Transportation aging prediction method, device, equipment and medium

By combining navigation software to predict time and historical transportation data, more accurate transportation forecast time is generated, which solves the problem of large deviation between the actual driving time and the predicted time in long-distance transportation, and achieves more accurate transportation time prediction.

CN120181287APending Publication Date: 2025-06-20新奥新智科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510199530.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-24
Publication Date
2025-06-20

AI Technical Summary

Technical Problem

In long-distance transportation, there is a large deviation from the predicted time of navigation software, mainly due to uncertain factors such as traffic control, parking and rest, and eating.

Method used

By obtaining the prediction time provided by the navigation software, and combining the transportation start, end, stop and other information in the historical transportation data, the target historical route and transportation data are determined, and finally input this information into the prediction model to generate a more accurate actual prediction time.

Benefits of technology

By combining real-time road conditions navigation information and historical transportation data, long-distance transportation consumption can be predicted more accurately, reducing the deviation between the actual driving time and the predicted time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120181287A_ABST
    Figure CN120181287A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a transportation aging prediction method and device, equipment and a medium, and is used for solving the problem that the deviation between the actual driving time and the prediction time in long-distance transportation is large in the prior art. The method comprises the following steps: acquiring prediction time provided by navigation software based on a target transportation starting point and a target transportation ending point; determining a target historical route corresponding to the target transportation starting point and the target transportation ending point and corresponding target historical transportation data according to the transportation starting point and the transportation ending point contained in the historical transportation data of each route in the historical data set; and the address information of the target transportation starting point, the target goods picking point and the target unloading point, each piece of target historical transportation data and information after prediction time splicing are input into the prediction model, actual prediction time is obtained, and in combination with information of staying points such as the goods picking point and the unloading point, tank car transportation features are extracted more comprehensively, and the prediction efficiency is improved. Real-time road condition navigation information is combined with long-term transportation information of a historical data set, and long-distance transportation time consumption is predicted more accurately.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a method, device, equipment and medium for predicting transportation timeliness. Background Art

[0002] Currently, the prediction of the transportation time of tank trucks is mainly based on the information provided by map merchants' navigation software. For example, navigation software such as Amap and Baidu Map on the market can provide the optimal driving route and estimated arrival time for tank trucks according to the current traffic conditions. In short-distance transportation, due to relatively small changes in road conditions and high predictability, the prediction effect of navigation software is usually good. However, in long-distance transportation, there are many uncertain factors that may be encountered, such as traffic control, parking for rest, eating, etc., which may cause a large deviation between the actual driving time and the predicted time of the navigation software. Summary of the Invention

[0003] Embodiments of this application provide a method, device, equipment and medium for predicting transportation timeliness, which are used to solve the problem of large deviation between the actual driving time and the predicted time in long-distance transportation in the prior art.

[0004] In a first aspect, embodiments of this application provide a method for predicting transportation timeliness. The method includes:

[0005] Obtain the predicted time provided by the navigation software based on the target transportation starting point and the target transportation ending point;

[0006] According to the target transportation starting point, the target transportation ending point, and the transportation starting points and transportation ending points included in the historical transportation data of each line in the historical dataset, determine the target historical line corresponding to the target transportation starting point and the target transportation ending point, and the target historical transportation data of the target historical line; wherein, at least the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point are included in the historical transportation data of each line;

[0007] Input the information obtained by splicing the address information of the target transportation starting point, the address information of the target pick-up point, the address information of the target unloading point, each target historical transportation data, and the predicted time into the prediction model, and based on the prediction model, obtain the actual predicted time.

[0008] In a second aspect, embodiments of this application provide a device for predicting transportation timeliness. The device includes:

[0009] An obtaining module, configured to obtain the predicted time provided by the navigation software based on the target transportation starting point and the target transportation ending point;

[0010] A determination module, configured to determine a target historical route corresponding to a target transportation origin and a target transportation destination, and target historical transportation data of the target historical route according to the target transportation origin, the target transportation destination, and the transportation origins and transportation destinations included in the historical transportation data of each route in the historical dataset; wherein, the historical transportation data of each route includes at least the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point.

[0011] A prediction module, configured to input the information obtained by splicing the address information of the target transportation origin, the address information of the target pick-up point, the address information of the target discharge point, each target historical transportation data, and the prediction time into a prediction model, and obtain an actual prediction time based on the prediction model.

[0012] In a third aspect, an embodiment of the present application further provides an electronic device, which at least includes a processor and a memory. When the processor executes a computer program stored in the memory, the steps of any one of the above transportation timeliness prediction methods are implemented.

[0013] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any one of the above transportation timeliness prediction methods are implemented.

[0014] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer is caused to execute the steps of the transportation timeliness prediction method described in any one of the above first aspects.

[0015] In an embodiment of the present application, a prediction time provided by a navigation software based on a target transportation origin and a target transportation destination is obtained; according to the target transportation origin, the target transportation destination, and the transportation origins and transportation destinations included in the historical transportation data of each route in the historical dataset, a target historical route corresponding to the target transportation origin and the target transportation destination, and target historical transportation data of the target historical route are determined; wherein, the historical transportation data of each route includes at least the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point; the information obtained by splicing the address information of the target transportation origin, the address information of the target pick-up point, the address information of the target discharge point, each target historical transportation data, and the prediction time is input into a prediction model, and an actual prediction time is obtained based on the prediction model. In the embodiment of the present application, information of stop points such as pick-up points and discharge points is combined, so that the transportation characteristics of the tank truck can be extracted more comprehensively; and by combining real-time road condition navigation information with long-term transportation information in the historical dataset, the long-distance transportation time can be predicted more accurately. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic diagram of a transportation timeliness prediction process provided by an embodiment of the present application;

[0018] Figure 2 It is a schematic diagram of a prediction model structure provided by an embodiment of the present application;

[0019] Figure 3 It is a schematic diagram of a transportation timeliness prediction process provided by an embodiment of the present application;

[0020] Figure 4 It is a schematic diagram of a structure of a transportation timeliness prediction device provided by an embodiment of the present application;

[0021] Figure 5 It is a schematic diagram of a structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0022] To make the purpose and implementation manners of the present application clearer, the following will clearly and completely describe the exemplary implementation manners of the present application with reference to the accompanying drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only some embodiments of the present application, rather than all embodiments.

[0023] It should be noted that the brief description of the terms in the present application is only for facilitating the understanding of the following described implementation manners, rather than intending to limit the implementation manners of the present application. Unless otherwise specified, these terms should be understood in their ordinary and common meanings.

[0024] The terms "first", "second", "third", etc. in the specification, claims and the above accompanying drawings of the present application are used to distinguish similar or the same type of objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that such terms can be interchanged under appropriate circumstances.

[0025] The terms "comprising" and "having" and any variations thereof are intended to cover but not exclude inclusion. For example, a product or device comprising a series of components does not necessarily have to be limited to all the clearly listed components, but may include other components not clearly listed or inherent to these products or devices.

[0026] The term "module" refers to any known or later-developed hardware, software, firmware, artificial intelligence, fuzzy logic, or a combination of hardware and / or software code that can perform functions related to that element.

[0027] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements 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 application.

[0028] For the sake of convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. According to the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, so that those skilled in the art can better use the embodiments and various different modified embodiments suitable for specific use considerations.

[0029] The embodiments of the present application provide a method, device, equipment and medium for predicting transportation timeliness. In this method, the predicted time provided by the navigation software based on the target transportation starting point and the target transportation ending point is obtained; according to the target transportation starting point, the target transportation ending point, and the transportation starting points and transportation ending points included in the historical transportation data of each line in the historical data set, the target historical line corresponding to the target transportation starting point and the target transportation ending point, and the target historical transportation data of the target historical line are determined; wherein, at least the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point are included in the historical transportation data of each line; the information obtained by splicing the address information of the target transportation starting point, the address information of the target pick-up point, the address information of the target unloading point, each target historical transportation data, and the predicted time is input into the prediction model, and based on the prediction model, the actual predicted time is obtained. In the embodiments of the present application, the information of stop points such as pick-up points and unloading points is combined, which can more comprehensively extract the transportation characteristics of the tank truck; and the real-time road condition navigation information is combined with the long-term transportation information of the historical data set, which can more accurately predict the long-distance transportation time.

[0030] Embodiment 1:

[0031] Figure 1 It is a schematic diagram of a transportation timeliness prediction process provided by the embodiments of the present application. This process includes:

[0032] S101: Obtain the predicted time provided by the navigation software based on the target transportation starting point and the target transportation ending point.

[0033] The transportation time prediction method provided by the embodiment of the present application is applied to an electronic device, which can be a personal computer (PC), a server, a mobile terminal, etc.

[0034] The electronic device receives the uploaded waybill, which contains information such as the target transportation starting point, the target transportation ending point, and the driver number of the truck (such as a tank truck); after receiving the uploaded waybill, the electronic device parses the waybill to obtain information such as the target transportation starting point and the corresponding address information, the target transportation ending point and the corresponding address information, etc.

[0035] Input the address information of the target transportation starting point and the address information of the target transportation ending point contained in the waybill into the navigation software, and obtain the predicted time provided by the navigation software based on the target transportation starting point and the target transportation ending point.

[0036] It can be understood that if the navigation software gives a predicted route, the predicted time corresponding to the predicted route is determined as the above predicted time; if the navigation software gives multiple predicted routes, the shortest predicted time among the predicted times corresponding to each predicted route is determined, and the shortest predicted time is determined as the above predicted time.

[0037] S102: According to the target transportation starting point, the target transportation ending point, and the transportation starting points and transportation ending points included in the historical transportation data of each line in the historical dataset, determine the target historical line corresponding to the target transportation starting point and the target transportation ending point, and the target historical transportation data of the target historical line; among them, the historical transportation data of each line includes at least the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point.

[0038] Obtain the saved historical dataset, which contains multiple historical transportation data of lines, and at least the transportation starting point, the transportation ending point, the total historical transportation time of the line, and the historical stage time of the transportation stage determined according to each stop point are included in the historical transportation data of each line.

[0039] Among them, the stop point can be the place where the vehicle stops, including but not limited to: the pick-up point, the unloading point, the security inspection station, and other stop points. Among them, other stop points include but not limited to stop points related to non-direct logistics activities such as rest and refueling.

[0040] Among them, according to the determined stop points, the whole transportation stage can be divided into multiple transportation stages, and the historical stage time of each transportation stage is determined according to the stop time period corresponding to each stop point. Among them, each transportation stage can include the stage of staying at the stop point and the stage of driving to the next stop point after staying at the stop point ends.

[0041] The electronic device determines, in the historical dataset, a target historical route with the shipping origin and destination being the target shipping origin and destination, and the target historical transport data of the target historical route, according to the target shipping origin, the target shipping destination, and the shipping origins and destinations included in the historical transport data of each route in the historical dataset.

[0042] S103: Input the information obtained by splicing the address information of the target shipping origin, the address information of the target pick-up point, the address information of the target unloading point, each target historical transport data, and the prediction time into the prediction model, and based on the prediction model, obtain the actual prediction time.

[0043] In the embodiments of the present application, the waybill also includes the target pick-up point and the corresponding address information, and the target unloading point and the corresponding address information. Therefore, after parsing the waybill, the target pick-up point and the corresponding address information, and the target unloading point and the corresponding address information included in the waybill are obtained.

[0044] Splice the data in the address information of the target shipping origin, the data in the address information of the target pick-up point, the data in the address information of the target unloading point, the data corresponding to the total target historical transport time included in each target historical transport data, the data corresponding to the target historical stage time of each transport stage, and the data corresponding to the prediction time provided by the navigation software to obtain the spliced fusion information. Standardize or normalize the data in the fusion information to obtain the corresponding fusion features, so as to combine the real-time road condition navigation information with the long-term transport information of the historical dataset and more accurately predict the long-distance transport time.

[0045] Input the fusion feature into the prediction model, and predict the transport timeliness of the waybill based on the prediction model to obtain the actual prediction time for the tanker truck transport corresponding to the waybill. Among them, the actual prediction time may include the predicted total transport time for the whole journey, and may also include the predicted stage time for each stage, etc.

[0046] Among them, the prediction model is a pre-trained model. Based on the prediction model, the predicted stage time for each stage of the tanker truck transport and the predicted total transport time for the whole journey can be predicted, that is, the time for pick-up, unloading, rest, etc. is combined, and the long-distance transport time can be predicted more accurately.

[0047] In the embodiments of the present application, the information of stop points such as the pick-up point and the unloading point is combined, and the transport characteristics of the tanker truck can be extracted more comprehensively; and the real-time road condition navigation information is combined with the long-term transport information of the historical dataset, and the long-distance transport time can be predicted more accurately.

[0048] Embodiment 2:

[0049] In order to more accurately predict the long-distance transportation time, based on the above embodiments, in the embodiments of the present application, the information obtained by splicing the address information of the target transportation starting point, the address information of the target pick-up point, the address information of the target unloading point, each target historical transportation data, and the prediction time is input into the prediction model, including:

[0050] The address information of the target transportation starting point, the address information of the target pick-up point, and the address information of the target unloading point are used as station information;

[0051] The total target historical transportation time and the corresponding historical route number included in each target historical transportation data are used as route information;

[0052] The target historical stage time of each transportation stage included in each target historical transportation data is used as stop information;

[0053] The prediction time is used as prediction information;

[0054] The station information, route information, stop information, and prediction information are spliced to obtain the first fusion information, and the first fusion information is input into the prediction model.

[0055] In the embodiments of the present application, the address information of the target transportation starting point is used as the empty return information in the station information. Specifically, the data corresponding to the longitude and latitude of the target transportation starting point is used as the empty return information; the address information of the target pick-up point is used as the pick-up point information in the station information. Specifically, the data corresponding to the longitude and latitude of the target pick-up point is used as the pick-up point information; the address information of the target unloading point is used as the unloading point information in the station information. Specifically, the data corresponding to the longitude and latitude of the target unloading point is used as the unloading point information. Thus, not only the geographical location information is retained, but also the prediction model is allowed to learn the potential relationship between geographical locations.

[0056] In addition, the historical route numbers corresponding to the historical transportation data of each route are also stored in the historical dataset of the electronic device. Therefore, in order to enable the prediction model to learn the characteristics of each route to better predict the actual total transportation time, the data corresponding to the total target historical transportation time included in each target historical transportation data and the corresponding historical route number are used as route information, so as to reflect the inherent characteristics and efficiency differences of different routes corresponding to the target transportation starting point and the target transportation end point.

[0057] In order to enable the prediction model to learn the time allocation during transportation, in the embodiments of the present application, the data corresponding to the target historical stage time of each transportation stage included in each target historical transportation data is used as stop information.

[0058] Meanwhile, the actual road conditions information of this transportation should be combined. Since the predicted time provided by the navigation software is obtained by combining the real-time information of the current route, such as whether the current route is restricted, congested, weather information, etc., and some rule information, such as taking a 20-minute break after driving for 4 hours, etc., in the embodiments of the present application, the data corresponding to the predicted time provided by the navigation software is used as the prediction information.

[0059] After obtaining the above-mentioned site information (i.e., the empty return site information, pick-up point information, and unloading point information), route information, stop information, and prediction information, the empty return site information, pick-up point information, unloading point information, route information, stop information, and prediction information are spliced to obtain the first fusion information.

[0060] The data in the first fusion information is standardized and normalized to obtain the first fusion feature, so as to ensure the dimensional consistency and comparability between different information. The first fusion feature is input into the prediction model, and based on this prediction model, the actual predicted time is obtained.

[0061] In the embodiments of the present application, the site information, route information, stop information, and prediction information are combined, so that the prediction model can learn the geographical location relationship, the characteristics and efficiency differences of each route, the time allocation during transportation, and the current actual road conditions information, which is convenient for the prediction model to more accurately predict the long-distance transportation time.

[0062] Embodiment 3:

[0063] In order to more accurately predict the long-distance transportation time, on the basis of the above-mentioned embodiments, in the embodiments of the present application, inputting the first fusion information into the prediction model includes:

[0064] According to the target driver number included in the input waybill and the driver numbers corresponding to each target historical route saved, determine the target driver's historical route corresponding to the target driver number;

[0065] Take the target driver number and the total target driver historical transportation time included in the target driver's historical transportation data of the target driver's historical route as the driver information;

[0066] Splice the driver information with the first fusion information to obtain the second fusion information, and input the second fusion information into the prediction model.

[0067] In the embodiments of the present application, since it is considered that the proficiency and familiarity of different drivers with the transportation route may be different, the driver information can also be combined to predict the actual transportation time.

[0068] Specifically, after parsing the waybill, the target driver number included in the waybill is obtained. Since the correspondence between the historical transportation data of each route and the driver number is also stored in the electronic device, in order to determine the historical transportation data of the historical route corresponding to the target transportation starting point and the target transportation ending point that the target driver has traveled, in the embodiment of the present application, according to the target driver number and the correspondence between each target historical route corresponding to the target transportation starting point and the target transportation ending point and the driver number, the target driver historical route corresponding to the target driver number is determined, and the total target driver historical transportation time included in the target driver historical transportation data of the target driver historical route is determined.

[0069] The data corresponding to the total target driver historical transportation time included in the target driver historical transportation data of the target driver historical route and the target driver number are used as driver information, and the driver information is concatenated with the first fusion information to obtain the second fusion information.

[0070] The data in the second fusion information are standardized and normalized to obtain the second fusion feature; the second fusion feature is input into the prediction model, and based on the prediction model, the actual prediction time is obtained.

[0071] In the embodiment of the present application, combining the driver information with the first fusion information combines the driver's proficiency and familiarity with the transportation route, thus facilitating the prediction model to more accurately predict the transportation long-distance time.

[0072] Embodiment 4:

[0073] In order to improve the robustness and accuracy of the prediction, on the basis of the above embodiments, in the embodiment of the present application, the prediction model includes multiple sub-models and an ensemble model. Then, based on the prediction model, obtaining the actual prediction time corresponding to the waybill information includes:

[0074] The second fusion information is respectively input into each sub-model in the prediction model, and based on each sub-model, the candidate prediction times output by each sub-model are obtained;

[0075] The candidate prediction times output by each sub-model are input into the ensemble model in the prediction model, and based on the ensemble model, the candidate prediction times are weighted and averaged to obtain the actual prediction time output by the ensemble model.

[0076] In the embodiment of the present application, as Figure 2 shown, the prediction model includes multiple sub-models (i.e., the base estimators (Base-Estimator) shown in Figure 2 ) and an ensemble model (i.e., the meta-estimator (Meta-Estimator) shown in Figure 2 ).

[0077] Among them, each sub-model can predict candidate prediction times according to the input information, and the machine learning algorithms used in the training of each sub-model can be the same or different. And it can be understood that, in order to better combine the prediction results of various models and make the final prediction result more accurate, in the embodiments of the present application, different machine learning algorithms are usually used to train each sub-model, such as Figure 2 The sub-models shown are models trained using eXtreme Gradient Boosting (XGBoost), Random Forest, Extra Trees, and Ridge Regression respectively. And, as Figure 2 shown, the integrated model can be a model trained using XGBoost. Additionally, the integrated model can also be a model trained using other machine learning algorithms. In the embodiments of the present application, there is no specific limitation on the machine learning algorithm used for training the integrated model.

[0078] Exemplarily, the machine learning algorithms include but are not limited to Random Forest, Gradient Boosting Tree, Extra Trees, Ridge Regression, Neural Network, Linear Regression, Logistic Regression, Decision Tree, Support Vector Machine, etc.

[0079] In the embodiments of the present application, after obtaining the second fusion information, the second fusion information is respectively input into each sub-model in the prediction model, and based on each sub-model, candidate prediction times output by each sub-model are obtained.

[0080] Among them, each candidate prediction time may include the whole-course candidate predicted transportation time and the stage candidate predicted times for each stage.

[0081] The candidate prediction times output by each sub-model are input into the integrated model in the prediction model. The integrated model performs weighted averaging on each candidate prediction time according to the candidate prediction times input by each sub-model to obtain the actual prediction time output by the integrated model.

[0082] Exemplarily, the integrated model performs weighted averaging on the whole-course candidate predicted transportation time included in each candidate prediction time according to the candidate prediction times input by each sub-model to obtain the whole-course predicted transportation time in the actual prediction time; and for each stage, the stage candidate predicted times corresponding to the stage included in each candidate prediction time are weighted averaged to obtain the stage predicted time corresponding to the stage in the actual prediction time.

[0083] In addition, it can be understood that each sub-model and the integrated model in the prediction model provided in the embodiments of the present application are all trained models, such as Figure 2As shown, after training each sub-model and the integrated model in the prediction model using the training set, then using the test set to test each sub-model and the integrated model in the prediction model, and determining each sub-model and the integrated model in the prediction model that pass the test as the trained models.

[0084] In the embodiment of the present application, the second fusion information is respectively input into each sub-model in the prediction model. Based on each sub-model, the candidate prediction times output by each sub-model are obtained, and the candidate prediction times output by each sub-model are input into the integrated model in the prediction model for weighted averaging to obtain the actual prediction time output by the integrated model, so as to reduce the possible bias of a single model and improve the robustness and accuracy of the prediction.

[0085] Embodiment 5:

[0086] Based on the above embodiments, in the embodiment of the present application, the determination process of the historical stage time consumption of the transportation stage determined according to each stop point in the historical transportation data of each line includes:

[0087] Obtain each piece of saved original transportation data and the corresponding historical waybill information; wherein, each piece of original transportation data includes the transportation line, the total transportation time period, the address information of the stop point, the stop time period at the corresponding stop point during transportation, and the corresponding stop duration;

[0088] Count the candidate stop points in each piece of original transportation data whose stop duration exceeds the preset duration;

[0089] For each first transportation line with the same starting point and ending point, for any candidate stop point in the first transportation line, count the first quantity of all candidate stop points in the first transportation line whose address information is the same as that of the candidate stop point, and determine whether the ratio of the first quantity to the second quantity of the first transportation line is greater than the preset ratio. If so, determine that the candidate stop point is the pick-up point or the unloading point in the first transportation line;

[0090] For each piece of original transportation data, determine the time consumption of the stage going to the pick-up point according to the transportation start time recorded in the total transportation time period in the original transportation data and the stop start time recorded in the stop time period corresponding to the candidate stop point that is the pick-up point; determine the time consumption of the loading stage according to the stop duration corresponding to the candidate stop point that is the pick-up point; determine the time consumption of the unloading stage as the stop duration corresponding to the candidate stop point that is the unloading point; according to the address information of at least one candidate stop point that is the unloading point and the address information of the starting point, determine the farthest unloading point as the last unloading point, and determine the time consumption of the empty return stage according to the stop end time recorded in the stop time period corresponding to the last unloading point and the transportation end time recorded in the total transportation time period.

[0091] The electronic device obtains each piece of original transportation data saved by itself and the corresponding historical waybill information. Among them, each piece of original transportation data at least includes the transportation route, the starting point and the ending point of the transportation route, the total transportation time period, the address information of the stop points, the stop time period at the corresponding stop points during transportation, and the corresponding residence duration.

[0092] In a possible implementation, before the electronic device saves each piece of original transportation data, in order to ensure that all transportation data uses a unified geographic coordinate system for the consistency of subsequent analysis, in the embodiments of the present application, the coordinate system used for identifying the position information of each point in the transportation route of each piece of original transportation data is identified, and the transportation route in each piece of original transportation data is converted from multiple possible coordinate systems to a specified standard geographic coordinate system; and since the accuracy of transportation data plays a crucial role in subsequent analysis, therefore, in the embodiments of the present application, it is also necessary to verify the transportation route in each piece of original transportation data, and save the original transportation data that passes the verification in the standard geographic coordinate system in the electronic device. Among them, the process of identifying the coordinate system used for the position information of each point in the transportation route of each piece of original transportation data is a prior art and will not be elaborated here.

[0093] Among them, various possible coordinate systems include but are not limited to the World Geodetic System 1984 (WGS-84), the Universal Transverse Mercator Grid System (UTM), etc.; in the embodiments of the present application, the specified standard geographic coordinate system can be GCJ-02 applicable to the Chinese region.

[0094] Exemplarily, verifying the transportation route in each piece of original transportation data may include but is not limited to: for the transportation route in each piece of original transportation data, determining whether there is coordinate drift data in the transportation route, that is, determining whether there are isolated points that suddenly deviate from the transportation route in the transportation route. If so, the coordinate points corresponding to the coordinate drift data are determined as abnormal position points caused by equipment failures or signal interference, and the abnormal position points are eliminated; determining whether there is a period in the transportation route where the continuous missing coordinate information exceeds a set threshold. If so, interpolation processing is performed on the coordinate points within this period, or the coordinate points within this period are all marked as invalid data to avoid misleading the timeliness prediction. Among them, the set threshold can be half an hour, which is not limited here; the interpolation processing process is a prior art and will not be elaborated here.

[0095] After obtaining the saved original transportation data, since each original transportation data contains the residence time period and corresponding residence duration at the corresponding stop point during transportation, therefore, for each original transportation data, at least one stop point with a residence duration exceeding the preset duration is counted according to the residence duration corresponding to each stop point in the original transportation data, and this stop point is determined as a candidate stop point. Among them, the preset duration can be 2 hours, and no specific limitation is provided here.

[0096] Since the candidate stop points with a residence duration exceeding the preset duration may be pick-up points, delivery points, other stop points (such as rest points), etc., therefore, in order to determine the specific classification of this candidate stop point, in the embodiments of the present application, each original transportation data is divided into multiple groups according to the same starting point and ending point, and for any first transportation route in any group with the same starting point and ending point, for any candidate stop point in this first transportation route, according to the address information of this candidate stop point and the address information of the candidate stop points in other first transportation routes in this group, the first quantity of all candidate stop points with the same address information as this candidate stop point in each first transportation route is counted, the ratio of this first quantity to the second quantity of all first transportation routes included in this group is determined, and it is judged whether this ratio is greater than the preset ratio. If so, it indicates that more than the preset ratio of vehicles stop at this candidate stop point, and this candidate stop point is determined as a pick-up point or a delivery point in this first transportation route. By way of example, the preset ratio can be 70% or 80%, etc., and no specific limitation is provided here.

[0097] In addition, each stop point with a residence duration not exceeding the preset duration can be determined as other stop points, and this other stop point can be a gas station, a security inspection station, etc. In order to determine whether each other stop point is a security inspection station, in the embodiments of the present application, the location information of each other stop point can also be sent to the security inspection station server, so that the security inspector can determine which other stop points are security inspection stations, and receive the security inspection station information returned by the security inspection station server.

[0098] After determining the specific classification of each stop point, in order to determine the historical stage time consumption of the transportation stage determined according to each stop point, in the embodiment of the present application, for each piece of original transportation data, according to the transportation start time recorded in the total transportation time period in the original transportation data and the stop start time recorded in the stop time period corresponding to the candidate stop point as the pick-up point, determine the time difference between the stop start time and the transportation start time, and determine this time difference as the time consumption of the stage of going to the pick-up point; according to the stop duration corresponding to the candidate stop point as the pick-up point, determine this stop duration as the time consumption of the loading stage; according to the stop duration corresponding to the candidate stop point as the unloading point, determine this stop duration as the time consumption of the unloading stage; according to the address information of at least one candidate stop point as the unloading point and the address information of the starting point, determine the distance between each unloading point and the starting point, determine the unloading point farthest from the starting point as the last unloading point, and according to the stop end time recorded in the stop time period corresponding to the last unloading point and the transportation end time recorded in the total transportation time period, determine the time difference between the transportation end time and this stop end time, and determine this time difference as the time consumption of the empty return stage.

[0099] In addition, according to the stop durations corresponding to other stop points, add up the stop durations corresponding to each other stop point to obtain the time consumption of the stop stage; according to the total transportation time consumption corresponding to the total transportation time period, the time consumption of the loading stage, the time consumption of the unloading stage, and the time consumption of the stop stage, determine the difference between the total transportation time consumption and the time consumption of the loading stage, the time consumption of the unloading stage, and the time consumption of the stop stage, and determine this difference as the time consumption of the driving stage.

[0100] Embodiment 6:

[0101] In order to improve the accuracy of determining the pick-up point or the unloading point, on the basis of the above embodiments, in the embodiment of the present application, if the ratio of the first quantity to the second quantity of the first transportation route is not greater than a preset ratio, the method further includes:

[0102] Count the third quantity of all candidate stop points within the preset address range including this candidate stop point in all the first transportation routes; judge whether the ratio of the third quantity to the second quantity is greater than the preset ratio, if so, determine this candidate stop point as the pick-up point or the unloading point in this first transportation route; if not, determine this candidate stop point as other stop points in this first transportation route.

[0103] Considering that for the same pick-up or drop-off point, since the pick-up or drop-off point itself is not actually a coordinate point but a regional range, that is, the stationary geographical locations of the vehicle at the pick-up or drop-off point may not be exactly the same. Therefore, in the embodiments of the present application, if it is determined that the ratio of the above-mentioned first quantity to the second quantity of the first transportation route is not greater than a preset ratio, then for the address information of each candidate stop point (for the convenience of distinction, other candidate stop points are used for subsequent description) in all the first transportation routes of this group, it is judged whether the other candidate stop point is within the preset address range including this candidate stop point; count the third quantity of all other candidate stop points within the preset address range including this candidate stop point in all the first transportation routes of this group, determine the ratio of this third quantity to the above-mentioned second quantity, and judge whether this ratio is greater than the preset ratio. If so, determine that this candidate stop point is the pick-up or drop-off point in this first transportation route; if not, determine that this candidate stop point is other stop points in this first transportation route, such as a rest point in this first transportation route.

[0104] Among them, the preset address range including this candidate stop point can be an address range with the coordinate of this candidate point as the center and a set distance as the radius. The set distance can be 2 kilometers, 3 kilometers, etc., and no specific limitation is made here.

[0105] In the embodiments of the present application, judging whether the ratio of the number of candidate stop points within the preset address range to the first transportation route is greater than the preset ratio can avoid misjudgment and other situations caused by geographical location floating or inaccuracy, and improve the accuracy of determining the pick-up or drop-off point.

[0106] Embodiment 7:

[0107] In order to further improve the accuracy of determining the pick-up or drop-off point, on the basis of the above embodiments, in the embodiments of the present application, determining that this candidate stop point is the pick-up or drop-off point in this first transportation route includes:

[0108] Judge whether the stay time period of this candidate stop point in each original transportation data is within the preset time interval including this pick-up time corresponding to the pick-up time recorded in the corresponding historical waybill information. If so, determine that this candidate stop point is the pick-up point in this first transportation route;

[0109] Judge whether the stay time period of this candidate stop point in each original transportation data is within the preset time interval including this unloading time corresponding to the unloading time recorded in the corresponding historical waybill information. If so, determine that this candidate stop point is the drop-off point in this first transportation route.

[0110] After determining that the candidate stop point is a pick-up point or a drop-off point on the first transportation route, in order to more accurately determine the specific classification of the candidate stop point, since the driver usually fills in the pick-up time and drop-off time during this transportation after completing the transportation task of a waybill, in the embodiment of the present application, the specific classification of the candidate stop point can be determined in combination with the corresponding historical waybill information.

[0111] Specifically, obtain the historical waybill information corresponding to the original transportation data to which the candidate stop point belongs, and determine the pick-up time and drop-off time recorded in the historical waybill information.

[0112] And considering that the pick-up time and drop-off time provided by the driver are not always completely accurate, in the embodiment of the present application, based on the pick-up time or drop-off time, a preset time interval including the pick-up time or drop-off time is determined. If the actual pick-up time is within the preset time interval including the pick-up time, it is determined that the stop point corresponding to the actual pick-up time is a pick-up point; if the actual pick-up time is within the preset time interval including the drop-off time, it is determined that the stop point corresponding to the actual pick-up time is a drop-off point.

[0113] Specifically, determine whether the stop time period of the candidate stop point in each piece of original transportation data corresponding to the first transportation route is within the preset time interval including the pick-up time recorded in the corresponding historical waybill information. If so, it is determined that the candidate stop point is a pick-up point on the first transportation route.

[0114] Determine whether the stop time period of the candidate stop point in each piece of original transportation data corresponding to the first transportation route is within the preset time interval including the drop-off time recorded in the corresponding historical waybill information. If so, it is determined that the candidate stop point is a drop-off point on the first transportation route.

[0115] The following uses a specific embodiment to illustrate the above embodiments. Refer to Figure 3 The schematic diagram of the transportation timeliness prediction process shown, including the following steps:

[0116] Step 1, perform coordinate transformation and trajectory cleaning on the original trajectory data. Specifically, perform coordinate transformation on the positions of each coordinate point in the transportation route (i.e., Figure 3 the original trajectory data shown in) in each piece of original transportation data, and transform it to the same standard geographic coordinate system; remove the coordinate drift data included in each transportation route, and perform interpolation and completion or mark as invalid data for the coordinate points during the time period when the continuous missing coordinate information exceeds the set threshold.

[0117] Step 2: Analyze spatiotemporal data (i.e., each original transportation data). Specifically, determine the specific classification of each stop point in each original transportation data, and divide the total transportation time period according to the stay time period of each stop point, determine the stage time consumption of each stage, and save the data such as the stage time consumption and the corresponding time of each stage in the historical data set.

[0118] The time spent at each stage may include the time spent on the delivery point (i.e. Figure 3 The time taken to get to the pickup location shown in Figure 3 The loading time shown in the figure), the unloading time (i.e. Figure 3 The unloading time shown in the figure), the emptying phase time (i.e. Figure 3 The time taken to return to the empty space shown in Figure 3 The dwell time shown in Figure 3 The time on the way / driving time shown in ).

[0119] In addition, the process of determining the specific classification of each stop point in each original transportation data, dividing the total transportation time period, and determining the stage time consumption of each stage can be referred to the above embodiments, and will not be repeated here.

[0120] Step 3: Perform multi-information fusion and predict the fused information based on the prediction model. Specifically, receive the waybill information reported by the driver before departure, and determine the target historical route corresponding to the target transport starting point and target transport end point, as well as the target historical transport data of the target historical route, based on the target transport starting point and target transport end point contained in the waybill information and the transport starting point and transport end point contained in the historical transport data of each route in the historical data set.

[0121] The address information of the target transportation starting point, the address information of the target pickup point, and the address information of the target unloading point are used as the site information (i.e. Figure 3 The total target historical transportation time and the corresponding historical route number contained in each target historical transportation data are used as route information (i.e. Figure 3 ); according to the target driver number contained in the waybill information and the driver number corresponding to each target historical route saved, determine the target driver historical route corresponding to the target driver number, and use the target driver number and the target driver historical transportation data of the target driver historical route as the driver information (i.e. Figure 3 The driver characteristics shown in FIG); the target historical stage time of each transportation stage contained in each target historical transportation data is used as the stop information (i.e. Figure 3 The predicted time is used as the prediction information (i.e. Figure 3The real-time navigation information shown in

[0122] The site information, route information, driver information, stop information, and prediction information are spliced to obtain the second fusion information. The second fusion information is standardized and normalized to obtain the second fusion feature. The second fusion feature is respectively input into each sub-model in the prediction model. Based on each sub-model, the candidate prediction times output by each sub-model are obtained. The candidate prediction times output by each sub-model are input into the ensemble model in the prediction model. Based on the ensemble model, the candidate prediction times are weighted and averaged to obtain the actual prediction time output by the ensemble model.

[0123] Embodiment 8:

[0124] Based on the same technical concept, on the basis of the above embodiments, the present application provides a transportation time prediction device. Figure 4 As shown in the structural schematic diagram of a transportation time prediction device provided by an embodiment of the present application, Figure 4 As shown, the device includes:

[0125] An acquisition module 401, configured to acquire the prediction time provided by the navigation software based on the target transportation starting point and the target transportation ending point;

[0126] A determination module 402, configured to determine the target historical route corresponding to the target transportation starting point and the target transportation ending point, and the target historical transportation data of the target historical route according to the target transportation starting point, the target transportation ending point, and the transportation starting points and transportation ending points included in the historical transportation data of each route in the historical dataset; wherein, the historical transportation data of each route includes at least the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point;

[0127] A prediction module 403, configured to input the information obtained by splicing the address information of the target transportation starting point, the address information of the target pick-up point, the address information of the target drop-off point, each target historical transportation data, and the prediction time into the prediction model, and based on the prediction model, obtain the actual prediction time.

[0128] In a possible implementation manner, the prediction module 403 is specifically configured to use the address information of the target transportation starting point, the address information of the target pick-up point, and the address information of the target drop-off point as the site information; use the total target historical transportation time and the corresponding historical route number included in each target historical transportation data as the route information; use the target historical stage time of each transportation stage included in each target historical transportation data as the stop information; use the prediction time as the prediction information; splice the site information, route information, stop information, and prediction information to obtain the first fusion information, and input the first fusion information into the prediction model.

[0129] In a possible implementation manner, the prediction module 403 is specifically configured to determine a target driver's historical route corresponding to the target driver number according to the target driver number included in the input waybill and the driver numbers corresponding to each saved target historical route; use the target driver number and the total historical transportation time included in the target driver's historical transportation data of the target driver's historical route as driver information; splice the driver information with the first fusion information to obtain second fusion information, and input the second fusion information into the prediction model.

[0130] In a possible implementation manner, if the prediction model includes multiple sub-models and an integration model, the prediction module 403 is specifically configured to input the second fusion information into each sub-model in the prediction model respectively, and based on each sub-model, obtain candidate prediction times output by each sub-model; input the candidate prediction times output by each sub-model into the integration model in the prediction model, and perform weighted averaging on each candidate prediction time based on the integration model to obtain the actual prediction time output by the integration model.

[0131] In a possible implementation manner, the determination module 402 is specifically configured to obtain each saved original transportation data and the corresponding historical waybill information; wherein, each original transportation data includes a transportation route, a total transportation time period, address information of a stop point, a stop time period and a corresponding stay duration at the corresponding stop point during transportation; count candidate stop points in each original transportation data whose stay duration exceeds a preset duration; for each first transportation route with the same starting point and ending point, for any candidate stop point in the first transportation route, count the first quantity of all candidate stop points in the first transportation route whose address information is the same as that of the candidate stop point, and determine whether the ratio of the first quantity to the second quantity of the first transportation route is greater than a preset ratio. If so, determine that the candidate stop point is a pick-up point or a delivery point in the first transportation route; for each original transportation data, determine the time consumed in the stage of going to the pick-up point according to the transportation start time recorded in the total transportation time period of the original transportation data and the stop start time recorded in the stop time period corresponding to the candidate stop point that is the pick-up point; determine the time consumed in the loading stage according to the stay duration corresponding to the candidate stop point that is the pick-up point; determine the stay duration corresponding to the candidate stop point that is the delivery point as the time consumed in the unloading stage; according to the address information of at least one candidate stop point that is the delivery point and the address information of the starting point, determine the farthest delivery point as the last delivery point, and determine the time consumed in the empty-return stage according to the stop end time recorded in the stop time period corresponding to the last delivery point and the transportation end time recorded in the total transportation time period.

[0132] In a possible implementation, the determining module 402 is further configured to, if the ratio of the first quantity to the second quantity of the first transportation route is not greater than a preset ratio, count the third quantity of all candidate stop points within a preset address range including the candidate stop point in all the first transportation routes; determine whether the ratio of the third quantity to the second quantity is greater than the preset ratio, and if so, determine that the candidate stop point is a pick-up point or a discharge point in the first transportation route; if not, determine that the candidate stop point is another stop point in the first transportation route.

[0133] In a possible implementation, the determining module 402 is specifically configured to determine whether the stop time period of the candidate stop point in each piece of original transportation data is within a preset time interval including the pick-up time recorded in the corresponding historical waybill information. If so, determine that the candidate stop point is a pick-up point in the first transportation route; determine whether the stop time period of the candidate stop point in each piece of original transportation data is within a preset time interval including the discharge time recorded in the corresponding historical waybill information. If so, determine that the candidate stop point is a discharge point in the first transportation route.

[0134] Embodiment 9:

[0135] Based on the same technical concept, the present application further provides an electronic device. Figure 5 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 5 shown, it includes: a processor 501, a communication interface 502, a memory 503, and a communication bus 504. Among them, the processor 501, the communication interface 502, and the memory 503 communicate with each other through the communication bus 504.

[0136] The memory 503 stores a computer program. When the program is executed by the processor 501, the processor 501 is caused to execute the following steps:

[0137] Obtain the predicted time provided by the navigation software based on the target transportation starting point and the target transportation ending point;

[0138] According to the target transportation starting point, the target transportation ending point, and the transportation starting points and transportation ending points included in the historical transportation data of each route in the historical dataset, determine the target historical route corresponding to the target transportation starting point and the target transportation ending point, and the target historical transportation data of the target historical route; wherein, the historical transportation data of each route at least includes the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point.

[0139] Input the information obtained by splicing the address information of the target transportation origin, the address information of the target pick-up point, the address information of the target unloading point, each piece of target historical transportation data, and the prediction time into the prediction model, and based on the prediction model, obtain the actual prediction time.

[0140] In a possible implementation manner, the processor 501 is specifically configured to use the address information of the target transportation origin, the address information of the target pick-up point, and the address information of the target unloading point as the station information; use the total target historical transportation time and the corresponding historical route number included in each piece of target historical transportation data as the route information; use the target historical stage time of each transportation stage included in each piece of target historical transportation data as the stay information; use the prediction time as the prediction information; splice the station information, the route information, the stay information, and the prediction information to obtain the first fusion information, and input the first fusion information into the prediction model.

[0141] In a possible implementation manner, the processor 501 is specifically configured to determine the target driver's historical route corresponding to the target driver number according to the target driver number included in the input waybill and the driver numbers corresponding to each saved target historical route; use the target driver number and the total target historical transportation time included in the target driver's historical transportation data of the target driver's historical route as the driver information; splice the driver information with the first fusion information to obtain the second fusion information, and input the second fusion information into the prediction model.

[0142] In a possible implementation manner, the processor 501 is specifically configured to, if the prediction model includes multiple sub-models and an integrated model, input the second fusion information into each sub-model in the prediction model respectively, and based on each sub-model, obtain the candidate prediction times output by each sub-model; input the candidate prediction times output by each sub-model into the integrated model in the prediction model, and perform weighted averaging on each candidate prediction time based on the integrated model to obtain the actual prediction time output by the integrated model.

[0143] In a possible implementation, the processor 501 is specifically configured to obtain the saved original transportation data and the corresponding historical waybill information; wherein, each piece of original transportation data includes a transportation route, a total transportation time period, the address information of a stop point, the stop time period at the corresponding stop point during transportation, and the corresponding stop duration; count the candidate stop points in each piece of original transportation data whose stop duration exceeds a preset duration; for each first transportation route with the same starting point and ending point, for any candidate stop point in the first transportation route, count the first quantity of all candidate stop points in the first transportation route whose address information is the same as that of the candidate stop point, and determine whether the ratio of the first quantity to the second quantity of the first transportation route is greater than a preset ratio. If so, determine that the candidate stop point is a pick-up point or a discharge point in the first transportation route; for each piece of original transportation data, determine the time consumed in the stage of going to the pick-up point according to the transportation start time recorded in the total transportation time period in the original transportation data and the stop start time recorded in the stop time period corresponding to the candidate stop point that is a pick-up point; determine the time consumed in the loading stage according to the stop duration corresponding to the candidate stop point that is a pick-up point; determine the stop duration corresponding to the candidate stop point that is a discharge point as the time consumed in the unloading stage; according to the address information of at least one candidate stop point that is a discharge point and the address information of the starting point, determine the last discharge point as the discharge point with the farthest distance, and determine the time consumed in the empty-return stage according to the stop end time recorded in the stop time period corresponding to the last discharge point and the transportation end time recorded in the total transportation time period.

[0144] In a possible implementation, the processor 501 is further configured to, if the ratio of the first quantity to the second quantity of the first transportation route is not greater than the preset ratio, count the third quantity of all candidate stop points within a preset address range including the candidate stop point in all the first transportation routes; determine whether the ratio of the third quantity to the second quantity is greater than the preset ratio. If so, determine that the candidate stop point is a pick-up point or a discharge point in the first transportation route; if not, determine that the candidate stop point is another stop point in the first transportation route.

[0145] In a possible implementation, the processor 501 is specifically configured to determine whether the stop time period of the candidate stop point in each piece of original transportation data is within a preset time interval including the pick-up time recorded in the corresponding historical waybill information. If so, determine that the candidate stop point is a pick-up point in the first transportation route; determine whether the stop time period of the candidate stop point in each piece of original transportation data is within a preset time interval including the discharge time recorded in the corresponding historical waybill information. If so, determine that the candidate stop point is a discharge point in the first transportation route.

[0146] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0147] The communication interface 502 is used for communication between the above electronic device and other devices.

[0148] The memory may include a Random Access Memory (RAM), and may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0149] The above processor may be a general-purpose processor, including a central processing unit, a Network Processor (NP), etc.; it may also be a Digital Signal Processing (DSP), an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0150] Embodiment 10:

[0151] Based on the same technical concept, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program executable by an electronic device. When the program runs on the electronic device, it enables the electronic device to implement any of the above embodiments when executed.

[0152] The above computer-readable storage medium may be any available medium or data storage device accessible by the processor in the electronic device, including but not limited to magnetic memories such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc., optical memories such as CDs, DVDs, BDs, HVDs, etc., and semiconductor memories such as ROM, EPROM, EEPROM, non-volatile memories (NAND FLASH), solid-state drives (SSD), etc.

[0153] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0154] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0155] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0157] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting transportation timeliness, characterized in that: The method comprises: Obtain the predicted time provided by the navigation software based on the target transportation starting point and the target transportation end point; According to the target transportation starting point, the target transportation destination, and the transportation starting point and transportation destination included in the historical transportation data of each route in the historical data set, determine the target historical route corresponding to the target transportation starting point and the target transportation destination, and the target historical transportation data of the target historical route; wherein the historical transportation data of each route at least includes the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point; The address information of the target transportation starting point, the address information of the target pickup point, the address information of the target unloading point, the historical transportation data of each target and the information after the prediction time is spliced ​​are input into the prediction model, and the actual prediction time is obtained based on the prediction model.

2. The method according to claim 1, characterized in that The step of inputting the address information of the target transportation starting point, the address information of the target pickup point, the address information of the target unloading point, the historical transportation data of each target, and the information obtained by splicing the predicted time into the prediction model includes: The address information of the target transportation starting point, the address information of the target pickup point, and the address information of the target unloading point are used as site information; The total target historical transportation time and the corresponding historical route number contained in each target historical transportation data are used as route information; The target historical stage time consumption of each transportation stage contained in each target historical transportation data is used as the stay information; using the predicted time as prediction information; The site information, route information, stop information and prediction information are spliced ​​to obtain first fusion information, and the first fusion information is input into the prediction model.

3. The method according to claim 2, characterized in that The step of inputting the first fusion information into the prediction model comprises: Determine the target driver historical route corresponding to the target driver number according to the target driver number contained in the input waybill and the driver number corresponding to each saved target historical route; The target driver number and the total historical transportation time of the target driver included in the target driver historical transportation data of the target driver's historical route are used as driver information; The driver information is concatenated with the first fused information to obtain second fused information, and the second fused information is input into the prediction model.

4. The method according to claim 3, characterized in that The prediction model includes multiple sub-models and an integrated model, and the actual prediction time corresponding to the waybill information is obtained based on the prediction model, including: Inputting the second fusion information into each sub-model in the prediction model respectively, and obtaining the candidate prediction time output by each sub-model based on the sub-model; The candidate prediction times output by each sub-model are input into the integrated model in the prediction model, and the candidate prediction times are weighted averaged based on the integrated model to obtain the actual prediction time output by the integrated model.

5. The method according to claim 1, characterized in that: The process of determining the historical stage time consumption of the transportation stage determined according to each stop point in the historical transportation data of each route includes: Obtaining the saved original transport data and the corresponding historical waybill information; wherein the original transport data includes the transport route, the total transport time period, the address information of the stop point, and the stop time period and the corresponding stop duration at the corresponding stop point during the transport; Count the candidate stop points whose stay time exceeds the preset time in each original transportation data; For each first transport route with the same starting point and end point, for any candidate stop point in the first transport route, counting a first number of all candidate stop points in the first transport route that have the same address information as the candidate stop point, determining whether a ratio of the first number to a second number of the first transport route is greater than a preset ratio, and if so, determining that the candidate stop point is a pickup point or a discharge point in the first transport route; For each of the original transportation data, the time consumed in the stage of going to the pick-up point is determined according to the transportation start time recorded in the total transportation time period in the original transportation data and the stay start time recorded in the stay time period corresponding to the candidate stay point of the pick-up point; the loading stage time is determined according to the stay time corresponding to the candidate stay point of the pick-up point; the unloading stage time is determined according to the stay time corresponding to the candidate stay point of the unloading point; the unloading point with the farthest distance is determined as the last unloading point according to the address information of at least one candidate stay point of the unloading point and the address information of the starting point, and the return stage time is determined according to the stay end time recorded in the stay time period corresponding to the last unloading point and the transportation end time recorded in the total transportation time period.

6. The method according to claim 5, characterized in that If the ratio of the first number to the second number of the first transportation routes is not greater than a preset ratio, the method further includes: Count the third quantity of all candidate stay points in the first transport routes within the preset address range including the candidate stay point; determine whether the ratio of the third quantity to the second quantity is greater than the preset ratio, and if so, determine that the candidate stay point is a pick-up point or an unloading point in the first transport route; if not, determine that the candidate stay point is other stay points in the first transport route.

7. The method according to claim 5 or 6, characterized in that: The step of determining the candidate stop point as a pickup point or a discharge point in the first transport route includes: Determine whether the stay time period of the candidate stop point in each original transport data is within a preset time interval corresponding to the pick-up time recorded in the corresponding historical waybill information and including the pick-up time; if so, determine that the candidate stop point is the pick-up point in the first transport route; Determine whether the stay time period of the candidate stop point in each original transportation data is within the preset time interval corresponding to the unloading time recorded in the corresponding historical waybill information and including the unloading time. If so, determine that the candidate stop point is the unloading point in the first transportation route.

8. A transportation time prediction device, characterized in that: The device comprises: An acquisition module, used for acquiring the predicted time provided by the navigation software based on the target transportation starting point and the target transportation end point; A determination module, for determining the target historical route corresponding to the target transportation starting point and the target transportation end point, and the target historical transportation data of the target historical route according to the target transportation starting point, the target transportation end point, and the transportation starting point and transportation end point contained in the historical transportation data of each route in the historical data set; wherein the historical transportation data of each route at least includes the total historical transportation time and the historical stage time of the transportation stage determined according to each stop point; The prediction module is used to input the address information of the target transportation starting point, the address information of the target pickup point, the address information of the target unloading point, the historical transportation data of each target and the information after the prediction time is spliced ​​into the prediction model, and obtain the actual prediction time based on the prediction model.

9. An electronic device, characterized in that: The electronic device comprises at least a processor and a memory, and the processor is used to implement the steps of the transportation time prediction method according to any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer storage medium, characterized in that: It stores a computer program executable by an electronic device. When the program runs on the electronic device, the electronic device executes the steps of the transportation time prediction method according to any one of claims 1 to 7.