Vehicle resource adjustment method and apparatus, and electronic device

Abstract

Provided are a vehicle resource adjustment method and apparatus, and an electronic device. The vehicle resource adjustment method comprises: in response to a change in feature data of a target shift, determining current feature data of the target shift, and acquiring offline feature data of the target shift, wherein the offline feature data is periodic feature data of the number of vehicle trips and cargo volume for the target shift within a preset historical period; inputting the offline feature data and the current feature data into a pre-constructed target time-series model, to obtain a vehicle addition probability and a vehicle reduction probability; and on the basis of the vehicle addition probability and the vehicle reduction probability, determining whether a vehicle addition or a vehicle reduction is required for the target shift. In this way, by introducing the current feature data and the offline feature data in combination as input features for the target time-series model, the real-time responsiveness and accuracy of vehicle addition / reduction decisions can be effectively improved, so as to achieve precise matching between vehicle resources and actual demand, thereby improving logistics transportation efficiency and reducing transportation costs.

Description

Vehicle resource adjustment methods, devices and electronic equipment Technical Field

[0001] This application relates to the field of logistics technology, specifically to a method, apparatus, and electronic equipment for adjusting vehicle resources. Background Technology

[0002] With the rapid development of technology and the economy, the logistics industry has also experienced rapid growth. However, due to factors such as the uncertainty of market demand and fluctuations in shipment volume, there is often a mismatch between vehicle resources and actual demand, leading to reduced logistics and transportation efficiency. Summary of the Invention

[0003] In view of this, this application aims to provide a vehicle resource adjustment method, device, and electronic device that can achieve precise matching between vehicle resources and actual needs, thereby improving logistics and transportation efficiency.

[0004] The first aspect of this application provides a vehicle resource adjustment method, comprising: in response to a change in the characteristic data of a target shift, determining the current characteristic data of the target shift and acquiring the offline characteristic data of the target shift; the offline characteristic data being the periodic characteristic data of the number of vehicles and freight volume of the target shift within a preset historical period; the current characteristic data being the characteristic data of the number of vehicles and freight volume of the target shift at the current time; inputting the offline characteristic data and the current characteristic data into a pre-constructed target time series model to obtain the probability of adding vehicles and the probability of reducing vehicles; and determining, based on the probability of adding vehicles and the probability of reducing vehicles, whether it is necessary to add or reduce vehicles for the target shift.

[0005] Optionally, the method further includes: acquiring the current feature data of the target train based on a preset time interval, and detecting whether there is a difference between the current feature data of the target train and the feature data of the target train acquired last time; if there is a difference, determining that the feature data of the target train has changed.

[0006] Optionally, the method further includes: for the target train, detecting whether train schedule adjustment information and / or freight volume adjustment information have been obtained; if train schedule adjustment information and / or freight volume adjustment information have been obtained, then determining that the characteristic data of the target train has changed.

[0007] Optionally, the target time series model includes a vehicle addition classification model and a vehicle reduction classification model; inputting offline feature data and current feature data into the pre-constructed target time series model to obtain vehicle addition probability and vehicle reduction probability includes: performing feature concatenation on offline feature data and current feature data to obtain target features; inputting the target features into the vehicle addition classification model and the vehicle reduction classification model respectively to obtain vehicle addition probability and vehicle reduction probability respectively.

[0008] Optionally, the method for constructing the target time series model includes: acquiring raw data and performing statistical analysis on the raw data at different time periods to obtain the periodic characteristics and long-term trend characteristics of different time periods; the raw data includes data representing historical train trips and cargo volumes; constructing a sample training set using the periodic characteristics and long-term trend characteristics of different time periods, and using the sample training set to train the preset time series model to obtain the target time series model.

[0009] Optionally, the target time series model is obtained by training a preset time series model using a sample training set, including: training a gradient boosting decision tree time series model using a sample training set to obtain the target time series model.

[0010] Optionally, based on the probability of adding or removing buses, determine whether to add or remove buses for the target shift, including: detecting whether the probability of adding buses is greater than a preset threshold for adding buses, and whether the probability of removing buses is greater than a preset threshold for removing buses; if the probability of adding buses is greater than the preset threshold for adding buses, and the probability of removing buses is greater than the preset threshold for removing buses, then compare the probabilities of adding buses and removing buses; if the probability of adding buses is greater than the probability of removing buses, then determine that buses need to be added for the target shift; if the probability of adding buses is less than or equal to the probability of removing buses, then determine that buses need to be removed for the target shift; if the probability of adding buses is less than or equal to the preset threshold for adding buses, and the probability of removing buses is greater than the preset threshold for removing buses, then buses need to be added for the target shift.

[0011] Optionally, the method further includes: obtaining first adjustment information sent by the user for a preset vehicle addition threshold, updating the preset vehicle addition threshold based on the first adjustment information, and obtaining an updated preset vehicle addition threshold; and / or, obtaining second adjustment information sent by the user for a preset vehicle reduction threshold, updating the preset vehicle reduction threshold based on the second adjustment information, and obtaining an updated preset vehicle reduction threshold.

[0012] Optionally, after determining whether to add or remove buses for the target trip, the method further includes: if the target trip needs to add buses, then detecting whether an addition prompt has been sent for the target trip; if no addition prompt has been sent, then determining a recommended vehicle model based on offline feature data and issuing an addition prompt; the addition prompt carries the recommended vehicle model; if the target trip needs to remove buses, then detecting whether a removal prompt has been sent for the target trip; if no removal prompt has been sent, then issuing a removal prompt.

[0013] Optionally, based on offline feature data, a recommended vehicle model is determined and a vehicle addition prompt is issued, including: determining the recommended vehicle model based on offline feature data; determining the number of vehicles to be added based on the current feature data and the recommended vehicle model, and issuing a vehicle addition prompt; the vehicle addition prompt also carries the number of vehicles to be added.

[0014] Optionally, based on the current feature data and recommended vehicle models, the number of additional vehicles is determined, including: determining the predicted freight volume of the target trip and the number and capacity of available vehicles for the target trip based on the current feature data; determining the cargo capacity that the target trip can carry using the number and capacity of available vehicles; determining the cargo volume to be carried based on the predicted freight volume and the cargo capacity; and determining the number of additional vehicles of the recommended vehicle models based on the cargo volume to be carried and the recommended vehicle models.

[0015] Optionally, a vehicle reduction prompt may be issued, including: determining the number of vehicles to be reduced based on current feature data and issuing a vehicle reduction prompt; the vehicle reduction prompt carries the number of vehicles to be reduced.

[0016] Optionally, the number of vehicles to be reduced is determined based on the current feature data, including: determining the predicted freight volume of the target trip and the number and capacity of available vehicles for the target trip based on the current feature data; determining the cargo capacity that the target trip can carry using the number and capacity of available vehicles; determining the carrying capacity margin based on the predicted freight volume and the carrying capacity; and determining the number of vehicles to be reduced based on the carrying capacity margin.

[0017] A second aspect of this application provides a vehicle resource adjustment device, comprising: a determination and acquisition module, configured to determine the current characteristic data of the target shift and acquire offline characteristic data of the target shift in response to changes in the characteristic data of the target shift; the offline characteristic data being periodic characteristic data of the number of vehicles and freight volume of the target shift within a preset historical period; and the current characteristic data being characteristic data of the number of vehicles and freight volume of the target shift at the current time; an input module, configured to input the offline characteristic data and the current characteristic data into a pre-constructed target time series model to obtain the probability of adding or removing vehicles; and a determination module, configured to determine whether it is necessary to add or remove vehicles for the target shift based on the probability of adding or removing vehicles.

[0018] A third aspect of this application provides an electronic device, including: a processor and a memory connected to the processor; the memory is used to store a computer program; the processor is used to call and execute the computer program in the memory to perform the vehicle resource adjustment method as described in the first aspect of this application.

[0019] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, causes the computer to perform the vehicle resource adjustment method as described in the first aspect of this application.

[0020] In this application, a target time-series model is pre-constructed to determine the probability of adding or removing vehicles for a target trip, providing a basis for vehicle resource scheduling. Based on this, in response to changes in the characteristic data of the target trip, the current characteristic data of the target trip is determined, and offline characteristic data of the target trip is obtained. The offline characteristic data consists of the periodic characteristic data of the trip's trips and freight volume within a preset historical period; the current characteristic data consists of the characteristic data of the trip's trips and freight volume at the current time. The offline and current characteristic data are then input into the target time-series model to obtain the probabilities of adding and removing vehicles. Based on these probabilities, it is determined whether to add or remove vehicles for the target trip. Thus, by introducing a combination of current and offline characteristic data as input features on top of the target time-series model, the real-time performance and accuracy of vehicle addition and removal decisions can be effectively improved, achieving precise matching of vehicle resources with actual demand, thereby improving logistics efficiency and reducing transportation costs. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 is a flowchart illustrating a vehicle resource adjustment method according to an embodiment of this application.

[0023] Figure 2 is a flowchart illustrating a method for constructing a target time series model according to an embodiment of this application.

[0024] Figure 3 is a flowchart illustrating a vehicle resource adjustment method according to another embodiment of this application.

[0025] Figure 4 is a schematic diagram of a vehicle resource adjustment device provided in one embodiment of this application.

[0026] Figure 5 is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] With rapid economic development, the logistics industry has also experienced explosive growth. However, due to factors such as market demand uncertainty and fluctuations in shipment volume, a mismatch has arisen between vehicle resources and actual demand, severely impacting logistics efficiency.

[0029] In view of this, embodiments of this application provide a vehicle resource adjustment method, as shown in FIG1. ​​The vehicle resource adjustment method may include at least the following steps:

[0030] S101. In response to changes in the characteristic data of the target train, determine the current characteristic data of the target train and obtain the offline characteristic data of the target train; the offline characteristic data is the periodic characteristic data of the train number and freight volume of the target train within a preset historical period; the current characteristic data is the characteristic data of the train number and freight volume of the target train at the current time.

[0031] The preset historical time period can be set according to actual needs, and there are no specific limitations here. For example, the preset historical time period can be a period within the past month, a period within the past three months, a period within the past week, and so on.

[0032] Specifically, the periodic characteristic data of train numbers and freight volume can be data with periodic characteristics extracted from the data on train numbers and freight volume. The data on train numbers and freight volume refers to data related to train numbers and freight volume.

[0033] During implementation, the data on train trips and freight volume can include vehicle codes, number of trips, load capacity of each vehicle, vehicle type, whether there are any additions / reductions to the fleet, and freight volume of each trip. Periodic characteristic data for train trips and freight volume can include historical freight volume, train trips, maximum, minimum, mean, median, standard deviation, and skewness of additions / reductions over different time periods, departure time determination (e.g., whether the departure date falls on a weekday, holiday, or peak commuting period), commonly used vehicle types, etc. Characteristic data for train trips and freight volume can include status data of each vehicle in the trip (e.g., vehicle code, freight volume, whether it has been reassigned), freight volume forecast data (representing the predicted freight volume of the trip), and planned train trip data at the next site dimension (i.e., the number of available vehicles for the trip), etc., which affect the freight volume and load factor of the trip.

[0034] It should be noted that changes in the characteristic data of the target train schedule, such as changes in the status data of each vehicle in the schedule, indicate that the vehicles have been relocated, which may lead to changes in the planned train schedule data in the dimension of the train schedule-next site, and may result in insufficient train capacity for the target train schedule; similarly, changes in freight volume forecast data may also lead to insufficient train capacity or empty trains for the target train schedule.

[0035] Correspondingly, if the characteristic data of the target shift changes—that is, if the characteristic data of the number of vehicles and the amount of cargo for the target shift change, such as changes in the planned vehicles in the target shift that render them unusable, or the addition / reduction of cargo volume in the target shift—then there may be a situation where the vehicles for the target shift cannot fully carry all the cargo volume or the vehicles are empty, resulting in a mismatch between vehicle resources and cargo demand. Responding to changes in the characteristic data of the target shift, determining the current characteristic data of the target shift, and obtaining the offline characteristic data of the target shift can lay the foundation for timely adjustments to vehicle resources, ensuring the real-time nature of vehicle resource adjustments.

[0036] S102. Input the offline feature data and the current feature data into the pre-built target time series model to obtain the probability of adding a vehicle and the probability of reducing a vehicle.

[0037] Current feature data is real-time feature data, while offline feature data is historical feature data. The above-mentioned determination of the current feature data of the target shift and acquisition of the offline feature data of the target feature data means that the real-time feature data and historical feature data of the target shift are determined. The offline feature data and the current feature data are input into the pre-built target time series model, that is, the real-time features and historical features are combined and used as input to the target time series model. This can make the output results of the target time series model more real-time, that is, the probability of adding and removing vehicles is more real-time, thereby further ensuring the real-time nature of vehicle resource adjustment.

[0038] The probability of adding a vehicle refers to the probability that an additional vehicle is needed for the target trip, while the probability of reducing a vehicle refers to the probability that a vehicle is needed to be reduced for the target trip. By constructing a well-developed target time series model, the probabilities of adding or reducing vehicles can be quickly obtained, which helps improve the efficiency and accuracy of vehicle resource adjustment.

[0039] S103. Based on the probability of adding or reducing buses, determine whether it is necessary to add or reduce buses for the target schedule.

[0040] After obtaining the probabilities of adding and removing vehicles, a judgment and analysis can be performed based on these probabilities to determine whether it is necessary to add or remove vehicles for the target shift, thus providing a theoretical basis for on-site vehicle dispatching decisions.

[0041] In this embodiment, a target time-series model is pre-constructed to determine the probability of adding or removing vehicles for a target trip, providing a basis for vehicle resource scheduling. Based on this, in response to changes in the characteristic data of the target trip, the current characteristic data of the target trip is determined, and the offline characteristic data of the target trip is obtained. The offline characteristic data consists of the periodic characteristic data of the number of trips and the amount of cargo for the target trip within a preset historical period; the current characteristic data consists of the characteristic data of the number of trips and the amount of cargo for the target trip at the current time. Then, the offline characteristic data and the current characteristic data are input into the target time-series model to obtain the probability of adding or removing vehicles. Based on the probability of adding or removing vehicles, it is determined whether to add or remove vehicles for the target trip. Thus, by introducing the combination of current characteristic data and offline characteristic data as input features on the basis of the target time-series model, the real-time performance and accuracy of adding or removing vehicles can be effectively improved, achieving precise matching of vehicle resources with actual needs, thereby improving logistics transportation efficiency and reducing transportation costs.

[0042] To ensure the timeliness of vehicle resource adjustments, some implementations may further include: acquiring current characteristic data of a target shift based on a preset time interval, and detecting whether there is a difference between the current characteristic data of the target shift and the previously acquired characteristic data of the target shift; if there is a difference, determining that the characteristic data of the target shift has changed; or, for the target shift, detecting whether shift adjustment information and / or freight volume adjustment information have been acquired; if shift adjustment information and / or freight volume adjustment information have been acquired, determining that the characteristic data of the target shift has changed.

[0043] The preset time interval can be set according to actual needs, and no specific limitation is made here. For example, the preset time interval can be 1 minute. Then, every 1 minute, the current feature data of the target train can be obtained once, and it can be checked whether there are any differences between the current feature data of the target train and the feature data of the target train obtained in the previous time. In this way, the feature data of the target train can be monitored in real time, which provides a guarantee for timely response to changes in the feature data of the target train.

[0044] Alternatively, taking the execution of the control terminal as an example, a timely feedback mechanism for train number adjustment information and freight volume adjustment information can be set up. In this way, when the train number of the target train changes, and / or the predicted freight volume of the target train changes, the control terminal can receive the corresponding train number adjustment information and / or freight volume adjustment information in a timely manner, thereby providing a guarantee for timely response to changes in the characteristic data of the target train.

[0045] Since vehicle scheduling requires reserving vehicle preparation time, in some other implementations, before determining the current characteristic data of the target shift and obtaining the offline characteristic data of the target shift, the vehicle resource adjustment method may further include: detecting whether the current time is before the execution time of the target shift, and whether the duration between the current time and the execution time is greater than a preset duration. If the current time is before the execution time of the target shift, and the duration between the current time and the execution time is greater than the preset duration, then the steps of determining the current characteristic data of the target shift and obtaining the offline characteristic data of the target shift can continue; otherwise, the response to changes in the characteristic data of the target shift is stopped.

[0046] During implementation, the preset duration can be set according to the actual vehicle preparation time requirements, without specific limitations. For example, the preset duration can be 48 hours, ensuring that the target shift can call up vehicles that match the cargo volume during the execution time, achieving precise matching of resources and demand, and improving vehicle resource utilization.

[0047] In order to obtain more accurate vehicle addition and reduction probabilities, some implementations may include a vehicle addition classification model and a vehicle reduction classification model in the target time series model.

[0048] Accordingly, the above-mentioned inputting offline feature data and current feature data into the pre-built target time series model to obtain the probability of adding a vehicle and the probability of subtracting a vehicle can specifically include: concatenating the offline feature data and current feature data to obtain target features; and inputting the target features into the vehicle addition classification model and the vehicle subtraction classification model respectively to obtain the probability of adding a vehicle and the probability of subtracting a vehicle.

[0049] Specifically, feature concatenation between offline and current feature data can be performed, combining the two to ensure that the target features possess both the characteristics of the target shift and strong real-time performance. Furthermore, inputting the target features into the add-on and remove-on-shift classification models respectively can yield more accurate and real-time probabilities of adding and removing shifts.

[0050] To ensure the accuracy of the target time series model, in some implementations, as shown in Figure 2, the method for constructing the target time series model may include the following steps:

[0051] S201. Obtain raw data and perform statistical analysis on the raw data for different time periods to obtain the periodic characteristics and long-term trend characteristics of different time periods; the raw data includes data representing historical train trips and freight volumes.

[0052] Periodic features refer to patterns of cyclical change in data, typically related to time-dependent periodic fluctuations. Extracting periodic features helps models identify short-term seasonal or cyclical changes. Long-term trend features refer to trends in data over a longer time span, usually reflecting overall growth or decline. Mining long-term trend features helps models capture long-term changes in time series.

[0053] Raw data can include historical vehicle codes, number of trips, load per vehicle, vehicle type, historical average load factor (average load factor per day), whether there were any additions / reductions to the fleet, and cargo volume per trip. Periodic characteristics can include the maximum, minimum, median, mean, standard deviation, and skewness of cargo volume for different time periods. Long-term trend characteristics can include cargo volume trends for different time periods.

[0054] Different time periods can be set according to actual needs, and there are no specific limitations here. For example, different time periods can include: the past 3 days, the past 6 days, and the past 12 days, etc.

[0055] During implementation, as many different types of periodic features and long-term trend features as possible can be obtained to ensure that the number of feature types reaches the preset number, such as 50, thereby enriching the training data and providing a guarantee for the training model to learn historical behavior patterns. At the same time, it also provides a guarantee for improving the accuracy and stability of the trained time series model.

[0056] S202. Construct a sample training set using the periodic characteristics and long-term trend characteristics of different time periods, and use the sample training set to train the preset time series model to obtain the target time series model.

[0057] Specifically, a machine learning framework designed for real-time data processing can be used to build a complete algorithm model development process covering feature extraction, model training, and model prediction. This real-time data processing-based framework can employ an event-driven stream processing framework, enabling feature extraction and transformation immediately upon data arrival, without waiting for the entire batch of data to accumulate. Furthermore, it supports incremental learning and online learning, allowing the trained model to be gradually updated as new data arrives without retraining the entire model. Additionally, it can parallelize machine learning tasks, significantly improving processing speed and throughput. Correspondingly, compared to traditional machine learning models that require timed triggering or encapsulation into interfaces for deployment, the real-time data processing-based framework can integrate the entire algorithm model development process into a single service, shortening the process, improving feature real-time performance, reducing operational complexity, and supporting online learning and online model updates, further enhancing model real-time performance.

[0058] In practical applications, model training tasks can be streamlined and managed using a pipeline approach, allowing for the reuse of the training sample set. The target time-series model can be obtained by training a Gradient Boosting Decision Tree (GBDT) model using this training set. The trained target time-series model can be stored as a file on a model management platform. During model prediction, the stored model file can be retrieved from the platform for real-time prediction, yielding the corresponding bonus and penalty probabilities. This eliminates the need for multiple service interactions to complete the entire process, shortening the workflow and improving real-time performance.

[0059] It should be noted that the embodiments of this application are only illustrative examples of constructing the target time series model based on the GBDT model. However, this application is not limited to this. In some other implementations, the target time series model may be other time series models, which are not specifically limited here.

[0060] The target time series model is obtained by using the above model construction method. That is, the vehicle addition classification model and vehicle reduction classification model are obtained by using the above model construction method, which can provide a faster tool for obtaining the vehicle addition probability and vehicle reduction probability in the future.

[0061] To further improve the efficiency of vehicle resource adjustment, some implementations determine whether to add or remove vehicles for a target shift based on the probability of adding and removing vehicles. Specifically, this may include: detecting whether the probability of adding vehicles is greater than a preset threshold for adding vehicles, and whether the probability of removing vehicles is greater than a preset threshold for removing vehicles; if the probability of adding vehicles is greater than the preset threshold for adding vehicles, and the probability of removing vehicles is greater than the preset threshold for removing vehicles, then comparing the probabilities of adding and removing vehicles; if the probability of adding vehicles is greater than the probability of removing vehicles, then it is determined that vehicles need to be added for the target shift; if the probability of adding vehicles is less than or equal to the probability of removing vehicles, then it is determined that vehicles need to be removed for the target shift; if the probability of adding vehicles is less than or equal to the preset threshold for adding vehicles, and the probability of removing vehicles is greater than the preset threshold for removing vehicles, then it is determined that vehicles need to be removed for the target shift; if the probability of adding vehicles is greater than the preset threshold for adding vehicles, and the probability of removing vehicles is less than or equal to the preset threshold for removing vehicles, then vehicles need to be added for the target shift.

[0062] The preset vehicle addition threshold and preset vehicle reduction threshold can both be set according to actual needs, and no specific restrictions are made here.

[0063] For example, the preset threshold for adding a bus can be 0.5, and the preset threshold for removing a bus can also be 0.5. After obtaining the probabilities of adding and removing buses, the magnitudes of the probabilities of adding and removing buses can be compared with 0.5. If the probability of adding a bus is greater than 0.5 and the probability of removing a bus is less than 0.5, then it is determined that an additional bus is needed for the target shift; if the probability of adding a bus is less than 0.5 and the probability of removing a bus is greater than 0.5, then it is determined that a bus needs to be removed for the target shift; if both the probability of adding and removing buses are less than 0.5, then it is determined that neither adding nor removing buses is needed for the target shift; if both the probability of adding and removing buses are greater than 0.5, then it is necessary to compare the magnitudes of the probabilities of adding and removing buses.

[0064] For example, if the probability of adding a bus is 0.75 and the probability of reducing a bus is 0.76, when the probability of adding a bus is greater than the preset threshold for adding a bus and the probability of reducing a bus is greater than the preset threshold for reducing a bus, since 0.75 < 0.76, that is, the probability of adding a bus is less than the probability of reducing a bus, it can be determined that a bus reduction is needed for the target shift.

[0065] By utilizing the probabilities of adding and removing vehicles, we can assist in making decisions about adding or removing vehicles, improve the accuracy of vehicle resource adjustments, and bring great convenience to users.

[0066] To facilitate users' flexible adjustment of preset vehicle addition and reduction thresholds, in some embodiments, the vehicle resource adjustment method may further include: obtaining first adjustment information sent by the user regarding the preset vehicle addition threshold, updating the preset vehicle addition threshold based on the first adjustment information, and obtaining the updated preset vehicle addition threshold; and / or, obtaining second adjustment information sent by the user regarding the preset vehicle reduction threshold, updating the preset vehicle reduction threshold based on the second adjustment information, and obtaining the updated preset vehicle reduction threshold.

[0067] During implementation, the actual effect of adding / reducing vehicles can be evaluated based on the vehicle addition / reduction prediction results. The preset vehicle addition threshold and preset vehicle reduction threshold can then be adjusted based on the evaluation results, which can greatly improve the accuracy of vehicle resource adjustment.

[0068] To provide greater convenience for users, in some implementations, as shown in Figure 4, after determining whether to add or remove vehicles for the target shift, the vehicle resource adjustment method may also include the following steps:

[0069] S104. If the target trip requires additional buses, check whether an additional bus notification has been sent for the target trip; if no additional bus notification has been sent, determine the recommended vehicle type based on offline feature data and send an additional bus notification; the additional bus notification carries the recommended vehicle type. If the target trip requires fewer buses, check whether a fewer bus notification has been sent for the target trip; if no fewer bus notification has been sent, send a fewer bus notification.

[0070] Among them, determining recommended models based on offline feature data can be done by identifying commonly used models from offline feature data and then selecting these commonly used models as recommended models.

[0071] By sending corresponding vehicle addition / reduction prompts, users can be promptly reminded that vehicle resource adjustments are needed, while also gaining a more intuitive understanding of the direction of these adjustments, thus facilitating a quick response to vehicle resource adjustment events.

[0072] In practice, the above-mentioned method of determining recommended vehicle models and issuing vehicle addition prompts based on offline feature data may specifically include: determining recommended vehicle models based on offline feature data; determining the number of vehicles to be added based on current feature data and recommended vehicle models, and issuing vehicle addition prompts; the vehicle addition prompts also carry the number of vehicles to be added.

[0073] Specifically, when determining the number of additional vehicles based on current feature data and recommended vehicle types, the predicted freight volume and the number and capacity of available vehicles for the target trip can be determined based on the current feature data. Using the number and capacity of available vehicles for the target trip, the maximum freight volume that the target trip can handle can be determined. Based on the predicted freight volume and the maximum freight volume, the amount of freight to be handled can be determined. Based on the amount of freight to be handled and the recommended vehicle types, the number of additional vehicles of the recommended vehicle types can be determined. This provides users with more intelligent vehicle addition suggestions, saving time on manual calculations, reducing labor costs, improving resource scheduling efficiency, and ensuring a high degree of matching between resources and demand.

[0074] On the other hand, the aforementioned vehicle reduction prompt may specifically include: determining the number of vehicles to be reduced based on current feature data, and issuing a vehicle reduction prompt; the vehicle reduction prompt carries the number of vehicles to be reduced.

[0075] Specifically, based on current feature data, the predicted freight volume and the number and capacity of available vehicles for the target trip can be determined. Using the number and capacity of available vehicles, the target trip's maximum freight capacity can be determined. Based on the predicted and maximum freight volume, the carrying capacity can be determined, and based on the carrying capacity, the number of vehicles to be reduced can be determined. This provides users with more intuitive suggestions for reducing vehicles, saving time on manual calculations, reducing labor costs, improving resource scheduling efficiency, and ensuring a high degree of matching between resources and demand.

[0076] As another optional implementation of the disclosure of this application, an embodiment of this application also provides a vehicle resource adjustment device, as shown in FIG4. The vehicle resource adjustment device may include at least: a determination and acquisition module 401, used to determine the current feature data of the target shift and acquire the offline feature data of the target shift in response to a change in the feature data of the target shift; the offline feature data is the periodic feature data of the number of vehicles and the amount of cargo of the target shift within a preset historical period; the current feature data is the feature data of the number of vehicles and the amount of cargo of the target shift at the current time; an input module 402, used to input the offline feature data and the current feature data into a pre-constructed target time series model to obtain the probability of adding vehicles and the probability of reducing vehicles; and a determination module 403, used to determine whether it is necessary to add or reduce vehicles for the target shift based on the probability of adding vehicles and the probability of reducing vehicles.

[0077] Optionally, the vehicle resource adjustment device may further include a detection and determination module, which may be used to: acquire the current characteristic data of the target shift based on a preset time interval, and detect whether there is a difference between the current characteristic data of the target shift and the characteristic data of the target shift acquired last time; if there is a difference, determine that the characteristic data of the target shift has changed; or, for the target shift, detect whether shift adjustment information and / or freight adjustment information have been acquired; if shift adjustment information and / or freight adjustment information have been acquired, determine that the characteristic data of the target shift has changed.

[0078] Optionally, the target time series model may include a vehicle addition classification model and a vehicle reduction classification model; correspondingly, when offline feature data and current feature data are input into the pre-constructed target time series model to obtain vehicle addition probability and vehicle reduction probability, the input module 402 may be used to: perform feature concatenation on offline feature data and current feature data to obtain target features; and input the target features into the vehicle addition classification model and the vehicle reduction classification model respectively to obtain the vehicle addition probability and vehicle reduction probability.

[0079] Optionally, the vehicle resource adjustment device may also include a construction module, which may be used to: acquire raw data and perform statistical analysis on the raw data at different time periods to obtain periodic characteristics and long-term trend characteristics at different time periods; the raw data includes data representing historical vehicle trips and cargo volume; construct a sample training set using the periodic characteristics and long-term trend characteristics at different time periods, and use the sample training set to train a preset time series model to obtain a target time series model.

[0080] Optionally, when determining whether to add or remove buses for a target shift based on the probability of adding or removing buses, the determination module 403 can be used to: detect whether the probability of adding buses is greater than a preset threshold for adding buses, and whether the probability of removing buses is greater than a preset threshold for removing buses; if the probability of adding buses is greater than the preset threshold for adding buses, and the probability of removing buses is greater than the preset threshold for removing buses, then compare the probabilities of adding buses and removing buses; if the probability of adding buses is greater than the probability of removing buses, then determine that buses need to be added for the target shift; if the probability of adding buses is less than or equal to the probability of removing buses, then determine that buses need to be removed for the target shift; if the probability of adding buses is less than or equal to the preset threshold for adding buses, and the probability of removing buses is greater than the preset threshold for removing buses, then determine that buses need to be removed for the target shift; if the probability of adding buses is greater than the preset threshold for adding buses, and the probability of removing buses is less than or equal to the preset threshold for removing buses, then buses need to be added for the target shift.

[0081] Optionally, the vehicle resource adjustment device may further include a prompting module, which can be used to: if the target shift requires additional vehicles, detect whether an additional vehicle prompt has been sent for the target shift; if no additional vehicle prompt has been sent, determine the recommended vehicle type based on offline feature data and issue an additional vehicle prompt; the additional vehicle prompt carries the recommended vehicle type; if the target shift requires fewer vehicles, detect whether a fewer vehicle prompt has been sent for the target shift; if no fewer vehicle prompt has been sent, issue a fewer vehicle prompt.

[0082] Optionally, when determining the recommended vehicle model based on offline feature data and issuing a vehicle addition prompt, the prompt module can specifically be used to: determine the recommended vehicle model based on offline feature data; determine the number of vehicles to be added based on the current feature data and the recommended vehicle model, and issue a vehicle addition prompt; the vehicle addition prompt also carries the number of vehicles to be added.

[0083] Optionally, when issuing a vehicle reduction prompt, the prompt module can be specifically used to: determine the number of vehicles to be reduced based on the current feature data, and issue a vehicle reduction prompt; the vehicle reduction prompt carries the number of vehicles to be reduced.

[0084] The specific implementation of the vehicle resource adjustment device provided in the embodiments of this application can refer to the implementation of the vehicle resource adjustment method described in any of the above embodiments, and will not be repeated here.

[0085] As another optional implementation of the disclosure of this application, an embodiment of this application also provides an electronic device, as shown in FIG5. The electronic device may include: a memory 501 and a processor 502; wherein, the memory 501 is connected to the processor 502 and is used to store a program; the processor 502 is used to implement the vehicle resource adjustment method disclosed in any of the above embodiments by running the program stored in the memory 501.

[0086] Specifically, the aforementioned electronic device may also include: a bus, a communication interface 503, an input device 504, and an output device 505.

[0087] The processor 502, memory 501, communication interface 503, input device 504, and output device 505 are interconnected via a bus. Among them:

[0088] A bus can include a pathway for transmitting information between various components of a computer system.

[0089] The processor 502 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0090] Processor 502 may include a main processor, as well as a baseband chip, modem, etc.

[0091] The memory 501 stores a program for executing the technical solution of this application, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 501 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0092] Input device 504 may include a device for receiving data and information input by a user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0093] Output device 505 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0094] The communication interface 503 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0095] The processor 502 executes the program stored in the memory 501 and calls other devices, which can be used to implement the various steps of the vehicle resource adjustment method provided in the above embodiments of this application.

[0096] Embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, causes the computer to perform the vehicle resource adjustment method in any of the above embodiments.

[0097] Embodiments of this application also provide a computer program product containing instructions that, when executed by a computer, cause the computer to perform the vehicle resource adjustment method described in any of the above embodiments.

[0098] It is understood that the specific examples in this document are only intended to help those skilled in the art better understand the embodiments described herein, and are not intended to limit the scope of the invention.

[0099] It is understood that in the various embodiments described in this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments described in this specification.

[0100] It is understood that the various implementation methods described in this specification can be implemented individually or in combination, and the implementation methods in this specification are not limited in this respect.

[0101] Unless otherwise stated, all technical and scientific terms used in the embodiments of this specification have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of this specification. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items. The singular forms "a," "the," and "the" as used in the embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0102] It is understood that the processor in the embodiments of this specification can be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method embodiments can be completed by the integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this specification. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this specification can be directly implemented by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0103] It is understood that the memory in the embodiments of this specification may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM). It should be noted that the memory in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0104] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this specification.

[0105] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the aforementioned method implementations, and will not be repeated here.

[0106] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0107] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0108] In addition, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0109] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of this specification, in essence, or the parts that contribute to the prior art, or parts of the technical solutions, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0110] The above description is merely a specific embodiment of this specification, but the scope of protection of this invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this specification should be included within the scope of protection of this specification. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A method for adjusting vehicle resources, characterized in that, include: In response to changes in the characteristic data of the target train, the current characteristic data of the target train is determined, and the offline characteristic data of the target train is obtained; The offline feature data is the periodic feature data of the target train's number of trains and cargo volume within a preset historical period; the current feature data is the feature data of the target train's number of trains and cargo volume at the current time. The offline feature data and the current feature data are input into the pre-constructed target time series model to obtain the probability of adding a vehicle and the probability of removing a vehicle; Based on the probability of adding or reducing buses, it is determined whether to add or reduce buses for the target schedule.

2. The method according to claim 1, characterized in that, Also includes: Based on a preset time interval, the current feature data of the target train is acquired, and it is detected whether there is a difference between the current feature data of the target train and the feature data of the target train acquired last time; if there is a difference, it is determined that the feature data of the target train has changed.

3. The method according to claim 1, characterized in that, Also includes: For the target train schedule, it is detected whether train schedule adjustment information and / or freight volume adjustment information have been obtained; if the train schedule adjustment information and / or freight volume adjustment information are obtained, it is determined that the characteristic data of the target train schedule has changed.

4. The method according to any one of claims 1 to 3, characterized in that, The target time series model includes a vehicle addition classification model and a vehicle reduction classification model; The step of inputting the offline feature data and the current feature data into a pre-constructed target time series model to obtain the probability of adding a vehicle and the probability of subtracting a vehicle includes: The offline feature data and the current feature data are concatenated to obtain the target features; The target features are input into the vehicle addition classification model and the vehicle reduction classification model respectively to obtain the vehicle addition probability and the vehicle reduction probability.

5. The method according to any one of claims 1 to 4, characterized in that, The method for constructing the target time series model includes: The raw data is acquired, and statistical analysis is performed on the raw data for different time periods to obtain the periodic characteristics and long-term trend characteristics of different time periods; the raw data includes data representing historical train numbers and freight volumes; A sample training set is constructed using the periodic characteristics and long-term trend characteristics of the different time periods, and the preset time series model is trained using the sample training set to obtain the target time series model.

6. The method according to claim 5, characterized in that, The step of training a preset time series model using the sample training set to obtain the target time series model includes: The gradient boosting decision tree time series model is trained using the sample training set to obtain the target time series model.

7. The method according to any one of claims 1 to 6, characterized in that, The step of determining whether to add or remove buses for the target schedule based on the probability of adding or removing buses includes: Detect whether the probability of adding a vehicle is greater than a preset threshold for adding a vehicle, and whether the probability of reducing a vehicle is greater than a preset threshold for reducing a vehicle; If the probability of adding a vehicle is greater than a preset threshold for adding a vehicle, and the probability of reducing a vehicle is greater than a preset threshold for reducing a vehicle, then the probability of adding a vehicle is compared with the probability of reducing a vehicle; if the probability of adding a vehicle is greater than the probability of reducing a vehicle, then it is determined that an additional vehicle is needed for the target shift; if the probability of adding a vehicle is less than or equal to the probability of reducing a vehicle, then it is determined that a reduction in the number of vehicles is needed for the target shift. If the probability of adding a vehicle is less than or equal to a preset threshold for adding a vehicle, and the probability of reducing a vehicle is greater than a preset threshold for reducing a vehicle, then it is determined that a vehicle reduction is needed for the target shift. If the probability of adding a vehicle is greater than a preset threshold for adding a vehicle, and the probability of reducing a vehicle is less than or equal to a preset threshold for reducing a vehicle, then additional vehicles are needed for the target shift.

8. The method according to claim 7, characterized in that, Also includes: Upon receiving first adjustment information sent by the user regarding the preset vehicle addition threshold, the preset vehicle addition threshold is updated based on the first adjustment information to obtain the updated preset vehicle addition threshold; and / or, The system obtains the second adjustment information sent by the user regarding the preset vehicle reduction threshold, updates the preset vehicle reduction threshold based on the second adjustment information, and obtains the updated preset vehicle reduction threshold.

9. The method according to any one of claims 1 to 8, characterized in that, After determining whether additional or fewer buses are needed for the target schedule, the method further includes: If the target bus route requires additional buses, it is checked whether an additional bus request has been sent for the target bus route; if no additional bus request has been sent, a recommended vehicle model is determined based on the offline feature data, and an additional bus request is issued; the additional bus request carries the recommended vehicle model. If the target train needs to reduce the number of trains, then check whether a reduction notification has been sent for the target train; if no reduction notification has been sent, then issue a reduction notification.

10. The method according to claim 9, characterized in that, The step of determining the recommended vehicle model based on the offline feature data and issuing a vehicle addition prompt includes: Based on the offline feature data, a recommended vehicle model is determined; based on the current feature data and the recommended vehicle model, the number of vehicles to be added is determined, and a vehicle addition prompt is issued; the vehicle addition prompt also carries the number of vehicles to be added.

11. The method according to claim 10, characterized in that, The step of determining the number of vehicles to be added based on the current feature data and the recommended vehicle models includes: Based on the current feature data, determine the predicted freight volume of the target train and the number and capacity of available vehicles for the target train; Using the number and capacity of the available vehicles, determine the cargo capacity that the target train can carry; Based on the predicted cargo volume and the carrying capacity, the cargo volume to be carried is determined; Based on the cargo volume to be carried and the recommended vehicle model, determine the number of additional vehicles of the recommended vehicle model.

12. The method according to claim 9, characterized in that, The issuance of the vehicle reduction prompt includes: Based on the current feature data, the number of vehicles to be reduced is determined, and a vehicle reduction prompt is issued; the vehicle reduction prompt carries the number of vehicles to be reduced.

13. The method according to claim 12, characterized in that, The process of determining the number of vehicles to be reduced based on the current feature data includes: Based on the current feature data, determine the predicted freight volume of the target train and the number and capacity of available vehicles for the target train; Using the number and capacity of the available vehicles, determine the cargo capacity that the target train can carry; Based on the predicted cargo volume and the carrying capacity, determine the carrying margin; The number of vehicles to be reduced is determined based on the aforementioned load margin.

14. A vehicle resource adjustment device, characterized in that, include: The determination and acquisition module is used to determine the current characteristic data of the target train in response to changes in the characteristic data of the target train, and to acquire the offline characteristic data of the target train; the offline characteristic data is the periodic characteristic data of the train number and freight volume of the target train within a preset historical period; the current characteristic data is the characteristic data of the train number and freight volume of the target train at the current time. The input module is used to input the offline feature data and the current feature data into the pre-built target time series model to obtain the probability of adding a vehicle and the probability of subtracting a vehicle; The determination module is used to determine, based on the probability of adding or reducing vehicles, whether it is necessary to add or reduce vehicles for the target shift.

15. An electronic device, characterized in that, include: A processor, and a memory connected to the processor; The memory is used to store computer programs; The processor is used to call and execute the computer program in the memory to perform the vehicle resource adjustment method as described in any one of claims 1-13.

Images