CN114584584A - System and method for processing vehicle driving data and storage medium - Google Patents
System and method for processing vehicle driving data and storage medium Download PDFInfo
- Publication number
- CN114584584A CN114584584A CN202210190866.8A CN202210190866A CN114584584A CN 114584584 A CN114584584 A CN 114584584A CN 202210190866 A CN202210190866 A CN 202210190866A CN 114584584 A CN114584584 A CN 114584584A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- target monitoring
- server
- monitoring data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a system and a method for processing vehicle driving data and a storage medium, relates to the technical field of data processing, and solves the problem of low vehicle control accuracy. The system comprises: the system comprises at least one vehicle terminal, a receiving server, a storage server and an operation server, wherein a plurality of vehicle algorithms are stored in the storage server; the vehicle terminal is used for acquiring target monitoring data of the vehicle and sending the target monitoring data to the receiving server, and the target monitoring data is used for indicating the target data in the driving process of the vehicle; the receiving server is used for receiving target monitoring data; the operation server is used for calling the target monitoring data and the plurality of vehicle algorithms, optimizing each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and sending the plurality of optimized vehicle algorithms to the vehicle terminal through the receiving server; and the vehicle terminal is used for controlling the vehicle by using the optimized vehicle algorithm.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a system and a method for processing vehicle driving data, and a storage medium.
Background
With the development of artificial intelligence technology, multi-sensor fusion technology and control decision technology, automatic driving technology and auxiliary driving gradually enter the daily life of people, and the travel mode of people is changed in a profound way. Among them, processing of travel data relating to automatic driving or driving assistance of a vehicle plays an important role in automatic driving technology.
In the prior art, generally, acquired vehicle driving related data is stored in a cloud server, and vehicle related data is processed and processed in the cloud server, but such data processing cannot be effectively used for accurately controlling a vehicle, and the problem that the vehicle control accuracy is not high exists.
Disclosure of Invention
The invention provides a processing system, a processing method and a storage medium of vehicle running data, which can improve the control accuracy of a vehicle.
In a first aspect of the embodiments of the present application, a system for processing vehicle driving data is provided, the system including: at least one vehicle terminal and local server cluster, local server cluster includes: the system comprises a receiving server, a storage server and an operation server, wherein a plurality of vehicle algorithms are stored in the storage server;
the vehicle terminal is used for acquiring target monitoring data of the vehicle and sending the target monitoring data to the receiving server, and the target monitoring data are used for indicating the target data in the driving process of the vehicle;
the receiving server is used for receiving target monitoring data;
the operation server is used for calling the target monitoring data and the plurality of vehicle algorithms, optimizing each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and sending the plurality of optimized vehicle algorithms to the vehicle terminal through the receiving server;
and the vehicle terminal is used for controlling the vehicle by using the optimized vehicle algorithm.
In one embodiment, the system further comprises a cloud server, and the vehicle terminal is further configured to:
sending a connection request to a receiving server, and acquiring the sending times of the current connection request, wherein the connection request is used for requesting to establish connection with the receiving server;
if the sending times are smaller than a preset threshold value, sending the target monitoring data to a receiving server;
and if the sending times are larger than a preset threshold value, sending the target monitoring data to a cloud server for caching.
In one embodiment, the cloud server is further configured to:
and sending the cached target monitoring data to a receiving server within a preset time after the target monitoring data is received.
In one embodiment, the receiving server is further configured to set an access right for the target monitoring data, obtain the isolated target monitoring data, and send the isolated target monitoring data to the storage server;
the storage server is further configured to: and receiving the isolated target monitoring data, and performing distributed storage on the isolated target monitoring data.
In one embodiment, the target monitoring data includes data for a plurality of attribute characteristics of the vehicle;
the storage server is used for extracting information of each attribute feature data in the target monitoring data sent by each vehicle to obtain feature information corresponding to each data, and dividing the data with the same feature information into a data set;
and the operation server is specifically used for acquiring target characteristic information corresponding to each vehicle algorithm, calling a target data set corresponding to the target characteristic information, and performing optimization processing on each vehicle algorithm by using data in the target data set, wherein the target characteristic information corresponding to each vehicle algorithm is the same or different.
In one embodiment, the calculation server comprises at least one container, and each container is used for optimizing at least one vehicle algorithm.
In one embodiment, the receiving server includes a plurality of servers, and each server includes a load balancing program for performing load balancing processing on the received connection request.
In a second aspect of the embodiments of the present application, a method for processing vehicle driving data is provided, where the method includes:
the method comprises the steps that a vehicle terminal obtains target monitoring data of a vehicle and sends the target monitoring data to a receiving server, wherein the target monitoring data are used for indicating the target data in the vehicle running process;
receiving target monitoring data by a receiving server;
the operation server calls the target monitoring data and the plurality of vehicle algorithms, optimizes each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and sends the plurality of optimized vehicle algorithms to the vehicle terminal through the receiving server;
and the vehicle terminal controls the vehicle by using the optimized vehicle algorithm.
In one embodiment, the method further comprises:
the vehicle terminal sends a connection request to a receiving server and acquires the sending times of the current connection request, wherein the connection request is used for requesting to establish connection with the receiving server;
if the sending times are smaller than a preset threshold value, sending the target monitoring data to a receiving server;
and if the sending times are larger than a preset threshold value, sending the target monitoring data to a cloud server for caching.
In one embodiment, the method further comprises: and the cloud server sends the cached target monitoring data to the receiving server within the preset time after receiving the target monitoring data.
In one embodiment, after the receiving server receives the target monitoring data, the method further comprises: the receiving server sets access authority for the target monitoring data to obtain isolated target monitoring data, and sends the isolated target monitoring data to the storage server;
and the storage server receives the isolated target monitoring data and performs distributed storage on the isolated target monitoring data.
In one embodiment, the target monitoring data includes data for a plurality of attribute characteristics of the vehicle, the method further comprising:
the storage server extracts information of each attribute feature data in the target monitoring data sent by each vehicle to obtain feature information corresponding to each data, and divides the data with the same feature information into a data set;
and optimizing each vehicle algorithm by using the target monitoring data, wherein the optimization comprises the following steps:
the operation server obtains target characteristic information corresponding to each vehicle algorithm, calls a target data set corresponding to the target characteristic information, and performs optimization processing on each vehicle algorithm by using data in the target data set, wherein the target characteristic information corresponding to each vehicle algorithm is the same or different.
In a third aspect of the embodiments of the present application, there is provided a computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the method for processing vehicle travel data of the second aspect of the embodiments of the present application.
The system for processing the vehicle driving data comprises at least one vehicle terminal and a local server cluster, wherein the local server cluster comprises a receiving server, a storage server and an operation server, and a plurality of vehicle algorithms are stored on the storage server. The vehicle terminal obtains target monitoring data of a vehicle and sends the target monitoring data to the receiving server, the target monitoring data are used for indicating abnormal data obtained in the driving process of the vehicle, the receiving server receives the target monitoring data, the operation server calls the target monitoring data and a plurality of vehicle algorithms, each vehicle algorithm is optimized by the target monitoring data, each optimized vehicle algorithm is obtained, the receiving server sends the optimized vehicle algorithms to the vehicle terminal, and the vehicle terminal controls the vehicle by the optimized vehicle algorithms. According to the vehicle driving data processing system, each vehicle algorithm is optimized through the local server cluster by means of the target monitoring data, each optimized vehicle algorithm is obtained, the vehicles are controlled by means of the optimized vehicle algorithms, and vehicle control accuracy can be achieved. Meanwhile, because the data processing is carried out in the local server cluster, the data processing safety can be improved, and the data processing cost can be reduced.
Drawings
Fig. 1 is a first structural diagram of a system for processing vehicle driving data according to an embodiment of the present disclosure;
fig. 2 is a second structural diagram of a vehicle driving data processing system according to an embodiment of the present application;
fig. 3 is a flowchart of a method for processing vehicle driving data according to an embodiment of the present application;
fig. 4 is a first schematic diagram illustrating a processing procedure of vehicle driving data according to an embodiment of the present application;
fig. 5 is a second schematic diagram of a process of processing vehicle driving data according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present disclosure, "a plurality" means two or more unless otherwise specified.
In addition, the use of "based on" or "according to" means open and inclusive, as a process, step, calculation, or other action that is "based on" or "according to" one or more conditions or values may in practice be based on additional conditions or values beyond those that are present.
With the development of artificial intelligence technology, multi-sensor fusion technology and control decision technology, automatic driving technology and auxiliary driving gradually enter the daily life of people, and the travel mode of people is changed in a profound way. Among them, processing of travel data relating to automatic driving or driving assistance of a vehicle plays an important role in automatic driving technology.
In the prior art, generally, acquired vehicle driving related data is stored in a cloud server, and vehicle related data is processed and processed in the cloud server, but such data processing cannot be effectively used for accurately controlling a vehicle, and the problem of low vehicle control accuracy exists.
Meanwhile, in the existing processing of the related data of mass production vehicles, the collected related data of the vehicles are generally sent to a cloud server for storage and management, but the processing method has potential data safety hazards and is high in cost.
In order to solve the problems in the prior art, an embodiment of the present application provides a system for processing vehicle driving data, where the system includes at least one vehicle terminal and a local server cluster, the local server cluster includes a receiving server, a storage server and an operation server, and a plurality of vehicle algorithms are stored in the storage server. The vehicle terminal obtains target monitoring data of a vehicle and sends the target monitoring data to the receiving server, the target monitoring data are used for indicating abnormal data obtained in the driving process of the vehicle, the receiving server receives the target monitoring data, the operation server calls the target monitoring data and the vehicle algorithms, optimization processing is carried out on each vehicle algorithm through the target monitoring data to obtain each optimized vehicle algorithm, the receiving server sends the optimized vehicle algorithms to the vehicle terminal, and the vehicle terminal controls the vehicle through the optimized vehicle algorithms. According to the vehicle driving data processing system, each vehicle algorithm is optimized through the local server cluster by means of the target monitoring data, each optimized vehicle algorithm is obtained, the vehicles are controlled by means of the optimized vehicle algorithms, and vehicle control accuracy can be achieved. Meanwhile, because the data processing is carried out in the local server cluster, the data processing safety can be improved, and the data processing cost can be reduced.
As shown in fig. 1, a system for processing vehicle driving data provided in an embodiment of the present application includes at least one vehicle terminal 10 and a local server cluster 20, where the local server cluster 20 includes: the vehicle algorithm management system comprises a receiving server 201, a storage server 202 and an operation server 203, wherein a plurality of vehicle algorithms are stored on the storage server 202.
The vehicle terminal 10 is configured to obtain target monitoring data of a vehicle, and send the target monitoring data to the receiving server 201, where the target monitoring data is used to indicate abnormal data obtained in a vehicle driving process;
a receiving server 201, configured to receive target monitoring data;
the operation server 203 is used for calling the target monitoring data and the plurality of vehicle algorithms, optimizing each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and sending the plurality of optimized vehicle algorithms to the vehicle terminal 10 through the receiving server 201;
and the vehicle terminal 10 is used for controlling the vehicle by utilizing the optimized vehicle algorithm.
Wherein the target monitoring data comprises: positioning data, vehicle-related data, which may include vehicle speed, steering wheel angle, or inertial sensor data, or sensor data, including: lane lines, target traffic signs or signal lights, etc.
It should be noted that the target monitoring data is target data generated during the running process of the vehicle monitored by the vehicle terminal 10, and the target data may be special condition data or normal running data of the vehicle. The acquisition of the target monitoring data may be: when the vehicle is monitored to be in a special working condition, the data monitoring algorithm on the vehicle terminal 10 may extract the vehicle driving data, so as to obtain target monitoring data of the vehicle, or send all data generated in the driving process of the vehicle to a server, and the data monitoring algorithm deployed on the server processes and identifies all data, and extracts the vehicle driving data in the special working condition, so as to obtain the target monitoring data of the vehicle.
In practice, the vehicle terminal 10 generates new vehicle driving data after controlling the vehicle by using the optimized vehicle algorithm. Therefore, the vehicle terminal 10 in the above-mentioned system for processing vehicle driving data may further obtain target monitoring data of the vehicle from the new vehicle driving data, and send the obtained target monitoring data to the receiving server 201, then the receiving server 201 receives the obtained target monitoring data, the operation server 203 is configured to call the obtained target monitoring data and a plurality of vehicle algorithms, optimize each vehicle algorithm by using the obtained target monitoring data, obtain each re-optimized vehicle algorithm, and send the plurality of re-optimized vehicle algorithms to the vehicle terminal 10 via the receiving server 201, and the vehicle terminal 10 is configured to control the vehicle by using the re-optimized vehicle algorithms. The whole system can continuously optimize the vehicle algorithm by recycling the vehicle running data, so that the accuracy of vehicle control can be improved.
The system for processing vehicle driving data provided by the embodiment of the application comprises at least one vehicle terminal 10 and a local server cluster 20, wherein the local server cluster 20 comprises a receiving server 201, a storage server 202 and an operation server 203, and a plurality of vehicle algorithms are stored on the storage server 202. The vehicle terminal 10 obtains target monitoring data of a vehicle and sends the target monitoring data to the receiving server 201, the target monitoring data are used for indicating abnormal data obtained in the vehicle running process, the receiving server 201 receives the target monitoring data, the operation server 203 calls the target monitoring data and a plurality of vehicle algorithms, each vehicle algorithm is optimized by the target monitoring data, each optimized vehicle algorithm is obtained, the receiving server 201 sends the optimized vehicle algorithms to the vehicle terminal 10, and the vehicle terminal 10 controls the vehicle by the optimized vehicle algorithms. According to the vehicle driving data processing system, each vehicle algorithm is optimized through the local server cluster 20 by using the target monitoring data, each optimized vehicle algorithm is obtained, and the vehicle is controlled by using the optimized vehicle algorithm, so that the vehicle control accuracy can be achieved. Meanwhile, because the data processing is performed in the local server cluster 20, the data processing security can be improved, and the data processing cost can be reduced.
In one embodiment, as shown in fig. 2, the system further includes a cloud server 30, and the vehicle terminal 10 is further configured to: sending a connection request to the receiving server 201, and acquiring the sending times of the current connection request, wherein the connection request is used for requesting to establish connection with the receiving server 201; if the sending times are less than a preset threshold, sending the target monitoring data to the receiving server 201; if the sending times are greater than a preset threshold value, the target monitoring data are sent to the cloud server 30 for caching.
Meanwhile, the receiving server 201 includes a plurality of servers, each of which includes a load balancing program for performing load balancing processing on the received connection request.
In practice, since the receiving server 201 needs to receive data uploaded by a plurality of vehicle terminals 10, there may be a case where the amount of data uploaded is relatively large, and the receiving server 201 also performs load balancing processing on connection requests of the vehicle terminals 10, so that the vehicle terminals 10 need to transmit a connection request to the receiving server 201 first in the process of uploading data to the receiving server 201, and after the receiving server 201 verifies that the verification request of the vehicle terminal 10 passes, the vehicle terminal 10 is successfully connected with the receiving server 201, and then the data can be uploaded to the receiving server 201.
It should be noted that, under the condition that the data upload amount is large, the data upload request sent by the vehicle terminal 10 may have a situation that the connection request is unsuccessful after multiple requests exist, for this situation, the vehicle terminal 10 sends a connection request every time within a preset time period, records the number of times of sending a request, and uploads the target monitoring data to the cloud server 30 for caching when detecting that the number of times of sending a current request is greater than a preset threshold, and the cloud server 30 may send the cached target monitoring data to the receiving server 201 at a preset time after receiving the target monitoring data, for example, the cloud server 30 may send the cached target monitoring data to the receiving server 201 at a certain time in the evening or at a time when the receiving server 201 is idle.
In one embodiment, the receiving server 201 is further configured to set an access right for the target monitoring data, obtain the isolated target monitoring data, and send the isolated target monitoring data to the storage server 202.
The storage server 202 is further configured to: and receiving the isolated target monitoring data, and performing distributed storage on the isolated target monitoring data.
It should be noted that, after receiving the target monitoring data, the receiving server 201 may also set an access right to the target monitoring data, for example, the target monitoring data may be called or processed in an intranet, and the target monitoring data may not be called by an extranet, so that the security of data processing may be ensured.
In addition, before the receiving server 201 sets the access right to the target monitoring data, integrity verification and security verification may be performed on the target monitoring data, and the access right may be set to the target monitoring data that meets the verification condition.
In the actual execution process, when the vehicle terminal uploads data, the vehicle terminal firstly verifies the preliminary compliance and validity of the data to ensure the availability of the data. Contact will then be established with the overhearing server through the wireless network (5G, LTE, etc.). Due to the presence of multiple concurrent connections to the server, limited by bandwidth requirements and receiving server throughput limitations, the vehicle end will re-attempt to establish contact with the local server at the next upload time slice when the connection reaches the upper bound. And if the connection is failed to be established for many times and the temporary buffer memory of the vehicle end reaches the upper limit, temporarily transferring the data to the cloud server for buffer memory. The cloud server periodically migrates the data to a local receiving server for storage. Once the vehicle end establishes communication with the local server end, the vehicle end uploads the encrypted data through the T-BOX on the vehicle or the vehicle gateway and other devices. The method comprises the steps of breakpoint continuous transmission, retransmission support, block combination processing of large files and integrity verification. After the receiving server receives and verifies the data validity and compliance, the data is stored into an internal data center through isolation transfer.
Meanwhile, the isolated data can be subjected to basic data cleaning, desensitization and other operations through a data processing platform, and video data and the like can be subjected to corresponding interception, frame extraction and duplication removal operations. The original data is generated by the data processing platform to process the data, the processed data is stored in a server based on object storage, such as a distributed storage mode, and information such as related data tag logs is stored in the metadata together for storage. After the original data is processed and verified to be correct, periodic destruction processing is carried out.
In one embodiment, the target monitoring data includes data for a plurality of attribute characteristics of the vehicle;
the storage server 202 is used for extracting information of each attribute feature data in the target monitoring data sent by each vehicle to obtain feature information corresponding to each data, and dividing the data with the same feature information into a data set;
the operation server 203 is specifically configured to obtain target feature information corresponding to each vehicle algorithm, call a target data set corresponding to the target feature information, and perform optimization processing on each vehicle algorithm by using data in the target data set, where the target feature information corresponding to each vehicle algorithm is the same or different.
It should be noted that the data of the plurality of attribute features of the vehicle may be understood as: the object monitoring data includes positioning data, vehicle-related data, or sensor data.
In an actual process, in order to call corresponding data for each algorithm, data can be classified, so that information extraction can be performed on data of each attribute feature in target monitoring data sent by each vehicle, feature information corresponding to each data is obtained, and the data with the same feature information is divided into a data set.
In addition, the verified data can firstly enter a data mining platform to carry out deep processing on the data, and the requirements of different training platforms are met. For deep processing of data, including but not limited to: labeling data, such as images, videos, point clouds, and the like; fusing multi-sensor data to obtain relevance data, such as perception data obtained by fusing multi-sensor data of a GPS (global positioning system), a camera, a laser radar and the like; the extraction of the data labels comprises the relevant labels recorded when the data are collected, such as time, weather, position scenes and the like, and the labeling processing and the filing processing are carried out on the data of different types.
In addition, some deep features in the data, such as feature extraction by statistical analysis, or by machine learning/deep learning algorithms, will be mined deep through the data to build a high-value scene library. The mining scene comprises the following steps: 1, signal level, data characteristics, correlation interaction analysis, and time/frequency domain analysis; 2, a behavior layer, which is mined by object behaviors based on time series, such as vehicle lane changing behaviors, driver decisions and the like; and 3, performing coded-based data feature extraction, such as performing dimensional transformation on the data through wavelet transformation, principal component analysis and the like, or performing feature extraction and coding on the data through a neural network (a convolutional neural network, an attention mechanism and the like) so as to be used for subsequent possible machine learning/deep learning algorithm training. The processed data passes through classification standards such as characteristics and scene categories, the high-value scene library is established and classified, a training set, a verification set and a test set are divided for the data according to requirements of a training platform, and format conversion of the data is performed to meet requirements of a subsequent algorithm module.
Before algorithm training, data of corresponding scenes and corresponding labeling information are called from a storage server according to requirements, and label information is used for algorithm training and iteration. Different algorithm training platforms call corresponding algorithm model codes, corresponding model parameter configuration documents and software tools from the code version management platform to use data, such as deep learning training, training of a virtual simulation platform and the like. The training module will iterate until a new version is run that can be iterated through the application and development versions, or the vehicle-side system is upgraded, for subsequent test validation. After the iterative correlation model and the parameter version are generated through the data, the existing algorithm and the iterative algorithm are tested through a data testing platform, such as data recharging, simulation testing and the like, the improvement and the stability of the algorithm are evaluated, and the integrated release and real vehicle deployment of subsequent application are determined. Product/algorithm iteration generated by interaction through the local server is performed, a part of product/algorithm iteration is performed by a research and development end for a new round of research and development and optimization, and meanwhile version upgrading and optimization are performed on the in-vehicle system through OTA upgrading and the like, or a new algorithm is deployed for subsequent acquisition and research.
In one embodiment, the calculation server 203 includes at least one container, each container being used for performing optimization processing on at least one vehicle algorithm.
The control algorithm of the vehicle can be stored in a mirror image form, when the operation server 203 calls the required algorithm, the image file corresponding to the algorithm can be called, meanwhile, at least one container is extracted and deployed in the operation server 203, and the optimization process of at least one control algorithm can be processed in each container. Therefore, when the resources in a certain container are not enough, the resources on the server can be directly called, and a set of data processing system does not need to be loaded again, so that the data processing efficiency can be improved, the resources can be saved, and the cost is reduced.
Compared with the traditional deep binding between the operation server and each platform, the distributed container deployment method improves the flexibility of the server through distributed container deployment. Corresponding mirror images are manufactured according to different research and development and test requirements, and corresponding environment configurations are packaged into corresponding mirror image sources so as to achieve light-weight operation of the platform. The operation server downloads corresponding mirror images based on different platform modules, and creates corresponding containers when in use, thereby ensuring that the platform algorithms are mutually isolated. And corresponding data, algorithm model codes, parameters and the like are called from the data storage platform in the container, and subsequent training operation is carried out. After the new server is expanded, corresponding environment deployment and configuration processes are not needed, and the expansion is easy. And the bottom hardware platform realizes low-delay data transmission and operations such as distribution, communication and the like among multiple servers, GPU, CPU and the like through hardware scheduling management.
The system for processing vehicle driving data provided by the embodiment of the application comprises at least one vehicle terminal 10 and a local server cluster 20, wherein the local server cluster 20 comprises a receiving server 201, a storage server 202 and an operation server 203, and a plurality of vehicle algorithms are stored on the storage server 202. The vehicle terminal 10 obtains target monitoring data of a vehicle and sends the target monitoring data to the receiving server 201, the target monitoring data are used for indicating abnormal data obtained in the running process of the vehicle, the receiving server 201 receives the target monitoring data, the operation server 203 calls the target monitoring data and a plurality of vehicle algorithms, each vehicle algorithm is optimized through the target monitoring data, each optimized vehicle algorithm is obtained, the receiving server 201 sends the plurality of optimized vehicle algorithms to the vehicle terminal 10, and the vehicle terminal 10 controls the vehicle through the optimized vehicle algorithms. According to the processing system for the vehicle running data, the local server cluster 20 is used for optimizing each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and the optimized vehicle algorithms are used for controlling the vehicle, so that the vehicle control accuracy can be achieved. Meanwhile, because the data processing is performed in the local server cluster 20, the data processing security can be improved, and the data processing cost can be reduced.
As shown in fig. 3, an embodiment of the present application further provides a method for processing vehicle driving data, where the method includes the following steps:
301, a vehicle terminal acquires target monitoring data of a vehicle and sends the target monitoring data to a receiving server, wherein the target monitoring data is used for indicating abnormal data obtained in the driving process of the vehicle;
303, calling target monitoring data and a plurality of vehicle algorithms by the operation server, optimizing each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and sending the optimized vehicle algorithms to the vehicle terminal through the receiving server;
and step 304, the vehicle terminal controls the vehicle by using the optimized vehicle algorithm.
In one embodiment, the method further comprises: the vehicle terminal sends a connection request to a receiving server and acquires the sending times of the current connection request, wherein the connection request is used for requesting to establish connection with the receiving server; if the sending times are smaller than a preset threshold value, sending the target monitoring data to a receiving server; and if the sending times are larger than a preset threshold value, sending the target monitoring data to a cloud server for caching.
In one embodiment, the method further comprises: and the cloud server sends the cached target monitoring data to the receiving server within the preset time after receiving the target monitoring data.
In one embodiment, after the receiving server receives the target monitoring data, the method further comprises: the receiving server sets access authority for the target monitoring data to obtain isolated target monitoring data, and sends the isolated target monitoring data to the storage server; and the storage server receives the isolated target monitoring data and performs distributed storage on the isolated target monitoring data.
In one embodiment, the target monitoring data includes data for a plurality of attribute characteristics of the vehicle, the method further comprising: the storage server extracts information of each attribute feature in the target monitoring data sent by each vehicle to obtain feature information corresponding to each data, and divides the data with the same feature information into a data set.
And optimizing each vehicle algorithm by using the target monitoring data, wherein the optimization comprises the following steps: the operation server 203 acquires target characteristic information corresponding to each vehicle algorithm, calls a target data set corresponding to the target characteristic information, and performs optimization processing on each vehicle algorithm by using data in the target data set, wherein the target characteristic information corresponding to each vehicle algorithm is the same or different.
As shown in fig. 4 and 5, in the method for processing vehicle driving data provided in the embodiment of the present application, target monitoring data of a vehicle is obtained through a vehicle terminal, and the target monitoring data is sent to a receiving server, where the target monitoring data is used to indicate abnormal data obtained during vehicle driving, the receiving server receives the target monitoring data, an operation server calls the target monitoring data and a plurality of vehicle algorithms, each vehicle algorithm is optimized by using the target monitoring data, so as to obtain each optimized vehicle algorithm, and the receiving server sends the plurality of optimized vehicle algorithms to the vehicle terminal, and the vehicle terminal controls the vehicle by using the optimized vehicle algorithms. According to the vehicle driving data processing system, each vehicle algorithm is optimized through the local server cluster by means of the target monitoring data, each optimized vehicle algorithm is obtained, the vehicles are controlled by means of the optimized vehicle algorithms, and vehicle control accuracy can be achieved. Meanwhile, because the data processing is carried out in the local server cluster, the data processing safety can be improved, and the data processing cost can be reduced.
In the actual implementation process, data generated by the vehicle end in the driving process is recorded through some special trigger conditions, such as a shadow mode and the like. And fragmenting the recorded data at a specific time and under a specific scene through a vehicle-mounted gateway or a wireless gateway, and encrypting and sending the fragmented data to a receiving server in the local server cluster. And for the high concurrency phenomenon caused by the fact that a large number of vehicles upload data at the same time, load balancing is carried out through the load balancing server, and data receiving is carried out dynamically and efficiently. And unpacking the uploaded data through a protocol analysis server, and obtaining corresponding data from an http protocol. And then temporarily storing the unpacked data in the kafka cluster through the kafka server cluster, and waiting for data merging, library dropping and the like. And finally, storing the data into a distributed storage server based on object storage, and realizing the complete operation of dropping the data from the vehicle end to the storage server.
The operation platform solves the delay generated by server-side data processing in network transmission by a bottom hardware scheduling mechanism, such as Remote Direct data Access (RDMA), and improves the data exchange bandwidth between the GPU and the CPU by an NvLinK bus protocol. And the containerization platform builds a container-based distributed architecture through an orchestration management tool of a portable container such as k8 s. The server performs distributed operations in units of containers, the container construction of which is provided by images integrated by the corresponding platforms. Light-weight configuration environments corresponding to different image integration, software platforms and the like. The platform can realize iteration by calling the data stored in a distributed mode, corresponding codes, models and weight files to process, train and test the data. The iterative algorithm will be re-deployed to the vehicle end for utility via Over-the-Air Technology (OTA) upgrade and upload newly generated data to achieve function iteration and perfection.
In another embodiment of the present application, there is also provided a computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of the method for processing vehicle travel data as provided in the embodiments of the present application.
In another embodiment of the present application, a computer program product is also provided, which includes computer instructions and can execute the steps executed by the method for processing vehicle driving data in the method flow shown in the above method embodiment.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The processes or functions according to the embodiments of the present application are generated in whole or in part when the computer-executable instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). Computer-readable storage media can be any available media that can be accessed by a computer or can comprise one or more data storage devices, such as servers, data centers, and the like, that can be integrated with the media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A system for processing vehicle travel data, the system comprising: at least one vehicle terminal and local server cluster, the local server cluster includes: the system comprises a receiving server, a storage server and an operation server, wherein a plurality of vehicle algorithms are stored in the storage server;
the vehicle terminal is used for acquiring target monitoring data of a vehicle and sending the target monitoring data to the receiving server, wherein the target monitoring data is used for indicating the target data of the vehicle in the running process;
the receiving server is used for receiving the target monitoring data;
the operation server is used for calling the target monitoring data and the plurality of vehicle algorithms, optimizing each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and sending the plurality of optimized vehicle algorithms to the vehicle terminal through the receiving server;
and the vehicle terminal is used for controlling the vehicle by utilizing the optimized vehicle algorithm.
2. The system of claim 1, further comprising a cloud server, the vehicle terminal further configured to:
sending a connection request to the receiving server, and acquiring the sending times of the current connection request, wherein the connection request is used for requesting to establish connection with the receiving server;
if the sending times are smaller than a preset threshold value, sending the target monitoring data to the receiving server;
and if the sending times are larger than the preset threshold value, sending the target monitoring data to the cloud server for caching.
3. The system of claim 2, wherein the cloud server is further configured to:
and sending the cached target monitoring data to the receiving server within a preset time after the target monitoring data is received.
4. The system according to any one of claims 1-3,
the receiving server is further used for setting access authority for the target monitoring data to obtain isolated target monitoring data and sending the isolated target monitoring data to the storage server;
the storage server is further configured to: and receiving the isolated target monitoring data, and performing distributed storage on the isolated target monitoring data.
5. The system of any one of claims 1-3, wherein the target monitoring data includes data for a plurality of attribute characteristics of the vehicle;
the storage server is used for extracting information of each attribute feature data in the target monitoring data sent by each vehicle to obtain feature information corresponding to each data, and dividing the data with the same feature information into a data set;
the operation server is specifically configured to obtain target feature information corresponding to each vehicle algorithm, call a target data set corresponding to the target feature information, and perform optimization processing on each vehicle algorithm by using data in the target data set, where the target feature information corresponding to each vehicle algorithm is the same or different.
6. The system according to any one of claims 1-3, wherein the calculation server comprises at least one container, each container being configured to optimize at least one of the vehicle algorithms.
7. The system according to claim 2 or 3, wherein the receiving server comprises a plurality of servers, and each server comprises a load balancing program, and the load balancing program is configured to perform load balancing processing on the received connection request.
8. A method of processing vehicle travel data, the method comprising:
the method comprises the steps that a vehicle terminal obtains target monitoring data of a vehicle and sends the target monitoring data to a receiving server, wherein the target monitoring data are used for indicating the target data in the vehicle running process;
the receiving server receives the target monitoring data;
the operation server calls the target monitoring data and the vehicle algorithms, optimizes each vehicle algorithm by using the target monitoring data to obtain each optimized vehicle algorithm, and sends a plurality of optimized vehicle algorithms to the vehicle terminal through the receiving server;
and the vehicle terminal controls the vehicle by using the optimized vehicle algorithm.
9. The method of claim 8, further comprising:
the vehicle terminal sends a connection request to the receiving server and obtains the sending times of the current connection request, wherein the connection request is used for requesting to establish connection with the receiving server;
if the sending times are smaller than a preset threshold value, sending the target monitoring data to the receiving server;
and if the sending times are larger than the preset threshold value, sending the target monitoring data to a cloud server for caching.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which when executed by a processor implements the method of processing vehicle travel data of claims 8 and 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210190866.8A CN114584584A (en) | 2022-02-28 | 2022-02-28 | System and method for processing vehicle driving data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210190866.8A CN114584584A (en) | 2022-02-28 | 2022-02-28 | System and method for processing vehicle driving data and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114584584A true CN114584584A (en) | 2022-06-03 |
Family
ID=81776393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210190866.8A Pending CN114584584A (en) | 2022-02-28 | 2022-02-28 | System and method for processing vehicle driving data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114584584A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115118754A (en) * | 2022-08-29 | 2022-09-27 | 中国汽车技术研究中心有限公司 | Remote monitoring test system and monitoring test method for electric vehicle |
| CN118132387A (en) * | 2024-04-30 | 2024-06-04 | 北京主线科技有限公司 | Method, device, equipment, storage medium and program product for determining target vehicle data quality |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108769047A (en) * | 2018-06-06 | 2018-11-06 | 厦门华厦学院 | A kind of big data risk monitoring system |
| CN109597991A (en) * | 2018-11-27 | 2019-04-09 | 北京巅峰科技有限公司 | Vehicle remote detection method |
| CN112287801A (en) * | 2020-10-23 | 2021-01-29 | 北京嘀嘀无限科技发展有限公司 | Vehicle-mounted data processing method and device, server and readable storage medium |
| KR20210037621A (en) * | 2020-07-30 | 2021-04-06 | 베이징 바이두 넷컴 사이언스 테크놀로지 컴퍼니 리미티드 | Method and apparatus for processing navigation data, device and storage medium |
| CN113178024A (en) * | 2021-05-11 | 2021-07-27 | 南京信易达计算技术有限公司 | Fusion type vehicle-mounted intelligent storage system and method based on artificial intelligence |
| CN113422806A (en) * | 2021-05-26 | 2021-09-21 | 中国联合网络通信集团有限公司 | Internet of vehicles data processing method, vehicle-mounted terminal and data storage server |
-
2022
- 2022-02-28 CN CN202210190866.8A patent/CN114584584A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108769047A (en) * | 2018-06-06 | 2018-11-06 | 厦门华厦学院 | A kind of big data risk monitoring system |
| CN109597991A (en) * | 2018-11-27 | 2019-04-09 | 北京巅峰科技有限公司 | Vehicle remote detection method |
| KR20210037621A (en) * | 2020-07-30 | 2021-04-06 | 베이징 바이두 넷컴 사이언스 테크놀로지 컴퍼니 리미티드 | Method and apparatus for processing navigation data, device and storage medium |
| EP3842761A2 (en) * | 2020-07-30 | 2021-06-30 | Beijing Baidu Netcom Science Technology Co., Ltd. | Method and apparatus for processing navigation data, device and storage medium |
| CN112287801A (en) * | 2020-10-23 | 2021-01-29 | 北京嘀嘀无限科技发展有限公司 | Vehicle-mounted data processing method and device, server and readable storage medium |
| CN113178024A (en) * | 2021-05-11 | 2021-07-27 | 南京信易达计算技术有限公司 | Fusion type vehicle-mounted intelligent storage system and method based on artificial intelligence |
| CN113422806A (en) * | 2021-05-26 | 2021-09-21 | 中国联合网络通信集团有限公司 | Internet of vehicles data processing method, vehicle-mounted terminal and data storage server |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115118754A (en) * | 2022-08-29 | 2022-09-27 | 中国汽车技术研究中心有限公司 | Remote monitoring test system and monitoring test method for electric vehicle |
| CN115118754B (en) * | 2022-08-29 | 2022-11-25 | 中国汽车技术研究中心有限公司 | Remote monitoring test system and monitoring test method for electric automobile |
| CN118132387A (en) * | 2024-04-30 | 2024-06-04 | 北京主线科技有限公司 | Method, device, equipment, storage medium and program product for determining target vehicle data quality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210011908A1 (en) | Model-based structured data filtering in an autonomous vehicle | |
| CN114584584A (en) | System and method for processing vehicle driving data and storage medium | |
| CN111104954B (en) | Object classification method and device | |
| CN107770280B (en) | Multimedia data processing and acquiring method, acquisition terminal and processing device | |
| CN104520829A (en) | Device and method for extracting data from a communication bus of a motor vehicle | |
| CN112492052A (en) | Remote debugging method and device for intelligent networked vehicle data | |
| CN115718868A (en) | Model training method, device and system | |
| US11726443B2 (en) | Efficient controller data generation and extraction | |
| CN114205141A (en) | IPC algorithm deployment admission method, system, medium and electronic terminal | |
| CN112712608B (en) | System and method for collecting performance data by a vehicle | |
| CN115934263A (en) | Data processing method and device, computer equipment and storage medium | |
| CN112035140B (en) | System upgrading method, device and equipment for intelligent parking scene and storage medium | |
| CN113612824A (en) | Calibration data management method, system, medium, and device | |
| CN114579153A (en) | Upgrading method and device, computer readable storage medium and electronic equipment | |
| CN111104366B (en) | Data archiving method, device, server and storage medium | |
| EP4073665A1 (en) | Automotive data processing system with efficient generation and exporting of metadata | |
| CN114945033A (en) | Vehicle end data returning method, vehicle end controller, cloud server and vehicle | |
| KR20230098030A (en) | on-board data processing method and device, electronic device and storage medium | |
| CA3053604A1 (en) | Data point suitability determination from edge device neural networks | |
| CN114199274B (en) | Vehicle travel determination method, device, equipment and readable storage medium | |
| CN116132474A (en) | Internet of vehicles terminal access system based on multi-protocol fusion | |
| US20190202581A1 (en) | Method and system to dynamically configure and load platform-specific maintenance software | |
| US20220350704A1 (en) | Machine learning systems for etl data streams | |
| CN111221556B (en) | Remote upgrade RSU mirror image method and system | |
| JP7353036B2 (en) | Data collection device, data collection system and data collection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |