Data preprocessing method of Internet of Vehicles, electronic equipment and storage medium

Abstract

The invention discloses a data pre-processing method of an Internet of Vehicles, an electronic device and a storage medium, and relates to the technical field of Internet of Vehicles, the data pre-processing method is applied to a vehicle end, the vehicle end is deployed with a calculation engine and a time sequence database, and the time sequence database is used for storing vehicle end data; the method comprises the steps that in response to a calculation task triggered by a user through a vehicle end data application, a calculation engine executes the calculation task according to data in a time sequence database, and a task result is obtained; and feeding back the task result to the user through the vehicle end data application. Compared with the current calculation performed by the cloud, the technical scheme of the embodiment of the invention completes the calculation task through the local calculation engine, so that the cloud is prevented from executing the calculation task, and the calculation pressure of the cloud is reduced. And the local computing engine can quickly and stably complete the computing task according to the data stored in the time sequence database, so that the reliability is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Vehicles, and in particular to a data preprocessing method for Internet of Vehicles, an electronic device and a storage medium. BACKGROUND

[0002] With the rapid development of the automobile industry, especially the popularity of electric vehicles and intelligent networked vehicles, the amount of vehicle data generated by vehicles has increased dramatically. Vehicle data comes from various sensors, control systems and vehicle-mounted devices, including driving data, environmental perception data, user behavior data, etc. With the dramatic increase in the amount of vehicle data generated by vehicles, the number of data applications is also increasing, and most application scenarios require not only real-time data from the vehicle end but also analysis of long-period data.

[0003] Currently, vehicle data needs to be uploaded to the cloud and stored, and analyzed by the cloud, and the analysis results are fed back to the vehicle end. This approach puts a huge resource pressure on the cloud. How to reduce the computing pressure of the cloud has become a problem to be solved. SUMMARY

[0004] The present application provides a data preprocessing method for Internet of Vehicles, an electronic device and a storage medium to solve the problem of high computing pressure of vehicle data in the cloud.

[0005] According to an aspect of the present application, a data preprocessing method for Internet of Vehicles is provided, applied to a vehicle end, wherein the vehicle end is deployed with a computing engine and a time series database, and the time series database is used to store vehicle end data; the method comprises:

[0006] In response to a computing task triggered by a user through a vehicle end data application, the computing engine executes the computing task according to the data in the time series database to obtain a task result;

[0007] The task result is fed back to the user through the vehicle end data application.

[0008] According to another aspect of the present application, a data preprocessing device for Internet of Vehicles is provided, applied to a vehicle end, wherein the vehicle end is deployed with a computing engine and a time series database, and the time series database is used to store vehicle end data; the device comprises:

[0009] A computing engine processing module is configured to, in response to a computing task triggered by a user through a vehicle end data application, the computing engine executes the computing task according to the data in the time series database to obtain a task result;

[0010] A feedback module is configured to feed back the task result to the user through the vehicle end data application.

[0011] According to another aspect of the present application, there is provided an electronic device comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected with the at least one processor; wherein

[0014] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the data pre-processing method of the vehicle-to-network according to any one of the embodiments of the present application.

[0015] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to implement the data pre-processing method of the vehicle-to-network according to any one of the embodiments of the present application when executed by the processor.

[0016] The technical solution of the embodiments of the present application deploys a computing engine and a time series database at a vehicle end to store vehicle data at the vehicle end. In response to a computing task triggered by a user through a vehicle end data application, the computing engine executes the computing task according to data in the time series database to obtain a task result, and feeds back the task result to the user through the vehicle end data application. Compared with the current computing performed by a cloud end, the technical solution of the embodiments of the present application completes the computing task through a local computing engine, thereby avoiding performing the computing task by the cloud end and reducing the computing pressure of the cloud end. The local computing engine can quickly and stably complete the computing task according to the data stored in the time series database, thereby improving the reliability.

[0017] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0018] 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.

[0019] Figure 1 A framework schematic diagram of a data pre-processing method of a vehicle-to-network provided by an embodiment of the present application;

[0020] Figure 2 A flow schematic of a data pre-processing method of a vehicle-to-network provided by an embodiment of the present application;

[0021] Figure 3 A structural schematic diagram of a data pre-processing device of a vehicle network provided by an embodiment of the present application is provided.

[0022] Figure 4 A structural schematic diagram of an electronic device for implementing a data pre-processing method of a vehicle network according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the scope of the present application.

[0024] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification and claims of the present application and the above-described drawings are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0025] With the rapid development of the automotive industry, especially the popularity of electric vehicles and intelligent networked vehicles, the amount of vehicle data generated by vehicles has increased dramatically. Vehicle data comes from various sensors, control systems and vehicle-mounted devices, including driving data, environmental perception data, user behavior data, etc. With the dramatic increase in the amount of vehicle data generated by vehicles, the number of data applications is also increasing, and most application business scenarios not only require real-time data at the vehicle end, but also require analysis of long-period data.

[0026] Currently, vehicle data needs to be uploaded to the cloud and stored, and analyzed by the cloud, and the analysis results are fed back to the vehicle end. This way puts a huge resource pressure on the cloud.

[0027] The inventors found that the large demand for data by business applications does not match the limited resources of the cloud, and the structured data that intelligent networked vehicles need to upload and parse in real time can reach GB level per vehicle per month. For a host manufacturer with tens or hundreds of thousands of vehicles, it has high requirements for the overall data transmission link and storage resources, but the user value it creates is often not proportional to the investment. Therefore, it is urgently needed to perform lightweight processing on this part of data, reduce the total amount of data upload and storage under the premise of ensuring the stability of the original data application.

[0028] Secondly, in the process of processing and analyzing data, the massive data has a greater demand for cloud computing resources, and the cloud is difficult to meet the demand of processing all vehicles of a single vehicle model within a certain period of data or even simultaneously processing full data of multiple vehicle models. The current solution is to process the computing process in layers, and complete the computing task layer by layer. However, the above-mentioned mode takes too long, and part of the task is limited by resources and may not be able to complete the calculation in time (T+1 day task may take several days to complete), which affects the timeliness of the cloud non-real-time application. At the same time, due to the large amount of data, the real-time performance of data uploading and analysis is poor, and the limitation of the cloud real-time application is more obvious, especially when it comes to real-time data application for C-end users, the delay will cause very bad influence.

[0029] It can be seen that how to reduce the cloud computing pressure and reduce the network load has become a problem to be solved.

[0030] Figure 1 It is a framework schematic diagram of a data pre-processing method of a vehicle network provided by an embodiment of the application. The vehicle end includes a computing engine, a time series database, a vehicle end data application and a variety of controller signals. The cloud end includes a cloud end database, a cloud end computing engine and a cloud end data application.

[0031] By deploying a time series database on the vehicle end and providing a computing engine, the data analysis task of the business application can be pre-processed to the vehicle end, so that the data loop of the business application on the vehicle end can be realized. The data obtained from the vehicle end includes real-time data, short-period historical data analysis (week, month dimension), and for long-period data analysis requirements, the result data uploaded to the cloud end for further summary and calculation after a round of calculation on the vehicle end. The high-frequency data signals are trimmed and downsampled, effectively reducing the total amount of data uploaded to the cloud by a single vehicle, reducing the transmission and storage link pressure, relieving the computing pressure of long-period data analysis business, and improving the data timeliness, providing effective protection for cloud real-time business application.

[0032] For the vehicle end, the time series database can support the storage of raw data within a certain period, and the application on the vehicle end can directly analyze and process the data. The long link from the vehicle to the cloud, which is calculated by the cloud and then transmitted to the vehicle end, can be directly shortened to be completed entirely on the vehicle, realizing the data loop of the vehicle end.

[0033] For the cloud end, the uploading of raw data signals is reduced, mainly in the form of calculation result data, with additional low-frequency raw data, effectively reducing the total amount of uploaded data, relieving the pressure of data transmission, storage and computing resources on the cloud, meeting the business data demand while effectively improving the application timeliness.

[0034] Figure 2is a flowchart of a data preprocessing method of a vehicle network provided by an embodiment of the present application. The embodiment can be applied to the case of historical trip analysis or auxiliary intelligent driving by the vehicle end in the vehicle network. The method can be executed by a data preprocessing device of the vehicle network, which can be realized in the form of hardware and / or software. The data preprocessing device of the vehicle network can be configured in an electronic device such as an automobile controller. The automobile controller can be a vehicle information entertainment system controller, an intelligent driving domain controller or a whole vehicle controller. As shown in Figure 2 the method comprises the following steps.

[0035] Step S101: In response to a calculation task triggered by a user through a vehicle-end data application, a calculation engine executes the calculation task according to data in a time series database to obtain a task result.

[0036] Optionally, in response to a calculation task triggered by a user through a vehicle-end data application, a calculation engine executes the calculation task according to data in a time series database to obtain a task result, which can be implemented in the following manner.

[0037] In response to a trip analysis task triggered by a vehicle-end data application, a calculation engine performs statistical analysis according to relevant information of effective trips in a time series database to obtain driving behavior analysis results in a preset period.

[0038] Specifically, the calculation task can be a periodical data analysis service. Optionally, the calculation engine performs statistical analysis according to relevant information of effective trips in a time series database to obtain driving behavior analysis results in a preset period, which can be implemented in the following manner.

[0039] The calculation engine filters effective trips according to data in a time series database; obtains relevant information of the effective trips; and performs statistical analysis according to a preset period and the relevant information of the effective trips to obtain driving behavior analysis results in the preset period.

[0040] The relevant information includes one or more of the following: trip mileage, average speed, three-acceleration-one-super or energy consumption.

[0041] As for the driving behavior analysis period data analysis service, the original scheme needs to upload a large amount of original data signals from the vehicle end, including mileage, vehicle speed, acceleration, energy consumption, auxiliary driving function usage, etc., and the cloud end processes the data. The scheme of the application is redesigned, a database and a computing engine are deployed on the vehicle end, the original data can be directly recorded on the vehicle end for several months, and the driving behavior analysis algorithm can be directly deployed on the computing engine. The computing process originally in the cloud is moved to the vehicle end, which can support real-time or non-real-time trip recognition. The computing engine identifies a single valid trip and records the trip mileage, average vehicle speed, three rapid and one over-speed (rapid acceleration, rapid deceleration, rapid turning and over-speed), energy consumption and other related information, and performs statistical analysis on the data in weeks, months and years. The driving behavior of the user within a certain period is evaluated to obtain an analysis result. The analysis result is issued in the form of an interface to the output interface of the vehicle end data application in the vehicle machine for information display, so that the user can understand his own driving behavior.

[0042] In addition, the single trip result record can also support data analysis in weeks, months and years, and the vehicle end directly calculates and applies it, effectively shortening the data application link, and the trip recognition result information can replace part of the high-frequency original data signal uploaded to the cloud, improving the timeliness and reducing data transmission.

[0043] Step S102, feeding back the task result to the user through the vehicle end data application.

[0044] Optionally, the task result is fed back to the user through the vehicle end data application, which can be implemented by the following way:

[0045] Output the driving behavior analysis result in the preset period through the output interface of the vehicle end data application.

[0046] A time series database is deployed on the vehicle end to provide a computing engine, support algorithm model deployment, collect vehicle controller data signals from the time series database, record original data and result data calculated by the vehicle end algorithm within a certain period, and support vehicle end data application.

[0047] The time series database on the vehicle end is used to store data for a long time to meet the data needs of the vehicle end application. The data stored in the time series database serves as a unified data source for the vehicle end application, ensuring that the same data is only stored once on the vehicle end, while avoiding the consumption of storage resources on the vehicle end caused by each application storing data independently. The data can be used to support data analysis of all businesses and provide storage for computing process data of the application. Periodic data analysis applications can further analyze and process the preliminary calculation results of the algorithm, complete the entire business data loop directly on the vehicle end, and do not need to upload to the cloud.

[0048] The vehicle end still needs to return data to the cloud, mainly low-frequency raw data and application calculation result data, which obviously reduces the pressure on the entire transmission and storage link compared with the original scheme, and the cloud only needs to store the data required by regulations and problem troubleshooting, thereby effectively relieving the resource pressure caused by the rapid increase in the number of intelligent networked vehicles and the rapid increase in vehicle network data.

[0049] The data preprocessing method of the vehicle network provided by the embodiment of the application is that a computing engine and a time series database are deployed at the vehicle end to store vehicle data from the vehicle end. In response to a computing task triggered by a user through a vehicle end data application, the computing engine executes the computing task according to the data in the time series database to obtain a task result, and feeds back the task result to the user through the vehicle end data application. Compared with the current computing task performed by the cloud, the data preprocessing method of the vehicle network provided by the embodiment of the application completes the computing task by using the local computing engine, thereby avoiding the execution of the computing task by the cloud and reducing the computing pressure of the cloud. The computing engine on the local can quickly and stably complete the computing task according to the data stored in the time series database, thereby improving the reliability. The data lightweight of the application is mainly reflected in that the data does not need to be uploaded from the vehicle end to the cloud through preprocessing, the vehicle end directly uses the data, or only the required feature data and the calculation result data are uploaded, thereby reducing the data transmission amount.

[0050] On the basis of the above-mentioned embodiment, after the computing engine executes the computing task according to the data in the time series database to obtain a task result in response to a computing task triggered by a user through a vehicle end data application, the method further includes:

[0051] The computing engine generates training features according to historical data in the time series database, and uploads the training features to the cloud for training of an artificial intelligence model.

[0052] Current AI model training related to intelligent driving needs massive vehicle end high-frequency signal data support. First, data preprocessing is performed on the cloud to eliminate invalid data and process the data into feature value form, and then the data can be input into an algorithm model for training. Because the amount of data required for model training is huge, the entire data preprocessing process consumes a large amount of computing resources, and in the current situation of limited resources and excessive data volume, model training is difficult and time-consuming. The scheme of the application is redesigned, the vehicle end database and the computing engine are used to deploy preprocessing algorithms on the vehicle end, data screening and feature processing are performed on the vehicle end, the feature results are uploaded to the cloud, and the cloud algorithm model directly uses the data for training, which can effectively improve the algorithm iteration speed.

[0053] The above embodiment can generate training data of the artificial intelligence model trained by the vehicle end to the cloud, avoid generating training data by the cloud according to historical data, thereby reducing the cloud computing amount, reducing the data amount of network transmission, and improving the training efficiency of the artificial intelligence model.

[0054] Further, after uploading the training features to the cloud model for training of the artificial intelligence model, the method further comprises:

[0055] The computing engine acquires intelligent driving real-time data; the computing engine generates real-time features according to the real-time data; and the real-time features are uploaded to the artificial intelligence model of the cloud for analysis.

[0056] The output result of the artificial intelligence model is received; and the output result of the artificial intelligence model is used for vehicle end intelligent driving assistance.

[0057] Optionally, the computing engine acquires intelligent driving real-time data, which can be implemented as:

[0058] The computing engine acquires real-time data through a time series database; and / or, the computing engine acquires real-time data through a vehicle-mounted controller signal.

[0059] The vehicle-mounted controller signal includes a CAN signal, a LIN signal or an ETH signal, etc. The CAN signal is a signal transmitted by a controller area network (CAN, Controller Area Network). The LIN signal is a serial bus protocol for low-speed device communication in an automotive electronic system, which realizes single master and multi-slave distributed control based on UART / SCI, has low cost and low speed characteristics, and is mainly applied to vehicle body control systems such as windows and seats. The ETH signal is a vehicle-mounted Ethernet signal.

[0060] The above embodiment can generate real-time features at the vehicle end, and send the real-time features to the cloud. After inputting the real-time features to the artificial intelligence model of the cloud, the output result is obtained by the artificial intelligence model of the cloud according to the real-time features. The output result is sent to the vehicle end. The vehicle end assists driving according to the output result, realizes the effect of quickly using the artificial intelligence model of the cloud under the condition that the artificial intelligence model of the cloud is reserved.

[0061] On the basis of the above embodiment, the artificial intelligence model can also be deployed at the vehicle end after being trained. The artificial intelligence model is run by the computing engine. Real-time feature generation, artificial intelligence model running and vehicle end intelligent driving assistance according to the output result of the artificial intelligence model are completed at the vehicle end.

[0062] The above embodiment can deploy the artificial intelligence model to the vehicle end, so that the vehicle end completes the auxiliary driving according to the local artificial intelligence model, and further improves the auxiliary driving efficiency and reliability.

[0063] Figure 3 is a structural schematic diagram of a data pre-processing device of a vehicle network provided by an embodiment of the present application. The embodiment can be applicable to the case of historical trip analysis or auxiliary intelligent driving by a vehicle end in a vehicle network. The method can be executed by a data pre-processing device of a vehicle network. The data pre-processing device of the vehicle network can be realized in the form of hardware and / or software. The data pre-processing device of the vehicle network can be configured in an electronic device such as an automobile controller. As shown in the figure, the device is applied to a vehicle end. The vehicle end is deployed with a computing engine and a time series database. The time series database is used to store vehicle end data. The device comprises a computing engine processing module 21 and a feedback module 22. Figure 3

[0064] The computing engine processing module 21 is configured to, in response to a computing task triggered by a vehicle end data application by a user, execute the computing task according to data in the time series database by the computing engine, and obtain a task result.

[0065] The feedback module 22 is configured to feed back the task result to the user through the vehicle end data application.

[0066] On the basis of the above-mentioned embodiments, the computing engine processing module 21 is configured to, in response to a trip analysis task triggered by the vehicle end data application, perform statistical analysis according to relevant information of an effective trip in the time series database by the computing engine, and obtain a driving behavior analysis result in a preset period.

[0067] Correspondingly, the feedback module 22 is configured to output the driving behavior analysis result in the preset period through an output interface of the vehicle end data application.

[0068] On the basis of the above-mentioned embodiments, the computing engine processing module 21 is configured to:

[0069] The computing engine filters an effective trip according to data in the time series database.

[0070] The relevant information of the effective trip is obtained.

[0071] Statistical analysis is performed according to a preset period and the relevant information of the effective trip, and a driving behavior analysis result in the preset period is obtained.

[0072] On the basis of the above-mentioned embodiments, the device further comprises a historical feature generation module and a transmission module.

[0073] The historical feature generation module is configured to generate training features according to historical data in the time series database by the computing engine.

[0074] ​The transmission module is configured to upload the training features to the cloud for training of an artificial intelligence model.

[0075] On the basis of the above-mentioned embodiments, the real-time feature generation module is further configured to:

[0076] The real-time feature generation module is configured to: the computing engine acquires intelligent driving real-time data; and the computing engine generates real-time features according to the real-time data.

[0077] The transmission module is further configured to upload the real-time features to the artificial intelligence model of the cloud for analysis.

[0078] The output result of the artificial intelligence model is received from the cloud, and intelligent driving assistance is performed at the vehicle end according to the output result of the artificial intelligence model.

[0079] On the basis of the above-mentioned embodiments, the real-time feature generation module is further configured to: the computing engine acquires real-time data through a time series database; and / or the computing engine acquires real-time data through a vehicle-mounted controller signal.

[0080] On the basis of the above-mentioned embodiments, the relevant information includes one or more of a trip mileage, an average vehicle speed, three rapid accelerations and one overspeed, or energy consumption.

[0081] The data preprocessing method of the vehicle-to-network provided in the embodiments of the present application is characterized in that a computing engine and a time series database are deployed at the vehicle end to store vehicle data from the vehicle end. The computing engine processing module 21 is configured to respond to a computing task triggered by a user through a vehicle end data application, and the computing engine executes the computing task according to data in the time series database to obtain a task result. The feedback module 22 is configured to feed back the task result to the user through the vehicle end data application. Compared with the current computing method in which all computing tasks are performed by the cloud, the data preprocessing method of the vehicle-to-network provided in the embodiments of the present application completes the computing task through a local computing engine, thereby avoiding execution of the computing task by the cloud and reducing the computing pressure of the cloud. The computing engine on the local side can quickly and stably complete the computing task according to the data stored in the time series database, thereby improving the reliability. The data lightweight of the present application is mainly embodied in that the data does not need to be uploaded from the vehicle end to the cloud, the vehicle end directly uses the data, or only the required feature data and the computing result data are uploaded, thereby reducing the data transmission amount.

[0082] The data preprocessing device of the vehicle-to-network provided in the embodiments of the present application can execute the data preprocessing method of the vehicle-to-network provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0083] Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Electronic device 10 is intended to represent various forms of electronic devices such as automotive controllers, including in-vehicle infotainment system controllers, intelligent driving domain controllers, or vehicle controllers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0084] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0085] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as touch screen, physical button, etc.; output unit 17, such as various types of display, speaker, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0086] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as data pre-processing methods for vehicle-to-everything (V2X) networks.

[0087] In some embodiments, the data pre-processing method of vehicle-to-network can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the data pre-processing method of vehicle-to-network described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the data pre-processing method of vehicle-to-network by any other suitable means, such as by means of firmware.

[0088] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0089] Computer programs used to implement the data pre-processing method of vehicle-to-network of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program running on the processor implements the functions / operations specified in the flowcharts and / or the block diagrams. The computer program can execute entirely on a machine, partly on a machine, partly on a machine and partly on a remote machine or entirely on a remote machine or server.

[0090] The embodiments of the present application also provide a computer readable storage medium, which stores computer instructions for causing a processor to execute a data pre-processing method of vehicle-to-network, applied to a vehicle end, the vehicle end being deployed with a computing engine and a time series database, the time series database being used to store vehicle end data; the method comprises:

[0091] In response to a computing task triggered by a user through a vehicle end data application, the computing engine executes the computing task according to the data in the time series database to obtain a task result;

[0092] The task result is fed back to the user through the vehicle-side data application.

[0093] On the basis of the above-mentioned embodiments, in response to a calculation task triggered by the user through the vehicle-side data application, the calculation engine executes the calculation task according to the data in the time-series database to obtain a task result, comprising:

[0094] In response to a trip analysis task triggered through the vehicle-side data application, the calculation engine performs statistical analysis according to the related information of the valid trips in the time-series database to obtain a driving behavior analysis result in a preset period;

[0095] Correspondingly, the task result is fed back to the user through the vehicle-side data application, comprising:

[0096] The driving behavior analysis result in the preset period is output through the output interface of the vehicle-side data application.

[0097] On the basis of the above-mentioned embodiments, optionally, the calculation engine performs statistical analysis according to the related information of the valid trips in the time-series database to obtain a driving behavior analysis result in a preset period, comprising:

[0098] The calculation engine filters valid trips according to the data in the time-series database;

[0099] The related information of the valid trips is obtained;

[0100] The related information of the valid trips is obtained;

[0101] On the basis of the above-mentioned embodiments, optionally, after the calculation engine executes the calculation task according to the data in the time-series database in response to a calculation task triggered by the user through the vehicle-side data application to obtain a task result, further comprising:

[0102] The calculation engine generates training features according to the historical data in the time-series database;

[0103] The training features are uploaded to the cloud for training of an artificial intelligence model.

[0104] On the basis of the above-mentioned embodiments, optionally, after the training features are uploaded to the cloud model for training of an artificial intelligence model, further comprising:

[0105] The calculation engine obtains intelligent driving real-time data;

[0106] The calculation engine generates real-time features according to the real-time data;

[0107] uploading the real-time features to a cloud-side artificial intelligence model for analysis;

[0108] receiving an output result of the cloud-side artificial intelligence model according to the output result of the artificial intelligence model.

[0109] On the basis of the above-mentioned embodiments, optionally, the computing engine acquires intelligent driving real-time data, including:

[0110] The computing engine acquires real-time data through a time series database; and / or,

[0111] The computing engine acquires real-time data through a vehicle-mounted controller signal.

[0112] On the basis of the above-mentioned embodiments, optionally, the relevant information includes one or more of a trip mileage, an average vehicle speed, three-acceleration-one-superpass, or energy consumption.

[0113] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more wires, portable computer disks, hard disk drives, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disc read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0114] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0115] The systems and techniques described herein can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0116] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0117] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the spirit and scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in different orders, as long as the desired results of the present disclosure are achieved, and are not limited herein.

[0118] The specific embodiments described above are not intended to limit the scope of the present disclosure. Those skilled in the art will understand that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments without departing from the spirit and principles of the present disclosure. Any further modifications, equivalents, alternatives, and / or improvements made to the specific embodiments described above are intended to fall within the scope of the present disclosure.

Claims

1. A data preprocessing method for a vehicle-to-everything (V2X) network, characterized in that, Applied to a vehicle-side application, the vehicle-side application is equipped with a computing engine and a time-series database, the time-series database being used to store vehicle-side data; the method includes: In response to a computing task triggered by a user through a vehicle-side data application, the computing engine executes the computing task based on data in the time-series database and obtains the task result; The task results are fed back to the user through the vehicle-side data application.

2. The method according to claim 1, characterized in that, In response to a computing task triggered by a user through a vehicle-side data application, the computing engine executes the computing task based on data in the time-series database to obtain the task results, including: In response to a trip analysis task triggered by vehicle-side data applications, the computing engine performs statistical analysis based on relevant information of valid trips in the time series database to obtain driving behavior analysis results within a preset period. Accordingly, the task results are fed back to the user through the vehicle-side data application, including: The vehicle-side data application outputs the driving behavior analysis results within a preset period through its output interface.

3. The method according to claim 2, characterized in that, The calculation engine performs statistical analysis based on relevant information from valid trips in the time-series database to obtain driving behavior analysis results within a preset period, including: The calculation engine filters valid trips based on data in the time-series database; Obtain relevant information about the valid itinerary; Statistical analysis is performed based on the preset period and the relevant information of the effective travel to obtain the posture behavior analysis results within the preset period.

4. The method according to claim 1, characterized in that, In response to a computing task triggered by a user through a vehicle-side data application, after the computing engine executes the computing task based on data in the time-series database and obtains the task result, it also includes: The computational engine generates training features based on historical data in a time-series database; The training features are uploaded to the cloud for training the artificial intelligence model.

5. The method according to claim 4, characterized in that, After uploading the training features to the cloud model for training the artificial intelligence model, the process also includes: The computing engine acquires real-time data for intelligent driving; The computing engine generates real-time features based on real-time data; The real-time features are uploaded to an artificial intelligence model in the cloud for analysis; Receive the output results of the artificial intelligence model from the cloud; perform vehicle-side intelligent driving assistance based on the output results of the artificial intelligence model.

6. The method according to claim 5, characterized in that, The computing engine acquires real-time data for intelligent driving, including: The computing engine obtains real-time data from a time-series database; and / or, The computing engine acquires real-time data through signals from the vehicle controller.

7. The method according to claim 3, characterized in that, The relevant information includes one or more of the following: mileage traveled, average speed, speed limits, emergency stops, overtaking, or energy consumption.

8. A data pre-processing device for a vehicle-to-everything (V2X) network, characterized in that, Applied to a vehicle-mounted system, the vehicle-mounted system is equipped with a computing engine and a time-series database, the time-series database being used to store vehicle-mounted data; the device includes: The computing engine processing module is used to respond to computing tasks triggered by users through vehicle-side data applications. The computing engine executes the computing tasks based on data in the time-series database and obtains the task results. The feedback module is used to feed back the task results to the user through the vehicle-side data application.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the data preprocessing method for the vehicle network according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the data preprocessing method for the vehicle network as described in any one of claims 1-7.

Images