Trajectory completion method and device of vehicle, electronic equipment and storage medium

Abstract

The application provides a trajectory completion method and device for a vehicle, electronic equipment and a storage medium. The method comprises the following steps: obtaining running data information of the vehicle during processing of a target transportation task; determining a first data completion result according to the running data information and a first completion method, and determining a second data completion result according to the running data information and a second completion method; wherein the first completion method is a completion method based on data training of the running data information, and the second completion method is a completion method based on filling of the running data information; and determining a target trajectory completion result of the vehicle for processing the target transportation task according to the first data completion result and the second data completion result. According to the technical scheme of the application, the first data completion result is determined by a completion method based on model training, the second data completion result is determined by a completion method based on filling, the target trajectory completion result of the vehicle is determined by fusing the completion results, and the completion accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, apparatus, electronic device, and storage medium for completing vehicle trajectory. Background Technology

[0002] In today's society, with the rapid development and popularization of global positioning technology, mobile Internet technology, and the development of transportation, massive amounts of vehicle trajectory data have been generated.

[0003] Currently, the traditional method of using statistical probability models to complete vehicle trajectory loss is highly dependent on data quality, cannot fully utilize data information during vehicle operation, and has a single completion method, resulting in poor trajectory completion performance. Summary of the Invention

[0004] This invention provides a vehicle trajectory completion method, device, electronic device, and storage medium to address the shortcomings of existing technologies that cannot fully utilize data information during vehicle operation for completion and that the single completion method leads to poor trajectory completion results. The invention achieves a fusion of model training and filling completion methods to determine the target trajectory completion result for the vehicle's target transportation task, thereby improving completion accuracy.

[0005] This invention provides a method for completing the trajectory of a vehicle, comprising the following steps.

[0006] Acquire operational data information of vehicles during the process of handling target transportation tasks.

[0007] The first data completion result is determined based on the running data information and the first completion method, and the second data completion result is determined based on the running data information and the second completion method; wherein, the first completion method is a data training method based on the running data information, and the second completion method is a filling method based on the running data information.

[0008] The target trajectory completion result for the vehicle's target transportation task is determined based on the first data completion result and the second data completion result.

[0009] According to the present invention, a vehicle trajectory completion method is provided, which determines a first data completion result based on operational data information and a first completion method, including: acquiring historical data information of historical transportation tasks; wherein the historical transportation tasks and the target transportation task are of the same type; inputting the historical data information into a basic training model for training to determine the completion model; inputting operational data information into the completion model, and performing data training based on the first completion method to determine the first data completion result.

[0010] According to a vehicle trajectory completion method provided by the present invention, the second completion method includes a mean-filling method or a nearest-neighbor filling method. The method determines a second data completion result based on operational data information and the second completion method, including: determining whether a lost data segment meets a preset threshold based on the operational data information; if the lost data segment meets the preset threshold, determining the second data completion result based on the operational data information and the mean-filling method; if the lost data segment does not meet the preset threshold, determining the second data completion result based on the operational data information and the nearest-neighbor filling method.

[0011] According to a vehicle trajectory completion method provided by the present invention, a second data completion result is determined based on operating data information and a mean-filling method, including: determining the location information of lost data based on the operating data information; obtaining the data loss distance and data loss time based on the location information of lost data; determining a first target speed based on the data loss distance, data loss time, and mean-filling method; and determining the second data completion result based on the first target speed.

[0012] According to a vehicle trajectory completion method provided by the present invention, a second data completion result is determined based on operational data information and a nearest neighbor filling method, including: determining lost data location information based on operational data information; determining a set of nearest neighbor data locations based on the lost data location information; wherein the set of nearest neighbor data locations includes data location information before the data location corresponding to the lost data location information and data location information after the data location corresponding to the lost data location information; obtaining a lost distance weighted average and a lost time weighted average based on the lost data location information and the set of nearest neighbor data locations; determining a second target speed based on the lost distance weighted average, the lost time weighted average, and the nearest neighbor filling method; and determining the second data completion result based on the second target speed.

[0013] According to a vehicle trajectory completion method provided by the present invention, after determining the target trajectory completion result of the vehicle handling the target transportation task based on the first data completion result and the second data completion result, the method further includes: acquiring basic drawing information and drawing tools; wherein, the basic drawing information includes drawing map data; and drawing the trajectory based on the target trajectory completion result, the basic drawing information and the drawing tools to determine the trajectory result.

[0014] According to the present invention, a vehicle trajectory completion method includes, after drawing the trajectory based on the target trajectory completion result, drawing basic information and drawing tools, and determining the trajectory result, the method further includes: obtaining the actual number of check-in trips; determining the trajectory trips based on the trajectory result; determining the trip verification result based on the actual number of check-in trips and the trajectory trips; and monitoring the vehicle transportation trips based on the verification result.

[0015] The present invention also provides a vehicle trajectory completion device, comprising the following modules.

[0016] The information acquisition module is used to acquire operational data information of the vehicle during the process of handling the target transportation task.

[0017] The result determination module is used to determine the first data completion result based on the running data information and the first completion method, and to determine the second data completion result based on the running data information and the second completion method; wherein, the first completion method is a data training completion method based on the running data information, and the second completion method is a filling completion method based on the running data information.

[0018] The trajectory determination module is used to determine the target trajectory completion result of the vehicle's target transportation task based on the first data completion result and the second data completion result.

[0019] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the trajectory completion method for any of the above-described vehicles.

[0020] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the trajectory completion method for any of the vehicles described above.

[0021] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the trajectory completion method for any of the vehicles described above.

[0022] This invention provides a vehicle trajectory completion method, apparatus, electronic device, and storage medium. It acquires operational data information of the vehicle during the processing of a target transportation task; determines a first data completion result based on the operational data information and a first completion method; and determines a second data completion result based on the operational data information and a second completion method. The first completion method is a data training method based on the operational data information, and the second completion method is a filling method based on the operational data information. The target trajectory completion result for the vehicle's processing of the target transportation task is determined based on the first and second data completion results. The technical solution of this invention determines the first data completion result through a model-trained completion method and the second data completion result through a filling method. By fusing the completion results, the target trajectory completion result of the vehicle is determined, improving the completion accuracy. This addresses the shortcomings of existing technologies that cannot fully utilize data information from the vehicle's operation for completion and that rely on a single completion method, resulting in poor trajectory completion effects. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in this invention 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 some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is one of the flowcharts illustrating the vehicle trajectory completion method provided by the present invention.

[0025] Figure 2 This is the second flowchart illustrating the vehicle trajectory completion method provided by the present invention.

[0026] Figure 3 This is a schematic diagram of the vehicle trajectory completion device provided by the present invention.

[0027] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0029] The following is combined with Figures 1-2 The present invention describes a vehicle trajectory completion method, which is applicable to real-time vehicle trajectory completion. The execution subject of this method can be an electronic device or a vehicle trajectory completion device installed in the electronic device. The vehicle trajectory completion device can be implemented by software, hardware, or a combination of both. Figure 1 This is one of the flowcharts illustrating the vehicle trajectory completion method provided by the present invention, such as... Figure 1 As shown, the method includes the following steps.

[0030] Step 101: Obtain the vehicle's operational data information during the process of handling the target transportation task.

[0031] In this step, the target transportation task is a pre-acquired processing task. The operational data information includes the vehicle's operating speed, operating status, operating trajectory, and number of trips during the processing of the target transportation task; this embodiment does not limit these aspects.

[0032] In this step, operational data is acquired by the vehicle's onboard telematics BOX (T-BOX) and uploaded to the cloud. The cloud then pushes the data to the big data server, enabling the server to access the operational data. The cloud serves as the database port for vehicle data collection. The big data server is the platform for processing the data, handling all data filing and processing.

[0033] Specifically, when a vehicle acquires and processes a target transportation task, it reports operational data such as vehicle location signal, speed, status, trajectory, and number of trips during the process through its onboard T-BOX.

[0034] Step 102: Determine the first data completion result based on the running data information and the first completion method, and determine the second data completion result based on the running data information and the second completion method.

[0035] In this step, the first completion method is a data training method based on runtime data information. Specifically, the first completion method is a data training method determined on the server for missing data determined based on runtime data information. The second completion method is a filling method based on runtime data information. Specifically, the second completion method is a filling method determined on the terminal for missing data determined based on runtime data information.

[0036] Specifically, after acquiring the vehicle's operational data, a first data completion result is determined based on a first completion method, and a second data completion result is determined based on a second completion method. Specifically, based on the first completion method, the vehicle's operational data is input into a basic training model for training. This basic training model could be, for example, a Long Short-Term Memory (LSTM) network model. The LSTM model is used to standardize the vehicle's operational data, and then the standardized operational data is used for model training to ultimately determine the first data completion result. Based on the second completion method, data is filled in according to the vehicle's operational data to determine the second data completion result.

[0037] For example, the electronic device can also be a trajectory completion system, which may include an in-vehicle T-BOX, a server, a terminal, and a cloud. The cloud is connected to both the in-vehicle T-BOX and the server. The in-vehicle T-BOX is used to acquire operational data information of the vehicle during the handling of the target transportation task, and the cloud is used to store and archive the operational data information. The server has an agreement with the cloud and can acquire the operational data information from the cloud. Then, in the server, a completion method determined by data training is performed on the missing data determined based on the operational data information, and a first data completion result is determined based on the operational data information and the first completion method. The terminal is connected to the server and can acquire the operational data information from the server. In the terminal, a completion method determined by filling the missing data determined based on the operational data information is performed, and a second data completion result is determined based on the operational data information and the second completion method. This embodiment does not limit this aspect.

[0038] Step 103: Determine the target trajectory completion result of the vehicle's target transportation task based on the first data completion result and the second data completion result.

[0039] Specifically, after determining the first data completion result and the second data completion result, the first data completion result and the second data completion result are merged to determine the target trajectory completion result of the vehicle's target transportation task.

[0040] This invention provides a vehicle trajectory completion method. It acquires operational data information of the vehicle during the processing of a target transportation task; determines a first data completion result based on the operational data information and a first completion method; and determines a second data completion result based on the operational data information and a second completion method. The first completion method is a data training method based on the operational data information, and the second completion method is a filling method based on the operational data information. The target trajectory completion result for the vehicle's processing of the target transportation task is determined based on the first and second data completion results. Building upon the above embodiments, the technical solution of this invention determines the first data completion result through a model-trained completion method and the second data completion result through a filling method. By fusing the completion results, the target trajectory completion result of the vehicle is determined, improving the completion accuracy. This addresses the shortcomings of existing technologies that cannot fully utilize data information from the vehicle's operation for completion and that rely on a single completion method, resulting in poor trajectory completion effects.

[0041] Figure 2This is the second flowchart illustrating the vehicle trajectory completion method provided by the present invention. The vehicle trajectory completion method provided by the present invention is applicable to real-time vehicle trajectory completion. The executing entity of this method can be an electronic device or a vehicle trajectory completion device installed in that electronic device. This vehicle trajectory completion device can be implemented through software, hardware, or a combination of both. Figure 2 As shown, the method further optimizes the determination of the first data completion result based on the running data information and the first completion method, and the determination of the second data completion result based on the running data information and the second completion method. The method includes the following steps.

[0042] Step 201: Obtain the vehicle's operational data information during the process of handling the target transportation task.

[0043] Specifically, when a vehicle acquires and processes a target transportation task, it acquires operational data information such as the vehicle's speed, status, trajectory, and number of trips during the task processing.

[0044] Step 202: Obtain historical data information of historical transportation tasks.

[0045] In this step, the historical transportation task and the target transportation task are of the same type. Historical data information refers to the number of trips, transportation speed, transportation time, etc., of the vehicle for the historical transportation task, as well as the task data of the historical transportation task, such as the task volume, when processing the historical transportation task. This embodiment does not limit this.

[0046] Specifically, identify historical transportation tasks that are similar to the target transportation task, and obtain historical data information such as the number of trips, transportation speed, transportation time, and task volume of the historical transportation tasks.

[0047] Step 203: Input historical data information into the basic training model to train and determine the complete model.

[0048] In this step, the base training model can be, for example, an LSTM model; this embodiment does not limit this. The completion model is a model determined through training using historical data and the base training model.

[0049] Specifically, after determining the historical data information, the historical data information is input into the basic training model for training, and the complete model is determined through multiple training iterations.

[0050] Step 204: Input the running data information into the completion model, and train the data based on the first completion method to determine the first data completion result.

[0051] In this step, the first completion method is a completion method based on data training using runtime data information.

[0052] Specifically, after determining the completion model, the running data information is input into the completion model. Based on the first completion method, the data is first standardized, and then the standardized running data information is trained. During the training process, the mean squared error (MSE) is used as the loss function, and the Adam optimizer is used to optimize the model, thereby training and determining the first data completion result.

[0053] Step 205: Determine whether the lost data segment meets the preset threshold based on the running data information.

[0054] In this step, the preset threshold is a pre-set threshold used to determine the length of the missing data segment in the running data information. This embodiment does not limit this.

[0055] Specifically, after determining the running data information, the lost data segment is determined by the location information of the running data information. If the lost data segment meets the preset threshold, then step 206 is executed; if the lost data segment does not meet the preset threshold, then step 207 is executed.

[0056] For example, if the acquisition of operational data information is performed within a preset period, meaning the location information in the acquired operational data information corresponds to the preset period, and the preset period is determined to be 5 times (e.g., A, B, C, D, and E), the acquired operational data information should contain data corresponding to the 5 location information A, B, C, D, and E. If the current operational data information includes data corresponding to location information A, B, D, and E, then the lost data segment is determined to be the data information between B and D. If the preset threshold is determined to be one preset period, then the lost data segments B and D meet the preset threshold, and step 206 continues; if the current operational data information includes data corresponding to location information A and E, then the lost data segment is determined to be the data information between A and E. If the preset threshold is determined to be one preset period, then the lost data segments A and E do not meet the preset threshold, and step 207 continues.

[0057] Step 206: Determine the second data completion result based on the running data information and the mean filling method.

[0058] In this step, the second completion method is a completion method based on runtime data information; the second completion method includes mean filling or nearest neighbor filling.

[0059] Specifically, if the missing data segment meets the preset threshold, the second data completion result is determined based on the running data information and the mean filling method.

[0060] In one specific implementation, the second data completion result is determined based on the running data information and the mean-filling method. The specific implementation steps are as follows: determine the location information of the lost data based on the running data information; obtain the data loss distance and data loss time based on the location information of the lost data; determine the first target speed based on the data loss distance, data loss time and mean-filling method; and determine the second data completion result based on the first target speed.

[0061] Specifically, after acquiring operational data, the location of lost data is determined based on a preset period for acquiring the operational data. It is then determined whether all corresponding operational data has been acquired within the preset period. If not all data corresponding to the preset period is acquired, it is determined that the missing data for that period has been lost, and the location of the lost data is locked. The data loss distance and time are obtained based on the location of the lost data. A first target speed is determined based on the data loss distance, data loss time, and average padding method. Finally, a second data completion result is determined based on the first target speed.

[0062] For example, when the preset cycle is determined to be 5 times, such as A, B, C, D, and E, the acquired operational data information should include data information corresponding to the 5 location information A, B, C, D, and E. If it is determined that the current operational data information includes data information corresponding to location information A, B, D, and E, then the lost data segment is determined to be the data information between B and D. When the preset threshold is determined to be a preset period, if the lost data segments B and D meet the preset threshold, then step 206 continues. The missing data location information is determined based on the data information between the missing data segments B and D. The first acquisition time corresponding to the running data information B and the second acquisition time corresponding to the running data information D are determined. The data loss time is determined based on the time difference between the second acquisition time and the first acquisition time. The first location information corresponding to the running data information B and the second location information corresponding to the running data information D are determined. The data loss time is determined based on the time difference between the second location information and the first location information. Then, the vehicle loss speed is determined by the quotient of the data loss distance and the data loss time. The first target speed is determined by averaging the vehicle loss speed and the average filling method. Finally, the missing data location information is filled based on the first target speed to determine the second data completion result.

[0063] Step 207: Determine the second data completion result based on the running data information and the nearest neighbor filling method.

[0064] Specifically, if the missing data segment does not meet the preset threshold, the second data completion result is determined based on the running data information and the nearest neighbor filling method.

[0065] In one specific implementation, the second data completion result is determined based on the running data information and the nearest neighbor filling method. The specific implementation steps are as follows: determine the location information of the lost data based on the running data information; determine the set of nearest neighbor data locations based on the location information of the lost data; wherein, the set of nearest neighbor data locations includes the data location information before the data location corresponding to the lost data location information and the data location information after the data location corresponding to the lost data location information; obtain the loss distance weighted and loss time weighted based on the loss data location information and the set of nearest neighbor data locations; determine the second target speed based on the loss distance weighted, loss time weighted and nearest neighbor filling method; and determine the second data completion result based on the second target speed.

[0066] Specifically, after acquiring operational data information, the location information of lost data is determined according to a preset period for acquiring operational data information. It is then determined whether the corresponding operational data information has been acquired within the preset period. If not all data corresponding to the preset period is acquired, then the set of nearest neighbor data locations is determined based on the location information of lost data. The set of nearest neighbor data locations includes the data location information before and after the data location corresponding to the location information of lost data. The distance-weighted and time-weighted loss values ​​are obtained based on the location information of lost data and the set of nearest neighbor data. The second target speed is determined based on the distance-weighted loss value, the time-weighted loss value, and the nearest neighbor filling method. The second data completion result is determined based on the second target speed.

[0067] For example, when the preset period is determined to be 8 times, such as A, B, C, D, E, F, G, and H, the acquired running data information should include data information corresponding to the four location information A, B, C, F, G, and H. If it is determined that the current running data information includes data information corresponding to the location information A, B, C, F, G, and H, then the lost data segment is determined to be the data information between C and F. When the preset threshold is determined to be one preset period, it is determined that the lost data segments C and F do not meet the preset threshold, so step 207 is continued. The lost data location information is determined based on the data information between C and F. The nearest neighbor data location set information is determined based on the lost data location information, where the nearest neighbor data location set information includes the data location information before the data location corresponding to the lost data location information and the data location information after the data location corresponding to the lost data location information. At this time, the nearest neighbor data location set information includes the data location information before the lost data segment C, i.e., A and B, and also includes the data location information after the lost data segment F, i.e., G and H. The loss distances from A to F, B to F, C to F, C to G, and C to H are determined, along with the loss times from A to F, B to F, C to F, C to G, and C to H. A weighted average for loss distance is then determined based on these distances. Similarly, a weighted average for loss time is determined based on these time values. The second target speed is then determined based on the quotient of the weighted averages for loss distance and loss time, along with the nearest neighbor filling method. Finally, data filling is performed on the lost data segment between C and F according to the second target speed, thus determining the second data completion result.

[0068] The advantage of this setting is that different padding methods can be selected to complete the data based on the length of the missing data segment, thereby improving the accuracy of data completion.

[0069] In one specific implementation, the execution of steps 202-204 and steps 205-207 is not sequential. Steps 202-204 can be executed first, followed by steps 205-207; or steps 205-207 can be executed first, followed by steps 202-204; or steps 202-204 and steps 205-207 can be executed simultaneously. This embodiment does not limit this.

[0070] Step 208: Determine the target trajectory completion result of the vehicle's target transportation task based on the first data completion result and the second data completion result.

[0071] Specifically, after determining the first data completion result and the second data completion result, the first data completion result and the second data completion result are merged to determine the target trajectory completion result of the vehicle's target transportation task.

[0072] The advantage of this setup is that by merging the first and second data completion results, the accuracy of the target estimation completion result is improved.

[0073] Step 209: Obtain basic drawing information and drawing tools.

[0074] In this step, drawing basic information includes drawing map data, and the drawing tool is one that can draw trajectories.

[0075] Specifically, obtain the basic information for drawing, including the data for drawing the map, and determine the drawing tools that can be used for trajectory drawing.

[0076] Step 210: Draw the trajectory based on the target trajectory completion result, basic information, and drawing tools, and determine the trajectory result.

[0077] Specifically, after determining the target trajectory completion result of the vehicle, the trajectory is drawn using drawing tools and the target trajectory completion result, based on the basic drawing information, thereby determining the trajectory result of the vehicle completing the target transportation task.

[0078] In one specific implementation, after drawing the trajectory based on the target trajectory completion result, drawing basic information and drawing tools, and determining the trajectory result, the method further includes: obtaining the actual number of check-in trips; determining the trajectory trips based on the trajectory result; determining the trip verification result based on the actual number of check-in trips and the trajectory trips; and monitoring the vehicle transportation trips based on the verification result.

[0079] In this step, the actual number of check-ins is the number of trips automatically recorded by the driver on the vehicle when transporting the target transportation task, and the number of track trips is the number of trips the vehicle completed to complete the target transportation task after supplementing the recorded vehicle operation data information.

[0080] Specifically, the actual number of clock-in trips is obtained, and the route trips are determined based on the trajectory results. A trip verification result is determined based on the actual number of clock-in trips and the route trips to verify if they match. If they match, the verification result is considered true, and vehicle transport trips continue to be monitored. If they do not match, the verification result is considered false, indicating an anomaly in the actual clock-in trips. Based on this false result, vehicle transport trips are monitored, and an alert is issued to alert monitoring personnel that the actual clock-in trips of the vehicles are abnormal.

[0081] The advantage of this setup is that it allows for real-time monitoring of the actual number of trips a vehicle makes while performing its target transportation task, ensuring the authenticity of the trips and improving the safety of the vehicle in completing the target transportation task.

[0082] In one specific implementation, the number of trajectory trips can also be visualized, improving the user experience for monitoring personnel.

[0083] This invention provides a vehicle trajectory completion method, which involves: acquiring vehicle operation data during the handling of a target transportation task; acquiring historical data of historical transportation tasks; inputting the historical data into a basic training model to train and determine a completion model; inputting the operation data into the completion model and training it based on a first completion method to determine a first data completion result; determining whether a lost data segment meets a preset threshold based on the operation data; after determining the operation data, determining the lost data segment using the location information of the operation data; if the lost data segment meets the preset threshold, determining a second data completion result based on the operation data and a mean-filling method; if the lost data segment does not meet the preset threshold, determining a second data completion result based on the operation data and a nearest-neighbor filling method; determining the target trajectory completion result of the vehicle handling the target transportation task based on the first and second data completion results; acquiring basic drawing information and drawing tools; and drawing the trajectory based on the target trajectory completion result, the basic drawing information, and the drawing tools to determine the trajectory result. Based on the above embodiments, the technical solution of the present invention determines the first data completion result through a model training completion method and the second data completion result through a filling completion method. By fusing the completion results, the target trajectory completion result of the vehicle is determined, thereby improving the completion accuracy. This addresses the shortcomings of existing technologies, which cannot fully utilize data information during vehicle operation for completion and employ a single completion method, resulting in poor trajectory completion effects. Furthermore, the trajectory is drawn based on the target trajectory completion result to determine the trajectory result, and the trajectory trips are determined through the trajectory. Based on the trajectory trips, the actual number of trips taken by the vehicle when performing the target transportation task is monitored in a timely manner to ensure the authenticity of the trips and improve the safety of the vehicle in completing the target transportation task.

[0084] The vehicle trajectory completion device provided by the present invention will be described below. The vehicle trajectory completion device described below can be referred to in correspondence with the vehicle trajectory completion method described above.

[0085] Figure 3 This is a schematic diagram of the vehicle trajectory completion device provided by the present invention, with reference to... Figure 3 As shown, the vehicle trajectory completion device 300 includes: an information acquisition module 301, a result determination module 302, and a trajectory determination module 303.

[0086] The information acquisition module 301 is used to acquire the vehicle's operational data information during the process of handling the target transportation task.

[0087] The result determination module 302 is used to determine a first data completion result based on the running data information and the first completion method, and to determine a second data completion result based on the running data information and the second completion method; wherein, the first completion method is a data training completion method based on the running data information, and the second completion method is a filling completion method based on the running data information.

[0088] The trajectory determination module 303 is used to determine the target trajectory completion result of the vehicle's target transportation task based on the first data completion result and the second data completion result.

[0089] In one example embodiment, the result determination module 302 determines the first data completion result based on the running data information and the first completion method. Specifically, it is used to: obtain historical data information of historical transportation tasks; wherein the historical transportation tasks and the target transportation task are of the same type; input the historical data information into the basic training model for training to determine the completion model; input the running data information into the completion model, and perform data training based on the first completion method to determine the first data completion result.

[0090] In one example embodiment, the second completion method includes mean fill or nearest neighbor fill.

[0091] In one example embodiment, the result determination module 302 determines the second data completion result based on the running data information and the second completion method. Specifically, it is used to: determine whether the lost data segment meets the preset threshold based on the running data information; if the lost data segment meets the preset threshold, determine the second data completion result based on the running data information and the mean filling method; if the lost data segment does not meet the preset threshold, determine the second data completion result based on the running data information and the nearest neighbor filling method.

[0092] In one example embodiment, the result determination module 302 determines a second data completion result based on the running data information and the mean filling method, specifically for: determining the location information of lost data based on the running data information; obtaining the data loss distance and data loss time based on the location information of lost data; determining a first target speed based on the data loss distance, data loss time and mean filling method; and determining the second data completion result based on the first target speed.

[0093] In one example embodiment, the result determination module 302 determines a second data completion result based on the running data information and the nearest neighbor filling method. Specifically, it is used to: determine the location information of lost data based on the running data information; determine the set information of nearest neighbor data locations based on the location information of lost data; wherein, the set information of nearest neighbor data locations includes the data location information before the data location corresponding to the location information of lost data and the data location information after the data location corresponding to the location information of lost data; obtain the weighted average of lost distance and the weighted average of lost time based on the location information of lost data and the set information of nearest neighbor data; determine a second target speed based on the weighted average of lost distance, the weighted average of lost time, and the nearest neighbor filling method; and determine the second data completion result based on the second target speed.

[0094] In one example embodiment, the device further includes a trajectory determination module. The trajectory determination module is configured to: after determining the target trajectory completion result for the vehicle's handling of the target transportation task based on the first data completion result and the second data completion result, acquire basic drawing information and drawing tools; wherein the basic drawing information includes map data; and perform trajectory drawing based on the target trajectory completion result, the basic drawing information, and the drawing tools to determine the trajectory result.

[0095] In one example embodiment, the device further includes a trip monitoring module. The trip monitoring module is used to: obtain the actual number of check-ins after drawing the trajectory based on the target trajectory completion result, drawing basic information, and drawing tools, and determining the trajectory result; determine the trajectory trips based on the trajectory result; determine the trip verification result based on the actual check-ins and the trajectory trips; and monitor the vehicle transportation trips based on the verification result.

[0096] The apparatus of this embodiment can be used to execute the method of any embodiment in the vehicle trajectory completion method side embodiment. Its specific implementation process and technical effects are similar to those in the vehicle trajectory completion method side embodiment. For details, please refer to the detailed description in the vehicle trajectory completion method side embodiment, which will not be repeated here.

[0097] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 4As shown, the electronic device may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a vehicle trajectory completion method. This method includes: acquiring operational data information of the vehicle during the processing of a target transportation task; determining a first data completion result based on the operational data information and a first completion method, and determining a second data completion result based on the operational data information and a second completion method; wherein the first completion method is a data training method based on the operational data information, and the second completion method is a filling method based on the operational data information; and determining the target trajectory completion result of the vehicle processing the target transportation task based on the first and second data completion results.

[0098] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes 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 of the various embodiments of the present invention. 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.

[0099] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle trajectory completion method provided by the above methods. The method includes: acquiring operational data information of the vehicle during the process of handling a target transportation task; determining a first data completion result based on the operational data information and a first completion method, and determining a second data completion result based on the operational data information and a second completion method; wherein the first completion method is a completion method based on data training using operational data information, and the second completion method is a completion method based on filling in operational data information; and determining the target trajectory completion result of the vehicle handling the target transportation task based on the first data completion result and the second data completion result.

[0100] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a vehicle trajectory completion method provided by the methods described above. This method includes: acquiring operational data information of the vehicle during the process of handling a target transportation task; determining a first data completion result based on the operational data information and a first completion method, and determining a second data completion result based on the operational data information and a second completion method; wherein the first completion method is a data training method based on the operational data information, and the second completion method is a filling method based on the operational data information; and determining the target trajectory completion result of the vehicle handling the target transportation task based on the first data completion result and the second data completion result.

[0101] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0102] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for completing the trajectory of a vehicle, characterized in that, include: Acquire operational data information of vehicles during the process of handling target transportation tasks; A first data completion result is determined based on the runtime data information and the first completion method, and a second data completion result is determined based on the runtime data information and the second completion method; wherein, the first completion method is a data training method based on the runtime data information, and the second completion method is a filling method based on the runtime data information; the second completion method includes a mean filling method or a nearest neighbor filling method, and determining the second data completion result based on the runtime data information and the second completion method includes: determining whether the lost data segment meets a preset threshold based on the runtime data information; if the lost data segment meets the preset threshold, then determining the second data completion result based on the runtime data information and the mean filling method; if the lost data segment does not meet the preset threshold, then determining the second data completion result based on the runtime data information and the nearest neighbor filling method. The target trajectory completion result for the vehicle to process the target transportation task is determined based on the first data completion result and the second data completion result.

2. The vehicle trajectory completion method according to claim 1, characterized in that, The step of determining the first data completion result based on the running data information and the first completion method includes: Obtain historical data information of historical transportation tasks; wherein, the historical transportation tasks and the target transportation task are of the same type; The historical data information is input into the basic training model to train and determine the complete model; The running data information is input into the completion model, and the data is trained based on the first completion method to determine the first data completion result.

3. The vehicle trajectory completion method according to claim 1, characterized in that, Determining the second data completion result based on the running data information and the mean filling method includes: The location information of the lost data is determined based on the aforementioned operational data information; The data loss distance and data loss time are obtained based on the location information of the lost data. The first target speed is determined based on the data loss distance, the data loss time, and the mean padding method. The second data completion result is determined based on the first target speed.

4. The vehicle trajectory completion method according to claim 1, characterized in that, Determining the second data completion result based on the running data information and the nearest neighbor filling method includes: The location information of the lost data is determined based on the aforementioned operational data information; The nearest neighbor data location set information is determined based on the lost data location information; wherein, the nearest neighbor data location set information includes data location information before the data location corresponding to the lost data location information and data location information after the data location corresponding to the lost data location information; Based on the location information of the lost data and the location set information of the nearest data, obtain the distance-weighted and time-weighted loss values; The second target velocity is determined based on the loss distance weighting, the loss time weighting, and the nearest neighbor filling method; The second data completion result is determined based on the second target speed.

5. The vehicle trajectory completion method according to claim 1, characterized in that, After determining the target trajectory completion result for the vehicle to process the target transportation task based on the first data completion result and the second data completion result, the method further includes: Obtain basic drawing information and drawing tools; wherein, the basic drawing information includes map data; Based on the target trajectory completion result, the basic drawing information, and the drawing tool, the trajectory is drawn, and the trajectory result is determined.

6. The vehicle trajectory completion method according to claim 5, characterized in that, After determining the trajectory result by drawing the trajectory based on the target trajectory completion result, the drawing basic information, and the drawing tool, the method further includes: Obtain the actual number of check-ins; The number of trajectory passes is determined based on the trajectory results; The trip verification result is determined based on the actual number of check-ins and the number of trips on the track. The vehicle transport trips are monitored based on the calibration results.

7. A vehicle trajectory completion device, characterized in that, include: The information acquisition module is used to acquire operational data information of the vehicle during the process of handling the target transportation task; The result determination module is used to determine a first data completion result based on the running data information and a first completion method, and to determine a second data completion result based on the running data information and a second completion method; wherein, the first completion method is a completion method based on data training using the running data information, and the second completion method is a completion method based on filling in the running data information; the second completion method includes a mean filling method or a nearest neighbor filling method, and determining the second data completion result based on the running data information and the second completion method includes: determining whether the lost data segment meets a preset threshold based on the running data information; if the lost data segment meets the preset threshold, then determining the second data completion result based on the running data information and the mean filling method; if the lost data segment does not meet the preset threshold, then determining the second data completion result based on the running data information and the nearest neighbor filling method. The trajectory determination module is used to determine the target trajectory completion result of the vehicle processing the target transportation task based on the first data completion result and the second data completion result.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the trajectory completion method for the vehicle as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the trajectory completion method for the vehicle as described in any one of claims 1 to 6.

Images