CN111866032A - A data processing method, apparatus and computing device - Google Patents

Abstract

The invention discloses a data processing method, device and computing device. The method includes: converting the data according to the data category, the converted data includes data description information and data content, and the data description information at least includes information representing the data category and a time stamp; according to the time sequence represented by the time stamps, converting The latter data is added to the data stream; based on the data description information, at least one type of data content in the data stream is processed to generate monitoring events and corresponding monitoring data.

Description

A data processing method, apparatus and computing device

technical field

The present invention relates to the technical field of intelligent networked vehicles, in particular to a data processing method, device and computing device.

Background technique

Intelligent Connected Vehicle (Intelligent Connected Vehicle) is a new generation of vehicles equipped with an intelligent operating system. It integrates advanced communication technology to realize the exchange and processing of intelligent information such as people, vehicles, roads, and the environment, serving efficient, safe, comfortable, Energy efficient driving experience. With the development of intelligent networked vehicles, more and more intelligent scenarios rely on data collection and analysis. Due to the sharp increase in the number of in-vehicle devices, the scale of data generated by the system is also growing explosively. Traditional cloud computing solutions are difficult to support more and more The ever-increasing data access and corresponding processing requirements.

In the traditional cloud computing solution, cloud computing is the main body, and the device side is only responsible for data collection and uploading. In terms of specific practices, it is required to collect data on demand on the device side, and then upload the data directly to the cloud server, while the core algorithms and business exports are implemented in the cloud, which is highly dependent on cloud computing. The disadvantages are mainly reflected in two aspects:

1) The data obtained by the cloud has limited dimensions, and the lack of data in other dimensions leads to a one-sided result of final data analysis and processing, with low accuracy. For example, driving behavior analysis usually only obtains vehicle position and speed information, while ignoring the environment, Data dimensions such as driver status can easily lead to one-sided analysis results.

2) The data is directly uploaded to the cloud, which is strongly dependent on cloud computing. The data is analyzed and processed in the cloud, which cannot meet the scenarios with high latency requirements, and the scale of data transmission is large, which is detrimental to bandwidth and user data privacy. Impact.

SUMMARY OF THE INVENTION

In view of the above problems, the present invention is proposed to provide a data processing method, apparatus and computing device that overcome the above problems or at least partially solve the above problems.

According to one aspect of the present invention, a data processing method is provided, comprising:

Converting the data according to the data category, the converted data includes data description information and data content, and the data description information includes at least information representing the data category and a timestamp;

Add the transformed data to the data stream according to the time sequence represented by the timestamp;

Based on the data description information, at least one category of data content in the data stream is processed to generate monitoring events and corresponding monitoring data.

Optionally, in the data processing method according to the present invention, the converting the data according to the data category includes: acquiring corresponding metadata according to the data category, where the metadata is data describing the data; according to the metadata description information, and convert the data into a format that conforms to the metadata description.

Optionally, in the data processing method according to the present invention, when the data is visual data, the converting the data includes: recognizing the change of the driver's fatigue state according to the visual data, and generating a data for characterizing the driver. Fatigue state data; obtain metadata corresponding to the data used to characterize the driver's fatigue state, and convert the data used to characterize the driver's fatigue state into a format that conforms to the metadata description.

Optionally, in the data processing method according to the present invention, the metadata is stored in the vehicle-mounted device in JSON format, XML format or plain text format.

Optionally, in the data processing method according to the present invention, the data description information further includes at least one of the following attributes of the data: data source, original signal name, access authority, data type, data unit and collection frequency .

Optionally, in the data processing method according to the present invention, the data includes a plurality of the following categories: vehicle-related data, driving-related data, positioning data, road-related data, and visual data.

Optionally, in the data processing method according to the present invention, the processing of at least one category of data content in the data stream based on the data description information includes: processing vehicle-related data in the data stream, to generate vehicle anomaly events and data used to characterize vehicle anomalies.

Optionally, in the data processing method according to the present invention, the processing of at least one type of data content in the data stream based on the data description information includes: processing vehicle-related data, driving-related data in the data stream data, road-related data, and visual data are processed to generate hazardous driving events and data used to characterize hazardous driving.

Optionally, in the data processing method according to the present invention, the processing of at least one category of data content in the data stream based on the data description information includes: processing driving-related data and visual data in the data stream Process to generate attentional anomaly events and data to characterize attentional anomalies.

Optionally, in the data processing method according to the present invention, the algorithm for processing the data stream is generated by the server and delivered to the vehicle-mounted device.

Optionally, in the data processing method according to the present invention, the method further includes sending the generated monitoring events and corresponding monitoring data to a server, and the server performs aggregation and analysis.

Optionally, in the data processing method according to the present invention, the method further includes: the server sends the analysis result of the monitoring event and the monitoring data to the application.

Optionally, in the data processing method according to the present invention, the application includes at least one of the following: an application for vehicle leasing, an application for vehicle sharing, an application for customizing auto insurance, and an application for vehicle-road coordination application.

According to another aspect of the present invention, a data processing device is provided, comprising:

a data access unit, adapted to convert the data according to the type of the data, the converted data includes data description information and data content, and the data description information at least includes information representing the vehicle data type and a time stamp;

a data stream generation unit, adapted to add the converted data to the data stream according to the time sequence represented by the timestamp;

The data stream processing unit is adapted to process at least one type of data content in the data stream based on the data description information to generate monitoring events and corresponding monitoring data.

According to yet another aspect of the present invention, a computing device is provided, comprising:

one or more processors;

memory;

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising means for performing a method according to the above instruction in any of the methods.

According to yet another aspect of the present invention, there is provided a computer-readable storage medium storing one or more programs including instructions that, when executed by a computing device, cause the computing device to execute according to any of the above methods.

According to the data processing solution provided by the embodiment of the present invention, by defining metadata, abstracting the original data, accessing and consuming data in a unified manner, it has the advantages of more flexible data access, more standardized data, and more unified processing methods.

In addition, the solution of the embodiment of the present invention also implements a data stream computing engine on the device side, so that business logic is run on the device side in a more direct way, shortening the distance between computing and data sources, and achieving more timely business decisions At the same time, it avoids uploading large-scale data to cloud servers, reduces data computing and operating costs, and avoids sensitive data being uploaded to the cloud, which has a certain protective effect on user privacy.

The above description is only an overview of the technical solutions of the present invention, in order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand , the following specific embodiments of the present invention are given.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered limiting of the invention. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

1 shows a schematic diagram of a data processing system 100 according to an embodiment of the present invention;

FIG. 2 shows a schematic diagram of a computing device 200 according to an embodiment of the present invention;

FIG. 3 shows a flowchart of a data processing method 300 according to an embodiment of the present invention;

FIG. 4 shows a structural diagram of a data processing apparatus 400 according to an embodiment of the present invention;

5 shows a schematic diagram of forming a data stream and processing the data stream in an embodiment of the present invention;

FIG. 6 shows a schematic diagram of an application scenario of a data processing method according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

First, the relevant terms involved in the embodiments of the present invention are defined as follows:

Meta data: It is the data that describes the data, mainly describing the name, type, source and other information of the data, so as to carry out the necessary specifications and constraints on the data.

Data Stream: The data is in the order of the time of generation, forming an unbounded data queue, called a data stream, which has strong timing and unbounded characteristics.

Complex Event Processing: The ability to make data decisions by analyzing time-series-based data streams, matching predetermined conditions or patterns, and extracting or monitoring meaningful events.

FIG. 1 shows a schematic diagram of a data processing system 100 according to one embodiment of the present invention. As shown in FIG. 1 , the system 100 includes a vehicle 110 and a server 120 , and the vehicle 110 and the server 120 can be connected through a network for communication. It should be noted that FIG. 1 is only for illustration, and the embodiment of the present invention does not limit the number of vehicles 110 included in the system 100 .

In addition to the basic configuration, the vehicle 110 is also provided with various collection devices such as sensors (not shown) and in-vehicle equipment 112 , through which various data collected during the driving of the vehicle are collected to generate in-vehicle data, and the in-vehicle equipment 112 The vehicle-mounted data collected by the collection device and the road-related data sent by the roadside unit can be acquired in real time, and the acquired data can be processed. In addition, the in-vehicle device 112 may also obtain in-vehicle data from an on-board diagnostic system (OBD). The present invention does not limit the specific manner in which the in-vehicle device 112 acquires data.

The data acquired by the in-vehicle device includes multiple categories, such as: vehicle-related data, driving-related data, positioning data, road-related data, and visual data. Vehicle-related data mainly refers to vehicle operating parameter data, such as engine data, chassis system data, and fuel consumption data. The driving-related data mainly refers to the running speed and acceleration of the vehicle. The positioning data mainly refers to the position of the vehicle at any time. The road-related data mainly refers to the static and/or dynamic information of all or part of the objects within the range of each road. The visual data mainly refers to the driver's video data collected by the in-vehicle camera, such as the driver's face video.

The server 120 may be, for example, a remote cloud server physically located in one or more locations, and the server 120 can perform various data interactions with the in-vehicle device 112 . The server 120 may also perform data interaction with various applications, for example, data interaction with applications for vehicle leasing, applications for vehicle sharing, applications for customizing auto insurance, and applications for vehicle-road coordination.

As mentioned above, in the existing solution, the device end is only responsible for data collection and uploading, and the data processing is performed by the server 120 in the cloud, which is highly dependent on cloud computing. On the one hand, the data obtained in the cloud has limited dimensions, and the lack of data in other dimensions leads to a one-sided result of final data analysis and processing, and the accuracy is not high; In high scenarios, and the scale of data transmission is large, both bandwidth and user data privacy are adversely affected.

Thus, in an embodiment according to the present invention, a data processing apparatus 400 is arranged in the vehicle 110 (in some embodiments, the apparatus 400 may be implemented as a part of the in-vehicle equipment 112, such as a The embodiment does not limit this), a data flow calculation engine is implemented in the device 400, and the business logic is run on the device side in a more direct way, shortening the distance between the calculation and the data source, and making more timely business decisions and response, and avoid sensitive data to the cloud, which has a certain protective effect on user privacy. According to an embodiment of the present invention, the apparatus 400 may be implemented by a computing device.

FIG. 2 shows a schematic diagram of a computing device 200 according to one embodiment of the present invention. As shown in FIG. 2 , in a basic configuration 202 , computing device 200 typically includes system memory 206 and one or more processors 204 . Memory bus 208 may be used for communication between processor 204 and system memory 206 .

Depending on the desired configuration, the processor 204 may be any type of process including, but not limited to, a microprocessor (μP), a microcontroller (μC), a digital information processor (DSP), or any combination thereof. Processor 204 may include one or more levels of cache, such as L1 cache 210 and L2 cache 212 , processor core 214 , and registers 216 . Exemplary processor cores 214 may include arithmetic logic units (ALUs), floating point units (FPUs), digital signal processing cores (DSP cores), or any combination thereof. The example memory controller 218 may be used with the processor 204 , or in some implementations, the memory controller 218 may be an internal part of the processor 204 .

Depending on the desired configuration, system memory 206 may be any type of memory including, but not limited to, volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. System memory 206 may include operating system 220 , one or more applications 222 , and program data 224 . Application 222 is actually a number of program instructions that instruct processor 204 to perform corresponding operations. In some implementations, the application 222 may be arranged to cause the processor 204 to operate with the program data 224 on the operating system.

Computing device 200 may also include an interface bus 240 that facilitates communication from various interface devices (eg, output device 242 , peripheral interface 244 , and communication device 246 ) to base configuration 202 via bus/interface controller 230 . Example output devices 242 include graphics processing unit 248 and audio processing unit 250 . They may be configured to facilitate communication via one or more A/V ports 252 with various external devices such as displays or speakers. Example peripheral interfaces 244 may include serial interface controller 254 and parallel interface controller 256, which may be configured to facilitate communication via one or more I/O ports 258 and input devices such as keyboard, mouse, pen, etc. , voice input devices, touch input devices) or other peripherals (eg printers, scanners, etc.) The example communication device 246 may include a network controller 260 that may be arranged to facilitate communication via one or more communication ports 264 with one or more other computing devices 262 over a network communication link.

A network communication link may be one example of a communication medium. Communication media may typically embody computer readable instructions, data structures, program modules in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media. A "modulated data signal" can be a signal of which one or more of its data sets or whose alterations can be made in such a way as to encode information in the signal. By way of non-limiting example, communication media may include wired media, such as wired or leased line networks, and various wireless media, such as acoustic, radio frequency (RF), microwave, infrared (IR), or other wireless media. The term computer readable medium as used herein may include both storage media and communication media.

In the computing device 200 according to the present invention, the application 222 includes a data processing apparatus 400 including a plurality of program instructions that may instruct the processor 204 to perform the data processing method 300 .

FIG. 3 shows a flowchart of a data processing method 300 according to an embodiment of the present invention. The method 300 is suitable for execution in a computing device, such as the aforementioned computing device 200 . As shown in FIG. 3, the method 300 begins at step S310. In step S310, the in-vehicle device 112 acquires various data, such as various in-vehicle data and road-related data, and for the acquired data, converts the data according to the data category, and the converted data includes data description information and data content .

In order to convert various data into data in a unified format, the embodiment of the present invention defines the metadata of the vehicle terminal to abstract the original data, so that the data description of the data can be reflected by the metadata, so that the metadata can be used in a unified manner. way to access and consume data.

Specifically, the data description information includes various attributes of the data, such as information characterizing the data category, data source, original signal name, access authority, data type, data unit, collection frequency, and time stamp. Here, the information representing the data category can be represented by the data name, which is the unique identifier of the category to which the data belongs, that is, each category of data corresponds to a data name, and different categories of data correspond to different data names. An example of the structure of the metadata of the in-vehicle device is shown in the following table:

In addition to the metadata attributes listed in the table, more attributes can be extended according to actual business requirements, such as: data category (Category), description (Description), other extended attributes (External), etc., in order to analyze data from more dimensions Describe and constrain.

In terms of expression, metadata is usually stored in JSON format, a simple metadata file example is shown below.

[

{"name":"VIN",

"signal":"VINString",

"permission":["DD_VEHICLE_INFO"],

"source": "car",

"type":"string"

},{

"name":"AcAutoMode",

"signal":"",

"permission":["DD_VEHICLE_INFO"],

"source":"car",

"type": "int32"

},{

"name":"VehicleSpeed",

"signal":"com.yunos.car.speed",

"permission":["DD_VEHICLE_INFO"],

"source": "car",

"type": "double"

},{

"name":"DriverStatus",

"signal":"com.yunos.vision.visionservice.signal.drive",

"description":"driver motion signal",

"permission":["DD_VEHICLE_INFO"],

"source":"vision",

"type": "int32"

}]

In addition to being stored in JSON format, metadata can also be stored in the in-vehicle device in other formats such as XML format and plain text format.

Through the definition of metadata, data can be easily transformed. Specifically, for each piece of data to be converted, first, the corresponding metadata is obtained according to the type of the data; then, according to the description information of the metadata, the data is converted into a format conforming to the description of the metadata.

In this embodiment of the present invention, each type of data corresponds to one type of metadata, and different types of data correspond to different metadata; each type of metadata may correspond to a data conversion algorithm, and data corresponding to different metadata Conversion algorithms vary.

As shown in Figure 5, for vehicle-related data (data corresponding to vehicle signals), the corresponding data conversion algorithm is conversion algorithm A; for driving-related data (data corresponding to driving signals), the corresponding data conversion algorithm is Conversion algorithm B; for positioning data or position data (data corresponding to the position signal), the corresponding data conversion algorithm is conversion algorithm C.

As for the visual data (data corresponding to the video signal), the data conversion algorithm determined according to the metadata of the visual data also includes an attention recognition algorithm. The attention recognition algorithm can identify changes in the driver's fatigue state from the visual data. And generate the data used to characterize the driver's fatigue state, and then convert the data used to characterize the driver's fatigue state into a format that conforms to the metadata description.

In the embodiment of the present invention, the data conversion algorithm can also use the metadata to verify the original data, find and filter out abnormal data in time, and check the data type and take the data value according to the constraints of the metadata. Scope verification, screening data at an earlier stage to ensure data quality for subsequent processing.

After converting the data, the method 300 proceeds to step S320. In step S320, the converted data is added to the data stream according to the time sequence indicated by the time stamps. As shown in Figure 5, vehicle-related data corresponds to some converted data, driving-related data corresponds to some converted data, visual data corresponds to some converted data, and positioning data corresponds to some converted data. Time-sequentially added to the data queue, forming a data stream.

Then, in step S330, based on the data description information, at least one category of data content in the data stream is processed to generate monitoring events and corresponding monitoring data. In one implementation, complex event processing (CEP) may be performed on a data stream based on a data stream processing algorithm to generate monitoring events and corresponding monitoring data. In the embodiment of the present invention, the in-vehicle device 112 includes a CEP engine (or a data stream processing engine), and various data stream processing algorithms can be added to the in-vehicle device 112 according to specific business requirements.

The CEP engine takes data flow as the processing object and provides basic data flow operation operators. The upper-level business logic completes more complex calculations by combining data flow operators to meet flexible business needs. The CEP engine draws on the relatively mature CEP technology theory in the industry, and implements several core data flow operators to meet most data processing requirements. Examples of some data flow operators are shown in the following table:

In addition to the above basic data flow operators, the CEP engine also implements higher-order data flow operators, such as statistical operators used to calculate the average, maximum, minimum, variance of a data sequence of a specified length, and feature extraction. The operator is used to calculate the feature vector of a specific data stream, and the classification operator is used for basic classification operations.

Based on the CEP engine, specific business logic and data stream processing algorithms can be implemented to support different business scenarios. As shown in FIG. 5 , the data stream processing algorithm may include a vehicle abnormality monitoring algorithm. The vehicle abnormality monitoring algorithm can generate vehicle abnormal events and data for characterizing vehicle abnormality by processing vehicle-related data in the data stream. The data stream processing algorithm may also include a dangerous driving monitoring (recognition) algorithm. The dangerous driving monitoring algorithm can generate driving behavior events by processing vehicle-related data, driving-related data, road-related data and visual data in the data stream. and driving behavior data, such as dangerous driving events and data used to characterize dangerous driving. The data stream processing algorithm may also include an attention anomaly monitoring (recognition) algorithm. The attention anomaly monitoring algorithm can generate attention anomalies and be used to characterize attention anomalies by processing driving-related data and visual data in the data stream. The data.

It should be noted that, in the embodiment of the present invention, the metadata can express not only the original data, but also the transformed data or the final output data, so as to achieve the consistency of the data specification. That is, the above monitoring data can also be expressed by metadata. For example, the data used to represent the driver's fatigue state after processing the original video stream data also has corresponding metadata. Using metadata of output data as part of opening to the outside world helps visitors understand how data is defined and used.

The data processing results can be output in different ways, for example:

1) Open the analyzed data to upper-layer applications in the form of API;

2) Directly notify the user in the form of an alarm;

3) Upload the data to the cloud, and do in-depth analysis and opening on the cloud service platform.

4) Send data to a specific application for visual display in the application.

FIG. 6 shows a schematic diagram of an application scenario of a data processing method according to an embodiment of the present invention. As shown in FIG. 6 , the application scenario includes a vehicle terminal (vehicle device), a cloud control platform (server), and an application. The vehicle terminal and the cloud establish a two-way data channel to connect the two, making full use of the respective advantages of terminal computing and cloud computing to meet the needs of more abundant and flexible IoV services, as follows.

First, the cloud integration of algorithm logic is based on different business requirements on the cloud control platform in the cloud, according to the basic vehicle model and vehicle owner model, to develop corresponding algorithm scripts or rule engines, form business scripts, and send them to the terminal. In the data flow framework, the real-time calculation of the data flow on the end is achieved. For the Internet of Vehicles business, this solution has built-in vehicle monitoring business, driving behavior and dangerous driving identification business, fatigue and distraction identification business, fuel consumption analysis business, etc. During the operation process, the cloud can update the relevant algorithms on demand and update to the end immediately And to be unaware of the system and the user. All businesses process data streams in this unified way, so the solution is highly scalable, and more businesses can be expanded only by adding more algorithm logic in the cloud.

Secondly, the cloud integration of data services, the output data calculated by the vehicle terminal for specific IoV services can be uploaded to the cloud on demand, and the analysis based on historical big data can be done on the cloud control platform to fully mine the historical data and data of vehicles. Driving behavior data can assist customers in in-depth analysis through visualization, and the results after analysis can be opened to other applications to support different user needs, such as vehicle leasing and sharing services, UBI customized auto insurance services, and vehicle-road collaboration services, etc. Here UBI refers to insurance based on driving behavior.

To sum up, the solution of the embodiment of the present invention starts from the application scenario of intelligent networked vehicles, closely integrates data with business, and provides comprehensive collection of vehicle static data, driving dynamic data, road data, etc. Flexible and efficient analysis and processing methods monitor the state of the vehicle in a quasi-real-time manner, provide early warnings for vehicle body abnormalities, and make real-time analysis and decision-making on the driver's driving behavior, identify dangerous driving behaviors, and take the trip as a unit. Behavior makes an overall evaluation to assist the driver to develop correct driving habits. In addition, corresponding to high-risk driving actions such as fatigued driving and distracted driving, this solution integrates in-vehicle camera data, integrates image analysis and recognition technology, and realizes real-time fatigue driving and distracted driving detection. When driving, timely and necessary warnings are given to drivers to avoid high-risk driving behaviors and effectively reduce the risk of traffic accidents.

In terms of specific business support, this solution provides the most basic data processing framework. After processing, the vehicle-end data is uniformly output to the cloud data analysis platform, and the historical data is aggregated in the cloud, providing analysis service capabilities based on big data, and finally output to various business. Specifically, on the one hand, abnormal vehicle condition data for a specific model car series can be output to the depot and repair station, assisting the depot to improve and optimize the design plan, and help the repair station to make vehicle diagnosis and prediction more accurately. After the data of driving behavior analysis is aggregated in the cloud, the driving habits of drivers can be more accurately perceived. After such data is combined with the insurance business, differentiated auto insurance services can be provided and the cost of claim settlement can be reduced. For the shared travel business or the truck logistics business, it can help the operating company to more accurately evaluate the driving habits of the hired drivers, and provide targeted training and positive guidance.

FIG. 4 shows a structural diagram of a data processing apparatus 400 according to an embodiment of the present invention. 4, apparatus 400 includes:

The data access unit 410 is adapted to convert the data according to the type of the data, the converted data includes data description information and data content, and the data description information at least includes the information of the data type and a time stamp;

The data stream generation unit 420 is adapted to add the converted data to the data stream according to the time sequence represented by the timestamp;

The data stream processing unit 430 is adapted to process at least one type of data content in the data stream based on the data description information to generate monitoring events and corresponding monitoring data.

For the specific processing performed by the data access unit 410, the data stream generation unit 420 and the data stream processing unit 430, reference may be made to the description in the method 300, which will not be repeated here.

The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with teaching based on this. The structure required to construct such a system is apparent from the above description. Furthermore, the present invention is not directed to any particular programming language. It is to be understood that various programming languages may be used to implement the inventions described herein, and that the descriptions of specific languages above are intended to disclose the best mode for carrying out the invention.

In the description provided herein, numerous specific details are set forth. It will be understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Claims (16)

1. A method of data processing, comprising:

converting data according to the category of the data, wherein the converted data comprises data description information and data content, and the data description information at least comprises information for representing the category of the data and a timestamp;

adding the converted data to the data stream in the time sequence indicated by the time stamps;

based on the data description information, at least one category of data content in the data stream is processed to generate monitoring events and corresponding monitoring data.

2. The data processing method of claim 1, wherein the converting the data according to the category of the data comprises:

acquiring corresponding metadata according to the category of the data, wherein the metadata is data describing the data;

and converting the data into a format conforming to the description of the metadata according to the description information of the metadata.

3. The data processing method of claim 2, wherein, when the data is visual data, the converting the data comprises:

identifying changes of the fatigue state of the driver according to the visual data, and generating data for representing the fatigue state of the driver;

and acquiring metadata corresponding to the data for representing the fatigue state of the driver, and converting the data for representing the fatigue state of the driver into a format conforming to the description of the metadata.

4. The data processing method of claim 2, wherein the metadata is stored in the vehicle-mounted device in a JSON format, an XML format, or a plain text format.

5. The data processing method of claim 1, wherein the data description information further comprises at least one of the following attributes of the data: data source, original signal name, access authority, data type, data unit and acquisition frequency.

6. The data processing method of claim 1, wherein the data comprises a plurality of the following categories: vehicle related data, travel related data, positioning data, road related data and visual data.

7. The data processing method of claim 1, wherein the processing at least one category of data content in the data stream based on the data description information comprises: vehicle-related data in the data stream is processed to generate vehicle anomaly events and data characterizing the vehicle anomalies.

8. The data processing method of claim 1, wherein the processing at least one category of data content in the data stream based on the data description information comprises: the vehicle-related data, the travel-related data, the road-related data, and the visual data in the data stream are processed to generate a dangerous driving event and data characterizing dangerous driving.

9. The data processing method of claim 1, wherein the processing at least one category of data content in the data stream based on the data description information comprises: the driving-related data and the visual data in the data stream are processed to generate an attention deficit event and data characterizing the attention deficit.

10. The data processing method of claim 1, wherein an algorithm for processing the data stream is generated by a server and issued to the in-vehicle device.

11. The data processing method of claim 1, further comprising sending the generated monitoring events and corresponding monitoring data to a server for aggregation and analysis by the server.

12. The data processing method of claim 11, further comprising: and the server sends the analysis result of the monitoring event and the monitoring data to the application.

13. The data processing method of claim 12, wherein the application comprises at least one of:

an application for vehicle rental, an application for vehicle sharing, an application for customizing a car insurance, and an application for vehicle-road coordination.

14. A data processing apparatus comprising:

the data access unit is suitable for converting data according to the category of the data, the converted data comprises data description information and data content, and the data description information at least comprises information for representing the category of the data and a timestamp;

a data stream generation unit adapted to add the converted data to the data stream in chronological order indicated by the time stamps;

and the data stream processing unit is suitable for processing at least one type of data content in the data stream based on the data description information so as to generate monitoring events and corresponding monitoring data.

15. A computing device, comprising:

at least one processor; and

a memory storing program instructions configured for execution by the at least one processor, the program instructions comprising instructions for performing the method of any of claims 1-13.

16. A readable storage medium storing program instructions that, when read and executed by a computing device, cause the computing device to perform the method of any of claims 1-13.

Images