Real-time prediction method, device and equipment for empty / full state of vehicle and storage medium
By generating loading and unloading area and waybill grid sequences through clustering and combining them with real-time trajectory data, the problem of real-time prediction of vehicle empty and full load status relying on waybill data was solved, achieving more accurate status judgment and scheduling optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING ZHONGJIAOXING ROAD INTERNET OF VEHICLES TECH CO LTD
- Filing Date
- 2026-01-20
- Publication Date
- 2026-06-09
AI Technical Summary
In existing technologies, real-time prediction of vehicle empty/full load status relies on waybill data, which is easily affected by waybill supplementation, omissions, or information delays, leading to inaccurate judgments.
By clustering loading and unloading point data and historical waybill trajectory data within a preset time period, loading and unloading area and waybill grid sequences are generated. Combined with real-time trajectory, empty and full load status is predicted, including predictions for two scenarios: loading and unloading area and road.
It enables real-time and accurate prediction of vehicle empty/full load status in the absence of real-time waybill data, improving vehicle dispatching efficiency and timeliness, and reducing misjudgment and waste of transportation resources.
Smart Images
Figure CN122175476A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle management technology, and more specifically, to a method, apparatus, device, and storage medium for real-time prediction of vehicle empty and full-load status. Background Technology
[0002] With the rapid development of the modern logistics and transportation industry, refined management of road freight vehicles, optimized capacity allocation, and improved transportation efficiency have become core industry needs. Among these, real-time and accurate perception of vehicle vacancy or full load status is a key technological foundation for achieving these goals. For example, if a logistics dispatch platform can accurately predict the real-time status of return vehicles, it can effectively organize return cargo and significantly reduce vehicle empty-running rates.
[0003] The current solution involves judging based on waybill data: if a vehicle has incomplete electronic waybills, it is considered fully loaded; if a waybill is completed, it is considered empty. This judgment logic relies entirely on the data from the waybill system. In actual operation, there are numerous instances of waybill entries being added, omitted, or information updates being delayed. If waybill data is missing or inaccurate, the system will be unable to make effective judgments and may even draw incorrect conclusions. Summary of the Invention
[0004] This application provides a method, apparatus, device, and storage medium for real-time prediction of vehicle empty / full load status, in order to at least solve the technical problem in the related art that it is difficult to accurately predict vehicle empty / full load status in real time.
[0005] According to one aspect of the embodiments of this application, a real-time prediction method for the empty / full load state of a vehicle is provided, including: Based on the loading and unloading point data of vehicles within a preset time period, the loading and unloading areas of vehicles are clustered. Based on the historical waybill data and trajectory data of vehicles within a preset time period, the loading and unloading areas corresponding to the origin and unloading locations of the waybills, as well as the waybill grid sequence from the origin to the unloading location, are obtained. When the real-time trajectory of the vehicle is within the loading and unloading area or within the preset range of the loading and unloading area, the empty or full-load status of the vehicle in the loading and unloading area is predicted based on the real-time trajectory of the vehicle, the loading and unloading area of the vehicle, and the loading and unloading area corresponding to the origin and destination of the waybill. When the real-time trajectory of the vehicle is not located within the loading and unloading area or within the preset range of the loading and unloading area, the empty or fully loaded status of the vehicle on the road is predicted based on the real-time trajectory of the vehicle, the loading and unloading area of the vehicle, and the waybill grid sequence from the place of origin to the place of unloading.
[0006] According to another aspect of the embodiments of this application, a real-time prediction device for the empty and fully loaded states of a vehicle is also provided, comprising: The loading and unloading area generation module is used to cluster the loading and unloading points of vehicles within a preset time period to obtain the loading and unloading areas of vehicles. The waybill data processing module is used to obtain the loading and unloading areas corresponding to the origin and unloading location of the waybill, and the waybill grid sequence from the origin to the unloading location, based on the historical waybill data and trajectory data of the vehicle within a preset time period. The loading and unloading area empty / full status prediction module is used to predict the empty / full status of a vehicle in the loading and unloading area when the vehicle's real-time trajectory is within the loading and unloading area or within a preset range of the loading and unloading area, based on the vehicle's real-time trajectory, the vehicle's loading and unloading area, and the loading and unloading areas corresponding to the waybill's origin and destination. The road empty / full load status prediction module is used to predict the empty / full load status of a vehicle on the road when the vehicle's real-time trajectory is not located in the loading / unloading area or within the preset range of the loading / unloading area, based on the vehicle's real-time trajectory, the vehicle's loading / unloading area, and the waybill grid sequence from the originating point to the unloading point.
[0007] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described real-time prediction method for the empty and full load states of a vehicle through the computer program.
[0008] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program is configured to execute the above-described real-time prediction method for the empty and full load states of a vehicle when it is run.
[0009] The technical solutions provided in this application embodiment may include the following beneficial effects: This application constructs loading / unloading areas and standard transportation routes that reflect the operational patterns of individual vehicles by deeply mining and integrating historical loading / unloading point data and historical waybill trajectory data. It also identifies two typical scenarios—"loading / unloading areas" and "on-the-road"—for empty / full load prediction. By combining and deeply mining historical loading / unloading data and historical waybill data, this application can achieve real-time prediction of vehicle empty / full load status even when real-time waybill data is unavailable, significantly improving the efficiency and timeliness of vehicle dispatching. Attached Figure Description
[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a real-time prediction method for vehicle empty / full load status according to an embodiment of this application; Figure 2 This is a flowchart of a real-time prediction method for vehicle empty / full load status according to an embodiment of this application; Figure 3 This is a schematic diagram of a real-time prediction device for the empty and fully loaded states of a vehicle according to an embodiment of this application. Figure 4 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of this application. Detailed Implementation
[0011] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0012] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0013] The real-time prediction method for vehicle empty / full load status according to embodiments of this application will be described in detail below with reference to the accompanying drawings. Figure 1 As shown, the method mainly includes the following steps: S101 clusters the loading and unloading areas of vehicles based on the loading and unloading point data of vehicles within a preset time period.
[0014] In one implementation, loading and unloading areas of vehicles are clustered based on loading and unloading point data of vehicles within a preset time period. First, the latitude and longitude of the vehicle loading and unloading points, vehicle identification, and parking duration at the loading and unloading points are obtained.
[0015] For example, by acquiring vehicle trajectory data from the past three months, stopping points can be identified based on the trajectory data. These stopping points can then be matched with logistics parks, factories, and other locations to determine loading and unloading points. Information such as the vehicle ID, the latitude and longitude of the loading and unloading point, and the duration of stop at the loading and unloading point can be recorded.
[0016] Furthermore, the latitude and longitude of the loading and unloading points are converted into geographic information grids, and the geographic information grids of each vehicle are clustered separately to obtain the loading and unloading areas of the vehicles.
[0017] In one implementation, the Uber H3 system is used to convert the latitude and longitude of loading and unloading points into discrete, standard-sized geographic information grids. The grid data for each vehicle is then clustered using DBSCAN, with a custom distance function defined as the distance between H3 grids and the number of hexagonal grids spanned, generating clusters. Each cluster represents a loading / unloading area for the vehicle. Vehicles with only one loading / unloading area are filtered out and not included in subsequent predictions.
[0018] Furthermore, the geographic information grid ID with the most loading and unloading points within the loading and unloading area is used as the ID of the loading and unloading area. The H3 grid with the most loading and unloading points within the loading and unloading area is used as the unique ID of the loading and unloading area for that vehicle.
[0019] In one implementation, the method further includes calculating the length of the longest side of the minimum bounding rectangle of all loading and unloading areas of the vehicle, as the long and short distance. Based on the long and short distances and a preset segmentation threshold, the long and short distance attributes of the vehicle are determined.
[0020] Specifically, the length of the longest side of the minimum bounding rectangle of all loading and unloading areas of a vehicle is calculated using the Shapely framework, and the long and short distances are determined based on the length of the long side of the bounding rectangle. The lengths are then segmented according to a threshold, defining long and short distance attributes, which are defined as short, medium, and long distances from smallest to largest, thus obtaining the long and short distance attributes for each vehicle.
[0021] For example: short distance: longer side length ≤ 50 km; medium distance: 50 km < longer side length ≤ 200 km; long distance: longer side length > 200 km. Specific values can be set according to actual conditions, and this application does not impose any restrictions.
[0022] It also includes calculating the median duration of vehicle dwell time at loading and unloading points in each loading and unloading area, which is used as the vehicle loading and unloading time in the loading and unloading area.
[0023] Based on the dwell time of a vehicle at a single loading / unloading point, the median dwell time of all dwell times for the same vehicle within the loading / unloading area is taken as the "standard loading / unloading time" for that vehicle in that area. By calculating the median dwell time, we assign a robust and representative standard operating time to each loading / unloading area. This enables the system to predict critical time points for state transitions, greatly improving the predictability of scheduling and management.
[0024] This application clusters vehicle loading and unloading areas based on vehicle loading and unloading point data within a preset time period. It also includes analyzing the ID of the loading and unloading area, vehicle loading and unloading time, long and short distance, and vehicle long and short distance attributes.
[0025] Based on the historical waybill data and trajectory data of vehicles within a preset time period, S102 obtains the loading and unloading areas corresponding to the origin and unloading locations of the waybills, as well as the waybill grid sequence from the origin to the unloading location.
[0026] In one implementation, the vehicle trajectory data is first converted into a sequence of trajectory grids of different sizes based on the vehicle's distance attributes.
[0027] After acquiring vehicle trajectory sequences within the same timeframe as the loading / unloading point data, a differentiated gridding strategy is adopted based on the vehicle's long / short distance attributes. Using the Uber H3 framework, trajectory points are converted into grid sequences of different sizes according to the vehicle's long / short distance attributes, with the grid size being smaller for short distances than for medium distances, and smaller for medium distances than for long distances. This ensures that the grid granularity matches the typical operational scale of the vehicles.
[0028] Furthermore, by associating the waybill and the vehicle trajectory grid sequence, and based on the fact that the waybill's dispatch start time is less than the vehicle trajectory grid sequence's entry time and the waybill's unloading end time is greater than the vehicle trajectory grid sequence's exit time, the trajectory grid sequence during the waybill's execution period is extracted to obtain the waybill grid sequence.
[0029] Specifically, based on vehicle ID information, the waybill and vehicle trajectory grid sequence are associated to obtain the vehicle trajectory corresponding to the waybill.
[0030] Then, based on the fact that the waybill dispatch start time is less than the vehicle trajectory grid sequence entry time and the waybill unloading end time is greater than the vehicle trajectory grid sequence exit time, the trajectory grid sequence during the waybill execution period is extracted to obtain the waybill grid sequence.
[0031] In an exemplary scenario, the loading and unloading times for a certain waybill are as follows: Loading start time: 8:40; Loading end time: 9:20; Unloading start time: 16:30; Unloading end time: 18:00.
[0032] The vehicle trajectory grid sequence is as follows:
[0033] Based on the fact that the waybill dispatch start time is less than the vehicle trajectory grid sequence entry time and the waybill unloading end time is greater than the vehicle trajectory grid sequence exit time, the trajectory grid sequence during the waybill execution period is extracted, and the resulting grids c, d, e, and f are the extracted waybill grid sequences.
[0034] Furthermore, the latitude and longitude of the shipping location and unloading location on the waybill are converted into a geographic information grid of the same size as the loading and unloading area, and then associated with the loading and unloading area grid to obtain the loading and unloading areas corresponding to the shipping location and unloading location of the waybill.
[0035] The latitude and longitude of the origin and the destination in the waybill data are grid-encoded using the same H3 resolution as when identifying the loading and unloading areas in step S101, to obtain the basic H3 grid corresponding to the origin and destination.
[0036] Subsequently, these basic grids are matched and associated with the vehicle loading / unloading area knowledge base constructed in step S101. If the grid ID of the origin / unloading location of the waybill can match the unique ID of a loading / unloading area corresponding to a certain vehicle, then the origin and destination of the waybill are successfully associated and converted into the identifier of that loading / unloading area. The grids of the loading / unloading areas corresponding to the origin and unloading locations of the waybill are obtained, which means the loading / unloading areas corresponding to the origin and unloading locations of the waybill are obtained.
[0037] Furthermore, waybill grid sequences for the same vehicle, same origin and destination are clustered, and the longest waybill grid sequence is selected from the clustering results as the waybill grid sequence from origin to destination.
[0038] Specifically, waybill grid sequences for the same vehicle and the same origin and destination are aggregated to obtain grid sequences of multiple vehicle trajectories for the same origin and destination. These grid sequences are then clustered, with the distance function defined as 1-Jaccard similarity coefficient, to generate clusters. The longest grid sequence within each cluster is selected as the unique waybill grid sequence for the same origin and destination.
[0039] When the real-time trajectory of the vehicle is within the loading and unloading area or within the preset range of the loading and unloading area, S103 predicts the empty or full load status of the vehicle in the loading and unloading area based on the real-time trajectory of the vehicle, the loading and unloading area of the vehicle, and the loading and unloading area corresponding to the origin and destination of the waybill.
[0040] In one implementation, the real-time trajectory of the vehicle is obtained, and the loading and unloading area is predicted by judging the real-time trajectory. If the current position of the vehicle is within the loading and unloading area identified in step S101 or within a certain distance range, it is considered that the vehicle is currently in the loading and unloading area, and the empty or full load prediction of the loading and unloading area needs to be performed.
[0041] In one implementation, the empty / full load status of the vehicle in the loading / unloading area is predicted based on the vehicle's real-time trajectory, the vehicle's loading / unloading area, and the loading / unloading area corresponding to the origin and destination of the waybill.
[0042] First, it is determined whether a historical waybill exists. If a historical waybill exists, the vehicle's real-time trajectory is used to determine whether the vehicle is in the loading / unloading area corresponding to the origin of the historical waybill or the loading / unloading area corresponding to the unloading location. In the implementation of this application, if a historical waybill exists, the distance is used to determine whether the vehicle is in the loading / unloading area grid associated with the origin of the waybill or the loading / unloading area grid associated with the unloading location of the waybill.
[0043] If the vehicle is in the loading / unloading area corresponding to the shipping location, the vehicle is considered to be fully loaded. If the vehicle is in the loading / unloading area corresponding to the unloading location, the vehicle is considered to be empty.
[0044] In the absence of historical waybills, determine whether the distance from the previous loading / unloading area to the current loading / unloading area in the vehicle trajectory is greater than the preset percentile value of the long and short distance. If it is greater, it is judged as an empty state; if it is less than or equal to, it is judged as a fully loaded state.
[0045] In one embodiment, the distance B from the vehicle to the current loading / unloading area is calculated. If this distance is greater than a certain quantile value of the vehicle's "long and short distance" (e.g., if the vehicle is a long-distance vehicle with a historical trajectory range of A kilometers and a preset quantile of 70%, then B >= A * 70%), the vehicle is inferred to be empty. Otherwise, the vehicle is inferred to be fully loaded.
[0046] In one implementation, the method further includes predicting when a vehicle will be fully loaded and when it will be empty, based on the time the vehicle enters the loading / unloading area and the duration of loading / unloading.
[0047] When a vehicle is determined to be fully loaded, the time when the vehicle is fully loaded is predicted based on the time the vehicle enters the loading and unloading area plus the loading and unloading time of the vehicle in the loading and unloading area. The vehicle status corresponding to the time from the vehicle's entry time to the time when it is fully loaded is determined as the state when it is about to be fully loaded.
[0048] For example, if a vehicle enters the loading / unloading area at 8:00 AM, and the standard loading / unloading time for this area is one hour, then the predicted time for the vehicle to reach full load is 9:00 AM. From the time the vehicle enters until the full load time, it is in a state of almost being fully loaded.
[0049] When a vehicle is determined to be in an empty state, the empty time of the vehicle is predicted based on the time the vehicle enters the loading and unloading area plus the loading and unloading time of the vehicle in the loading and unloading area. The vehicle state corresponding to the period from the vehicle's entry time to the empty time is determined as the state of the vehicle about to be empty.
[0050] For example, if a vehicle enters the loading / unloading area at 12:00, and the standard loading / unloading time for that area is 1 hour, then the predicted empty time for the vehicle is 13:00. From the time the vehicle enters until the empty time, it is in a state of impending emptyness.
[0051] This solution achieves refined status management of vehicles operating within loading and unloading areas by introducing a transitional state of "approaching full load / empty load" and precise termination time prediction. It elevates single, static status judgments to dynamic, time-predictive, and continuous status awareness. This allows the dispatching system to anticipate critical time points for vehicle status transitions, providing crucial decision-making support for accurately allocating loading / unloading resources and optimizing the matching and timing of subsequent waybills, thereby improving operational efficiency.
[0052] When the real-time trajectory of a vehicle is not located within the loading / unloading area or within the preset range of the loading / unloading area, S104 predicts the empty / full load status of the vehicle on the road based on the real-time trajectory of the vehicle, the loading / unloading area of the vehicle, and the waybill grid sequence from the place of origin to the place of unloading.
[0053] The system acquires the vehicle's real-time trajectory. If the vehicle is currently located within the loading / unloading area or within a certain distance, it is considered to be in the loading / unloading area. Otherwise, it is determined that the vehicle is currently on the road, and the road's empty / full load status is predicted.
[0054] In one implementation, the vehicle's empty / full load status on the road is predicted based on the vehicle's real-time trajectory, the vehicle's loading and unloading areas, and the waybill grid sequence from the originating point to the unloading point.
[0055] First, determine whether the vehicle's parking time exceeds a preset threshold. If it does, then determine that the vehicle is in an unloaded state.
[0056] In an exemplary scenario, firstly, it is determined whether the vehicle's parking duration exceeds a preset threshold, for example, whether the parking duration exceeds 36 hours. If it does, it indicates that the vehicle has not performed any transportation tasks and is in a resting state, thus determining that the vehicle is in an empty state. The preset threshold can be set according to actual circumstances, and this embodiment does not impose any restrictions.
[0057] If the stop time is less than or equal to a preset threshold, determine if there are any historical waybills. If historical waybills exist, obtain the actual grid sequence of the vehicle's trajectory from the previous loading / unloading area to the current location; calculate the matching degree between the actual grid sequence and the waybill grid sequence from the origin to the unloading location; if the matching degree is greater than the threshold, determine that the vehicle is in a fully loaded state.
[0058] In this embodiment of the application, the trajectory grid sequence of the vehicle from the previous loading and unloading area to the current point is matched with the "waybill grid sequence from the place of origin to the unloading point" of the waybill generated in step S102. The route similarity can be calculated. If the matching degree exceeds the threshold, it is verified that the vehicle is executing the waybill and the status is confirmed as fully loaded.
[0059] In the absence of historical waybills, the current status is based on the vehicle's empty / full load status in the previous loading / unloading area. That is, the status of the previous area is inherited; if the previous loading / unloading area was empty, it is determined to be empty; if it was full, it is determined to be full. In this embodiment, the identification result is also dynamically corrected based on the vehicle's actual road conditions. The vehicle's mileage is accumulated; if the vehicle's accumulated mileage exceeds a preset percentile value for long / short distance, the vehicle's empty / full load status is changed to full load status in real time.
[0060] Specifically, the cumulative mileage of the vehicle from the previous loading / unloading area to the current point is calculated. If the mileage exceeds a certain percentile value of the vehicle's historical "long and short distances", such as the 80th percentile, it is judged to be fully loaded, indicating that the vehicle is carrying out a long-distance transport without any historical waybill records.
[0061] This solution introduces a dynamic correction mechanism based on real-time mileage, significantly improving the fault tolerance and adaptability of status judgment. When the system determines a vehicle to be empty due to missing waybill data or initial judgment errors, it automatically corrects the status to full load by accumulating the actual mileage and comparing it with long and short distances based on individual operational characteristics, allowing the vehicle to travel a long distance (strongly indicating it is performing a transport task). This enhances the system's robustness and accuracy in complex real-world environments, preventing misjudgments and waste of transport capacity resources.
[0062] To facilitate understanding of the methods provided in the embodiments of this application, the following description is in conjunction with the appendix. Figure 2 Further description.
[0063] like Figure 2 As shown in the flowchart, this clearly illustrates the two-stage architecture of the technical solution in this application. The first stage, offline modeling, focuses on building a knowledge base from raw data: Step 1 generates a personalized loading / unloading area profile (vehicle profile) for each vehicle through clustering; Step 2 extracts the standard transportation route from the shipping location to the unloading location (route profile). The second stage, real-time prediction, utilizes this knowledge base for real-time status assessment: Step 3 predicts the vehicle's status within the loading / unloading area, and Step 4 predicts the vehicle's status on the road. The two prediction steps work together to ultimately output accurate prediction results, including empty / full load status and their duration. The entire process embodies a complete closed loop from learning from historical data to real-time intelligent decision-making.
[0064] This application's technical solution achieves a leap from passive recording to proactive intelligent prediction in vehicle status perception through a complete technical framework combining "historical data mining" and "real-time prediction." In the offline phase, the system mines historical data to form "loading / unloading areas" and "waybill grid sequences" that characterize the operating habits of individual vehicles, laying a solid foundation for accurate judgment. In the real-time prediction phase, the system distinguishes between the two core scenarios of "loading / unloading areas" and "roads," enabling accurate prediction of empty / full load status. This solution effectively reduces reliance on real-time waybill data, providing crucial data support for advanced applications such as intelligent scheduling and capacity optimization, ultimately achieving the industry goal of improving transportation efficiency and reducing empty-load rates.
[0065] According to another aspect of the embodiments of this application, a real-time prediction device for vehicle empty / full load status is also provided for implementing the above-described real-time prediction method for vehicle empty / full load status. For example... Figure 3 As shown, the device includes: The loading and unloading area generation module 301 is used to cluster the loading and unloading points of vehicles within a preset time period to obtain the loading and unloading areas of vehicles. The waybill data processing module 302 is used to obtain the loading and unloading areas corresponding to the origin and unloading location of the waybill, and the waybill grid sequence from the origin to the unloading location, based on the historical waybill data and trajectory data of the vehicle within a preset time period. The empty / full load status prediction module 303 is used to predict the empty / full load status of a vehicle in the loading / unloading area when the real-time trajectory of the vehicle is within the loading / unloading area or within a preset range of the loading / unloading area, based on the real-time trajectory of the vehicle, the loading / unloading area of the vehicle, and the loading / unloading area corresponding to the origin and destination of the waybill. The road empty / full load status prediction module 304 is used to predict the empty / full load status of a vehicle on the road based on the vehicle's real-time trajectory, the vehicle's loading / unloading area, and the waybill grid sequence from the origin to the destination when the vehicle's real-time trajectory is not located within the loading / unloading area or within the preset range of the loading / unloading area.
[0066] It should be noted that the real-time vehicle empty / full load state prediction device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the real-time vehicle empty / full load state prediction method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the real-time vehicle empty / full load state prediction device and the real-time vehicle empty / full load state prediction method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.
[0067] According to another aspect of the embodiments of this application, an electronic device corresponding to the real-time prediction method for vehicle empty / full load status provided in the foregoing embodiments is also provided, so as to execute the real-time prediction method for vehicle empty / full load status.
[0068] Please refer to Figure 4 This illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 4 As shown, the electronic device includes: a processor 400, a memory 401, a bus 402, and a communication interface 403. The processor 400, the communication interface 403, and the memory 401 are connected via the bus 402. The memory 401 stores a computer program that can run on the processor 400. When the processor 400 runs the computer program, it executes the real-time prediction method for the empty and full load status of a vehicle provided in any of the foregoing embodiments of this application.
[0069] The memory 401 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 403 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.
[0070] Bus 402 can be an ISA bus, PCI bus, or EISA bus, etc. Buses can be divided into address buses, data buses, control buses, etc. Memory 401 is used to store programs. After receiving execution instructions, processor 400 executes the programs. The real-time prediction method for vehicle empty / full load status disclosed in any of the aforementioned embodiments of this application can be applied to processor 400, or implemented by processor 400.
[0071] The processor 400 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 400 or by instructions in software form. The processor 400 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may 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. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may 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. The storage medium is located in memory 401. The processor 400 reads the information in memory 401 and, in conjunction with its hardware, completes the steps of the above method.
[0072] The electronic device provided in this application embodiment and the real-time prediction method for vehicle empty / full load status provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate, or implement.
[0073] According to another aspect of the embodiments of this application, a computer-readable storage medium corresponding to the real-time prediction method for the empty and full load status of a vehicle provided in the foregoing embodiments is also provided, wherein a computer program (i.e., a program product) is stored thereon, and when the computer program is run by a processor, it executes the real-time prediction method for the empty and full load status of a vehicle provided in any of the foregoing embodiments.
[0074] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.
[0075] The computer-readable storage medium provided in the above embodiments of this application and the real-time prediction method for vehicle empty / full load status provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run, or implemented by the applications stored therein.
[0076] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0077] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.
Claims
1. A real-time prediction method for vehicle empty / full load status, characterized in that, include: Based on the loading and unloading point data of vehicles within a preset time period, the loading and unloading areas of vehicles are clustered. Based on the historical waybill data and trajectory data of vehicles within a preset time period, the loading and unloading areas corresponding to the origin and unloading locations of the waybills, as well as the waybill grid sequence from the origin to the unloading location, are obtained. When the real-time trajectory of the vehicle is within the loading and unloading area or within the preset range of the loading and unloading area, the empty or full-load status of the vehicle in the loading and unloading area is predicted based on the real-time trajectory of the vehicle, the loading and unloading area of the vehicle, and the loading and unloading area corresponding to the origin and destination of the waybill. When the real-time trajectory of the vehicle is not located within the loading and unloading area or within the preset range of the loading and unloading area, the empty or fully loaded status of the vehicle on the road is predicted based on the real-time trajectory of the vehicle, the loading and unloading area of the vehicle, and the waybill grid sequence from the place of origin to the place of unloading.
2. The method according to claim 1, characterized in that, Based on the loading and unloading point data of vehicles within a preset time period, the loading and unloading areas of vehicles are clustered, including: Obtain the latitude and longitude of the loading and unloading points mentioned by the vehicle, the vehicle identification number, and the duration of the vehicle's stop at the loading and unloading points; The latitude and longitude of the loading and unloading points are converted into geographic information grids, and the geographic information grids of each vehicle are clustered separately to obtain the loading and unloading areas of the vehicles. The geographic information grid ID with the most loading and unloading points in the loading and unloading area is used as the ID of the loading and unloading area.
3. The method according to claim 2, characterized in that, Also includes: Calculate the length of the longest side of the minimum bounding rectangle of all loading and unloading areas of the vehicle, and use it as the long and short distances; Based on the long and short distances and the preset segmentation thresholds, the long and short distance attributes of the vehicle are determined. Calculate the median dwell time of vehicles at loading and unloading points in each loading and unloading area, and use it as the vehicle loading and unloading time of the loading and unloading area.
4. The method according to claim 1, characterized in that, Based on historical waybill data and trajectory data of vehicles within a preset time period, the loading and unloading areas corresponding to the origin and unloading locations of the waybills, and the waybill grid sequence from the origin to the unloading location are obtained, including: Based on the vehicle's distance attributes, the vehicle trajectory data is converted into a sequence of trajectory grids of different sizes; By associating waybills and vehicle trajectory grid sequences, and based on the fact that the waybill's dispatch start time is less than the vehicle trajectory grid sequence's entry time and the waybill's unloading end time is greater than the vehicle trajectory grid sequence's exit time, the trajectory grid sequence during the waybill's execution period is extracted to obtain the waybill grid sequence. The latitude and longitude of the shipping location and the unloading location of the waybill are converted into a geographic information grid of the same size as the loading and unloading area, and then associated with the loading and unloading area grid respectively to obtain the loading and unloading area corresponding to the shipping location and the unloading location of the waybill. The waybill grid sequences of the same vehicle, same origin and destination are clustered, and the longest waybill grid sequence is selected from the clustering results as the waybill grid sequence from the origin to the destination.
5. The method according to claim 1, characterized in that, Based on the vehicle's real-time trajectory, the vehicle's loading and unloading areas, and the loading and unloading areas corresponding to the origin and destination on the waybill, the empty / full load status of the vehicle in the loading and unloading area is predicted, including: In the case of historical waybills, the vehicle is located in the loading and unloading area corresponding to the origin of the historical waybill or the loading and unloading area corresponding to the destination of the unloading, based on the vehicle's real-time trajectory. If the vehicle is in the loading and unloading area corresponding to the place of shipment, the vehicle is judged to be fully loaded; if the vehicle is in the loading and unloading area corresponding to the place of unloading, the vehicle is judged to be empty. In the absence of historical waybills, determine whether the distance from the previous loading / unloading area to the current loading / unloading area in the vehicle trajectory is greater than the preset percentile value of the long and short distance. If it is greater, it is judged as an empty state; if it is less than or equal to, it is judged as a fully loaded state.
6. The method according to claim 5, characterized in that, Also includes: When a vehicle is determined to be fully loaded, the time when the vehicle is fully loaded is predicted based on the time when the vehicle enters the loading and unloading area plus the loading and unloading time of the vehicle in the loading and unloading area. The vehicle status corresponding to the time period from the time the vehicle enters to the time when it is fully loaded is determined as the state when it is about to be fully loaded. When a vehicle is determined to be in an empty state, the empty time of the vehicle is predicted based on the time the vehicle enters the loading and unloading area plus the loading and unloading time of the vehicle in the loading and unloading area. The vehicle state corresponding to the time period from the vehicle's entry time to the empty time is determined as the state of the vehicle about to be empty.
7. The method according to claim 1, characterized in that, Based on the vehicle's real-time trajectory, the vehicle's loading and unloading areas, and the waybill grid sequence from the originating point to the unloading point, the empty / full-load status of the vehicle on the road is predicted, including: Determine if the vehicle's parking time exceeds a preset threshold; if it does, determine that the vehicle is in an unloaded state. If the stop time is less than or equal to a preset threshold, determine whether there are any historical waybills. If historical waybills exist, obtain the actual grid sequence of the vehicle's trajectory transformation from the previous loading / unloading area to the current location; calculate the matching degree between the actual grid sequence and the waybill grid sequence from the origin to the unloading location; if the matching degree is greater than a threshold, it is determined to be a fully loaded state. In the absence of historical waybills, the current status is based on the vehicle's empty or fully loaded status in the previous loading / unloading area. The vehicle's mileage is accumulated. If the vehicle's accumulated mileage is greater than the preset percentile value for long and short distances, the vehicle's empty / fully loaded status is changed to fully loaded status in real time.
8. A real-time prediction device for vehicle empty / full load status, characterized in that, include: The loading and unloading area generation module is used to cluster the loading and unloading points of vehicles within a preset time period to obtain the loading and unloading areas of vehicles. The waybill data processing module is used to obtain the loading and unloading areas corresponding to the origin and unloading location of the waybill, and the waybill grid sequence from the origin to the unloading location, based on the historical waybill data and trajectory data of the vehicle within a preset time period. The loading and unloading area empty / full status prediction module is used to predict the empty / full status of a vehicle in the loading and unloading area when the vehicle's real-time trajectory is within the loading and unloading area or within a preset range of the loading and unloading area, based on the vehicle's real-time trajectory, the vehicle's loading and unloading area, and the loading and unloading areas corresponding to the waybill's origin and destination. The road empty / full load status prediction module is used to predict the empty / full load status of a vehicle on the road when the vehicle's real-time trajectory is not located in the loading / unloading area or within the preset range of the loading / unloading area, based on the vehicle's real-time trajectory, the vehicle's loading / unloading area, and the waybill grid sequence from the originating point to the unloading point.
9. An electronic device, characterized in that, It includes a processor and a memory storing program instructions, the processor being configured to, when executing the program instructions, perform a real-time prediction method for the empty / full load state of a vehicle as described in any one of claims 1 to 7.
10. A computer-readable medium, characterized in that, It stores computer-readable instructions, which are executed by a processor to implement a real-time prediction method for the empty and full load status of a vehicle as described in any one of claims 1 to 7.