pre-calculated confidence can be updated at a set time period. The set time period can be, for example, one week, 15 days, 30 days, etc., and the present application is not limited thereto. Thus, the confidence can be automatically and adaptively calculated by periodic updating.

[0049] In other embodiments, the historical trajectory data having at least one same attribute as the to-be-predicted waybill can be obtained in real time according to the waybill data of the to-be-predicted waybill, and the confidence of the historical time limit prediction of the historical trajectory data can be calculated in real time. In this embodiment, step S110 can be implemented by calculating the confidence of the historical time limit prediction of the historical trajectory data having at least one same attribute as the to-be-predicted waybill. In addition, in this embodiment, the historical trajectory data obtained in real time can be historical trajectory data within a set time period before the current time of the to-be-predicted waybill. The set time period can be, for example, one week, 15 days, 30 days, etc., and the present application is not limited thereto. Thus, the historical trajectory data obtained in recent time can be used to increase the relevance of the historical trajectory data to the to-be-predicted waybill, and the confidence of the to-be-predicted waybill can be better reflected, thereby realizing automatic and adaptive calculation of the confidence.

[0050] The present application can be implemented in more ways, and the present application is not limited thereto.

[0051] Step S120: judging whether the confidence is greater than a set confidence threshold.

[0052] Specifically, the confidence threshold can be set as needed, and the application does not limit the value of the confidence threshold.

[0053] If step S120 judges yes, step S130 is performed: providing a first predicted waybill time limit according to the to-be-predicted waybill.

[0054] If step S120 judges no, step S140 is performed: providing a second predicted waybill time limit according to the to-be-predicted waybill.

[0055] The second predicted waybill time limit is later than the first predicted waybill time limit.

[0056] Specifically, it can be understood that the first predicted waybill time limit is an accurate predicted time limit, and the second predicted waybill time limit is a timely predicted time limit (for example, it can be manifested as the latest arrival time / the longest transportation time, etc.).

[0057] In some embodiments, the first predicted waybill time limit and the second predicted waybill time limit are obtained by using the same time limit prediction model. The time limit prediction model may, for example, be a prediction model obtained by training historical waybill data (historical trajectory data). The time limit prediction model can be any machine learning or deep learning model. In a preferred example of the application, the time limit prediction model may, for example, be a time limit prediction model based on a regression algorithm. In this embodiment, the time limit prediction model outputs multiple time limit prediction results and the probabilities of the multiple time limit prediction results. Thus, the first predicted waybill time limit can be the waybill time limit with the highest probability output by the time limit prediction model, that is, the most accurate waybill time limit predicted by the time limit prediction model (this most accurate represents the prediction angle of the time limit prediction model, not the actual waybill time limit angle); the second predicted waybill time limit is the latest waybill time limit output by the time limit prediction model, in other words, the second predicted waybill time limit is the latest possible arrival time (or the longest transportation time) of the waybill. The first predicted waybill time limit and the second predicted waybill time limit of this embodiment can share the same time limit prediction model, thereby reducing system storage requirements and development costs.

[0058] In some embodiments of the present invention, the first predicted waybill timeliness and the second predicted waybill timeliness are obtained using different timeliness prediction models. The timeliness prediction models can be, for example, two prediction models with the same architecture, trained on different historical waybill data (historical trajectory data). The timeliness prediction models can be any machine learning or deep learning model. In a preferred embodiment of the invention, the timeliness prediction model can be, for example, a timeliness prediction model based on a regression algorithm. In some variations, the prediction model used to predict the first predicted waybill timeliness and the prediction model used to predict the second predicted waybill timeliness can also employ prediction models with different structures. In this embodiment, each timeliness prediction model can provide only one output data (the output data with the highest probability). Further, the timeliness prediction model used to predict the first predicted waybill timeliness is used to predict the most accurate (highest probability of occurrence) waybill timeliness calculated by the timeliness prediction model. The timeliness prediction model used to predict the second predicted waybill timeliness is used to predict the waybill timeliness with the highest probability of occurrence among the multiple waybill timelinesses calculated by the timeliness prediction model, which are the longest / latest waybill timelinesses.

[0059] Specifically, the confidence level of the historical timeliness prediction of the waybill to be predicted is: the accuracy of the timeliness prediction model used to predict the timeliness of the first predicted waybill, and the historical timeliness prediction of the waybill to be predicted. Therefore, the confidence level of this invention is equivalent to the confidence level of the prediction result of the final timeliness prediction model to be used. This invention is not intended to be limiting.

[0060] In the logistics timeliness prediction method provided by the present invention, the confidence level of the historical timeliness prediction of the waybill to be predicted is obtained, and then the first predicted timeliness or the second predicted timeliness is provided to the user based on the comparison of the confidence level with the set confidence threshold. By making the second predicted timeliness of the waybill later than the first predicted timeliness, the second predicted timeliness of the waybill has a larger timeliness range than the first predicted timeliness, reducing the possibility of timeliness prediction errors, thereby improving the user's logistics timeliness experience.

[0061] See below. Figure 2 , Figure 2 A flowchart illustrating the accuracy of historical timeliness prediction for a waybill to be predicted according to an embodiment of the present invention is shown. Figure 2 The following steps are shown:

[0062] Step S111: The number of historical waybills within a preset time period that have the same route and the same predicted time of the waybill to be predicted is taken as the first quantity.

[0063] Step S112: The number of historically accurate waybills with the same route and the same predicted delivery time as the waybill to be predicted within the preset time period is taken as the second quantity.

[0064] Step S113: taking the ratio of the second number and the first number as the accuracy rate of the historical time limit prediction of the delivery order to be predicted.

[0065] Specifically, in one specific implementation, the accuracy rate of the historical time limit prediction of the delivery order to be predicted is calculated according to the following formula:

[0066]

[0067] The calculation of the accuracy rate can be achieved through the above embodiments and the above formula, thereby achieving the calculation of the aforementioned confidence level, and the calculation method has low complexity and high efficiency.

[0068] Referring to Figure 3 , Figure 3 A flowchart of a logistics time limit prediction method according to a specific embodiment of the present application is shown. As Figure 3 shown, offline, the time limit prediction model 230 can be trained by the historical delivery order data 210 and the historical delivery order time limit 220, and the trained time limit prediction model 230 is stored. In the online state, the trained time limit prediction model 230 can be input with delivery order data 240 of a plurality of delivery orders similar to the delivery order to be predicted (having at least one same attribute as the delivery order to be predicted), thereby obtaining predicted time limits 250 of the plurality of similar delivery orders, and combining the actual time limits of the similar delivery orders, the confidence level of the time limit prediction model 230 can be calculated.

[0069] Thus, in the uncertain operation scenario of logistics time limit prediction, the confidence level of the prediction is calculated for each delivery order, for the delivery order with high confidence level, the predicted delivery order arrival date is transmitted to the user. For the delivery order with low confidence level, the latest delivery order arrival date is transmitted. The confidence level of the delivery order can be calculated according to the historical actual confidence level statistics of the actual predicted time of the delivery order route, thereby realizing automatic and adaptive confidence level calculation.

[0070] The above are only a plurality of specific implementations of the logistics time limit prediction method of the present application, each implementation can be implemented independently or in combination, and the present application is not limited thereto. Further, the flowchart of the present application is only schematic, and the execution order between the steps is not limited thereto, and the splitting, merging, order exchange, other synchronous or asynchronous execution mode of the steps are all within the protection scope of the present application.

[0071] Referring to Figure 4 , Figure 4 A module diagram of a logistics time limit prediction device according to an embodiment of the present application is shown. The logistics time limit prediction device 300 includes an acquisition module 310, a judgment device 320, a first providing device 330, and a second providing device 340.

[0072] The obtaining module 310 is configured to obtain a confidence of a historical time limit prediction of a to-be-predicted waybill;

[0073] The determining device 320 is configured to determine whether the confidence is greater than a set confidence threshold;

[0074] The first providing device 330 is configured to provide a first predicted waybill time limit according to the to-be-predicted waybill when the determining device determines yes;

[0075] The second providing device 340 is configured to provide a second predicted waybill time limit according to the to-be-predicted waybill when the determining device determines no,

[0076] The second predicted waybill time limit is later than the first predicted waybill time limit.

[0077] In the logistics time limit prediction device of the exemplary embodiments of the present application, the confidence of the historical time limit prediction of the to-be-predicted waybill is obtained, so that it is determined whether to provide the first predicted time limit or the second predicted waybill time limit to the user based on the comparison of the confidence and the set confidence threshold, and the second predicted waybill time limit is made later than the first predicted waybill time limit, so that the second predicted waybill time limit has a larger time limit range than the first predicted waybill time limit, the possibility of time limit prediction error is reduced, and the user's logistics time limit experience is improved.

[0078] Figure 4 The logistics time limit prediction device 300 provided by the present application is only illustrative, and the splitting, merging, and adding of the modules are within the protection scope of the present application without departing from the concept of the present application. The logistics time limit prediction device 300 provided by the present application can be realized by software, hardware, firmware, plug-ins, and any combination thereof, and the present application is not limited in this regard.

[0079] In the exemplary embodiments of the present application, a computer readable storage medium having a computer program stored thereon is also provided, and the program can implement the steps of the logistics time limit prediction method described in any one of the above embodiments when executed by a processor. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product including program code for causing a terminal device to perform the steps described in the above-mentioned logistics time limit prediction method part of the present specification according to various exemplary embodiments of the present application when the program product is run on the terminal device.

[0080] Reference Figure 5As shown, a program product 700 for implementing the above-described method according to an embodiment of the present application is described, which can take the form of a portable compact disc read-only memory (CD-ROM) and includes a program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto, and in the present document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0081] The program product can take any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium, for example, can be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0082] The computer readable storage medium can include a data signal carried by a carrier wave or a propagated signal, where the readable program code is carried by the data signal. Such a propagated signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The readable storage medium can also be any readable medium that is not a storage medium and that can be used to carry or store program code in any form, which can be used by or in connection with an instruction execution system, apparatus or device. The program code contained on the readable storage medium can be transmitted as program code signals using any suitable medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0083] The program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, C++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the tenant computing device, partly on the tenant device, as a stand-alone software package, partly on the tenant computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the tenant computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0084] In an example embodiment of the present application, an electronic device is also provided, which can include a processor, and a memory for storing executable instructions of the processor. Wherein the processor is configured to perform the steps of the logistics time limit prediction method described in any one of the above embodiments via executing the executable instructions.

[0085] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method or a program product. Therefore, various aspects of the present application can be embodied in the form of a complete hardware, a complete software (including firmware, microcode, etc.), or a combination of hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system".

[0086] The electronic device 500 according to this embodiment of the present application will be described below with reference to Figure 6 Figure 6 The electronic device 500 shown is merely an example, and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0087] As shown in Figure 6 , the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 can include, but are not limited to, at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510), a display unit 540, etc.

[0088] The storage unit stores program codes, which can be executed by the processing unit 510, so that the processing unit 510 performs the steps according to various example embodiments of the present application described in the above logistics time limit prediction method part of the present specification. For example, the processing unit 510 can perform the steps shown in any one or more of the accompanying drawings. Figures 1 to 2

[0089] The storage unit 520 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 5201 and / or a cache memory unit 5202, and can further include a read-only memory (ROM) 5203.

[0090] The storage unit 520 can also include a program / utility 5204 having a set of (at least one) program modules 5205, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof can include implementation of a network environment. ​​

[0091] Bus 530 can be one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, a graphics bus, a processor or local bus using any of a variety of bus architectures.

[0092] Electronic device 500 can also communicate with one or more external devices 600 such as a keyboard or pointing device, a Bluetooth device, etc.; one or more devices that enable a user to interact with electronic device 500; and / or one or more devices (e.g., a router, a modem, a server, etc.) that enable electronic device 500 to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface 550. Still yet, electronic device 500 can communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), and / or a public network (e.g., the Internet) via network adapter 560. As depicted, network adapter 560 can communicate with the other components of electronic device 500 via bus 530. It should be appreciated that although not shown, other hardware and / or software modules could be used in conjunction with electronic device 500. Such modules include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0093] Those skilled in the art will readily understand that the example embodiments described herein can be implemented by software and / or by software in combination with the necessary hardware. Thus, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to perform the above-mentioned logistics time limit prediction method according to the embodiments of the present application.

[0094] Compared with the prior art, the advantages of the present application are that:

[0095] The present application acquires the confidence of the historical time limit prediction of the to-be-predicted waybill, and then determines whether to provide the first predicted time limit or the second predicted waybill time limit to the user based on comparison of the confidence with a set confidence threshold, and makes the second predicted waybill time limit later than the first predicted waybill time limit, so that the second predicted waybill time limit has a larger time limit range than the first predicted waybill time limit, reduces the possibility of time limit prediction error, and improves the user's logistics time limit experience.

[0096] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

Claims

1. A method for predicting logistics timeliness, characterized in that, include: Obtain the confidence level of historical time-to-delivery forecasts for the shipment to be predicted; Determine whether the confidence level is greater than the set confidence threshold; If so, then based on the forecasted waybill, a first forecasted waybill timeliness is provided; If not, then based on the forecasted waybill, a second forecasted waybill delivery time is provided. The step of obtaining the confidence level of the historical timeliness prediction of the waybill to be predicted includes: querying the confidence level of the historical timeliness prediction of historical trajectory data that has at least one same attribute as the waybill to be predicted; or calculating the confidence level of the historical timeliness prediction of historical trajectory data that has at least one same attribute as the waybill to be predicted. The first predicted transit time and the second predicted transit time are obtained by the same transit time prediction model. The confidence level of the historical transit time prediction of the transit time to be predicted is the accuracy of the transit time prediction model in predicting the historical transit time of the transit time to be predicted. The timeliness prediction model outputs multiple timeliness prediction results and the probabilities of the multiple timeliness prediction results. The first predicted waybill timeliness is the waybill timeliness with the highest probability output by the timeliness prediction model, and the second predicted waybill timeliness is the latest waybill timeliness output by the timeliness prediction model. The second predicted waybill timeliness is later than the first predicted waybill timeliness.

2. The logistics timeliness prediction method as described in claim 1, characterized in that, The attributes include one or more combinations of logistics service providers, sender address, recipient address, pickup node, pickup city, delivery node, delivery city, and transit node.

3. The logistics timeliness prediction method as described in claim 1, characterized in that, The accuracy of the historical transit time prediction for the shipment to be predicted is calculated according to the following steps: The number of historical waybills with the same route and the same predicted timeframe as the waybill to be predicted within a preset time period is taken as the first quantity. The number of historically accurate waybills with the same route and the same predicted timeliness as the waybill to be predicted within a preset time period is used as the second quantity. The ratio of the second quantity to the first quantity is used as the accuracy of the historical timeliness prediction for the waybill to be predicted.

4. A logistics timeliness prediction device, characterized in that, include: The acquisition module is configured to acquire the confidence level of historical time-delivery predictions for the shipments to be predicted; The process of obtaining the confidence level of historical timeliness prediction for the shipment to be predicted includes: querying the confidence level of historical timeliness prediction for historical trajectory data that has at least one identical attribute to the shipment to be predicted; or calculating the confidence level of historical timeliness prediction for historical trajectory data that has at least one identical attribute to the shipment to be predicted. The judging device is configured to judge whether the confidence level is greater than a set confidence threshold; A first providing device is configured to provide a first predicted delivery time based on the delivery order to be predicted when the judging device determines that it is true. The second providing device is configured to, if the determining device determines otherwise, provide a second predicted delivery time based on the delivery order to be predicted. Wherein, the first predicted transit time and the second predicted transit time are obtained by the same transit time prediction model, and the confidence level of the historical transit time prediction of the transit time to be predicted is the accuracy of the transit time prediction model for the historical transit time prediction of the transit time to be predicted. The timeliness prediction model outputs multiple timeliness prediction results and the probabilities of the multiple timeliness prediction results. The first predicted waybill timeliness is the waybill timeliness with the highest probability output by the timeliness prediction model, and the second predicted waybill timeliness is the latest waybill timeliness output by the timeliness prediction model. The second predicted waybill timeliness is later than the first predicted waybill timeliness.

5. An electronic device, characterized in that, The electronic device includes: processor; A memory, on which a computer program is stored, is executed by the processor during runtime: The logistics timeliness prediction method as described in any one of claims 1 to 3.

6. A storage medium, characterized in that, The storage medium stores a computer program, which is executed by a processor: The logistics timeliness prediction method as described in any one of claims 1 to 3.

Images