Intelligent networked vehicle remote control data analysis method and system and vehicle

Abstract

The application discloses a smart networked vehicle remote control data analysis method and system and a vehicle, and the method comprises the following steps: acquiring a real-time data stream of a vehicle network by using a vehicle network remote control technology; merging the real-time data stream of the vehicle network and historical remote control data of the vehicle network to generate batch processing data; and calculating remote control execution success rates and instruction execution success rates of each vehicle after analyzing and filtering the batch processing data. When the remote control instructions required by the vehicle increase or the data stream transmission speed increases, the real-time processing requirements can be met without excessive reconfiguration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobiles, in particular to a remote control data analysis method and system for intelligent networked vehicles and a vehicle. BACKGROUND

[0002] With the development of technology, intelligent networked vehicles have gradually become the development trend of the automobile industry. Intelligent networked vehicles refer to vehicles that realize intelligent information exchange, sharing between vehicles, roadside infrastructure, and cloud systems through Internet technology, and have complex environmental perception, decision-making, and execution capabilities.

[0003] Among them, remote control is an important technology for intelligent networked vehicles, which can realize remote control of vehicles and provide convenience. However, how to effectively and accurately analyze remote control data and improve the efficiency and accuracy of remote control is a major challenge in current technology.

[0004] Therefore, in view of different remote control instruction requirements and different signal transmission rates, it is urgent to develop a data analysis method that can reduce computing resources and meet real-time analysis requirements. SUMMARY

[0005] The present application aims to provide a remote control data analysis method and system for intelligent networked vehicles and a vehicle, which can meet real-time processing requirements without excessive reconfiguration when the number of remote control instructions required by the vehicle increases or the data stream transmission speed increases.

[0006] To achieve the above-mentioned purpose, the present application provides a remote control data analysis method for intelligent networked vehicles, comprising:

[0007] Using vehicle networking remote control technology, real-time data stream of vehicle networking is obtained;

[0008] The real-time data stream of vehicle networking and the historical remote control data of vehicle networking are merged to generate batch processing data;

[0009] After parsing and filtering the batch processing data, the remote control execution success rate and the instruction execution success rate of each vehicle are calculated.

[0010] Further, the use of vehicle networking remote control technology to obtain real-time data stream of vehicle networking comprises:

[0011] Using Kafka platform to obtain real-time data stream of vehicle networking and storing it in Redis database;

[0012] Among them, the real-time data stream of vehicle networking includes: running state data, environmental data and user behavior data of the vehicle.

[0013] Further, the merging of the real-time data stream of the Internet of Vehicles and the historical remote control data of the Internet of Vehicles to generate batch processing data comprises:

[0014] The latest frame of data in the Redis database is obtained by using a Spark-Kafka connection component;

[0015] The historical remote control data in the ClickHouse database is obtained by using a DBeaver link software to access the ClickHouse database;

[0016] The latest frame of data and the historical remote control data are merged, and the data entries are rearranged to generate batch processing data.

[0017] Further, the merging of the latest frame of data and the historical remote control data, the rearrangement of the data entries, and the generation of batch processing data comprise:

[0018] In the merging process, the corresponding terminal ID is matched with the vehicle frame number, and all execution module signal data of a single instruction are merged by using the same remote control instruction ID to generate a column of remote control instruction result forms.

[0019] Further, after the batch processing data is parsed and filtered, the remote control execution success rate and the instruction execution success rate of each vehicle are calculated, comprising:

[0020] The batch processing data is parsed into analyzable data by using a Spark computing engine, and the required analysis fields are obtained and imported into a PowerBI analysis system;

[0021] The required analysis fields are grouped, sorted, and connected for calculation by using the PowerBI analysis system to filter out the same event sent by different terminals and calculate the remote control execution success rate and the instruction execution success rate of each vehicle;

[0022] The required analysis fields include: vehicle frame number, operator, operation time, remote control instruction name, remote control instruction ID, execution result, and failure reason.

[0023] Further, the required analysis fields are grouped, sorted, and connected for calculation by using the PowerBI analysis system to filter out the same event sent by different terminals and calculate the remote control execution success rate and the instruction execution success rate of each vehicle, comprising:

[0024] The execution data and timestamps of each remote control instruction are obtained by using each vehicle frame number;

[0025] The same event sent by different terminals is filtered out according to the vehicle frame number and the remote control instruction ID;

[0026] Merge each module execution data into a remote control instruction result form by frame number, and calibrate the execution result; wherein the execution result includes: execution success, execution failure or execution timeout;

[0027] Group the required analysis fields according to the remote control instruction name, and calculate the remote control execution success rate of each vehicle and the instruction execution success rate through the execution result of the required analysis field, and store it in the ClickHouse database.

[0028] Further, the Kafka platform is used to obtain the real-time data stream of Internet of Vehicles, and stored in the Redis database, comprising:

[0029] After obtaining the initial real-time data stream of Internet of Vehicles, the initial real-time data stream of Internet of Vehicles needs to be sequentially preprocessed and analyzed to obtain the final real-time data stream of Internet of Vehicles and store it in the Redis database;

[0030] Wherein, the data preprocessing of the initial real-time data stream of Internet of Vehicles includes: cleaning, sorting and formatting the initial real-time data stream of Internet of Vehicles to obtain the real-time data stream of Internet of Vehicles after data preprocessing;

[0031] The data analysis of the real-time data stream of Internet of Vehicles after data preprocessing includes: using machine learning algorithm to classify and analyze the real-time data stream of Internet of Vehicles after data preprocessing to obtain the final real-time data stream of Internet of Vehicles.

[0032] Based on the same inventive concept, the application also provides an intelligent networked vehicle remote control data analysis system, comprising:

[0033] The acquisition unit is used to obtain the real-time data stream of Internet of Vehicles by using Internet of Vehicles remote control technology;

[0034] The merging unit is used to merge the real-time data stream of Internet of Vehicles and the historical remote control data of Internet of Vehicles to generate batch processing data;

[0035] The computing unit is used to calculate the remote control execution success rate of each vehicle and the instruction execution success rate after parsing and filtering the batch processing data.

[0036] Further, the computing unit is specifically used to parse the batch processing data into analyzable data by using Spark computing engine, obtain the required analysis fields and import them into PowerBI analysis system; group, sort and connect the required analysis fields by using PowerBI analysis system to filter out the same events sent by different terminals, and calculate the remote control execution success rate of each vehicle and the instruction execution success rate;

[0037] Among them, the required analysis fields include: frame number, operator, operation time, remote control instruction name, remote control instruction ID, execution result and failure reason.

[0038] Based on the same inventive concept, the present application also provides a vehicle comprising the intelligent connected vehicle remote control data analysis system as described above.

[0039] The technical effects and advantages of the present application are as follows: the present application calculates the remote control execution success rate of a single vehicle and the execution success rate of the same type of remote control instruction, and obtains the remote control failure reason, which can optimize different situations and improve the remote control service level of the vehicle enterprise, has high practical value and wide application prospect; the present application can more comprehensively understand the condition of the vehicle and the demand of the user by collecting the running state data, environment data and user behavior data of the vehicle; through data preprocessing and data analysis, abnormal data and potential risks can be quickly and accurately identified, and the efficiency and accuracy of remote control are improved; through data feedback, the results calculated by the analysis system can be transmitted to the user and the vehicle control system in time, and the user experience and driving safety are improved.

[0040] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and achieved by the structures indicated in the specification, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0042] Figure 1 The flow chart of the intelligent connected vehicle remote control data analysis method of the embodiment of the present application is shown in the figure.

[0043] Figure 2 The detailed flow chart of the intelligent connected vehicle remote control data analysis method of the embodiment of the present application is shown in the figure.

[0044] Figure 3 The structure schematic diagram of the intelligent connected vehicle remote control data analysis system of the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0045] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0046] To solve the problems in the prior art, the present application discloses a remote control data analysis method for intelligent networked vehicles, as shown in Figure 1 and Figure 2 , comprising the following steps:

[0047] Step S1: acquiring real-time data stream of vehicle networking by using vehicle networking remote control technology;

[0048] Step S2: merging the real-time data stream of vehicle networking and the historical remote control data of vehicle networking to generate batch processing data;

[0049] Step S3: calculating the remote control execution success rate and the instruction execution success rate of each vehicle after parsing and filtering the batch processing data.

[0050] In some specific embodiments, step S1: acquiring real-time data stream of vehicle networking by using vehicle networking remote control technology, comprises:

[0051] Acquiring the real-time data stream of vehicle networking by using Kafka platform and storing it in Redis database; Kafka platform is a high-throughput distributed publish-subscribe message system, which can process all action stream data of consumers in the website.

[0052] The real-time data stream of vehicle networking comprises: running state data, environmental data and user behavior data of the vehicle;

[0053] The running state data comprises vehicle speed, rotating speed and battery capacity, the environmental data comprises weather, road condition and traffic condition, and the user behavior data comprises driving habit, driving route and parking location.

[0054] In some specific embodiments, the real-time data stream of vehicle networking is acquired by using Kafka platform and stored in Redis database, comprising:

[0055] After acquiring the initial real-time data stream of vehicle networking, the initial real-time data stream of vehicle networking needs to be sequentially preprocessed and analyzed to obtain the final real-time data stream of vehicle networking and store it in Redis(RemoteDictionary Server, i.e., remote dictionary service) database;

[0056] The data preprocessing of the initial vehicle networking real-time data stream includes cleaning, sorting and formatting (such as removing invalid data, filling in missing data, and converting data in different formats) of the initial vehicle networking real-time data stream, so as to obtain the vehicle networking real-time data stream after data preprocessing for subsequent analysis.

[0057] The data analysis of the vehicle networking real-time data stream after data preprocessing includes classification and analysis of the vehicle networking real-time data stream after data preprocessing by using machine learning algorithms (such as classification and prediction of the vehicle networking real-time data stream by decision tree, neural network, etc.), so as to identify abnormal data and potential risks, and obtain the final vehicle networking real-time data stream.

[0058] In some specific embodiments, step S2: merging the vehicle networking real-time data stream and the historical remote control data of the vehicle networking to generate batch processing data, includes:

[0059] The latest frame of data in the Redis database is obtained by using the Spark-Kafka connection component;

[0060] The ClickHouse database is accessed by using the DBeaver link software, and the historical remote control data in the ClickHouse database is obtained;

[0061] The latest frame of data and the historical remote control data are merged, the data entries are rearranged, and batch processing data is generated.

[0062] In some specific embodiments, the merging of the latest frame of data and the historical remote control data, the rearrangement of the data entries, and the generation of batch processing data, includes:

[0063] During the merging process, the corresponding terminal ID is matched with the vehicle frame number, and all execution module signal data of a single instruction are merged by using the same remote control instruction ID to generate a column of remote control instruction result table.

[0064] In some specific embodiments, after step S3: the batch processing data is parsed and filtered, the remote control execution success rate and the instruction execution success rate of each vehicle are calculated, including:

[0065] The batch processing data is parsed into analyzable data by using the Spark computing engine, the required analysis fields are obtained, and are imported into the PowerBI analysis system;

[0066] The required analysis fields are grouped, sorted and connected by the PowerBI analysis system to filter out the same events sent by different terminals, and to calculate the remote control execution success rate and the instruction execution success rate of each vehicle;

[0067] The required analysis fields include a frame number, an operator, an operation time, a remote control instruction name, a remote control instruction ID, an execution result, and a failure cause.

[0068] In some specific embodiments, the required analysis fields are grouped, sorted, and connected by the PowerBI analysis system to filter out the same event sent by different terminals and calculate the remote control execution success rate and the instruction execution success rate of each vehicle, including:

[0069] Each module execution data and a timestamp of each remote control instruction are obtained by using each frame number.

[0070] According to the frame number and the remote control instruction ID, the same event sent by different terminals is filtered out.

[0071] Each module execution data is merged into a remote control instruction result form by the frame number, and the execution result is calibrated; the execution result includes execution success, execution failure, or execution timeout.

[0072] The required analysis fields are grouped according to the remote control instruction name, and the remote control execution success rate and the instruction execution success rate of each vehicle are calculated by the execution result corresponding to the required analysis field and stored in the ClickHouse database, to prepare for the next calculation and provide data for subsequent display.

[0073] After the calculation result of the execution success rate is obtained by analyzing the real-time data stream of the Internet of Vehicles, the result can be fed back to the user and the automobile control system (for example, the vehicle condition and the early warning information are displayed to the user through a mobile phone APP or a vehicle-mounted display screen), so that the user and the automobile control system can make corresponding decisions according to the feedback information.

[0074] Based on the same inventive concept, the embodiments of the present application also provide an intelligent networked vehicle remote control data analysis system, as shown in Figure 3 The system includes:

[0075] An acquisition unit is configured to acquire a real-time data stream of the Internet of Vehicles by using a remote control technology of the Internet of Vehicles.

[0076] A merging unit is configured to merge the real-time data stream of the Internet of Vehicles and historical remote control data of the Internet of Vehicles to generate batch processing data.

[0077] A calculation unit is configured to calculate the remote control execution success rate and the instruction execution success rate of each vehicle after the batch processing data is parsed and filtered.

[0078] In some specific embodiments, the computing unit is specifically configured to parse the batch data into analyzable data by using a Spark computing engine, obtain the required analysis fields and import them into a PowerBI analysis system; and the required analysis fields are grouped, sorted and connected for calculation by the PowerBI analysis system to filter out the same events sent by different terminals and calculate the remote control execution success rate and instruction execution success rate of each vehicle.

[0079] The required analysis fields include a vehicle frame number, an operator, an operation time, a remote control instruction name, a remote control instruction ID, an execution result and a failure cause.

[0080] As to the system in the above embodiments, the specific manner in which each unit module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

[0081] Based on the same inventive concept, the embodiments of the present application also provide a vehicle comprising the intelligent networked vehicle remote control data analysis system as described above.

[0082] The present application calculates the remote control execution success rate of a single vehicle and the execution success rate of the same type of remote control instruction, and obtains the remote control failure cause, which can be well optimized for different situations, thereby improving the remote control service level of the vehicle enterprise, and has high practical value and wide application prospect; the present application can more comprehensively understand the condition of the vehicle and the demand of the user by collecting the running state data, environmental data and user behavior data of the vehicle; by data preprocessing and data analysis, abnormal data and potential risks can be quickly and accurately identified, thereby improving the efficiency and accuracy of remote control; through data feedback, the results calculated by the analysis system can be timely transmitted to the user and the vehicle control system, thereby improving the user experience and driving safety.

[0083] Finally, it should be noted that: the above only describes the preferred embodiments of the present application and is not used to limit the present application, although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents, any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for analyzing intelligent connected vehicle remote control data, characterized in that, The application relates to a remote control data analysis method based on a vehicle internet, and belongs to the technical field of remote control data analysis. The method comprises the following steps: Remote control data of the vehicle internet is obtained by using a vehicle internet remote control technology; The remote control data of the vehicle internet is combined with historical remote control data to generate batch processing data; After the batch processing data is parsed and filtered, the remote control execution success rate and the instruction execution success rate of each vehicle are calculated; The method comprises the following steps: The batch processing data is parsed into analyzable data by using a Spark computing engine, and the required analysis fields are obtained and imported into a PowerBI analysis system; the required analysis fields are grouped, sorted and connected for calculation by using the PowerBI analysis system, so that the same event sent by different terminals is filtered out, and the remote control execution success rate and the instruction execution success rate of each vehicle are calculated; wherein the required analysis fields comprise a vehicle frame number, an operator, an operation time, a remote control instruction name, a remote control instruction ID, an execution result and a failure reason; The method comprises the following steps: The execution data and timestamps of each module of each remote control instruction are obtained by using each vehicle frame number; the same event sent by different terminals is filtered out according to the vehicle frame number and the remote control instruction ID; the execution data of each module is combined into a remote control instruction result table by using the vehicle frame number, and the execution result is calibrated; the required analysis fields are grouped according to the remote control instruction name, and the remote control execution success rate and the instruction execution success rate of each vehicle are calculated according to the execution result corresponding to the required analysis fields, and are stored in a ClickHouse database; wherein the execution result comprises execution success, execution failure or execution timeout. 2.The intelligent networked vehicle remote control data analysis method of claim 1, wherein, The method comprises the following steps: The remote control data of the vehicle internet is obtained by using a vehicle internet remote control technology; The remote control data of the vehicle internet is combined with historical remote control data to generate batch processing data; 3.The intelligent networked vehicle remote control data analysis method of claim 1, wherein, The method comprises the following steps: The latest frame data in the Redis database is obtained by using a Spark-Kafka connection component; The historical remote control data in the ClickHouse database is obtained by using a DBeaver linking software; The latest frame data and the historical remote control data are combined, the data entries are rearranged, and batch processing data is generated. 4.The intelligent networked vehicle remote control data analysis method of claim 3, wherein, The method comprises the following steps: In the combining process, the corresponding terminal ID is matched according to the vehicle frame number, and all execution module signal data of a single instruction are combined by using the same remote control instruction ID to generate a column of remote control instruction result table. 5.The intelligent networked vehicle remote control data analysis method of claim 2, wherein, The Kafka platform is used to obtain the real-time data stream of the Internet of Vehicles, and the real-time data stream is stored in a Redis database, including: After obtaining the initial real-time data stream of the Internet of Vehicles, the initial real-time data stream of the Internet of Vehicles needs to be sequentially subjected to data preprocessing and data analysis to obtain the final real-time data stream of the Internet of Vehicles and store the final real-time data stream in the Redis database; The data preprocessing of the initial real-time data stream of the Internet of Vehicles includes: cleaning, arranging and formatting the initial real-time data stream of the Internet of Vehicles to obtain the real-time data stream of the Internet of Vehicles after data preprocessing; The data analysis of the real-time data stream of the Internet of Vehicles after data preprocessing includes: classifying and analyzing the real-time data stream of the Internet of Vehicles after data preprocessing by using an algorithm to obtain the final real-time data stream of the Internet of Vehicles.

6. An intelligent networked vehicle remote control data analysis system, characterized in that, It includes: The acquisition unit is used to obtain the real-time data stream of the Internet of Vehicles by using the remote control technology of the Internet of Vehicles; The merging unit is used to merge the real-time data stream of the Internet of Vehicles and the historical remote control data of the Internet of Vehicles to generate batch processing data; The computing unit is used to calculate the remote control execution success rate and the instruction execution success rate of each vehicle after parsing and filtering the batch processing data; The computing unit is specifically configured to parse the batch processing data into analyzable data by using a Spark computing engine, obtain the required analysis fields and import them into a PowerBI analysis system, group, sort and connect the required analysis fields by using the PowerBI analysis system to filter out the same events sent by different terminals, and calculate the remote control execution success rate and the instruction execution success rate of each vehicle; wherein the required analysis fields include: frame number, operator, operation time, remote control instruction name, remote control instruction ID, execution result and failure reason; The required analysis fields are grouped, sorted and connected by using the PowerBI analysis system to filter out the same events sent by different terminals and calculate the remote control execution success rate and the instruction execution success rate of each vehicle, including: Each frame number is used to obtain the module execution data and timestamp of each remote control instruction; the same events sent by different terminals are filtered out according to the frame number and the remote control instruction ID; the module execution data is merged into a remote control instruction result table by the frame number, and the execution result is calibrated; the required analysis fields are grouped according to the remote control instruction name, and the remote control execution success rate and the instruction execution success rate of each vehicle are calculated according to the execution result corresponding to the required analysis fields, and stored in a ClickHouse database; wherein the execution result includes: execution success, execution failure or execution timeout. The intelligent Internet of Vehicles remote control data analysis system of claim 6 is included.

7. A vehicle characterized by comprising: ​

Images