WO2021237465A1 - 数据处理方法、装置及设备 - Google Patents

数据处理方法、装置及设备 Download PDF

Info

Publication number
WO2021237465A1
WO2021237465A1 PCT/CN2020/092381 CN2020092381W WO2021237465A1 WO 2021237465 A1 WO2021237465 A1 WO 2021237465A1 CN 2020092381 W CN2020092381 W CN 2020092381W WO 2021237465 A1 WO2021237465 A1 WO 2021237465A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
driving
historical
vehicle
historical driving
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/092381
Other languages
English (en)
French (fr)
Inventor
包那日松
张桂成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to CN202080004348.1A priority Critical patent/CN112543937A/zh
Priority to PCT/CN2020/092381 priority patent/WO2021237465A1/zh
Priority to EP20937789.4A priority patent/EP4148700A4/en
Priority to KR1020227045056A priority patent/KR102992439B1/ko
Priority to JP2022572680A priority patent/JP7662668B2/ja
Publication of WO2021237465A1 publication Critical patent/WO2021237465A1/zh
Priority to US17/993,609 priority patent/US12482226B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
    • G11B27/02—Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
    • G11B27/031—Electronic editing of digitised analogue information signals, e.g. audio or video signals
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
    • G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0808—Diagnosing performance data
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data

Definitions

  • This application relates to the technical fields of smart driving and smart cars, and in particular to a data processing method, device, and equipment.
  • a driving recorder can be installed in many vehicles, and the driving recorder can shoot and store the video of the vehicle in the process of driving.
  • the video taken by the dash cam and the time the video was taken can be stored in the preset storage space.
  • special circumstances such as a vehicle accident, a user recalling a driving scene, etc., the user needs to find the corresponding video segment in the preset storage space.
  • the user usually estimates the approximate time and searches for the corresponding video in the preset storage space according to the estimated time.
  • the efficiency of finding the required video segment in the above is low.
  • the embodiments of the present application provide a data processing method, device, and equipment. Improve the search efficiency of video segments.
  • an embodiment of the present application provides a data processing method.
  • the method includes: acquiring first data and a first historical driving characteristic, and determining that the vehicle is abnormal in a first period according to the first data and the first historical driving characteristic; Mark the driving record video of the vehicle according to the first time period.
  • the first data includes the first driving data of the vehicle in the first time period, and the first historical driving characteristic is determined according to the historical driving data of the vehicle.
  • the first data can reflect the driving situation of the vehicle in the first time period
  • the first historical driving characteristic can reflect the driving habits of the driver of the vehicle. Since the user's driving habits are usually relatively fixed, according to the first driving data and the first historical driving characteristics, it can be accurately determined whether the vehicle is abnormal in the first time period.
  • the driving record video taken by the camera device can be marked to record the abnormality of the vehicle in the first time period, so that the driving record video can be accurately marked. Record the annotation result of the video, you can find the required video accurately and quickly, and improve the efficiency of video search.
  • the first driving data includes at least one of the following data: status data of components in the vehicle; operating data of components in the vehicle; or sensor data collected by components in the vehicle.
  • the first driving data includes one or more of component status data, operating data or sensor data. These data are all generated during the operation of the vehicle and can accurately reflect the driving situation of the vehicle. Therefore, it is possible to accurately determine whether the vehicle is abnormal in the first period of time according to the above-mentioned first driving data.
  • the first historical driving feature includes: multiple historical data curves corresponding to various historical driving data, the historical data curves are used to indicate the distribution law of the historical driving data, and the historical driving data includes at least one of the following : Historical status data of components in the vehicle; historical operating data of components in the vehicle; or historical sensor data collected by components in the vehicle.
  • the historical driving data includes one or more of the historical state data, historical operating data or historical sensor data of the components. These data are all generated during the historical operation of the vehicle and can accurately reflect the vehicle.
  • the historical driving situation of the vehicle reflects the user’s driving habits. Therefore, according to the above-mentioned first historical driving characteristic, it can be accurately determined whether the vehicle is abnormal in the first period of time.
  • the first historical driving characteristic may be obtained in the following manner: the historical driving data is processed through the first model to obtain the first historical driving characteristic; wherein, the first model is the same for multiple groups.
  • each group of first samples in the multiple groups of first samples includes: sample driving data and sample historical driving characteristics.
  • the first module has the function of acquiring the formal characteristics of the driving data. Therefore, by processing the historical sample data through the first model, the first module can be accurately obtained. Historical driving characteristics.
  • the similarity between the first data and the first historical driving characteristics reflects the similarity between the operation of the vehicle in the first period and the user's driving habits. Since the user's driving habits are usually fixed, , Through the similarity, it can be accurately determined whether the vehicle is abnormal in the first period.
  • the similarity between the first data and the first historical driving characteristic may be determined in the following manner: the first data and the first historical driving characteristic are processed through the second model to obtain the similarity;
  • the second model is obtained by learning from multiple sets of second samples, each of the multiple sets of second samples includes sample data, sample driving characteristics, and sample similarity, and the sample data includes sample driving data.
  • the second model has the function of determining the similarity between the data and the driving characteristics. Therefore, the first data and the first historical driving characteristics are analyzed by the second model. By processing, the similarity between the first data and the first historical driving feature can be accurately determined.
  • processing the first data and the first historical driving characteristics through the second model to obtain the similarity includes: determining the first data curve corresponding to the first data through the second model; The model compares the first data curve and the historical data curve in the first historical driving characteristic to obtain the similarity.
  • the first data curve can accurately reflect the first data. Therefore, by comparing the first data curve with the historical data curve, the similarity can be accurately obtained.
  • the first data further includes scene data
  • the scene data includes at least one of the following information: time information, location information, road condition information, or weather information.
  • the user's driving habits in different scenarios may be different. Therefore, when the first data also includes scenario data, it can be determined that the user is in the first period of time according to the scenario data.
  • the driving scene in this way, based on the first data, it can be more accurately determined whether the vehicle is abnormal in the first time period.
  • the first historical driving characteristic may be obtained in the following manner: according to scene data, the first historical driving characteristic is determined from among a plurality of historical driving characteristics.
  • the acquired first historical driving feature is related to the scene data, so that the scene corresponding to the first data and the scene corresponding to the first historical driving feature are the same, so that the accuracy of determining whether the vehicle is abnormal in the first period of time is more accurate. high.
  • the driving record video of the vehicle may be marked according to the first time period in the following manner: abnormal information is generated; and the abnormal information is marked in the driving record video according to the first time period.
  • the abnormality information includes at least one of the following information: abnormality level, abnormality type, or abnormality description information.
  • the user can accurately and quickly find the desired video based on the marking result of the driving record video, which improves the efficiency of video search.
  • an embodiment of the present application provides a data processing device, including: an acquisition module, a determination module, and a labeling module, where:
  • the acquisition module is configured to acquire first data and a first historical driving characteristic, the first data includes first driving data of a vehicle in a first period, and the first historical driving characteristic is based on the historical driving of the vehicle The data is confirmed;
  • the determining module is configured to determine that the vehicle is abnormal in the first time period according to the first data and the first historical driving characteristic
  • the labeling module is configured to label the driving record video of the vehicle according to the first time period.
  • the first driving data includes at least one of the following data:
  • the first historical driving feature includes: a plurality of historical data curves corresponding to various historical driving data, the historical data curves are used to indicate the distribution law of the historical driving data, the The historical driving data includes at least one of the following:
  • the acquisition module is specifically configured to:
  • the first model is obtained by learning from multiple groups of first samples, and each group of first samples in the multiple groups of first samples includes: sample driving data and sample historical driving characteristics.
  • the determining module is specifically configured to:
  • the determining module is specifically configured to:
  • the second model is obtained by learning from multiple sets of second samples, each of the multiple sets of second samples includes sample data, sample driving characteristics, and sample similarity, and the sample data includes samples Driving data.
  • the determining module is specifically configured to:
  • the second model is used to compare the first data curve and the historical data curve in the first historical driving characteristic to obtain the similarity.
  • the first data further includes scene data
  • the scene data includes at least one of the following information:
  • Time information location information, road conditions or weather information.
  • the determining module is specifically configured to:
  • the first historical driving characteristic is determined among a plurality of historical driving characteristics.
  • the labeling module is specifically configured to:
  • the abnormal information is marked in the driving record video.
  • the abnormal information includes at least one of the following information:
  • Anomaly level, anomaly type, or anomaly description information is anomaly level, anomaly type, or anomaly description information.
  • an embodiment of the present application provides a data processing device, the data processing device includes a memory and a processor, the memory stores computer program instructions, and the processor runs the computer program instructions to perform any of the tasks in the first aspect. One of the operations described.
  • an embodiment of the present application provides a computer storage medium, which is characterized by including computer instructions, which implement the method described in any one of the first aspects when the computer instructions are executed by a processor.
  • an embodiment of the present application provides a computer program product, characterized in that, when the computer program product runs on a processor, the method described in any one of the first aspect is implemented.
  • the data processing method, device, and equipment provided by the embodiments of the present application can obtain the first data and the first historical driving characteristic of the vehicle in the first time period, and determine that the vehicle is in the first time period according to the first data and the first historical driving characteristic. An abnormality occurs, and the driving record video of the vehicle is marked according to the first time period.
  • the first data may reflect the driving situation of the vehicle in the first time period
  • the first historical driving characteristic may reflect the driving habits of the driver of the vehicle. Since the user's driving habits are usually relatively fixed, based on the first driving data and the first historical driving characteristics, it can be determined whether the vehicle is abnormal in the first time period.
  • the driving record video taken by the camera device can be marked to record the abnormality of the vehicle in the first time period, so that the driving record video can be accurately marked. Recording the annotation results of the video can accurately and quickly find the required video, and improve the efficiency of video search.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the application
  • FIG. 2A is a schematic diagram of a video acquisition method provided by an embodiment of this application.
  • 2B is a schematic diagram of another video acquisition method provided by an embodiment of this application.
  • 2C is a schematic diagram of another video acquisition method provided by an embodiment of this application.
  • FIG. 3 is a schematic flowchart of a data processing method provided by an embodiment of this application.
  • FIG. 4 is a schematic diagram of driving data and driving characteristics provided by an embodiment of the application.
  • FIG. 5A is a schematic diagram of obtaining historical driving data according to an embodiment of the application.
  • FIG. 5B is another schematic diagram of obtaining historical driving data according to an embodiment of the application.
  • FIG. 6 is a schematic diagram of historical driving characteristics provided by an embodiment of this application.
  • FIG. 7A is a schematic diagram of determining similarity provided by an embodiment of the application.
  • FIG. 7B is a schematic diagram of determining similarity provided by an embodiment of the application.
  • FIG. 8 is a schematic diagram of a video viewing method provided by an embodiment of the application.
  • FIG. 9 is a schematic diagram of a video tagging method provided by an embodiment of the application.
  • FIG. 10 is a schematic diagram of a video viewing method provided by an embodiment of the application.
  • FIG. 11 is a schematic flowchart of another data processing method provided by an embodiment of the application.
  • FIG. 12A is a schematic structural diagram of a driving recording device provided by an embodiment of this application.
  • FIG. 12B is a schematic structural diagram of another driving recording device provided by an embodiment of the application.
  • FIG. 13A is a schematic diagram of a device connection provided by an embodiment of this application.
  • FIG. 13B is a schematic diagram of another device connection provided by an embodiment of this application.
  • FIG. 13C is a schematic diagram of another device connection provided by an embodiment of this application.
  • 14A is a schematic structural diagram of a vehicle provided by an embodiment of the application.
  • 14B is a schematic structural diagram of another vehicle provided by an embodiment of the application.
  • 15 is a schematic structural diagram of a data processing device provided by an embodiment of this application.
  • FIG. 16 is a schematic diagram of the hardware structure of the data processing device provided by this application.
  • Vehicles The vehicles involved in this application may include private cars, buses, freight vehicles, passenger vehicles, motorcycles, etc.
  • the components in the vehicle may be parts or sensors in the vehicle, and the parts may be parts that maintain the operation of the vehicle.
  • the parts may include engines, generators, shock absorbers, lights, and so on.
  • the sensors may include temperature sensors, speed sensors, acceleration sensors, and so on.
  • Driving data refers to the data generated by the vehicle during driving.
  • the driving data may include at least one of the following data: status data of the component, operating data of the component, or sensor data collected by the component.
  • Status data is used to indicate the status of the component.
  • the status data of a car light is used to indicate whether the status of the car light is on or off
  • the status data of an engine is used to indicate that the state of the engine is on or paused
  • the status data of a solenoid valve is used to indicate that the state of the solenoid valve is open or closed.
  • Operating data is used to indicate the data generated during the operation of the component.
  • the operating data of the engine may include the rotational speed of the engine
  • the operating data of the electronic shifter may include the gear position of the electronic shifter
  • the operating data of the battery may include the remaining power of the battery.
  • Sensor data refers to the data collected by the sensor.
  • the sensor data may include: the temperature collected by the temperature sensor, the speed collected by the speed sensor, and the air-fuel ratio collected by the air-fuel ratio sensor.
  • the data generated by different components may be different, and the components may generate one or more of status data, operating data, and sensor data.
  • some components generate status data
  • some components may generate status data and operating data
  • some components generate sensor data.
  • the top switch can generate status data
  • the engine can generate status data and operating data
  • the temperature sensor can generate sensor data.
  • Driving record video refers to the video taken during the driving of the vehicle.
  • the video may include the video obtained by shooting around the vehicle body and the video obtained by shooting the inside of the vehicle.
  • the video is captured by camera equipment, which can be a device that comes with the vehicle or a device installed on the vehicle.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the application.
  • the vehicle includes engine electronics, disk electronics, body electronics, safety and comfort systems, entertainment communication systems, and camera equipment.
  • the engine electronic system may include: engine management electronic control unit (ECU), battery, generator, starter, temperature sensor, knock sensor, air-fuel ratio sensor, oxygen sensor, engine wiring harness, cooling system, ignition system, Intake and exhaust system, variable speed transmission system, electronic fuel pump, etc.
  • ECU engine management electronic control unit
  • generator starter
  • temperature sensor knock sensor
  • air-fuel ratio sensor oxygen sensor
  • engine wiring harness cooling system
  • ignition system ignition system
  • Intake and exhaust system variable speed transmission system
  • variable speed transmission system electronic fuel pump, etc.
  • the chassis electronic system may include: steering system, suspension system, braking system, etc.
  • Body electronics can include: business continuity management (BCM) system, relay/fuse, floor wiring harness, door wiring harness, roof wiring harness, instrument panel wiring harness, universal serial bus (USB)/HD Multimedia interface (high definition multimedia interface, HDMI) cables, electric rearview mirrors, window lift motors, tailgate electric struts, door and window switches, wiper motors, sunroof motors, vehicle diagnostics (on board diagnostics, OBD), lighting systems , Switches, etc.
  • BCM business continuity management
  • USB universal serial bus
  • HDMI high definition multimedia interface
  • Safety and comfort systems can include: safety systems, seat adjustment motors, active noise reduction units, horns, air conditioning systems, etc.
  • Entertainment communication systems may include: human machine interaction (HMI) systems, communication systems, and so on.
  • HMI human machine interaction
  • the camera device can be arranged on the outside of the vehicle body and/or inside the vehicle, and the number of camera devices can be one or more.
  • camera equipment can be set at points A, B, C, and D of the vehicle.
  • the camera device can take a video, for example, the camera device can take a video while the vehicle is running (or starting).
  • a storage space can be provided in the vehicle, and the video captured by the camera device can be stored in the storage space.
  • a wireless communication module can be provided in the vehicle, and the video captured by the camera device can be sent to the cloud server, or the video captured by the camera device can be sent to the user's terminal device (for example, a mobile phone, a computer, etc.).
  • the driving data of the vehicle can be obtained.
  • the historical driving characteristics of the vehicle can be determined according to the historical driving data of the vehicle, and the historical driving characteristics of the vehicle can represent the driving habits of the driver of the vehicle.
  • the first driving data of the vehicle in the first time period (for example, the time period before the current moment) may indicate the driving situation of the vehicle in the first time period. Since the user's driving habits are usually relatively fixed, comparing the first driving data with the historical driving characteristics of the vehicle can determine whether the vehicle is abnormal in the first time period. When it is determined that the vehicle is abnormal in the first time period, the driving record video taken by the camera device can be marked to record that the vehicle is abnormal in the first time period.
  • the abnormal conditions of the vehicle may include: vehicle failure, car accident, and abnormal driving of the user.
  • the abnormal driving of the user may include: the speed of the user driving the vehicle is too fast, the speed of the user driving the vehicle is too slow, the user driving the vehicle wandering in a certain area, and so on.
  • the user can view the driving record video (the video taken by the camera equipment, or the video after marking the video taken by the camera equipment) through the terminal device.
  • the terminal device can obtain the driving record video in a variety of ways. Below, in conjunction with Figures 2A-2C, several methods for the terminal device to obtain the driving record video are introduced.
  • FIG. 2A is a schematic diagram of a video acquisition method provided by an embodiment of this application. Please refer to Figure 2A, including vehicle A, mobile hard disk B and terminal device C.
  • the driving record video can be stored in the preset storage space in vehicle A.
  • the user when the user needs to view the driving record video through the terminal device C, the user can copy the driving record video in the storage space through the mobile hard disk B, and copy the driving record video to the terminal device C.
  • the driving record video can be stored in the mobile hard disk B, for example, the mobile hard disk B is inserted in the vehicle, and the video taken by the camera device is stored in the mobile hard disk B.
  • the user when the user needs to view the driving record video through the terminal device C, the user can remove the mobile hard disk B from the vehicle, and copy the driving record video in the mobile hard disk B to the terminal device C.
  • FIG. 2B is a schematic diagram of another video acquisition method provided by an embodiment of the application.
  • vehicle A and terminal device B The driving record video can be stored in the preset storage space in vehicle A.
  • vehicle A is provided with a communication module, and the vehicle A can communicate with the terminal device B through the communication module.
  • the vehicle A can communicate with the terminal device B via Bluetooth communication or WIFI communication.
  • the terminal device B may be installed with an application program, and the user can control the transmission of the video in the preset storage space of the vehicle A to the terminal device B through the application program.
  • the user can select the video of the driving record in a certain period of time through the application, so that the vehicle can transmit the video of the driving record in the period of time to the terminal device.
  • FIG. 2C is a schematic diagram of another video acquisition method provided by an embodiment of the application.
  • vehicle A is provided with a communication module, and the vehicle A can upload the driving record video to the cloud server C through the communication module, and the cloud server C stores the driving record video.
  • the terminal device B can be installed with an application program, and the user can control the terminal device B to download the driving record video from the cloud server C through the application program. For example, the user can select the driving record video in a certain period of time through the application, so that the terminal device B requests to download the driving record video in the period of time from the cloud server C.
  • FIGS. 2A to 2C are merely illustrative of the manner in which the terminal device obtains the driving record video, and are not a limitation on the manner.
  • FIG. 3 is a schematic flowchart of a data processing method provided by an embodiment of the application. Please refer to Figure 3. This method can include:
  • the execution subject of the embodiments of the present application may be a vehicle, a driving recording device, a data processing device provided in a vehicle or a driving recording device.
  • the data processing device may be implemented by software or a combination of software and hardware, for example, data
  • the processing device may be a processing chip.
  • the following takes the execution subject as the driving recording device as an example for description.
  • the first model is used to process driving data to obtain corresponding driving characteristics.
  • the driving characteristic can be represented by a curve, for example, the driving characteristic can represent the distribution law of driving data.
  • driving data and driving characteristics will be described by taking driving data as acceleration as an example.
  • FIG. 4 is a schematic diagram of driving data and driving characteristics provided by an embodiment of the application.
  • the horizontal axis of the coordinate axis represents the road condition index, which can be determined according to the road congestion degree, weather and other parameters.
  • the vertical axis of the coordinate axis represents the normalized acceleration.
  • the points in the coordinate system represent discrete accelerations (driving data), which can be accelerations under different road conditions collected within a preset time period.
  • the curve in the coordinate system represents driving characteristics (also called acceleration characteristics), which may indicate the distribution law of acceleration.
  • the first model can be obtained in the following manner:
  • the first method other devices generate the first model, and the driving recorder obtains the first model from the other devices.
  • other devices may be servers, terminal devices, etc.
  • Other devices may generate the first model in the following manner: obtain multiple sets of first samples, and learn the multiple sets of first samples to obtain the first model, and each set of first samples includes: sample driving data and sample driving characteristics.
  • the sample driving data in a group of first samples may be one type of driving data, and the type of driving data may be speed, acceleration, transmitter rotation speed, engine temperature, etc., for example, in a group of first samples
  • the sample driving data of can be the speed within a preset time period.
  • the sample driving characteristics correspond to the sample driving data, and the sample driving characteristics are used to reflect the characteristics of the sample driving data.
  • a sample curve may be used to indicate the characteristics of the sample driving, and the sample curve is used to indicate the distribution law of the sample driving data.
  • the sample driving characteristics can be obtained by manually labeling the sample driving data.
  • Algorithms for learning the first model may include: logistic regression (logistic regression) algorithm, decision tree algorithm, vector machine algorithm, naive Bayes algorithm, etc.
  • the first model After the first model is obtained by learning multiple sets of first samples, the first model has the following functions: input driving data to the first model, and the first model can process the driving data to output driving characteristics corresponding to the driving data .
  • the first model may be obtained from the other device, and the first model may be an offline model.
  • the second way the driving recorder generates the first model.
  • the process of generating the first model by the driving recorder can refer to the first method, which will not be repeated here.
  • Historical driving data can be the data generated by the vehicle in the historical driving process.
  • the historical driving process can be the driving process of the vehicle in a historical period.
  • the historical period can be one week, one month, six months, one year, etc. before the current moment, which can be based on actual conditions. Set the historical period.
  • the historical driving data includes at least one of the following: historical state data of components in the vehicle, historical operation data of components in the vehicle, or historical sensor data collected by components in the vehicle.
  • the driving recorder can obtain historical driving data generated by the vehicle.
  • the following describes the manner in which the driving recorder obtains historical driving data with reference to FIGS. 5A-5B.
  • FIG. 5A is a schematic diagram of obtaining historical driving data according to an embodiment of the application.
  • the vehicle includes a plurality of components and a body state system, and the plurality of components includes a plurality of parts and a plurality of sensors.
  • the components that start the work can generate driving data
  • the body state system can obtain and store the driving data generated by the components.
  • Communication between the driving recorder and the body state system may be possible.
  • the driving recorder and the body state system may be wired or wirelessly connected, so that the driving recorder may obtain historical driving data from the body state system.
  • FIG. 5B is another schematic diagram of obtaining historical driving data provided by an embodiment of the application.
  • the vehicle includes a plurality of components and a body state system, and the plurality of components includes a plurality of parts and a plurality of sensors. After the vehicle is started, most of the components can start to work, and the components that start the work can generate driving data.
  • the body state system can obtain the driving data generated by the components, and transmit the driving data generated by the components to the cloud server, which stores the driving data.
  • the driving recorder may request the cloud server to obtain historical driving data.
  • FIGS. 5A to 5B merely illustrate the manner in which the driving recorder obtains historical driving data in the form of examples, and are not a limitation on this.
  • the historical driving data includes various types of historical driving data.
  • the types of historical driving data include: speed, acceleration, engine speed, engine temperature, and so on.
  • the first historical driving characteristics include driving characteristics corresponding to multiple types of historical driving data.
  • the first historical driving characteristics include: driving characteristics corresponding to historical speeds, driving characteristics corresponding to historical accelerations, driving characteristics corresponding to historical engine speeds, and the like.
  • the driving characteristic corresponding to the historical speed is used to indicate the distribution law of the historical speed
  • the driving characteristic corresponding to the historical acceleration is used to indicate the distribution law of the historical acceleration.
  • the user driving the vehicle is usually one or more fixed users.
  • the user’s driving habits are usually fixed, so that the driving data of the vehicle usually meets a fixed curve distribution.
  • the speed at which the user drives the vehicle under different road conditions usually meets a fixed Speed curve distribution
  • the acceleration of the user driving the vehicle under different road conditions usually meets a fixed acceleration curve distribution. Therefore, the first historical driving characteristic determined according to the historical driving data may represent the driving habits of the user, or the first historical driving characteristic may also be referred to as a user portrait of the user driving the vehicle.
  • the historical driving data may be input to the first model, and the first model outputs the first historical driving characteristic corresponding to the historical driving data.
  • the first historical driving characteristic includes a plurality of historical data curves corresponding to each type of historical driving data, and the historical data curve is used to indicate the distribution law of the historical driving data, that is, the driving characteristic corresponding to the historical driving data is expressed by the historical data curve.
  • Fig. 6 is a schematic diagram of historical driving characteristics provided by an embodiment of the application.
  • the coordinate system includes multiple curves, each curve represents a type of historical driving characteristic, and one type of historical driving characteristic corresponds to a type of historical driving data.
  • the horizontal axis of the coordinate and the vertical axis of the coordinate have different meanings.
  • the horizontal axis of the coordinate can represent the road condition index
  • the vertical axis of the coordinate can represent the acceleration.
  • the horizontal axis of the coordinate can represent the road condition index
  • the vertical axis of the coordinate can represent the speed.
  • Fig. 6 illustrates the first historical driving characteristic only in the form of an example, and is not a limitation on the first historical driving characteristic.
  • the second model is used to obtain the similarity between the data and the driving characteristics, and the data may include driving data, or the data may include driving data and scene data.
  • the second model can be obtained in the following manner:
  • the first method another device generates a second model, and the driving recorder obtains the second model from the other device.
  • other devices may be servers, terminal devices, etc.
  • Other devices may generate the second model in the following manner: obtain multiple sets of second samples, and learn the multiple sets of second samples to obtain the second model.
  • Each set of second samples includes: sample data, sample driving characteristics, and sample similarity.
  • sample data may include sample driving data, or the sample data may include sample driving data and sample scene data.
  • sample scene data includes at least one of the following information: sample time information, sample location information, sample road condition information, or sample weather information.
  • the sample similarity may be the similarity between the sample data and the sample driving characteristics, and the sample similarity may be the similarity manually labeled.
  • the sample driving data in a set of second samples may be one type of driving data, and the type of driving data may be speed, acceleration, transmitter speed, engine temperature, etc., for example, the driving data in the first set of samples
  • the sample driving data may be the speed within a preset time period.
  • the sample driving characteristics correspond to the sample driving data.
  • a sample curve can be used to express the characteristics of the sample driving.
  • Algorithms for learning the second model may include: logistic regression (logistic regression) algorithm, decision tree algorithm, vector machine algorithm, naive Bayes algorithm, etc.
  • the second model After the second model is obtained by learning multiple sets of second samples, the second model has the following functions: input data and driving characteristics to the second model, and the second model can process the input data and driving characteristics to obtain data and Similarity between driving characteristics.
  • the second model may be obtained from the other device, and the second model may be an offline model.
  • the second way the driving recorder generates the second model.
  • the second model and the first model may be integrated into one model.
  • the integrated model may have the functions of the first model and the functions of the second model at the same time.
  • the second model and the first model can also be two independent models.
  • S301-S304 can be a one-time execution process or a periodic execution process, that is, before S305, it only needs to execute S301-S304 once, and there is no need to execute S301-S304 in real time.
  • the first data includes first driving data of the vehicle in the first time period.
  • the first data may include first driving data and scene data, and the scene data includes at least one of the following information: time information, location information, road condition information, or weather information.
  • the first time period may be a time period before and closest to the current time.
  • the first time period may be 5 minutes, 10 minutes, 30 minutes, 1 hour, etc. before the current time.
  • the method for obtaining the first data by the driving recorder may refer to the method for obtaining historical driving data in S302, which will not be repeated here.
  • S306 Process the first data and the first historical driving feature through the second model to obtain the similarity between the first data and the first historical driving feature.
  • the first data and the first historical driving characteristic may be input to the second model, so that the second model outputs the similarity between the first data and the first historical driving characteristic.
  • the second model may first determine the first data curve corresponding to the first data, and then compare the first data curve and the first historical driving characteristics. The historical data curve is compared and processed to obtain the similarity. If the first data also includes scene data, the historical data curve corresponding to the scene data can also be obtained from the first historical driving characteristic, and the first data curve is compared with the historical data curve corresponding to the scene data to obtain Similarity.
  • the first data may include the first driving data, or the first data may include the first driving data and scene data.
  • the process of determining the similarity between the first data and the first historical driving characteristic is also different, which may include the following two cases:
  • the first driving data may include multiple types of driving data, and the first historical driving characteristics include historical driving characteristics corresponding to each type of driving data.
  • the similarity between each type of driving data and the corresponding historical driving characteristic can be obtained separately, and then the first data and the first historical driving characteristic can be determined according to the similarity between each type of driving data and the corresponding historical driving characteristic The similarity between.
  • the first data curve corresponding to the type of driving data can be obtained, and the historical data curve corresponding to the type of driving data can be obtained in the first historical driving feature, and the first data curve can be compared with The similarity of the corresponding historical data curve is determined as the similarity between the type of driving data and the historical driving characteristics.
  • FIG. 7A is a schematic diagram of determining similarity provided by an embodiment of the application.
  • the first data includes first driving data.
  • the first travel data may include multiple types of travel data, where travel data 1, travel data 2, travel data 3, ..., travel data N (N is an integer greater than 1) are N different types of travel data.
  • driving data 1 may be speed
  • driving speed 2 may be acceleration
  • driving data 3 may be engine speed.
  • the data curve corresponding to each type of driving data can be obtained.
  • the data curve corresponding to each type of driving data can be obtained through the second model.
  • the driving data 1 may be input to the second model, so that the second model outputs the data curve 1 corresponding to the driving data 1.
  • the driving data 2 may be input to the second model, so that the second model outputs the data curve 2 corresponding to the driving data 2.
  • N data curves corresponding to N types of driving data can be obtained.
  • the first historical driving characteristic includes multiple historical data curves.
  • the first historical driving characteristic includes historical data curve 1 corresponding to driving data 1 and historical data curve 2 corresponding to driving data 2.
  • Data curve 1 and historical data curve 1 can be compared to obtain similarity 1
  • data curve 2 and historical data curve 2 can be compared to obtain similarity 2, and so on, to obtain N similarities.
  • the average or weighted average of the N similarities may be determined as the similarity between the first data and the first historical driving characteristic.
  • the second case the first data includes the first driving feature and scene data.
  • the first traveling data may include multiple types of traveling data.
  • the first traveling data may include speed, acceleration, engine speed, and the like.
  • the scene data includes at least one of the following information: time information, location information, road condition information, or weather information.
  • the corresponding scene type can be determined according to the scene data.
  • the scene type may include rainy weather type, morning peak type, and evening peak. Type, holiday type, weekday type, traffic flow type, etc.
  • the first historical driving characteristics include multiple historical driving characteristics corresponding to each type of driving data, and the multiple historical driving characteristics correspond to different scene types. For example, assuming that the driving data is speed, the first historical driving characteristic includes multiple historical speed driving characteristics corresponding to the speed, and the multiple historical speed driving characteristics may include: historical speed driving characteristics corresponding to rainy weather, and history corresponding to morning peaks Speed driving characteristics, historical speed driving characteristics corresponding to holidays, etc.
  • the similarity between each type of driving data and the corresponding historical driving feature can be obtained according to the scene data, and then the first data and the first data can be determined according to the similarity between each type of driving data and the corresponding historical driving feature.
  • a similarity between historical driving characteristics can be obtained according to the scene data, and then the first data and the first data can be determined according to the similarity between each type of driving data and the corresponding historical driving feature.
  • the first data curve corresponding to the type of driving data can be obtained, and multiple historical data curves corresponding to the type of driving data can be obtained in the first historical driving feature, and then according to the scene data Determine the scene type, determine the first historical data curve corresponding to the scene type among the multiple historical data curves, and determine the similarity between the first data curve and the first historical data curve as the type of driving data and history Similarity between driving characteristics.
  • FIG. 7B is a schematic diagram of determining similarity provided by an embodiment of the application.
  • the first data includes first driving data and scene data.
  • the first travel data may include multiple types of travel data, where travel data 1, travel data 2, travel data 3, ..., travel data N (N is an integer greater than 1) are N different types of travel data.
  • driving data 1 may be speed
  • driving speed 2 may be acceleration
  • driving data 3 may be engine speed.
  • the data curve corresponding to each type of driving data can be obtained.
  • the data curve corresponding to each type of driving data can be obtained through the second model.
  • the driving data 1 may be input to the second model, so that the second model outputs the data curve 1 corresponding to the driving data 1.
  • the driving data 2 may be input to the second model, so that the second model outputs the data curve 2 corresponding to the driving data 2.
  • N data curves corresponding to N types of driving data can be obtained.
  • the first historical driving characteristic includes a plurality of historical data curves corresponding to each type of driving data.
  • the first historical driving characteristic includes a plurality of historical data curves corresponding to driving data 1 (for example, historical data curve 11, historical data Curve 12,..., historical data curve 1X), multiple historical data curves corresponding to driving data 2 (for example, historical data curve 21, historical data curve 22, ..., historical data curve 2K), etc.
  • Data curve 1 and historical data curve 1 can be compared to obtain similarity 1
  • data curve 2 and historical data curve 2 can be compared to obtain similarity 2, and so on, to obtain N similarities.
  • the average or weighted average of the N similarities may be determined as the similarity between the first data and the first historical driving characteristic.
  • FIGS. 7A-7B are only illustratively determining the similarity between the first data and the first historical driving characteristic in the form of examples, and are not a limitation on this, and the similarity may also be determined in other ways.
  • the similarity between the first data and the first historical driving feature can also be obtained through an algorithm, and the process is similar to the process of obtaining the similarity through the second model, and will not be repeated here.
  • S307 Determine, according to the similarity, that the vehicle is abnormal in the first period of time.
  • the abnormal situation of the vehicle in the first time period may include: the vehicle fails in the first time period, the vehicle has a car accident in the first time period, and the user drives the vehicle abnormally in the first time period.
  • the abnormal driving of the vehicle by the user may include: the speed of the user driving the vehicle is too fast, the speed of the user driving the vehicle is too slow, the user driving the vehicle wandering in a certain area, and so on.
  • the similarity is less than or equal to the similarity threshold, it is determined that the vehicle is abnormal in the first time period.
  • S308 Mark the driving record video of the vehicle according to the first time period.
  • the driving record video of the vehicle may be marked in the following manner: abnormal information is generated, and the abnormal information is marked in the driving record video according to the first time period.
  • the abnormality information includes at least one of the following information: abnormality indication, abnormality level, abnormality type, or abnormality description information.
  • the abnormal indication is used to indicate the abnormality of the vehicle.
  • the abnormality level is used to indicate the degree of abnormality of the vehicle. For example, it is determined in S306 that the lower the degree of similarity is, the higher the degree of abnormality of the vehicle is, and the higher the abnormality level is.
  • Abnormal types may include abnormal braking, abnormal turning, abnormal acceleration, abnormal engine, abnormal driving trajectory, and so on.
  • the abnormal description information is used to describe the specific conditions of the abnormality of the vehicle.
  • the abnormal description information may include: 5 sudden brakes in one minute, or acceleration greater than the first threshold, or 10 round trips on the same road section within 1 hour, or 3 Change lanes 10 times a minute.
  • the user After marking the video of the driving record, the user can view the marked video of the driving record through a terminal device (computer, mobile phone, etc.).
  • a terminal device computer, mobile phone, etc.
  • the first video annotation method :
  • the camera device can take multiple driving record videos of the vehicle.
  • one trip of the vehicle (the vehicle starts to when the vehicle is turned off) can correspond to one driving record video, or the preset driving time of the vehicle (for example, one hour, etc.) can correspond to one drive. Record the video.
  • Multiple driving record videos of multiple trips of the vehicle can be stored in the form of a list.
  • abnormal information is generated, and the abnormal information is used as the attribute information of the driving video.
  • the abnormal information can be displayed when the driving video list is displayed in the form of a list.
  • Part of the information in the abnormal information (for example, the abnormal description information or part of the content in the abnormal description information) may also be added to the corresponding position in the driving record video in the form of subtitles or pop-up screens.
  • FIG. 8 is a schematic diagram of a video viewing method provided by an embodiment of the application. Please refer to Fig. 8, including interface 801-interface 803.
  • the terminal device can display the folder corresponding to the video of driving of the driving.
  • the user can click the folder corresponding to the video of the driving record to make the terminal device display a list of the driving record video.
  • the list includes 5 driving videos and attribute information of the 5 driving videos.
  • the attribute information includes shooting time, abnormal indication, abnormal level, abnormal type, and abnormal description information. .
  • the attribute information may also include others, which is not limited.
  • the 5 driving record videos may be videos corresponding to 5 trips of the vehicle.
  • the abnormal indication corresponding to the three driving record videos is "normal"
  • the driving In the time period corresponding to recorded video 2 and driving recording video 3 if the vehicle is abnormal, the abnormal indications corresponding to the two driving recording videos are both "abnormal", and the two driving recording videos also have attributes: abnormal level, abnormal type and abnormality Description.
  • the abnormal description information may be brief description information, and the user can click on the brief description information to make the terminal device display detailed description information.
  • the terminal device can display the detailed description information "8 sudden brakes occurred in the 20th to 22th minutes".
  • the identification and attribute information of normal and abnormal driving recording videos may be displayed in different display modes, including font color, font type, font size, etc.
  • the identification and attribute information of the abnormal driving recording video may be displayed in red font
  • the identification and attribute information of the normal driving recording video may be displayed in black font.
  • the user can click the logo of the driving record video in the driving record video list to make the terminal device play the driving record video. For example, when the user needs to view the driving record video 2, the user can click the logo of the driving record video 2 to make the electronic device play the driving record video 2.
  • the terminal device plays the driving record video 2.
  • the user can determine according to the abnormal description information of the driving record video 2 that the vehicle is abnormal at the 20th to 22th minutes of the driving record video 2, then the user can drag and drop the video playback progress bar according to the abnormal description information.
  • part of the abnormal description information (sudden brake) is displayed in the form of subtitles in the video.
  • the user can easily learn the abnormal driving record video corresponding to the vehicle according to the list of driving record videos, and can also record the abnormal time period in the driving record video according to the abnormal description information, and accurately record the video during the driving In this time period, the operation is convenient and flexible, and the user experience is higher.
  • the aforementioned driving record video may also be a video with a preset duration.
  • the duration of each driving record video is 1 hour.
  • the driving record video whose abnormality indication is “abnormal” may also be a video taken during the abnormal period of the vehicle.
  • the duration of the driving record video 2 may be 2 minutes, and the vehicle is abnormal within the 2 minutes.
  • the second video annotation method is a first video annotation method
  • a driving record video captured by a camera device can correspond to a video file. If the vehicle is abnormal during the shooting period of the driving record video, an abnormal information file is generated.
  • the abnormal information file may include one or more abnormal information.
  • the abnormal information file Can be used as the configuration file of the video file.
  • An abnormal information in the abnormal information file can correspond to an abnormal period (or abnormal moment) in the driving record video, and the abnormal information has an association relationship with the abnormal period (or abnormal moment) in the driving record video, for example, through an abnormal The information can be located to the corresponding abnormal period (or abnormal moment).
  • FIG. 9 is a schematic diagram of a video tagging method provided by an embodiment of the application.
  • the video file may be an 80-minute video
  • the abnormal information file may include three abnormal information, which are respectively recorded as abnormal information 1, abnormal information 2, and abnormal information 3.
  • the abnormal information 1 corresponds to the time t1 in the driving record video, that is, the abnormal information 1 can be used to locate the position at the time t1 in the driving record video.
  • the abnormal information 2 corresponds to the t2 time in the driving record video, that is, the abnormal information 2 can be used to locate the position at the time t2 in the driving record video.
  • the abnormal information 13 corresponds to the time t3 in the driving record video, that is, the abnormal information 3 can be used to locate the position at the time t3 in the driving record video.
  • FIG. 10 is a schematic diagram of a video viewing method provided by an embodiment of the application. Please refer to Figure 10, which includes interface 1001-interface 1006.
  • the interface 1001. It is assumed that the manner in which the terminal device records a video while driving is as shown in Fig. 2B or Fig. 2C.
  • An application program is installed in the terminal device, and it is assumed that the driving record video has been transmitted to the terminal device through the application program.
  • the user can open the application in the terminal device.
  • the application includes the "video review" icon, and the user can click on the icon to make the terminal device display Interface 1002.
  • the interface 1001 may also include other icons, and the embodiment of the present application does not specifically limit the icons included in the interface 1001.
  • the interface 1002 which includes the "all videos” icon and the "abnormal video” icon.
  • the page corresponding to the "all videos” icon includes the identifiers of all videos, and the page corresponding to the "abnormal video” icon includes the identifiers of abnormal videos.
  • the user can click the "abnormal video” icon to make the terminal device display the interface 1003.
  • Abnormal video refers to a video in which the shooting period includes the period when the vehicle is abnormal.
  • the interface 1003 which includes a list of abnormal videos.
  • the user can click any abnormal video to make the terminal device play the abnormal video. For example, suppose that the user needs to watch video 2, and the user performs a click operation on video 2, so that the terminal device displays interface 1004.
  • interface 1004 which includes a video playback window M and at least one "abnormal point” icon.
  • the number of "abnormal point” icons is consistent with the number of abnormalities in the abnormal video. For example, assuming that there are 3 abnormalities in video 2, the interface includes 3 "abnormal point” icons, namely "abnormal point 1" icon, "abnormal point 2" icon and "abnormal point 3" icon.
  • the three “abnormal point” icons may be generated according to the three abnormal information in FIG. 9. Assuming that the user needs to watch the video corresponding to the abnormal point 1, the user can click the "abnormal point 1" icon to make the terminal device display the interface 1005.
  • the user can conveniently view the abnormal video through the application in the terminal device, and can quickly locate the abnormal period according to the "abnormal point" icon, the operation is convenient and flexible, and the user experience is high.
  • the data processing method provided by the embodiment of the present application can obtain the first data and the first historical driving characteristic of the vehicle in the first time period. According to the first data and the first historical driving characteristic, it is determined that the vehicle is abnormal in the first time period, and The driving record video of the vehicle is marked according to the first time period.
  • the first data may reflect the driving situation of the vehicle in the first time period
  • the first historical driving characteristic may reflect the driving habits of the driver of the vehicle. Since the user's driving habits are usually relatively fixed, comparing the first driving data with the historical driving characteristics of the vehicle can determine whether the vehicle is abnormal in the first time period.
  • the driving record video taken by the camera device can be marked to record the abnormality of the vehicle in the first time period, so that the driving record video can be accurately marked. Record the annotation result of the video, you can find the required video accurately and quickly, and improve the efficiency of video search.
  • processing steps (S301-S308) shown in the embodiment of FIG. 3 do not constitute a specific limitation on the data processing process.
  • the data processing process may include more or fewer steps than the embodiment in FIG. 3, for example, the data processing process may include part of the steps in the embodiment in FIG. 3, or, in the embodiment in FIG. Some steps in may be replaced by steps with the same function, or some steps in the embodiment of FIG. 3 may be split into multiple steps, etc.
  • FIG. 11 is a schematic flowchart of another data processing method provided by an embodiment of the application. Referring to Figure 11, the method may include:
  • S1101 Acquire first data and first historical driving characteristics.
  • the execution subject of the embodiments of the present application may be a vehicle, a driving recording device, a data processing device provided in a vehicle or a driving recording device.
  • the data processing device may be implemented by software or a combination of software and hardware, for example, data
  • the processing device may be a processing chip.
  • the first data includes the first driving data of the vehicle in the first time period, and the first historical driving characteristic is determined according to the historical driving data of the vehicle.
  • the process of obtaining the first historical driving feature may refer to the execution process of S303, and the process of obtaining the first data may refer to the execution process of S305, which will not be repeated here.
  • S1103 Mark the driving record video of the vehicle according to the first time period.
  • the first data and the first historical driving characteristics of the vehicle in the first time period can be obtained, and according to the first data and the first historical driving characteristics, it is determined that the vehicle is abnormal in the first time period, and
  • the driving record video of the vehicle is marked according to the first time period.
  • the first data may reflect the driving situation of the vehicle in the first time period
  • the first historical driving characteristic may reflect the driving habits of the driver of the vehicle. Since the user's driving habits are usually relatively fixed, comparing the first driving data with the historical driving characteristics of the vehicle can determine whether the vehicle is abnormal in the first time period.
  • the driving record video taken by the camera device can be marked to record the abnormality of the vehicle in the first time period, so that the driving record video can be accurately marked. Record the annotation result of the video, you can find the required video accurately and quickly, and improve the efficiency of video search.
  • the embodiment of the present application also provides a driving recording device.
  • the driving recorder will be introduced in conjunction with Fig. 12A-Fig. 12B.
  • FIG. 12A is a schematic structural diagram of a driving recording device provided by an embodiment of the application.
  • the driving recording device 120 includes a processing chip and 121 a camera device 122, wherein,
  • the camera device 121 is used to take a video of a driving record.
  • the processing chip 122 is used to obtain the first data and the first historical driving characteristics, and according to the first data and the first historical driving characteristics, determine that the vehicle is abnormal in the first time period, and perform the driving record video according to the first time period.
  • the first data includes the first driving data of the vehicle in the first time period
  • the first historical driving characteristic is determined according to the historical driving data of the vehicle.
  • processing chip 122 may also execute the data processing method shown in the foregoing method embodiment, and the process and beneficial effects are similar, and details are not described herein again.
  • FIG. 12B is a schematic structural diagram of another driving recording device provided by an embodiment of the application. On the basis of FIG. 12A, please refer to FIG. 12B.
  • the driving recorder 120 may further include a memory 123, and the memory 123 is used for storing driving record videos.
  • the camera device 121 may send the driving record video to the memory 123 so that the memory 123 stores the driving record video.
  • the memory 123 may also store program instructions, and the processing chip 122 may execute the technical solutions shown in the foregoing method embodiments according to the program instructions.
  • the driving recording device 120 may further include a communication module 124, and the communication module 124 may communicate with other devices (for example, a vehicle, a cloud server, etc.).
  • the communication module 124 may communicate with other devices (for example, a vehicle, a cloud server, etc.).
  • the driving recording device 120 may further include a data collection device, the data collection device may include a camera, a millimeter wave radar, a lidar, or an inertial sensor, etc., and the data collection device may obtain the first data.
  • the data collection device may include a camera, a millimeter wave radar, a lidar, or an inertial sensor, etc., and the data collection device may obtain the first data.
  • the driving recording device 120 is usually installed on the vehicle.
  • the connection relationship between the driving recording device and the vehicle will be described below with reference to FIGS. 13A to 13C.
  • the driving recording device is illustrated in FIG. 12B as an example.
  • FIG. 13A is a schematic diagram of a device connection provided by an embodiment of the application.
  • the communication module 124 of the driving recorder 120 may be provided with an interface, and the vehicle may also be provided with an interface.
  • the interface in the driving recorder 120 can be connected to the interface in the vehicle, so that the driving recorder and the vehicle can communicate through the interface.
  • the interface may also be set in other positions, which is not specifically limited in the embodiment of the present application.
  • FIG. 13B is a schematic diagram of another device connection provided by an embodiment of this application.
  • a communication module is provided in the vehicle, and the communication module 124 in the driving recorder 120 can communicate with the communication module in the vehicle (for example, wireless communication).
  • the vehicle may send driving information to the driving recorder through the communication module. data.
  • FIG. 13C is a schematic diagram of another device connection provided by an embodiment of the application.
  • a communication module is provided in the vehicle, and the communication module in the vehicle can communicate with the server.
  • the vehicle can send driving data to the cloud server through the communication module.
  • the driving recorder 120 may communicate with the cloud server through the communication module 124.
  • the driving recorder 120 may obtain driving data from the cloud server through the communication module 124.
  • FIGS. 13A to 13C the structure of the vehicle is merely illustrated by way of example, and is not a limitation on the structure of the vehicle linkage.
  • the embodiment of the present application also provides a vehicle.
  • the structure of the vehicle will be described below with reference to FIGS. 14A-14B.
  • FIG. 14A is a schematic structural diagram of a vehicle provided by an embodiment of the application.
  • the vehicle 140 may include a processing chip 141 and a camera device 142, where:
  • the camera device 141 is used to take a video of driving records
  • the processing chip 142 is used to obtain the first data and the first historical driving characteristics, and according to the first data and the first historical driving characteristics, determine that the vehicle is abnormal in the first time period, and mark the driving record video according to the first time period,
  • the first data includes the first driving data of the vehicle in the first time period, and the first historical driving characteristic is determined according to the historical driving data of the vehicle.
  • processing chip 122 may also execute the data processing method shown in the foregoing method embodiment, and the process and beneficial effects are similar, and details are not described herein again.
  • FIG. 14B is a schematic structural diagram of another vehicle provided by an embodiment of the application. On the basis of FIG. 14A, please refer to FIG. 14B.
  • the vehicle may also have a memory 143, and the memory 143 may store driving record videos.
  • the camera device 141 may send the driving record video to the memory 143 so that the memory 143 stores the driving record video.
  • the memory 143 may also store program instructions, and the processing chip 142 may execute the technical solutions shown in the foregoing method embodiments according to the program instructions.
  • the vehicle further includes a body state system 144, and the body state system 144 can obtain the first driving data and send the first driving data to the processing chip 141.
  • the vehicle also includes components.
  • the components include multiple components and multiple sensors.
  • the body state system 144 can obtain the first driving data from the vehicle components.
  • the vehicle 140 may further include a communication module (not shown in the figure), and the communication module may communicate with other devices (for example, a cloud server, etc.).
  • a communication module not shown in the figure
  • the communication module may communicate with other devices (for example, a cloud server, etc.).
  • the vehicle 140 may further include a data collection device.
  • the data collection device may include a camera, a millimeter wave radar, a lidar, or an inertial sensor, etc., and the data collection device may obtain the first data.
  • FIG. 15 is a schematic structural diagram of a data processing device provided by an embodiment of the application.
  • the data processing device 150 may include: an acquisition module 151, a determination module 152, and a labeling module 153, where:
  • the acquisition module 151 is configured to acquire first data and a first historical driving characteristic.
  • the first data includes first driving data of a vehicle in a first period.
  • the first historical driving characteristic is based on the history of the vehicle. The driving data is confirmed;
  • the determining module 152 is configured to determine that the vehicle is abnormal in the first period according to the first data and the first historical driving characteristic;
  • the labeling module 153 is configured to label the driving record video of the vehicle according to the first time period.
  • the acquiring module 151 may execute S303 and S305 in the embodiment of FIG. 3 and S1101 in the embodiment of FIG. 11.
  • the determining module 152 may execute S306-S307 in the embodiment in FIG. 3 and S1102 in the embodiment in FIG. 11.
  • the labeling module 153 may execute S308 in the embodiment in FIG. 3 and S1103 in the embodiment in FIG. 11.
  • the first driving data includes at least one of the following data:
  • the first historical driving feature includes: a plurality of historical data curves corresponding to various historical driving data, the historical data curves are used to indicate the distribution law of the historical driving data, the The historical driving data includes at least one of the following:
  • the acquisition module is specifically configured to:
  • the first model is obtained by learning from multiple groups of first samples, and each group of first samples in the multiple groups of first samples includes: sample driving data and sample historical driving characteristics.
  • the determining module 152 is specifically configured to:
  • the determining module 152 is specifically configured to:
  • the second model is obtained by learning from multiple sets of second samples, each of the multiple sets of second samples includes sample data, sample driving characteristics, and sample similarity, and the sample data includes samples Driving data.
  • the determining module 152 is specifically configured to:
  • the second model is used to compare the first data curve and the historical data curve in the first historical driving characteristic to obtain the similarity.
  • the first data further includes scene data
  • the scene data includes at least one of the following information:
  • Time information location information, road conditions or weather information.
  • the determining module 152 is specifically configured to:
  • the first historical driving characteristic is determined among a plurality of historical driving characteristics.
  • the labeling module 153 is specifically configured to:
  • the abnormal information is marked in the driving record video.
  • the abnormal information includes at least one of the following information:
  • Anomaly level, anomaly type, or anomaly description information is anomaly level, anomaly type, or anomaly description information.
  • FIG. 16 is a schematic diagram of the hardware structure of the data processing device provided by this application.
  • the data processing device 160 may include: a processor 161 and a memory 162, where the processor 161 and the memory 162 can communicate; for example, the processor 161 and the memory 162 communicate through a communication bus 163, and the memory 162 is used to store program instructions, and the processor 161 is used to run the program instructions in the memory to execute the data processing method shown in any of the foregoing method embodiments.
  • the processor 161 may implement the steps in the embodiment shown in FIG. 3 or FIG. 11.
  • the data processing device 160 may also include a transmitter and/or a receiver.
  • the above-mentioned processor may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like. The steps of the method disclosed in this application may be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.
  • the data processing device 160 may be a chip, a driving recorder, a vehicle, a component in the driving recorder, a component in a vehicle, or the like.
  • the data processing device 160 may also include at least one of a camera device or a data collection device.
  • the data collection device may exist in the form of a sensor.
  • the data collection device may include a camera, millimeter wave radar, lidar, or inertial sensor, etc.
  • the camera device is used to shoot the driving record video, so The data collection device is used to obtain the first data, and the memory may also be used to store the driving record video.
  • the structure of the data processing device 160 may be as shown in FIG. 12A or FIG. 12B.
  • the data processing device 160 may also include at least one of a camera device or a data collection device, the camera device is used to shoot the driving record video, and the data collection device is used to obtain all
  • the memory may also be used to store the driving record video.
  • the data acquisition device may exist in the form of a sensor.
  • the data acquisition device may include: a camera, millimeter wave radar, lidar, or inertial sensor, etc.; the data acquisition device may also be a device for acquiring first driving data.
  • Body condition system For example, the structure of the data processing device may also be as shown in FIG. 14A or FIG. 14B.
  • the present application provides a readable storage medium with a computer program stored on the readable storage medium; the computer program is used to implement the data processing method described in any of the foregoing embodiments.
  • the embodiments of the present application provide a computer program product.
  • the computer program product includes instructions that, when executed, cause a computer to execute the above-mentioned data processing method.
  • All or part of the steps in the foregoing method embodiments can be implemented by a program instructing relevant hardware.
  • the aforementioned program can be stored in a readable memory.
  • the program executes the steps including the foregoing method embodiments; and the foregoing memory (storage medium) includes: read-only memory (English: read-only memory, abbreviation: ROM), RAM, flash memory, hard disk, Solid state drives, magnetic tapes (English: magnetic tape), floppy disks (English: floppy disk), optical discs (English: optical disc), and any combination thereof.
  • These computer program instructions can be provided to the processing unit of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processing unit of the computer or other programmable data processing equipment are generated It is a device that implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.
  • the term “including” and its variations may refer to non-limiting inclusion; the term “or” and its variations may refer to “and/or”.
  • the terms “first”, “second”, etc. in this application are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence.
  • “plurality” refers to two or more.
  • “And/or” describes the association relationship of the associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone.
  • the character “/” generally indicates that the associated objects before and after are in an "or” relationship.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Traffic Control Systems (AREA)
  • Time Recorders, Dirve Recorders, Access Control (AREA)

Abstract

本申请实施例提供一种数据处理方法、装置及设备，该方法包括：获取第一数据和第一历史行驶特征，第一数据包括车辆在第一时段的第一行驶数据，第一历史行驶特征为根据车辆的历史行驶数据确定得到的；根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常；根据第一时段对车辆的行车记录视频进行标注。提高了视频段的查找效率。

Description

数据处理方法、装置及设备 技术领域
本申请涉及智能驾驶及智能车技术领域，尤其涉及一种数据处理方法、装置及设备。
背景技术
目前，很多车辆中可以安装行车记录仪，行车记录仪可以拍摄并存储车辆在行驶过程中的视频。
行车记录仪拍摄的视频以及视频的拍摄时间可以存储在预设存储空间。在特殊情况下，例如，车辆发生事故、用户回忆驾驶场景等，用户需要在预设存储空间中查找相应的视频段。在现有技术中，用户通常估计大概的时间，并根据该估计的时间在预设存储空间中查找相应的视频。然而，在上述查找所需视频段的效率较低。
发明内容
本申请实施例提供一种数据处理方法、装置及设备。提高了视频段的查找效率。
第一方面，本申请实施例提供一种数据处理方法，该方法包括：获取第一数据和第一历史行驶特征，根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常，根据第一时段对车辆的行车记录视频进行标注。其中，第一数据包括车辆在第一时段的第一行驶数据，第一历史行驶特征为根据车辆的历史行驶数据确定得到的。
在上述过程中，第一数据可以反应车辆在第一时段内的行驶情况，第一历史行驶特征可以反应车辆的驾驶人员的驾驶习惯。由于用户的驾驶习惯通常较为固定，因此，根据第一行驶数据和第一历史行驶特征，可以准确的确定车辆在第一时段内是否存在异常。在确定车辆在第一时段内存在异常时，可以对摄像设备拍摄的行车记录视频进行标注，以记录车辆在第一时段内存在异常，使得可以对行车记录视频进行准确的标注，用户根据对行车记录视频的标注结果，可以准确快速的查到所需的视频，提高的视频查找的效率。
在一种可能的实施方式中，第一行驶数据包括如下数据中的至少一种：车辆中的部件的状态数据；车辆中的部件的运行数据；或者，车辆中的部件采集的传感数据。
在上述过程中，第一行驶数据包括部件的状态数据、运行数据或传感数据中的一种或多种，这些数据均是车辆在运行的过程中产生的，可以准确的反映车辆的行驶情况，因此，根据上述第一行驶数据可以准确的确定车辆在第一时段内是否存在异常。
在一种可能的实施方式中，第一历史行驶特征包括：多种历史行驶数据对应的多条历史数据曲线，历史数据曲线用于指示历史行驶数据的分布规律，历史行驶数据包括如下至少一种：车辆中的部件的历史状态数据；车辆中的部件的历史运行数据；或者，车辆中的部件采集的历史传感数据。
在上述过程中，历史行驶数据包括部件的历史状态数据、历史运行数据或历史传感数据中的一种或多种，这些数据均是车辆在历史运行的过程中产生的，可以准确的反映车辆 的历史行驶情况，该车辆的历史行驶情况体现了用户的驾驶习惯，因此，根据上述第一历史行驶特征可以准确的确定车辆在第一时段内是否存在异常。
在一种可能的实施方式中，可以通过如下方式获取第一历史行驶特征：通过第一模型对历史行驶数据进行处理，得到第一历史行驶特征；其中，第一模型为对多组第一样本学习得到的，多组第一样本中的每组第一样本包括：样本行驶数据和样本历史行驶特征。
在上述过程中，通过对多组第一样本进行学习，使得第一模块具有获取行驶数据的形式特征的功能，因此，通过第一模型对历史样本数据进行处理，可以准确的获取得到第一历史行驶特征。
在一种可能的实施方式中，可以通过如下方式根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常：确定第一数据和第一历史行驶特征之间的相似度；根据相似度确定车辆在第一时段出现异常。
在上述过程中，第一数据和第一历史行驶特征之间的相似度体现了车辆在第一时段内的运行情况与用户的驾驶习惯之间的相似度，由于用户的驾驶习惯通常固定，因此，通过该相似度可以准确的确定车辆在第一时段是否出现异常。
在一种可能的实施方式中，可以通过如下方式确定第一数据和第一历史行驶特征之间的相似度：通过第二模型对第一数据和第一历史行驶特征进行处理，得到相似度；其中，第二模型为对多组第二样本学习得到的，多组第二样本中的每组第二样本包括样本数据、样本行驶特征和样本相似度，样本数据包括样本行驶数据。
在上述过程中，通过对多组第二样本进行学习，使得第二模型具有确定数据和行驶特征之间的相似度的功能，因此，通过第二模型对第一数据和第一历史行驶特征进行处理，可以准确的确定得到第一数据和第一历史行驶特征之间的相似度。
在一种可能的实施方式中，通过第二模型对第一数据和第一历史行驶特征进行处理，得到相似度，包括：通过第二模型确定第一数据对应的第一数据曲线；通过第二模型对第一数据曲线和第一历史行驶特征中的历史数据曲线进行对比处理，得到相似度。
在上述过程中，第一数据曲线可以准确的反映第一数据，因此，将第一数据曲线和历史数据曲线进行比对，可以准确的获取得到相似度。
在一种可能的实施方式中，第一数据还包括场景数据，场景数据包括如下信息中的至少一种：时间信息、位置信息、路况信息或天气信息。
在上述过程中，用户在不同场景(例如，不同天气、不同路况)下的驾驶习惯可能有所差异，因此，当第一数据还包括场景数据时，可以根据场景数据确定用户在第一时段内驾驶所处的场景，这样，根据第一数据可以更加准确的确定车辆在第一时段是否出现异常。
在一种可能的实施方式中，可以通过如下方式获取第一历史行驶特征：根据场景数据，在多个历史行驶特征中确定第一历史行驶特征。
在上述过程中，获取得到的第一历史行驶特征与场景数据相关，使得第一数据对应的场景和第一历史行驶特征对应的场景相同，使得确定车辆在第一时段是否出现异常的准确度较高。
在一种可能的实施方式中，可以通过如下方式根据第一时段对车辆的行车记录视频进行标注：生成异常信息；根据第一时段，在行车记录视频中标注异常信息。
在一种可能的实施方式中，异常信息包括如下信息中的至少一种：异常等级、异常类 型或者异常描述信息。
在上述过程中，通过在行车记录视频中标注异常信息，使得用户根据对行车记录视频的标注结果，可以准确快速的查到所需的视频，提高的视频查找的效率。
第二方面，本申请实施例提供一种数据处理装置，包括：获取模块、确定模块和标注模块，其中，
所述获取模块用于，获取第一数据和第一历史行驶特征，所述第一数据包括车辆在第一时段的第一行驶数据，所述第一历史行驶特征为根据所述车辆的历史行驶数据确定得到的；
所述确定模块用于，根据所述第一数据和所述第一历史行驶特征，确定所述车辆在第一时段出现异常；
所述标注模块用于，根据所述第一时段对所述车辆的行车记录视频进行标注。
在一种可能的实施方式中，所述第一行驶数据包括如下数据中的至少一种：
所述车辆中的部件的状态数据；
所述车辆中的部件的运行数据；
或者，所述车辆中的部件采集的传感数据。
在一种可能的实施方式中，所述第一历史行驶特征包括：多种历史行驶数据对应的多条历史数据曲线，所述历史数据曲线用于指示所述历史行驶数据的分布规律，所述历史行驶数据包括如下至少一种：
所述车辆中的部件的历史状态数据；
所述车辆中的部件的历史运行数据；
或者，所述车辆中的部件采集的历史传感数据。
在一种可能的实施方式中，所述获取模块具体用于：
通过第一模型对所述历史行驶数据进行处理，得到所述第一历史行驶特征；
其中，所述第一模型为对多组第一样本学习得到的，所述多组第一样本中的每组第一样本包括：样本行驶数据和样本历史行驶特征。
在一种可能的实施方式中，所述确定模块具体用于：
确定所述第一数据和所述第一历史行驶特征之间的相似度；
根据所述相似度确定所述车辆在所述第一时段出现异常。
在一种可能的实施方式中，所述确定模块具体用于：
通过第二模型对所述第一数据和所述第一历史行驶特征进行处理，得到所述相似度；
其中，所述第二模型为对多组第二样本学习得到的，所述多组第二样本中的每组第二样本包括样本数据、样本行驶特征和样本相似度，所述样本数据包括样本行驶数据。
在一种可能的实施方式中，所述确定模块具体用于：
通过所述第二模型确定所述第一数据对应的第一数据曲线；
通过所述第二模型对所述第一数据曲线和所述第一历史行驶特征中的历史数据曲线进行对比处理，得到所述相似度。
在一种可能的实施方式中，所述第一数据还包括场景数据，所述场景数据包括如下信息中的至少一种：
时间信息、位置信息、路况信息或天气信息。
在一种可能的实施方式中，所述确定模块具体用于：
根据所述场景数据，在多个历史行驶特征中确定所述第一历史行驶特征。
在一种可能的实施方式中，所述标注模块具体用于：
生成异常信息；
根据所述第一时段，在所述行车记录视频中标注所述异常信息。
在一种可能的实施方式中，所述异常信息包括如下信息中的至少一种：
异常等级、异常类型或者异常描述信息。
第三方面，本申请实施例提供一种数据处理装置，所述数据处理装置包括存储器和处理器，所述存储器存储计算机程序指令，所述处理器运行所述计算机程序指令以执行第一方面任一项所述的操作。
第四方面，本申请实施例提供一种计算机存储介质，其特征在于，包括计算机指令，当所述计算机指令在被处理器运行时，实现第一方面任一项所述的方法。
第五方面，本申请实施例提供一种计算机程序产品，其特征在于，当所述计算机程序产品在处理器上运行时，实现第一方面任一项所述的方法。
本申请实施例提供的数据处理方法、装置及设备，可以获取车辆在第一时段内的第一数据和第一历史行驶特征，根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常，并根据第一时段对车辆的行车记录视频进行标注。第一数据可以反应车辆在第一时段内的行驶情况，第一历史行驶特征可以反应车辆的驾驶人员的驾驶习惯。由于用户的驾驶习惯通常较为固定，因此，根据第一行驶数据和第一历史行驶特征，可以确定车辆在第一时段内是否存在异常。在确定车辆在第一时段内存在异常时，可以对摄像设备拍摄的行车记录视频进行标注，以记录车辆在第一时段内存在异常，使得可以对行车记录视频进行准确的标注，用户根据对行车记录视频的标注结果，可以准确快速的查到所需的视频，提高视频查找的效率。
附图说明
图1为本申请实施例提供的一种应用场景示意图；
图2A为本申请实施例提供的一种视频获取方式的示意图；
图2B为本申请实施例提供的另一种视频获取方式的示意图；
图2C为本申请实施例提供的又一种视频获取方式的示意图；
图3为本申请实施例提供的一种数据处理方法的流程示意图；
图4为本申请实施例提供的行驶数据和行驶特征的示意图；
图5A为本申请实施例提供的一种获取历史行驶数据的示意图；
图5B为本申请实施例提供的另一种获取历史行驶数据的示意图；
图6为本申请实施例提供的历史行驶特征的示意图；
图7A为本申请实施例提供的确定相似度的示意图；
图7B为本申请实施例提供的确定相似度的示意图；
图8为本申请实施例提供的一种视频查看方式的示意图；
图9为本申请实施例提供的视频标注方式的示意图；
图10为本申请实施例提供的一种视频查看方式的示意图；
图11为本申请实施例提供的另一种数据处理方法的流程示意图；
图12A为本申请实施例提供的一种行车记录设备的结构示意图；
图12B为本申请实施例提供的另一种行车记录设备的结构示意图；
图13A为本申请实施例提供的一种设备连接示意图；
图13B为本申请实施例提供的另一种设备连接示意图；
图13C为本申请实施例提供的又一种设备连接示意图；
图14A为本申请实施例提供的一种车辆的结构示意图；
图14B为本申请实施例提供的另一种车辆的结构示意图；
图15为本申请实施例提供的一种数据处理装置的结构示意图；
图16为本申请提供的数据处理装置的硬件结构示意图。
具体实施方式
为了便于理解，首先对本申请所涉及的概念进行介绍。
车辆：本申请所涉及的车辆可以包括私家汽车、公共汽车、货运车、客运车、摩托车等。
车辆中的部件：车辆中的部件可以为车辆中零件或传感器，零件可以是维持车辆运行的部件，例如，零件可以包括发动机、发电机、减震器、车灯等。传感器可以包括温度传感器、速度传感器、加速度传感器等。
行驶数据：是指车辆在行驶过程中产生的数据。行驶数据可以包括如下数据中的至少一种：部件的状态数据、部件的运行数据或部件采集的传感数据。
状态数据用于指示部件的状态。例如，车灯的状态数据用于指示车灯的状态为开或者关，发动机的状态数据用于指示发动机的状态为启动或者暂停，电磁阀的状态数据用于指示电磁阀的状态为打开或者关闭。
运行数据用于指示部件在运行的过程中生成的数据。例如，发动机的运行数据可以包括发动机的转速，电子换挡器的运行数据可以包括电子换挡器的档位，蓄电池的运行数据可以包括蓄电池的剩余电量。
传感数据是指传感器采集得到的数据。例如，传感数据可以包括：温度传感器采集得到的温度、速度传感器采集得到的速度、空燃比传感器采集得到的空燃比等。
不同的部件所产生的数据可能不同，部件可能产生状态数据、运行数据、传感数据中的一种或多种。例如，有的部件会产生状态数据，有的部件可能会产生状态数据和运行数据，有的部件会产生传感数据。例如，顶篷开关可以产生状态数据，发动机可以产生状态数据和运行数据，温度传感器可以生成传感数据。
行车记录视频：是指车辆在行驶过程中拍摄得到的视频，该视频可以包括对车身周围进行拍摄得到的视频、对车辆内部进行拍摄得到的视频。该视频有摄像设备拍摄得到，摄像设备可以为车辆自带的装置，也可以为安装在车辆上的装置。
为了便于理解，下面，结合图1，对本申请所适用的应用场景进行说明。
图1为本申请实施例提供的一种应用场景示意图。请参见图1，车辆中包括发动机电 子系统、磁盘电子系统、车身电子电器、安全舒适系统、娱乐通信系统和摄像设备。
发动机电子系统可以包括：发动机管理电子控制单元(electronic control unit，ECU)、蓄电池、发电机、起动机、温度传感器、爆震传感器、空燃比传感器、氧气传感器、发动机线束、冷却系统、点火系统、进排气系统、变速传动系统、电子燃油泵等。
底盘电子系统可以包括：转向系统、悬架系统、制动系统等。
车身电子电器可以包括：业务连续性管理(business continuity management，BCM)系统、继电器/保险丝、地板线束、车门线束、顶篷线束、仪表台线束、通用串行总线(universal serial bus，USB)/高清多媒体接口(high definition multimedia interface，HDMI)线、电动后视镜、车窗升降电机、尾门电动撑杆、门窗开关、雨刮电机、天窗电机、车辆诊断(on board diagnostics，OBD)、照明系统、开关等。
安全舒适系统可以包括：安全系统、座椅调节电机、主动降噪单元、喇叭、空调系统等。
娱乐通讯系统可以包括：人机交互(human machine interaction，HMI)系统、通讯系等。
摄像设备可以设置在车身外侧和/或车内，摄像设备的数量可以为1个，也可以为多个。例如，在车辆的A点、B点、C点和D点处均可以设置摄像设备。摄像设备可以拍摄视频，例如，摄像设备可以在车辆运行(或者启动)的过程中拍摄视频。可选的，车辆中可以设置存储空间，可以将摄像设备拍摄得到的视频存储至该存储空间。可选的，车辆中可以设置无线通信模块，可以将摄像设备拍摄得到的视频发送至云服务器，或者将摄像设备拍摄得到的视频发送至用户的终端设备(例如，手机、电脑等设备)。
需要说明的是，上述只是以示例的形式示意车辆中包括的部件，并非对车辆中的部件进行的限定。
在车辆行驶(或者运行)的该过程中，可以获取车辆的行驶数据。根据车辆的历史行驶数据可以确定车辆的历史行驶特征，车辆的历史行驶特征可以表示车辆的驾驶人员的驾驶习惯。车辆在第一时段(例如，当前时刻之前的时段)的第一行驶数据可以表示车辆在第一时段的行驶情况。由于用户的驾驶习惯通常较为固定，因此，将第一行驶数据和车辆的历史行驶特征进行比较，可以确定车辆在第一时段内是否存在异常。在确定车辆在第一时段内存在异常时，可以对摄像设备拍摄的行车记录视频进行标注，以记录车辆在第一时段内存在异常。可选的，车辆存在异常的情况可以包括：车辆故障、车祸、用户异常驾驶。用户异常驾驶可以包括：用户驾驶的车速过快、用户驾驶的车速过慢、用户驾驶车辆在某区域徘徊等。
用户可以通过终端设备查看行车记录视频(摄像设备拍摄得到的视频，或者对摄像设备拍摄得到的视频进行标注后的视频)。可选的，终端设备可以通过多种方式获取行车记录视频，下面，结合图2A-图2C，介绍几种终端设备获取行车记录视频的方式。
图2A为本申请实施例提供的一种视频获取方式的示意图。请参见图2A，包括车辆A、移动硬盘B和终端设备C。
行车记录视频可以存储在车辆A中的预设存储空间。在该种情况下，当用户需要通过终端设备C查看行车记录视频时，用户可以通过移动硬盘B在存储空间中拷贝行车记录视频，并将行车记录视频拷贝至终端设备C。
行车记录视频可以存储在移动硬盘B中，例如，移动硬盘B插设在车辆中，摄像设备拍摄的视频存储至移动硬盘B中。在该种情况下，当用户需要在通过终端设备C查看行车记录视频时，用户可以在车辆中取下移动硬盘B，并将移动硬盘B中的行车记录视频拷贝至终端设备C。
图2B为本申请实施例提供的另一种视频获取方式的示意图。请参见图2B，包括车辆A和终端设备B。行车记录视频可以存储在车辆A中的预设存储空间。车辆A中设置有通信模块，车辆A可以通过该通信模块与终端设备B进行通信，例如，车辆A可以与终端设备B进行蓝牙通信、WIFI通信等。终端设备B中可以安装有应用程序，用户可以通过应用程序控制将车辆A的预设存储空间中的视频传输至终端设备B。例如，用户可以通过应用程序选择某时段内的行车记录视频，以使车辆将该时段内的行车记录视频传输至终端设备。
图2C为本申请实施例提供的又一种视频获取方式的示意图。请参见图2C，包括车辆A、终端设备B和云服务器C。车辆A中设置有通信模块，车辆A可以通过该通信模块将行车记录视频上传至云服务器C，由云服务器C存储该行车记录视频。终端设备B中可以安装应用程序，用户可以通过应用程序控制终端设备B从云服务器C下载行车记录视频。例如，用户可以通过应用程序选择某时段内的行车记录视频，以使终端设备B请求从云服务器C下载该时段内的行车记录视频。
需要说明的是，上述图2A-图2C只是以示例的形式示意终端设备获取行车记录视频的方式，并非对该方式进行的限定。
下面，通过具体实施例，对本申请所示的技术方案进行详细说明。需要说明的是，下面几个实施例可以独立存在，也可以相互结合，对于相同或相似的内容，在不同的实施例中不再重复说明。
图3为本申请实施例提供的一种数据处理方法的流程示意图。请参加图3，该方法可以包括：
S301、获取第一模型。
本申请实施例的执行主体可以为车辆、行车记录设备、设置在车辆或者行车记录设备中的数据处理装置，该数据处理装置可以通过软件实现，也可以通过软件和硬件的结合实现，例如，数据处理装置可以为处理芯片。
为了便于描述，下文以执行主体为行车记录设备为例进行说明。
其中，第一模型用于对行驶数据进行处理，以得到对应的行驶特征。可以通过曲线表示行驶特征，例如，行驶特征可以表示行驶数据的分布规律。
下面，结合图4，以行驶数据为加速度为例，对行驶数据和行驶特征进行说明。
图4为本申请实施例提供的行驶数据和行驶特征的示意图。请参见图4，坐标轴的横轴表示路况指数，路况指数可以为根据道路的拥堵程度、天气等参数确定得到的。坐标轴的纵轴表示归一化的加速度。坐标系中的点表示离散的加速度(行驶数据)，该加速度可以为在预设时段内采集得到的不同路况下的加速度。坐标系中的曲线表示行驶特征(还可以称为加速度特征)，该行驶特征可以指示加速度的分布规律。
可选的，可以通过如下方式获取第一模型：
第一种方式：其它设备生成第一模型，行车记录设备从其它设备获取第一模型。
可选的，其它设备可以为服务器、终端设备等。
其它设备可以通过如下方式生成第一模型：获取多组第一样本，对多组第一样本进行学习得到第一模型，每组第一样本包括：样本行驶数据和样本行驶特征。
可选的，一组第一样本中样本行驶数据可以为一种类型的行驶数据，行驶数据的类型可以为速度、加速度、发送机转速、发动机温度等，例如，一组第一样本中的样本行驶数据可以为预设时段内的速度。在一组样本数据中，样本行驶特征与样本行驶数据对应，样本行驶特征用于反映样本行驶数据的特点。可选的，可以通过样本曲线表示样本行驶特征，该样本曲线用于指示样本行驶数据的分布规律。样本行驶特征可以为人工对样本行驶数据进行标注得到的。
学习第一模型的算法可以包括：逻辑回归(logistic回归)算法、决策树算法、向量机算法、朴素贝叶斯算法等。
通过对多组第一样本进行学习得到第一模型后，第一模型具有如下功能：向第一模型输入行驶数据，第一模型可以对行驶数据的进行处理，以输出行驶数据对应的行驶特征。
在其它设备学习得到第一模型之后，可以从其它设备获取该第一模型，该第一模型可以为离线的模型。
第二种方式：行车记录设备生成第一模型。
需要说明的是，行车记录设备生成第一模型的过程可以参见第一种方式，此处不再进行赘述。
S302、获取车辆的历史行驶数据。
历史行驶数据可以为车辆在历史行驶过程中产生的数据，历史行驶过程可以为车辆在历史时段的行驶过程，历史时段可以为当前时刻之前一周、一个月、半年、一年等，可以根据实际情况设置历史时段。
可选的，历史行驶数据包括如下至少一种：车辆中的部件的历史状态数据、车辆中的部件的历史运行数据或者车辆中的部件采集的历史传感数据。
需要说明的是，历史行驶数据的描述可以参见上述对行驶数据的描述，此处不再进行赘述。
可选的，在车辆启动之后，车辆中的多数部件启动工作，并产生行驶数据，行车记录设备可以获取车辆产生的历史行驶数据。为了便于理解，下面，结合图5A-图5B，对行车记录设备获取历史行驶数据的方式进行说明。
图5A为本申请实施例提供的一种获取历史行驶数据的示意图。请参见图5A，车辆中包括多个部件和车身状态系统，多个部件中包括多个零件和多个传感器。在车辆启动之后，多数部件可以启动工作，启动工作的部件可以产生行驶数据，车身状态系统可以获取并存储部件产生的行驶数据。行车记录设备和车身状态系统之间可以通信，例如，行车记录设备和车身状态系统可以有线连接或者无线连接，以使行车记录设备可以从车身状态系统获取历史行驶数据。
图5B为本申请实施例提供的另一种获取历史行驶数据的示意图。请参见图5B，车辆中包括多个部件和车身状态系统，多个部件中包括多个零件和多个传感器。在车辆启动之后，多数部件可以启动工作，启动工作的部件可以产生行驶数据，车身状态系统可以获取部件产生的行驶数据，并将部件产生的行驶数据传输至云服务器，有云服务器存储行驶数 据。当行车记录设备需要获取历史行驶数据时，行车记录设备可以向云服务器请求获取历史行驶数据。
需要说明的是，图5A-图5B只是以示例的形式示意行车记录设备获取历史行驶数据的方式，并非对此进行的限定。
S303、通过第一模型对历史行驶数据进行处理，得到第一历史行驶特征。
历史行驶数据包括多种类型的历史行驶数据。例如，历史行驶数据的类型包括：速度、加速度、发动机转速、发动机温度等。
第一历史行驶特征中包括多种类型的历史行驶数据对应的行驶特征。例如，第一历史行驶特征中包括：历史速度对应的行驶特征、历史加速度对应的行驶特征、历史发动机转速对应的行驶特征等。历史速度对应的行驶特征用于指示历史速度的分布规律，历史加速度对应的行驶特征用于指示历史加速度的分布规律。
对于一个车辆来说，驾驶该车辆的用户通常为固定的一个或多个用户。针对任意一个用户，用户的驾驶习惯通常为固定的，使得车辆的行驶数据通常满足固定的曲线分布，例如，对于同一用户和同一车辆，该用户驾驶该车辆在不同路况下的速度通常满足固定的速度曲线分布，该用户驾驶该车辆在不同路况下的加速度通常满足固定的加速度曲线分布。因此，根据历史行驶数据确定得到的第一历史行驶特征可以表示用户的驾驶习惯，或者，第一历史行驶特征还可以称为驾驶车辆的用户的用户画像。
可以将历史行驶数据输入至第一模型，第一模型输出历史行驶数据对应的第一历史行驶特征。第一历史行驶特征中包括每种类型的历史行驶数据对应的多条历史数据曲线，历史数据曲线用于指示历史行驶数据的分布规律，即，通过历史数据曲线表示历史行驶数据对应的行驶特征。
下面，结合图6，对第一历史行驶特征进行说明。
图6为本申请实施例提供的历史行驶特征的示意图。请参见图6，坐标系中包括多条曲线，每条曲线表示一种历史行驶特征，一种历史行驶特征与一种类型的历史行驶数据对应。需要说明的是，针对不同的曲线，坐标横轴和坐标纵轴所表示的含义不同，例如，当历史行驶特征与加速度对应时，则坐标横轴可以表示路况指数，坐标纵轴可以表示加速度。当历史行驶特征与速度对应是，则坐标横轴可以表示路况指数，坐标纵轴可以表示速度。
图6只是以示例的形式示意第一历史行驶特征，并非对第一历史行驶特征进行的限定。
S304、获取第二模型。
其中，第二模型用于获取数据与行驶特征之间的相似度，该数据可以包括行驶数据，或者，该数据可以包括行驶数据和场景数据。
可选的，可以通过如下方式获取第二模型：
第一种方式：其它设备生成第二模型，行车记录设备从其它设备获取第二模型。
可选的，其它设备可以为服务器、终端设备等。
其它设备可以通过如下方式生成第二模型：获取多组第二样本，对多组第二样本进行学习得到第二模型，每组第二样本包括：样本数据、样本行驶特征和样本相似度。
可选的，样本数据可以包括样本行驶数据，或者，样本数据可以包括样本行驶数据和样本场景数据。样本场景数据包括如下信息中的至少一种：样本时间信息、样本位置信息、样本路况信息或样本天气信息。
样本相似度可以为样本数据和样本行驶特征之间的相似度，该样本相似度可以为人工标注的相似度。
可选的，一组第二样本中样本行驶数据可以为一种类型的行驶数据，行驶数据的类型可以为速度、加速度、发送机转速、发动机温度等，例如，一组第一样本中的样本行驶数据可以为预设时段内的速度。在一组样本数据中，样本行驶特征与样本行驶数据对应。可选的，可以通过样本曲线表示样本行驶特征。
学习第二模型的算法可以包括：逻辑回归(logistic回归)算法、决策树算法、向量机算法、朴素贝叶斯算法等。
通过对多组第二样本进行学习得到第二模型后，第二模型具有如下功能：向第二模型输入数据和行驶特征，第二模型可以对输入的数据和行驶特征进行处理，以获取数据和行驶特征之间的相似度。
在其它设备学习得到第二模型之后，可以从其它设备获取该第二模型，该第二模型可以为离线的模型。
第二种方式：行车记录设备生成第二模型。
需要说明的是，行车记录设备生成第二模型的过程可以参见第一种方式，此处不再进行赘述。
可选的，第二模型和第一模型可以集成在一个模型中，例如，集成得到的模型可以同时具有第一模型的功能和第二模型的功能。第二模型和第一模型也可以为两个独立的模型。
需要说明的是，S301-S304的过程可以一次性的执行过程或者周期性的执行过程，即，在S305之前，只要执行了一次S301-S304即可，无需实时执行S301-S304。
S305、获取第一数据。
可选的，第一数据包括车辆在第一时段的第一行驶数据。或者，第一数据可以包括第一行驶数据和场景数据，场景数据包括如下信息中的至少一种：时间信息、位置信息、路况信息或天气信息。
第一时段可以为当前时刻之前、且距离当前时刻最近的一个时段，例如，第一时段可以为当前时刻之前的5分钟、10分钟、30分钟、1个小时等。
需要说明的是，行车记录设备获取第一数据的方式可以参见S302中获取历史行驶数据的方式，此处不再进行赘述。
S306、通过第二模型对第一数据和第一历史行驶特征进行处理，得到第一数据和第一历史行驶特征之间的相似度。
可以将第一数据和第一历史行驶特征输入至第二模型，以使第二模型输出第一数据和第一历史行驶特征之间的相似度。例如，在将第一数据和第一历史行驶特征输入至第二模型之后，第二模型可以先确定第一数据对应的第一数据曲线，再对第一数据曲线和第一历史行驶特征中的历史数据曲线进行对比处理，得到相似度。若第一数据中还包括场景数据，则还可以在第一历史行驶特征中获取场景数据对应的历史数据曲线，并将第一数据曲线与场景数据对应的历史数据曲线进行比对处理，以得到相似度。
可选的，第一数据中可以包括第一行驶数据，或者，第一数据中可以包括第一行驶数据和场景数据。当第一数据中包括的内容不同时，确定第一数据和第一历史行驶特征之间 的相似度的过程也不同，可以包括如下两种情况：
第一种情况：第一数据中包括第一行驶数据。
第一行驶数据中可以包括多种类型的行驶数据，第一历史行驶特征中包括每种类型的行驶数据对应的历史行驶特征。可以分别获取每种类型的行驶数据与对应的历史行驶特征之间的相似度，再根据每种类型的行驶数据与对应的历史行驶特征之间的相似度确定第一数据和第一历史行驶特征之间的相似度。
针对任意一种类型的行驶数据，可以获取该种类型的行驶数据对应的第一数据曲线，在第一历史行驶特征中获取该种类型的行驶数据对应的历史数据曲线，将第一数据曲线与对应的历史数据曲线的相似度确定为该种类型的行驶数据与历史行驶特征之间的相似度。
下面，结合图7A，对确定第一数据和第一历史行驶特征之间的相似度的过程进行说明。
图7A为本申请实施例提供的确定相似度的示意图。请参见图7A，第一数据包括第一行驶数据。第一行驶数据中可以包括多种类型的行驶数据，其中，行驶数据1、行驶数据2、行驶数据3、…、行驶数据N(N为大于1的整数)为N种不同类型的行驶数据。例如，行驶数据1可以为速度，行驶速度2可以为加速度，行驶数据3可以为发动机转速。
可以获取每种类型的行驶数据对应的数据曲线。可选的，可以通过第二模型获取每种类型的行驶数据对应的数据曲线。例如，可以将行驶数据1输入至第二模型，以使第二模型输出行驶数据1对应的数据曲线1。可以将行驶数据2输入至第二模型，以使第二模型输出行驶数据2对应的数据曲线2。以此类推，可以得到N种类型的行驶数据对应的N条数据曲线。
第一历史行驶特征中包括多条历史数据曲线，例如，第一历史行驶特征中包括行驶数据1对应的历史数据曲线1、行驶数据2对应的历史数据曲线2。可以将数据曲线1和历史数据曲线1进行比对处理，得到相似度1，将数据曲线2和历史数据曲线2进行比对处理，得到相似度2，以此类推，可以得到N个相似度。
可以将该N个相似度的平均值或者加权平均值确定为第一数据和第一历史行驶特征之间的相似度。
第二种情况：第一数据包括第一行驶特征和场景数据。
第一行驶数据中可以包括多种类型的行驶数据，例如，第一行驶数据中可以包括速度、加速度、发动机转速等。场景数据包括如下信息中的至少一种：时间信息、位置信息、路况信息或天气信息，根据场景数据可以确定得到对应的场景类型，例如，场景类型可以包括阴雨天气类型、早高峰类型、晚高峰类型、节假日类型、工作日类型、路况畅通类型等。
第一历史行驶特征中包括每种类型的行驶数据对应的多个历史行驶特征，该多个历史行驶特征与不同的场景类型对应。例如，假设行驶数据为速度，则第一历史行驶特征中包括速度对应的多个历史速度行驶特征，该多个历史速度行驶特征可以包括：阴雨天气对应的历史速度行驶特征、早高峰对应的历史速度行驶特征、节假日对应的历史速度行驶特征等。
可以根据场景数据，分别获取每种类型的行驶数据与对应的历史行驶特征之间的相似度，再根据每种类型的行驶数据与对应的历史行驶特征之间的相似度确定第一数据和第一历史行驶特征之间的相似度。
针对任意一种类型的行驶数据，可以获取该种类型的行驶数据对应的第一数据曲线， 在第一历史行驶特征中获取该种类型的行驶数据对应的多种历史数据曲线，再根据场景数据确定场景类型，并在该多种历史数据曲线中确定该场景类型对应的第一历史数据曲线，将第一数据曲线与该第一历史数据曲线的相似度确定为该种类型的行驶数据与历史行驶特征之间的相似度。
下面，结合图7B，对确定第一数据和第一历史行驶特征之间的相似度的过程进行说明。
图7B为本申请实施例提供的确定相似度的示意图。请参见图7B，第一数据包括第一行驶数据和场景数据。第一行驶数据中可以包括多种类型的行驶数据，其中，行驶数据1、行驶数据2、行驶数据3、…、行驶数据N(N为大于1的整数)为N种不同类型的行驶数据。例如，行驶数据1可以为速度，行驶速度2可以为加速度，行驶数据3可以为发动机转速。
可以获取每种类型的行驶数据对应的数据曲线。可选的，可以通过第二模型获取每种类型的行驶数据对应的数据曲线。例如，可以将行驶数据1输入至第二模型，以使第二模型输出行驶数据1对应的数据曲线1。可以将行驶数据2输入至第二模型，以使第二模型输出行驶数据2对应的数据曲线2。以此类推，可以得到N种类型的行驶数据对应的N条数据曲线。
第一历史行驶特征中包括每种类型的行驶数据对应的多条历史数据曲线，例如，第一历史行驶特征中包括行驶数据1对应的多条历史数据曲线(例如，历史数据曲线11、历史数据曲线12、……、历史数据曲线1X)、行驶数据2对应的多条历史数据曲线(例如，历史数据曲线21、历史数据曲线22、……、历史数据曲线2K)等。可以根据场景数据在行驶数据1对应的多条历史数据曲线中选择场景数据对应的第一历史数据曲线(假设为历史数据曲线11)，根据场景数据在行驶数据2对应的多条历史数据曲线中选择场景数据对应的第一历史数据曲线(假设为历史数据曲线21)，以此类推，直至根据场景数据选择出每种类型的行驶数据对应的第一历史数据曲线。可以将数据曲线1和历史数据曲线1进行比对处理，得到相似度1，将数据曲线2和历史数据曲线2进行比对处理，得到相似度2，以此类推，可以得到N个相似度。
可以将该N个相似度的平均值或者加权平均值确定为第一数据和第一历史行驶特征之间的相似度。
需要说明的是，上述图7A-图7B只是以示例的形式示意确定第一数据和第一历史行驶特征之间的相似度，并非对此进行的限定，还可以通过其他方式确定该相似度。
需要说明的是，还可以通过算法获取第一数据和第一历史行驶特征之间的相似度，其过程与通过第二模型获取该相似度的过程类似，此处不再进行赘述。
S307、根据相似度确定车辆在第一时段出现异常。
车辆在第一时段出现异常的情况可以包括：车辆在第一时段实现故障、车辆在第一时段出现车祸、用户在第一时段对车辆的驾驶异常。用户对车辆的驾驶异常可以包括：用户驾驶的车速过快、用户驾驶的车速过慢、用户驾驶车辆在某区域徘徊等。
可选的，若相似度小于或等于相似度阈值，则确定车辆在第一时段出现异常。
S308、根据第一时段对车辆的行车记录视频进行标注。
可以通过如下方式对车辆的行车记录视频进行标注：生成异常信息，根据第一时段，在行车记录视频中标注异常信息。
异常信息包括如下信息中的至少一种：异常指示、异常等级、异常类型或者异常描述信息。异常指示用于指示车辆异常。异常等级用于指示车辆异常的程度，例如，S306确定得到相似度越低，则车辆异常的程度越高，异常等级也越高。异常类型可以包括刹车异常、转弯异常、加速异常、发动机异常、行驶轨迹异常等。异常描述信息用于描述车辆异常的具体情况，例如，异常描述信息可以包括：一分钟内急刹车5次，或者，加速度大于第一阈值，或者，1小时内在相同路段往返行驶10次，或者，3分钟变道10次。
在对行车记录视频进行标注之后，用户可以通过终端设备(电脑、手机等设备)查看标注后的行车记录视频。下面，对行车记录视频进行标注以及用户车看标注后的行车记录视频的过程进行说明。
第一种视频标注方式：
摄像设备可以拍摄车辆的多个行车记录视频，例如，车辆的一次出行(车辆启动至车辆熄火)可以对应一个行车记录视频，或者，车辆的预设行驶时长(例如一个小时等)可以对应一个行车记录视频。车辆多次出行的多个行车记录视频可以以列表的形式存储。在对行车记录视频进行标注时，生成异常信息，并将异常信息作为行车记录视频的属性信息，这样，在以列表的形式显示行车记录视频列表时，可以显示异常信息。还可以将异常信息中的部分信息(例如，异常描述信息或者异常描述信息中的部分内容)以字幕或者弹屏的形式添加至行车记录视频中对应的位置。
在该种视频标注方式中，下面，结合图8，对用户查看标注后的行车记录视频的方式进行说明。
图8为本申请实施例提供的一种视频查看方式的示意图。请参见图8，包括界面801-界面803。
请参见界面801，假设终端设备行车记录视频的方式如图2A所示，则在终端设备获取得到行车记录视频之后，终端设备中可以显示行车记录视频对应的文件夹。当用户需要查看行车记录视频时，用户可以对行车记录视频对应的文件夹进行点击操作，以使终端设备显示行车记录视频的列表。
请参见界面802，包括行车记录视频的列表，该列表中包括5个行车记录视频和该5个行车记录视频的属性信息，属性信息包括拍摄时间、异常指示、异常等级、异常类型和异常描述信息。当然，属性信息还可以包括其它，对此不作限定。其中，该5个行车记录视频可以为车辆5次出行对应的视频。由行车记录视频的列表可知，在行车记录视频1、行车记录视频4和行车记录视频5对应的时段，车辆均不存在异常，则该3个行车记录视频对应的异常指示为“正常”，行车记录视频2和行车记录视频3对应的时段，车辆存在异常，则该两个行车记录视频对应的异常指示均为“异常”，该两个行车记录视频还存在属性：异常等级、异常类型和异常描述信息。可选的，异常描述信息可以为简要的描述信息，用户可以对该简要的描述信息进行点击操作，以使终端设备显示详细的描述信息。例如，用户对简要的描述信息“刹车频繁”进行点击操作后，终端设备可以显示详细的描述信息“在第20-22分钟出现8次急刹车”。可选的，为了便于用户查看存在异常的行车记录视频，可以以不同的显示方式显示正常和异常的行车记录视频的标识和属性信息，显示方式包括字体颜色、字体类型、字体大小等。例如，可以以红色字体显示异常的行车记录视频的标识和属性信息，以黑色字体显示正常的行车记录视频的标识和属性信息。用户可 以对行车记录视频列表中的行车记录视频的标识进行点击操作，以使终端设备播放该行车记录视频。例如，当用户需要查看行车记录视频2时，用户可以对行车记录视频2的标识进行点击操作，以使电子设备播放行车记录视频2。
请参见界面803，终端设备播放行车记录视频2。用户可以根据行车记录视频2的异常描述信息确定在行车记录视频2的第20-22分钟时车辆存在异常，则用户可以根据该异常描述信息，对视频播放进度条进行拖拽操作，当用户将进度条拖拽至第20分钟时，视频中以字幕的形式显示异常描述信息中的部分内容(急刹车)。
在上述过程中，用户根据行车记录视频的列表可以方便的获知车辆存在异常对应的行车记录视频，还可以根据异常描述信息在行车记录视频中车辆存在异常的时间段，并准确的在行车记录视频中定位该时间段，操作方便灵活，使得用户体验较高。
需要说明的是，上述行车记录视频还可以为预设时长的视频，例如，每个行车记录视频的时长均为1个小时。可选的，异常指示为“异常”的行车记录视频还可以为在车辆出现异常时段拍摄的视频，例如，行车记录视频2的时长可以为2分钟，车辆在该2分钟内出现异常。
第二种视频标注方式：
摄像设备拍摄的一个行车记录视频可以对应一个视频文件，若该行车记录视频的拍摄时段内车辆出现异常，则生成异常信息文件，异常信息文件中可以包括一个或多个异常信息，该异常信息文件可以作为该视频文件的配置文件。异常信息文件中的一个异常信息可以与行车记录视频中的一个异常时段(或者异常时刻)对应，且异常信息与行车记录视频中的异常时段(或者异常时刻)具有关联关系，例如，通过一个异常信息可以定位至对应的异常时段(或者异常时刻)。
下面，结合图9，对标注行车记录视频的过程进行说明。
图9为本申请实施例提供的视频标注方式的示意图。请参见图9，当在一个行车记录视频对应的拍摄时段内车辆出现异常时，可以生成视频文件和异常文件信息。例如，视频文件可以为一个80分钟时长的视频，异常信息文件中可以包括三个异常信息，分别记为异常信息1、异常信息2和异常信息3。异常信息1与行车记录视频中的t1时刻对应，即，通过异常信息1可以定位置行车记录视频中的t1时刻。异常信息2与行车记录视频中的t2时刻对应，即，通过异常信息2可以定位置行车记录视频中的t2时刻。异常信息13与行车记录视频中的t3时刻对应，即，通过异常信息3可以定位置行车记录视频中的t3时刻。
在该种视频标注方式中，下面，结合图10，对用户查看标注后的行车记录视频的方式进行说明。
图10为本申请实施例提供的一种视频查看方式的示意图。请参见图10，包括界面1001-界面1006。
请参见界面1001，假设终端设备行车记录视频的方式如图2B或图2C所示。终端设备中安装有应用程序，假设已经通过应用程序将行车记录视频传输至终端设备。当用户需要通过终端设备查看行车记录视频时，用户可以在终端设备终端中打开该应用程序，该应用程序中包括“视频回看”图标，用户可以对该图标进行点击操作，以使终端设备显示界面1002。界面1001中还可以包括其它图标，本申请实施例对界面1001中包括的图标不作具体限定。
请参见界面1002，包括“全部视频”图标和“异常视频”图标。“全部视频”图标对应的页面中包括所有的视频的标识，“异常视频”图标对应的页面中包括异常视频的标识。当用户需要查看异常视频时，用户可以对“异常视频”图标进行点击操作，以使终端设备显示界面1003。异常视频是指：拍摄时段包括车辆出现异常的时段的视频。
请参见界面1003，包括异常视频列表，用户可以对任意一个异常视频进行点击操作，以使终端设备播放该异常视频。例如，假设用户需要观看视频2，则用户对视频2进行点击操作，以使终端设备显示界面1004。
请参见界面1004，包括视频播放窗口M和至少一个“异常点”图标，“异常点”图标的数量与该异常视频中出现异常的数量一致。例如，假设视频2中出现3次异常，则该界面中包括3个“异常点”图标，分别为“异常点1”图标、“异常点2”图标和“异常点3”图标。可选的，该3个“异常点”图标可以为根据图9中的3个异常信息生成的。假设用户需要观看异常点1对应的视频，则用户可以对“异常点1”图标进行点击操作，以使终端设备显示界面1005。
请参见界面1005，视频播放窗口M中的视频的播放进度跳转至时刻t1，且视频中显示异常描述信息(急刹车)。假设用户需要观看异常点2对应的视频，则用户可以对“异常点2”图标进行点击操作，以使终端设备显示界面1006。
请参见界面1006，视频播放窗口M中的视频的播放进度跳转至时刻t2，且视频中显示异常描述信息(急转弯)。
在上述过程中，用户通过终端设备中的应用程序，可以方便的查看异常视频，且根据“异常点”图标可以快速的定位到异常时段，操作方便灵活，使得用户体验较高。
本申请实施例提供的数据处理方法，可以获取车辆在第一时段内的第一数据和第一历史行驶特征，根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常，并根据第一时段对车辆的行车记录视频进行标注。第一数据可以反应车辆在第一时段内的行驶情况，第一历史行驶特征可以反应车辆的驾驶人员的驾驶习惯。由于用户的驾驶习惯通常较为固定，因此，将第一行驶数据和车辆的历史行驶特征进行比较，可以确定车辆在第一时段内是否存在异常。在确定车辆在第一时段内存在异常时，可以对摄像设备拍摄的行车记录视频进行标注，以记录车辆在第一时段内存在异常，使得可以对行车记录视频进行准确的标注，用户根据对行车记录视频的标注结果，可以准确快速的查到所需的视频，提高的视频查找的效率。
需要说明的是，在图3实施例所示的各个处理步骤(S301-S308)并不构成对数据处理过程的具体限定。在本申请另一些实施例中，数据处理过程可以包括比图3实施例更多或者更少的步骤，例如，数据处理过程可以包括图3实施例中的部分步骤，或者，图3实施例中的一些步骤可以由具有相同功能的步骤替换，或者，图3实施例中的一些步骤可以被拆分成多个步骤等。
下面，结合图11，介绍另一种可行的数据处理方法。
图11为本申请实施例提供的另一种数据处理方法的流程示意图。请参见图11，该方法可以包括：
S1101、获取第一数据和第一历史行驶特征。
本申请实施例的执行主体可以为车辆、行车记录设备、设置在车辆或者行车记录设备 中的数据处理装置，该数据处理装置可以通过软件实现，也可以通过软件和硬件的结合实现，例如，数据处理装置可以为处理芯片。
其中，第一数据包括车辆在第一时段的第一行驶数据，第一历史行驶特征为根据车辆的历史行驶数据确定得到的。
需要说明的是，获取第一历史行驶特征的过程可以参见S303的执行过程，获取第一数据的过程可以参见S305的执行过程，此处不再进行赘述。
S1102、根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常。
需要说明的是，S1102的执行过程可以参见S306-S307的执行过程，此处不再进行赘述。
S1103、根据第一时段对车辆的行车记录视频进行标注。
需要说明的是，S1103的执行过程可以参见S308的执行过程，此处不再进行赘述。
在图11所示的实施例中，可以获取车辆在第一时段内的第一数据和第一历史行驶特征，根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常，并根据第一时段对车辆的行车记录视频进行标注。第一数据可以反应车辆在第一时段内的行驶情况，第一历史行驶特征可以反应车辆的驾驶人员的驾驶习惯。由于用户的驾驶习惯通常较为固定，因此，将第一行驶数据和车辆的历史行驶特征进行比较，可以确定车辆在第一时段内是否存在异常。在确定车辆在第一时段内存在异常时，可以对摄像设备拍摄的行车记录视频进行标注，以记录车辆在第一时段内存在异常，使得可以对行车记录视频进行准确的标注，用户根据对行车记录视频的标注结果，可以准确快速的查到所需的视频，提高的视频查找的效率。
本申请实施例还提供一种行车记录设备。下面，结合图12A-图12B介绍行车记录设备。
图12A为本申请实施例提供的一种行车记录设备的结构示意图。请参见图12A，行车记录设备120包括处理芯片和121摄像设备122，其中，
所述摄像设备121用于，拍摄行车记录视频。
所述处理芯片122用于，获取第一数据和第一历史行驶特征，并根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常，并根据第一时段对行车记录视频进行标注，第一数据包括车辆在第一时段的第一行驶数据，第一历史行驶特征为根据车辆的历史行驶数据确定得到的。
可选的，处理芯片122还可以执行上述方法实施例所示的数据处理方法，其过程和有益效果类似，此处不再进行赘述。
图12B为本申请实施例提供的另一种行车记录设备的结构示意图。在图12A的基础上，请参加图12B，行车记录设备120还可以包括存储器123，存储器123用于存储行车记录视频。
可选的，摄像设备121拍摄得到行车记录视频之后，可以将行车记录视频发送至存储器123，以使存储器123存储行车记录视频。
可选的，存储器123中还可以存储程序指令，处理芯片122可以根据该程序指令执行上述方法实施例所示的技术方案。
请参见图12B，行车记录设备120还可以包括通信模块124，通信模块124可以与其他设备(例如车辆、云服务器等)进行通信。
可选的，行车记录设备120还可以包括数据数据采集设备，数据采集设备可以包括：摄像头、毫米波雷达、激光雷达或惯性传感器等，数据采集设备可以获取所述第一数据。
在实际应用过程中，行车记录设备120通常设置在车辆上，下面，结合图13A-图13C，对行车记录设备和车辆之间的连接关系进行说明。其中，在图13A-图13C中，以行车记录设备为图12B为例进行说明。
图13A为本申请实施例提供的一种设备连接示意图。请参见图13A，行车记录设备120的通信模块124中可以设置有接口，车辆中也可以设置有接口。
在实际应用过程中，可以将行车记录设备120中的接口与车辆中的接口连接，以使行车记录设备和车辆可以通过接口进行通信。
需要说明的是，在行车记录设备中，接口还可以设置在其它位置，本申请实施例对此不作具体限定。
图13B为本申请实施例提供的另一种设备连接示意图。请参见图13B，车辆中设置有通信模块，行车记录设备120中的通信模块124可以与车辆中的通信模块进行通信(例如，无线通信)，例如，车辆可以通过通信模块向行车记录设备发送行驶数据。
图13C为本申请实施例提供的又一种设备连接示意图。请参见图13C，车辆中设置有通信模块，车辆中的通信模块可以与与服务器进行通信，例如，车辆可以通过通信模块向云服务器发送行驶数据。行车记录设备120可以通过通信模块124与云服务器通信，例如，行车记录设备120可以通过通信模块124从云服务器获取行驶数据。
需要说明的是，在图13A-图13C中，只是以示例的形式示意车辆的结构，并非对车联的结构进行的限定。
本申请实施例还提供一种车辆，下面，结合图14A-图14B，对车辆的结构进行说明。
图14A为本申请实施例提供的一种车辆的结构示意图。请参见图14A，车辆140中可以包括处理芯片141和摄像设备142，其中，
摄像设备141用于，拍摄行车记录视频；
处理芯片142用于，获取第一数据和第一历史行驶特征，并根据第一数据和第一历史行驶特征，确定车辆在第一时段出现异常，并根据第一时段对行车记录视频进行标注，第一数据包括车辆在第一时段的第一行驶数据，第一历史行驶特征为根据车辆的历史行驶数据确定得到的。
可选的，处理芯片122还可以执行上述方法实施例所示的数据处理方法，其过程和有益效果类似，此处不再进行赘述。
图14B为本申请实施例提供的另一种车辆的结构示意图。在图14A的基础上，请参见图14B，车辆中还可以存储器143，存储器143可以存储行车记录视频。
可选的，摄像设备141拍摄得到行车记录视频之后，可以将行车记录视频发送至存储器143，以使存储器143存储行车记录视频。
可选的，存储器143中还可以存储程序指令，处理芯片142可以根据该程序指令执行上述方法实施例所示的技术方案。
请参见图14B，车辆还包括车身状态系统144，车身状态系统144可以获取第一行驶数据，并向处理芯片141发送第一行驶数据。车辆还包括部件，部件中包括多个零件和多个传感器，车身状态系统144可以从车辆的部件获取第一行驶数据。
可选的，车辆140还可以包括通信模块(图中未示出)，通信模块可以与其他设备(例如云服务器等)进行通信。
可选的，车辆140还可以包括数据数据采集设备，数据采集设备可以包括：摄像头、毫米波雷达、激光雷达或惯性传感器等，数据采集设备可以获取所述第一数据。
图15为本申请实施例提供的一种数据处理装置的结构示意图。请参见图15，该数据处理装置150可以包括：获取模块151、确定模块152和标注模块153，其中，
所述获取模块151用于，获取第一数据和第一历史行驶特征，所述第一数据包括车辆在第一时段的第一行驶数据，所述第一历史行驶特征为根据所述车辆的历史行驶数据确定得到的；
所述确定模块152用于，根据所述第一数据和所述第一历史行驶特征，确定所述车辆在第一时段出现异常；
所述标注模块153用于，根据所述第一时段对所述车辆的行车记录视频进行标注。
可选的，获取模块151可以执行图3实施例中的S303和S305，以及图11实施例中的S1101。
可选的，确定模块152可以执行图3实施例中的S306-S307，以及图11实施例中的S1102。
可选的，标注模块153可以执行图3实施例中的S308，以及图11实施例中的S1103。
需要说明的是，本申请实施例所示的数据处理装置可以执行上述方法实施例所示的技术方案，其实现原理以及有益效果类似，此处不再进行赘述。
在一种可能的实施方式中，所述第一行驶数据包括如下数据中的至少一种：
所述车辆中的部件的状态数据；
所述车辆中的部件的运行数据；
或者，所述车辆中的部件采集的传感数据。
在一种可能的实施方式中，所述第一历史行驶特征包括：多种历史行驶数据对应的多条历史数据曲线，所述历史数据曲线用于指示所述历史行驶数据的分布规律，所述历史行驶数据包括如下至少一种：
所述车辆中的部件的历史状态数据；
所述车辆中的部件的历史运行数据；
或者，所述车辆中的部件采集的历史传感数据。
在一种可能的实施方式中，所述获取模块具体用于：
通过第一模型对所述历史行驶数据进行处理，得到所述第一历史行驶特征；
其中，所述第一模型为对多组第一样本学习得到的，所述多组第一样本中的每组第一样本包括：样本行驶数据和样本历史行驶特征。
在一种可能的实施方式中，所述确定模块152具体用于：
确定所述第一数据和所述第一历史行驶特征之间的相似度；
根据所述相似度确定所述车辆在所述第一时段出现异常。
在一种可能的实施方式中，所述确定模块152具体用于：
通过第二模型对所述第一数据和所述第一历史行驶特征进行处理，得到所述相似度；
其中，所述第二模型为对多组第二样本学习得到的，所述多组第二样本中的每组第二 样本包括样本数据、样本行驶特征和样本相似度，所述样本数据包括样本行驶数据。
在一种可能的实施方式中，所述确定模块152具体用于：
通过所述第二模型确定所述第一数据对应的第一数据曲线；
通过所述第二模型对所述第一数据曲线和所述第一历史行驶特征中的历史数据曲线进行对比处理，得到所述相似度。
在一种可能的实施方式中，所述第一数据还包括场景数据，所述场景数据包括如下信息中的至少一种：
时间信息、位置信息、路况信息或天气信息。
在一种可能的实施方式中，所述确定模块152具体用于：
根据所述场景数据，在多个历史行驶特征中确定所述第一历史行驶特征。
在一种可能的实施方式中，所述标注模块153具体用于：
生成异常信息；
根据所述第一时段，在所述行车记录视频中标注所述异常信息。
在一种可能的实施方式中，所述异常信息包括如下信息中的至少一种：
异常等级、异常类型或者异常描述信息。
需要说明的是，本申请实施例所示的数据处理装置可以执行上述方法实施例所示的技术方案，其实现原理以及有益效果类似，此处不再进行赘述。
图16为本申请提供的数据处理装置的硬件结构示意图。请参见图16，该数据处理装置160可以包括：处理器161和存储器162，其中，处理器161和存储器162可以通信；示例性的，处理器161和存储器162通过通信总线163通信，所述存储器162用于存储程序指令，所述处理器161用于运行存储器中的程序指令执行上述任意方法实施例所示的数据处理方法。
可选的，处理器161可以实现图3或者图11所示实施例中各步骤。
数据处理装置160还可以包括发送器和/或接收器。
上述处理器可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。
可选的，数据处理装置160可以为芯片、行车记录设备、车辆、行车记录设备中的部件或车辆中的部件等。
当数据处理装置160为行车记录设备时，所述数据处理装置还可以包括摄像设备或数据采集设备中的至少一个。可选的，数据数据采集设备可以以传感器的形式存在，例如，数据采集设备可以包括：摄像头、毫米波雷达、激光雷达或惯性传感器等，所述摄像设备用于拍摄所述行车记录视频，所述数据采集设备用于获取所述第一数据，所述存储器还可用于存储所述行车记录视频。例如，数据处理装置160的结构可以如图12A或图12B所示。
当数据处理装置160为车辆时，所述数据处理装置还可以包括摄像设备或数据采集设备中的至少一个，所述摄像设备用于拍摄所述行车记录视频，所述数据采集设备用于获取所述第一数据，所述存储器还可用于存储所述行车记录视频。所述数据数据采集设备可以 以传感器的形式存在，例如，数据采集装置可以包括：摄像头、毫米波雷达、激光雷达或惯性传感器等；所述数据采集设备还可以为用于获取第一行驶数据的车身状态系统。例如，数据处理装置的结构还可以为图14A或图14B所示。
本申请提供一种可读存储介质，所述可读存储介质上存储有计算机程序；所述计算机程序用于实现如上述任意实施例所述的数据处理方法。
本申请实施例提供一种计算机程序产品，所述计算机程序产品包括指令，当所述指令被执行时，使得计算机执行上述数据处理方法。
实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一可读取存储器中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储器(存储介质)包括：只读存储器(英文：read-only memory，缩写：ROM)、RAM、快闪存储器、硬盘、固态硬盘、磁带(英文：magnetic tape)、软盘(英文：floppy disk)、光盘(英文：optical disc)及其任意组合。
本申请实施例是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理单元以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理单元执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本申请实施例进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请实施例的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。
在本申请中，术语“包括”及其变形可以指非限制性的包括；术语“或”及其变形可以指“和/或”。本本申请中术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。本申请中，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。

Claims (25)

  1. 一种数据处理方法，其特征在于，包括：
    获取第一数据和第一历史行驶特征，所述第一数据包括车辆在第一时段的第一行驶数据，所述第一历史行驶特征为根据所述车辆的历史行驶数据确定得到的；
    根据所述第一数据和所述第一历史行驶特征，确定所述车辆在第一时段出现异常；
    根据所述第一时段对所述车辆的行车记录视频进行标注。
  2. 根据权利要求1所述的方法，其特征在于，所述第一行驶数据包括如下数据中的至少一种：
    所述车辆中的部件的状态数据；
    所述车辆中的部件的运行数据；
    或者，所述车辆中的部件采集的传感数据。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第一历史行驶特征包括：多种历史行驶数据对应的多条历史数据曲线，所述历史数据曲线用于指示所述历史行驶数据的分布规律，所述历史行驶数据包括如下至少一种：
    所述车辆中的部件的历史状态数据；
    所述车辆中的部件的历史运行数据；
    或者，所述车辆中的部件采集的历史传感数据。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，获取所述第一历史行驶特征，包括：
    通过第一模型对所述历史行驶数据进行处理，得到所述第一历史行驶特征；
    其中，所述第一模型为对多组第一样本学习得到的，所述多组第一样本中的每组第一样本包括：样本行驶数据和样本历史行驶特征。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，根据所述第一数据和所述第一历史行驶特征，确定所述车辆在第一时段出现异常，包括：
    确定所述第一数据和所述第一历史行驶特征之间的相似度；
    根据所述相似度确定所述车辆在所述第一时段出现异常。
  6. 根据权利要求5所述的方法，其特征在于，所述确定所述第一数据和所述第一历史行驶特征之间的相似度，包括：
    通过第二模型对所述第一数据和所述第一历史行驶特征进行处理，得到所述相似度；
    其中，所述第二模型为对多组第二样本学习得到的，所述多组第二样本中的每组第二样本包括样本数据、样本行驶特征和样本相似度，所述样本数据包括样本行驶数据。
  7. 根据权利要求6所述的方法，其特征在于，所述通过第二模型对所述第一数据和所述第一历史行驶特征进行处理，得到所述相似度，包括：
    通过所述第二模型确定所述第一数据对应的第一数据曲线；
    通过所述第二模型对所述第一数据曲线和所述第一历史行驶特征中的历史数据曲线进行对比处理，得到所述相似度。
  8. 根据权利要求1-7任一项所述的方法，其特征在于，所述第一数据还包括场景数据，所述场景数据包括如下信息中的至少一种：
    时间信息、位置信息、路况信息或天气信息。
  9. 根据权利要求8所述的方法，其特征在于，获取所述第一历史行驶特征，包括：
    根据所述场景数据，在多个历史行驶特征中确定所述第一历史行驶特征。
  10. 根据权利要求1-9任一项所述的方法，其特征在于，所述根据所述第一时段对所述车辆的行车记录视频进行标注，包括：
    生成异常信息；
    根据所述第一时段，在所述行车记录视频中标注所述异常信息。
  11. 根据权利要求10所述的方法，其特征在于，所述异常信息包括如下信息中的至少一种：
    异常等级、异常类型或者异常描述信息。
  12. 一种数据处理装置，其特征在于，包括：获取模块、确定模块和标注模块，其中，
    所述获取模块用于，获取第一数据和第一历史行驶特征，所述第一数据包括车辆在第一时段的第一行驶数据，所述第一历史行驶特征为根据所述车辆的历史行驶数据确定得到的；
    所述确定模块用于，根据所述第一数据和所述第一历史行驶特征，确定所述车辆在第一时段出现异常；
    所述标注模块用于，根据所述第一时段对所述车辆的行车记录视频进行标注。
  13. 根据权利要求12所述的装置，其特征在于，所述第一行驶数据包括如下数据中的至少一种：
    所述车辆中的部件的状态数据；
    所述车辆中的部件的运行数据；
    或者，所述车辆中的部件采集的传感数据。
  14. 根据权利要求12或13所述的装置，其特征在于，所述第一历史行驶特征包括：多种历史行驶数据对应的多条历史数据曲线，所述历史数据曲线用于指示所述历史行驶数据的分布规律，所述历史行驶数据包括如下至少一种：
    所述车辆中的部件的历史状态数据；
    所述车辆中的部件的历史运行数据；
    或者，所述车辆中的部件采集的历史传感数据。
  15. 根据权利要求12-14任一项所述的装置，其特征在于，所述获取模块具体用于：
    通过第一模型对所述历史行驶数据进行处理，得到所述第一历史行驶特征；
    其中，所述第一模型为对多组第一样本学习得到的，所述多组第一样本中的每组第一样本包括：样本行驶数据和样本历史行驶特征。
  16. 根据权利要求12-15任一项所述的装置，其特征在于，所述确定模块具体用于：
    确定所述第一数据和所述第一历史行驶特征之间的相似度；
    根据所述相似度确定所述车辆在所述第一时段出现异常。
  17. 根据权利要求16所述的装置，其特征在于，所述确定模块具体用于：
    通过第二模型对所述第一数据和所述第一历史行驶特征进行处理，得到所述相似度；
    其中，所述第二模型为对多组第二样本学习得到的，所述多组第二样本中的每组第二 样本包括样本数据、样本行驶特征和样本相似度，所述样本数据包括样本行驶数据。
  18. 根据权利要求17所述的装置，其特征在于，所述确定模块具体用于：
    通过所述第二模型确定所述第一数据对应的第一数据曲线；
    通过所述第二模型对所述第一数据曲线和所述第一历史行驶特征中的历史数据曲线进行对比处理，得到所述相似度。
  19. 根据权利要求12-18任一项所述的装置，其特征在于，所述第一数据还包括场景数据，所述场景数据包括如下信息中的至少一种：
    时间信息、位置信息、路况信息或天气信息。
  20. 根据权利要求19所述的装置，其特征在于，所述确定模块具体用于：
    根据所述场景数据，在多个历史行驶特征中确定所述第一历史行驶特征。
  21. 根据权利要求12-20任一项所述的装置，其特征在于，所述标注模块具体用于：
    生成异常信息；
    根据所述第一时段，在所述行车记录视频中标注所述异常信息。
  22. 根据权利要求21所述的装置，其特征在于，所述异常信息包括如下信息中的至少一种：
    异常等级、异常类型或者异常描述信息。
  23. 一种数据处理装置，其特征在于，所述数据处理装置包括存储器和处理器，所述存储器存储计算机程序指令，所述处理器运行所述计算机程序指令以执行权利要求1-11任一项所述的方法。
  24. 一种计算机存储介质，其特征在于，包括计算机指令，当所述计算机指令在被处理器运行时，实现权利要求1-11任一项所述的方法。
  25. 一种计算机程序产品，其特征在于，当所述计算机程序产品在处理器上运行时，实现权利要求1-11任一项所述的方法。
PCT/CN2020/092381 2020-05-26 2020-05-26 数据处理方法、装置及设备 Ceased WO2021237465A1 (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
CN202080004348.1A CN112543937A (zh) 2020-05-26 2020-05-26 数据处理方法、装置及设备
PCT/CN2020/092381 WO2021237465A1 (zh) 2020-05-26 2020-05-26 数据处理方法、装置及设备
EP20937789.4A EP4148700A4 (en) 2020-05-26 2020-05-26 DATA PROCESSING METHOD, DEVICE AND FACILITIES
KR1020227045056A KR102992439B1 (ko) 2020-05-26 2020-05-26 데이터 처리 방법, 장치 및 디바이스
JP2022572680A JP7662668B2 (ja) 2020-05-26 2020-05-26 データ処理方法及び装置、及び、デバイス
US17/993,609 US12482226B2 (en) 2020-05-26 2022-11-23 Data processing method and apparatus, and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/092381 WO2021237465A1 (zh) 2020-05-26 2020-05-26 数据处理方法、装置及设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/993,609 Continuation US12482226B2 (en) 2020-05-26 2022-11-23 Data processing method and apparatus, and device

Publications (1)

Publication Number Publication Date
WO2021237465A1 true WO2021237465A1 (zh) 2021-12-02

Family

ID=75017350

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/092381 Ceased WO2021237465A1 (zh) 2020-05-26 2020-05-26 数据处理方法、装置及设备

Country Status (6)

Country Link
US (1) US12482226B2 (zh)
EP (1) EP4148700A4 (zh)
JP (1) JP7662668B2 (zh)
KR (1) KR102992439B1 (zh)
CN (1) CN112543937A (zh)
WO (1) WO2021237465A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114120633A (zh) * 2021-11-02 2022-03-01 吉旗（成都）科技有限公司 车辆行程回放方法、装置、服务器及存储介质
CN114281446A (zh) * 2021-11-26 2022-04-05 上海闪马智能科技有限公司 异常事件的显示方法及装置、存储介质、电子装置
US12488594B1 (en) * 2022-08-04 2025-12-02 Zoox, Inc. Systems and methods for ingesting data based on predefined driving sequences
CN115384541A (zh) * 2022-08-11 2022-11-25 支付宝(杭州)信息技术有限公司 行驶风险检测的方法和系统
CN117714766A (zh) * 2022-09-09 2024-03-15 抖音视界有限公司 视频内容预览交互方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001097252A (ja) * 1999-08-20 2001-04-10 Robert Bosch Gmbh 車両の事故データレコーダの記録部を制御する方法、および車両の事故データレコーダ
CN110349291A (zh) * 2018-04-06 2019-10-18 罗伯特·博世有限公司 用于车辆的数据记录器装置
CN110505423A (zh) * 2019-08-15 2019-11-26 杭州鸿晶自动化科技有限公司 一种行车记录系统
CN110956800A (zh) * 2018-09-27 2020-04-03 杭州海康威视系统技术有限公司 一种路段交通数据预处理方法、装置及电子设备

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5664605B2 (ja) * 2012-07-26 2015-02-04 株式会社デンソー ドライブ映像記録装置及びドライブ映像記録システム
JP6486640B2 (ja) * 2014-10-09 2019-03-20 株式会社日立製作所 運転特性診断装置、運転特性診断システム、運転特性診断方法、情報出力装置、情報出力方法
CN104535069B (zh) 2015-01-12 2017-08-25 重庆嗨驾科技有限公司 车载路书游记系统
EP3139346B1 (en) * 2015-09-01 2019-01-16 Veoneer Sweden AB Vision system for a motor vehicle and method of controlling a vision system
US20190279447A1 (en) * 2015-12-03 2019-09-12 Autoconnect Holdings Llc Automatic vehicle diagnostic detection and communication
US9925987B1 (en) * 2015-12-11 2018-03-27 Lytx, Inc. Driving abnormality detection
US10397516B2 (en) * 2016-04-29 2019-08-27 Ford Global Technologies, Llc Systems, methods, and devices for synchronization of vehicle data with recorded audio
JP6926644B2 (ja) * 2016-07-25 2021-08-25 株式会社デンソー 異常推定装置および表示装置
JP6817531B2 (ja) * 2016-09-05 2021-01-20 日本電気株式会社 運転状況記録装置
CN106504367B (zh) * 2016-11-02 2019-03-22 中车青岛四方机车车辆股份有限公司 车辆故障预警方法和装置
TWI654106B (zh) 2017-06-12 2019-03-21 勝捷光電股份有限公司 利用數位錄影方式以記錄行車資訊與產生汽車履歷之方法
CN107911405A (zh) 2017-09-30 2018-04-13 惠州市德赛西威汽车电子股份有限公司 一种可自动生成路书的智能车载系统
CN108091133B (zh) * 2017-11-27 2020-01-10 银江股份有限公司 一种基于海量交通数据分析的车辆安全驾驶行为分析方法
CN108846997A (zh) * 2018-06-23 2018-11-20 张譯丹 无车承运人辅助安全监控系统
KR102847801B1 (ko) * 2019-08-28 2025-08-20 현대자동차주식회사 차량 및 그 제어 방법
CN110807436B (zh) * 2019-11-07 2022-10-18 深圳鼎然信息科技有限公司 危险驾驶行为识别与危险事件预测方法、装置及存储介质
CN110942671B (zh) * 2019-12-04 2022-06-07 北京京东乾石科技有限公司 车辆危险驾驶检测方法、装置以及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001097252A (ja) * 1999-08-20 2001-04-10 Robert Bosch Gmbh 車両の事故データレコーダの記録部を制御する方法、および車両の事故データレコーダ
CN110349291A (zh) * 2018-04-06 2019-10-18 罗伯特·博世有限公司 用于车辆的数据记录器装置
CN110956800A (zh) * 2018-09-27 2020-04-03 杭州海康威视系统技术有限公司 一种路段交通数据预处理方法、装置及电子设备
CN110505423A (zh) * 2019-08-15 2019-11-26 杭州鸿晶自动化科技有限公司 一种行车记录系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4148700A4 *

Also Published As

Publication number Publication date
US20230108895A1 (en) 2023-04-06
KR102992439B1 (ko) 2026-07-16
JP7662668B2 (ja) 2025-04-15
EP4148700A1 (en) 2023-03-15
JP2023527387A (ja) 2023-06-28
KR20230014749A (ko) 2023-01-30
US12482226B2 (en) 2025-11-25
CN112543937A (zh) 2021-03-23
EP4148700A4 (en) 2023-03-29

Similar Documents

Publication Publication Date Title
US20230108895A1 (en) Data processing method and apparatus, and device
US9849865B2 (en) Emergency braking system and method of controlling the same
US11361555B2 (en) Road environment monitoring device, road environment monitoring system, and road environment monitoring program
US10053101B2 (en) Device for controlling driving mode and method for controlling driving mode using the same
DE112018001422T5 (de) Anzeigesteuersystem und verfahren zum erzeugen einer virtuellen umgebung in einem fahrzeug
US20160214482A1 (en) Personalized display system for integrating and varying car content, car content management method of personalized display system, and computer readable medium for performing car content management method
EP3195287A1 (en) Personalized driving of autonomously driven vehicles
EP4506852A1 (en) Car computer avatar interaction method and system, and vehicle and storage medium
KR20230172636A (ko) V2x 환경에서 주행 중 안전하게 광고를 제공하는 방법 및 장치
CN116048055B (zh) 车辆故障检测方法、装置和存储介质
JP7351805B2 (ja) 情報処理方法、プログラム、車載装置及び車両
KR102736392B1 (ko) 자동차에 확장된 기능을 제공하는 장치 및 그 방법
CN116198538A (zh) 驾驶控制方法、装置、电子设备及可读存储介质
CN112700658B (zh) 用于车辆的图像分享的系统及相应的方法和存储介质
EP4492832A1 (en) Vehicle control method, vehicle control system, and storage medium
US12609048B2 (en) Driving diagnostic device, driving diagnostic system, machine learning device and generation method of learned model
US20230192087A1 (en) System and method for generating and simulating vehicle events and data
CN116620315A (zh) Adas自适应场景重构的实现方法、系统、终端及储存介质
CN115730340A (zh) 一种数据处理方法及相关装置
US20230274586A1 (en) On-vehicle device, management system, and upload method
WO2022033487A1 (zh) 驾驶模式的控制方法、装置、设备、程序及存储介质
CN113127710A (zh) 信息呈现方法、装置、服务器及介质
KR102809834B1 (ko) 광고 대상지로의 목적지 변경을 위한 사용자 인터페이스 제공 방법 및 장치
JP7270206B2 (ja) 情報提示システム、情報提示方法、プログラム、及び、移動体
US12424035B2 (en) Driving diagnostic device, driving diagnostic system, driving diagnostic method, and storage medium

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20937789

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022572680

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2020937789

Country of ref document: EP

Effective date: 20221207

ENP Entry into the national phase

Ref document number: 20227045056

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE