WO2021063005A1 - 驾驶数据分析方法、装置、电子设备和计算机存储介质 - Google Patents

驾驶数据分析方法、装置、电子设备和计算机存储介质 Download PDF

Info

Publication number
WO2021063005A1
WO2021063005A1 PCT/CN2020/092603 CN2020092603W WO2021063005A1 WO 2021063005 A1 WO2021063005 A1 WO 2021063005A1 CN 2020092603 W CN2020092603 W CN 2020092603W WO 2021063005 A1 WO2021063005 A1 WO 2021063005A1
Authority
WO
WIPO (PCT)
Prior art keywords
driver
driving data
vehicle
driving
data
Prior art date
Application number
PCT/CN2020/092603
Other languages
English (en)
French (fr)
Inventor
张胜
彭明星
Original Assignee
上海商汤临港智能科技有限公司
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 上海商汤临港智能科技有限公司 filed Critical 上海商汤临港智能科技有限公司
Priority to KR1020217030885A priority Critical patent/KR20210129190A/ko
Priority to JP2021556962A priority patent/JP2022526509A/ja
Publication of WO2021063005A1 publication Critical patent/WO2021063005A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2457—Query processing with adaptation to user needs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
    • G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the present disclosure relates to data analysis technology for vehicle systems, and in particular to a driving data analysis method, device, electronic equipment, and computer storage medium.
  • Vehicle travel has become very popular in our lives. Whether it is a fleet operated by an enterprise or a fleet of general passenger transport services facing the public, multiple drivers are usually involved, and drivers need to be managed by quasi-personnel to ensure traffic safety and service quality. In addition, industries other than the transportation industry, such as insurance, also need to evaluate and report each driver to determine the corresponding insurance policy.
  • the embodiments of the present disclosure are expected to provide a technical solution for driving data analysis.
  • An embodiment of the present disclosure provides a driving data analysis method, the method includes: receiving a driver data analysis request, where the driver data analysis request includes the facial feature requested to be analyzed; Matching driver’s facial features, the database stores the correspondence between the driver’s facial features and driving data; acquiring the driving data corresponding to the determined driver’s facial features in the database; analyzing the acquired Driving data to obtain driver evaluation results corresponding to the facial features of the driver.
  • the embodiment of the present disclosure also provides a driving data analysis device, the device includes a receiving module, a first processing module, an acquiring module, and a second processing module, wherein the receiving module is configured to receive a driver data analysis request,
  • the driver data analysis request includes the facial feature requested for analysis;
  • the first processing module is configured to determine the driver's facial feature matching the facial feature in a database, and the database stores the driver's face Correspondence between the driving data and the driving data;
  • the acquisition module is used to acquire driving data corresponding to the determined facial characteristics of the driver in the database;
  • the second processing module is used to analyze the acquired driving data Driving data to obtain driver evaluation results corresponding to the facial features of the driver.
  • the embodiments of the present disclosure also provide an electronic device, including a processor and a memory for storing a computer program that can run on the processor; wherein the processor is used to run the computer program to execute any of the above-mentioned driving methods. Data analysis method.
  • the embodiment of the present disclosure also provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a processor, any one of the driving data analysis methods described above is realized.
  • the embodiments of the present disclosure also provide a computer program product, including computer program instructions, which enable a computer to implement any one of the driving data analysis methods described above when executed by a computer.
  • a driver data analysis request is received, and the driver data analysis request includes the facial feature requested to be analyzed; Driver facial features matched by facial features, the database stores the correspondence between the driver’s facial features and driving data; acquiring driving data corresponding to the determined driver’s facial features in the database; analyzing and acquiring To obtain the driver evaluation result corresponding to the facial feature of the driver.
  • the driving data corresponding to the driver's facial features can be determined based on the driver's facial features, and then data analysis can be performed; the driver-related driving data can be analyzed from the driver's perspective. The analysis can then realize the accurate evaluation of the driver's driving behavior, and provide more accurate driver evaluation data for application scenarios such as driver management, fleet management, and insurance management.
  • FIG. 1 is a schematic flowchart of a driving data analysis method according to an embodiment of the disclosure
  • FIG. 2 is a schematic diagram of alarm data statistics results in an embodiment of the disclosure
  • FIG. 3 is a schematic structural diagram of an application scenario of an embodiment of the disclosure.
  • FIG. 4 is a schematic diagram of the composition structure of the driving data analysis device according to the embodiment of the disclosure.
  • FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
  • the terms "including”, “including” or any other variations thereof are intended to cover non-exclusive inclusion, so that a method or device including a series of elements not only includes the explicitly stated Elements, and also include other elements not explicitly listed, or elements inherent to the implementation of the method or device. Without more restrictions, the element defined by the sentence “including a" does not exclude the existence of other related elements in the method or device that includes the element (such as steps or steps in the method).
  • the unit in the device for example, the unit may be a part of a circuit, a part of a processor, a part of a program or software, etc.).
  • the driving data analysis method provided by the embodiment of the present disclosure includes a series of steps, but the driving data analysis method provided by the embodiment of the present disclosure is not limited to the recorded steps.
  • the driving data analysis device provided by the embodiment of the present disclosure It includes a series of modules, but the device provided by the embodiments of the present disclosure is not limited to include the explicitly recorded modules, and may also include modules that need to be set to obtain related information or perform processing based on information.
  • the application scenario of the embodiments of the present disclosure may be in a computer system composed of a vehicle-mounted device and a cloud platform, and may be operated with many other general-purpose or special-purpose computing system environments or configurations.
  • the on-board equipment may be a driver monitoring system (Driver Monitor System, DMS), an advanced driving assistant system (ADAS) or other equipment installed on the vehicle
  • the cloud platform may include a small computer system or Distributed cloud computing technology environment for large-scale computer systems, etc.
  • Vehicle-mounted equipment, cloud platforms, etc. may be described in the general context of computer system executable instructions (such as program modules) executed by a computer system.
  • program modules may include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types.
  • tasks are performed by remote processing equipment linked through a communication network.
  • the program module may be located on a storage medium of a local or remote computing system including a storage device.
  • the in-vehicle equipment may be in communication connection with the vehicle's sensors, positioning device, etc., and the in-vehicle equipment may obtain data collected by the vehicle's sensors and geographic location information reported by the positioning device through the communication connection.
  • the sensor of the vehicle may be at least one of millimeter wave radar, lidar, camera and other equipment;
  • the positioning device may be a device for providing positioning services based on at least one of the following positioning systems: Global Positioning System (Global Positioning System) Positioning System, GPS), Beidou satellite navigation system or Galileo satellite navigation system.
  • FIG. 1 is a schematic flowchart of a driving data analysis method according to an embodiment of the disclosure. As shown in FIG. 1, the process may include:
  • Step 101 Receive a driver data analysis request, where the driver data analysis request includes the facial features requested to be analyzed.
  • the facial feature requested for analysis may be a feature extracted from the driver's facial image.
  • the vehicle-mounted equipment or third-party equipment can use a facial recognition algorithm to extract the driver's facial features from the driver's facial image.
  • the third-party device may be an external device that provides third-party services, and the external device may be connected to the cloud platform in communication; for example, the external device may be an electronic device such as a computer.
  • the embodiments of the present disclosure do not limit the types of third-party services.
  • the third-party services may be business analysis services, school bus services, or other third-party services. It should be noted that the types of face recognition algorithms are not limited in the embodiments of the present disclosure.
  • the vehicle-mounted device or third-party device can generate a driver data analysis request and send the driver data analysis request to the cloud platform.
  • Step 102 Determine the driver's facial features matching the facial features in a database, and the database stores the correspondence between the driver's facial features and driving data.
  • the database can be pre-established in the cloud platform.
  • the on-board equipment installed on the vehicle can send driving data and the driver’s facial features to the cloud platform;
  • the cloud platform can establish the received driving data and the driver’s facial features in the database according to the received driving data and the driver’s facial features sent by the on-board equipment.
  • the correspondence between the driver’s facial features and driving data Since the facial features of the driver are not easy to forge, the relationship between the facial features of the driver and the driving data to be analyzed is established, which helps to improve the accuracy of the analysis results and is not easy to tamper with.
  • the cloud platform receives the facial features requested for analysis, the feature comparison can be used to determine and request analysis in the database.
  • the facial features match the facial features of the driver.
  • Step 103 Acquire driving data corresponding to the determined facial feature of the driver in the database.
  • the driving data corresponding to the determined facial features of the driver can be obtained according to the corresponding relationship stored in the database.
  • Step 104 Analyze the acquired driving data to obtain a driver evaluation result corresponding to the facial feature of the driver.
  • the analysis of the driving data may be an analysis of the safety of the driving behavior of the driver.
  • the obtained driver evaluation result may characterize the safety of the driver's driving behavior. It should be noted that the foregoing content is only an exemplary description of driving data analysis, and in the embodiments of the present disclosure, the content of driving data analysis is not limited to this.
  • steps 101 to 104 can be implemented based on a processor of a cloud platform, etc.
  • the aforementioned processor can be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), Digital Signal Processing Device (Digital Signal Processing Device, DSPD), Programmable Logic Device (Programmable Logic Device, PLD), Field Programmable Gate Array (Field Programmable Gate Array, FPGA), Central Processing Unit (Central Processing Unit, CPU), At least one of a controller, a microcontroller, and a microprocessor.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processor
  • DSPD Digital Signal Processing Device
  • PLD Programmable Logic Device
  • Field Programmable Gate Array Field Programmable Gate Array
  • FPGA Field Programmable Gate Array
  • CPU Central Processing Unit
  • CPU Central Processing Unit
  • the driving data corresponding to the facial features of the driver can be determined according to the facial features of the driver, and then the data analysis can be performed; the driving related to the driver can be analyzed from the perspective of the driver.
  • the data can be analyzed to achieve an accurate assessment of the driver's driving behavior, so as to provide more accurate driver assessment data for application scenarios such as driver management, fleet management, and insurance management.
  • the facial feature requested for analysis is the feature extracted from the driver's facial image taken by the vehicle-mounted camera; therefore, the analysis based on the request is Facial features acquire driving data and analyze it, and accurate behavior evaluation can be carried out for the actual driver of the vehicle, that is, the driver evaluation result obtained by the analysis can reflect the driving behavior of the current driver of the vehicle.
  • the driving data may include driver behavior data and/or vehicle driving data;
  • the driver behavior data includes at least one of the following: yawning, calling, drinking, smoking, putting on makeup, driving The driver is not in the driving position;
  • the vehicle driving data includes at least one of the following: lane departure warning, forward collision warning, speeding warning, pedestrian in front of the vehicle, backward collision warning, and obstacle warning in front of the vehicle. That is, the driver behavior data and/or the vehicle driving data may be warning data.
  • the above content is only an exemplary description of the driver behavior data and the vehicle travel data, and in the embodiments of the present disclosure, the content of the driver behavior data and the vehicle travel data is not limited to this.
  • DMS can send driver behavior data to the cloud platform after obtaining driver behavior data
  • ADAS can send vehicle driving data to the cloud platform after obtaining vehicle driving data
  • the DMS can be set on the vehicle.
  • the DMS includes a vehicle-mounted camera, and the image collection direction of the vehicle-mounted camera faces the cabin; the DMS can analyze the driver images captured by the vehicle-mounted camera, and determine that the driver’s behavior needs to be alerted according to the analysis results
  • the above-mentioned driver behavior data can be generated.
  • the driver behavior data indicates behaviors that need to be alerted, for example, it can be distracted driving behaviors such as yawning, calling, drinking water, smoking, and putting on makeup.
  • ADAS can be set on the vehicle.
  • ADAS can include a camera.
  • the camera is installed on the vehicle but the image collection direction is facing the outside of the car.
  • ADAS can analyze the image of the environment outside the car collected by the camera. According to the analysis result, it can be determined that the driving behavior of the vehicle is the behavior that needs to be alerted.
  • the above-mentioned vehicle driving data can be generated, and the vehicle driving data indicates the driving behavior of the vehicle that needs to be alerted, for example, it can be lane departure, forward collision, speeding, pedestrian presence in front of the vehicle, etc.
  • the facial features of a driver reflect the unique biological characteristics of a driver
  • the facial features of a driver reflect the unique biological characteristics of a driver
  • the facial features requested to be analyzed are facial features extracted from the driver's facial image taken by the vehicle-mounted camera.
  • the analysis based on the request Using facial features to obtain driver behavior data and/or vehicle driving data and analyze them, the actual driver of the vehicle can be accurately evaluated. That is, the driver’s evaluation result obtained by the analysis can reflect the current driver’s behavior of the vehicle. Driving behavior.
  • the driving behavior and vehicle driving behavior of the same driver can be comprehensively considered, and the behavior of the same driver can be analyzed more comprehensively, and the analysis result is more objective and accurate.
  • the in-vehicle device may send driving data together with the driver's facial features to the cloud platform.
  • the DMS can send the driver data and the driver's facial features to the cloud platform;
  • ADAS can send the vehicle data and the driver's facial features to the cloud platform together.
  • the driver data may include driver behavior data
  • the vehicle data may include vehicle driving data.
  • the cloud platform receives driver behavior data and driver facial features sent by DMS, and receives vehicle driving data and driver facial features sent by ADAS; it can respond to the driver’s facial features sent by DMS and ADAS. Compare the driver's facial features and correlate the driver's behavior data corresponding to the facial features of the driver with the vehicle driving data to obtain driving data including the driver's behavior data and the vehicle driving data.
  • the driver data may further include the first device identification of the DMS
  • the vehicle data may further include the second device identification of the ADAS.
  • the first device identification of the DMS may be the ID of the DMS or other identification information of the DMS
  • the first device identification is used to uniquely identify the DMS
  • the second device identification of the ADAS may be the ID of the ADAS or other identification information of the ADAS
  • the second The device identifier is used to uniquely identify ADAS.
  • the cloud platform After the cloud platform receives the driver data and the vehicle data, it can determine the respective vehicle identifications of the first device identification and the second device identification according to the first mapping relationship between the device identification and the vehicle identification established in the database.
  • the vehicle identification can be the license plate number of the vehicle or other identification information.
  • the vehicle identification can be sent to the cloud platform together; correspondingly, ADAS is sending to the cloud platform
  • the vehicle identification can be sent to the cloud platform together.
  • the cloud platform after the cloud platform receives the data sent by DMS and ADAS, it can establish device identification and vehicle identification in the database based on the vehicle identification carried in the data sent by DMS and the vehicle identification carried in the data sent by ADAS
  • the corresponding relationship between the device identification and the vehicle identification may include: the corresponding relationship between the first device identification and the vehicle identification, and the corresponding relationship between the second device identification and the vehicle identification.
  • the first device identifier and the second device identifier can be found in the database according to the corresponding relationship. Identify the respective vehicle identifications; in response to the first device identification and the second device identification corresponding to the same vehicle identification, it can be determined that the received driver behavior data and vehicle driving data correspond to the same vehicle. At this time, the received driver behavior data and vehicle driving data can be correlated to obtain driving data including driver behavior data and vehicle driving data.
  • the cloud platform receives the driving data and the facial features of the driver sent by the on-board equipment
  • the corresponding relationship between the received facial features of the driver and the received driving data can be established in the database;
  • the corresponding relationship between the driver’s facial features matched with the received driver’s facial features and the received driving data is established in the database.
  • it can be in the driver’s facial features stored in the database.
  • the realization method may include: determining the danger level of driving behavior according to the driving data; according to the mapping relationship between the pre-determined danger level and the evaluation weight, obtaining and The evaluation weight corresponding to the determined danger level; according to the determined danger level and its corresponding evaluation weight, the driver evaluation result corresponding to the driver's facial features is determined.
  • multiple risk levels of driving behavior can be pre-divided, and a corresponding evaluation weight can be set for each risk level; the evaluation weight corresponding to each risk level can be set according to actual needs, and different risk levels have different evaluation weights.
  • the evaluation weight can be -10, for moderately dangerous behaviors, the evaluation weight can be -5; for mildly dangerous behaviors, the evaluation weight can be -2; for the case of no dangerous behaviors per unit time, The evaluation weight can be 2.
  • various driving behaviors represented by the driving data can be determined, and then the risk level corresponding to each driving behavior can be scored; and then the scores corresponding to the various driving behaviors can be scored.
  • the sum is performed and the result of the driver's evaluation is obtained.
  • the results of driver evaluation can be used as a basis for unit or individual performance management. In an example, the higher the value of the evaluation result of the driver, the safer the driving behavior of the driver.
  • the risk levels of various driving behaviors can be set according to actual application requirements. Therefore, the method of determining the driver evaluation results according to the risk levels of driving behaviors is conducive to obtaining accurate driver evaluation results and can accurately evaluate driving.
  • the safety of the driver s driving behavior.
  • exemplary may include: determining the credibility of the driving data; determining the driving data based on driving data that is determined to be credible or driving data whose credibility exceeds a set threshold The risk level of the behavior.
  • the set threshold can be set according to actual application requirements.
  • the credibility of the driving data after determining the credibility of the driving data, according to the credibility of the driving data, judge whether the driving data is credible driving data, or whether the credibility of the driving data exceeds the set threshold; When the driving data is credible or the credibility of the driving data exceeds the set threshold, then the driving data is used to determine the risk level of the driving behavior; when the driving data is unreliable driving data or the credibility of the driving data does not exceed the set threshold At the threshold, the risk level of driving behavior is uncertain.
  • the dangerous level of the driving behavior can be determined, which can eliminate unreliability or less credibility.
  • Low driving data when the driving data is alarm data, by introducing a re-confirmation processing mechanism for the alarm data, the probability of false alarms and false alarms of the on-board equipment can be reduced to a certain extent, making the analysis results of the alarm data more objective and reliable; Furthermore, by excluding unreliable or low-reliability alarm data, it is helpful to accurately evaluate the driving behavior of the driver, and then it is helpful to accurately evaluate the risk level of the driving behavior.
  • the driving data includes vehicle driving data
  • the vehicle driving data includes vehicle driving geographic location information and vehicle driving time information; for the implementation of determining the credibility of the driving data, in one example, Including: obtaining the weather condition information and/or traffic condition information corresponding to the vehicle driving time information and the vehicle driving geographic location information; and determining the credibility of the driving data according to the weather condition information and/or traffic condition information.
  • the geographic location information of the vehicle traveling is used to indicate the current geographic location of the vehicle, and the representation form of the geographic location information of the vehicle traveling may be latitude and longitude data or other types of geographic location data.
  • ADAS can obtain the geographic location information of the vehicle from the positioning device of the vehicle.
  • the vehicle travel time information indicates the point in time when the vehicle travel data is sent.
  • the cloud platform can obtain vehicle driving time information and vehicle driving geographic location information.
  • the weather information includes but is not limited to rain, snow, sunny, night, cloudy, etc.
  • traffic information includes, but is not limited to, uphill, downhill, turning, road leveling, uneven roads, and unobstructed roads , Traffic jams, car accidents, etc.
  • weather condition information and/or traffic condition information are important factors that affect driver behavior. Therefore, by introducing a re-confirmation processing mechanism for alarm data, the probability of false alarms and false alarms of on-board equipment can be reduced to a certain extent, so that The analysis result of the alarm data is more objective and reliable, for example, in the case of determining the credibility of the driving data according to the weather condition information and/or traffic condition information, and determining the danger level of the driving behavior according to the credibility of the driving data , By excluding unreliable or low-reliability alarm data, it is helpful to accurately evaluate the driving behavior of the driver, and then it is helpful to accurately evaluate the risk level of the driving behavior.
  • the DMS and/or ADAS can send the alarm data to the cloud platform, and the cloud platform can, when receiving the alarm data,
  • FIG. 2 for verification and statistical analysis of the alarm data, refer to FIG. 2 for a schematic diagram of the statistical results of the alarm data in an embodiment of the disclosure.
  • the cloud platform when the cloud platform receives the alarm data, it can verify the alarm data according to weather condition information and/or traffic condition information.
  • the alarm data when the alarm data indicates that the vehicle is speeding, if the traffic condition information indicates that there is a traffic jam at the current location of the vehicle, the alarm data can be determined to be unreliable data.
  • the alarm data indicates that when the vehicle is in front of a car accident, if the traffic condition information indicates that there is no accident at the current location of the vehicle, the alarm data can be determined to be unreliable data.
  • the credibility is set to a credibility value lower than the set value.
  • FIG. 3 is a schematic diagram of an application scenario structure of an embodiment of the disclosure.
  • an implementation manner of obtaining the weather condition information corresponding to the vehicle driving time information and the vehicle driving geographic location information may be: the cloud platform receives the vehicle After the vehicle travel time information and vehicle travel geographic location information sent by the device, the first query request can be sent to the first server that provides weather services. The first query request is used to query the weather corresponding to the vehicle travel time information and vehicle travel geographic location information.
  • Condition information The weather condition information represents the weather condition corresponding to the geographic location corresponding to the vehicle's geographic location information at the time point corresponding to the vehicle's travel time information.
  • the first server After receiving the first query request, the first server performs a query according to the first query request, obtains the corresponding weather condition information, and sends the weather condition information to the cloud platform. In this way, the cloud platform can receive the weather condition information sent by the first server.
  • an implementation method for obtaining the traffic condition information corresponding to the vehicle travel time information and the vehicle travel geographic location information may be: the cloud platform receives the vehicle travel time information and vehicle travel geographic location information sent by the on-board equipment After that, a second query request can be sent to a second server that provides traffic status information.
  • the second query request is used to query the vehicle travel time information and the traffic status information corresponding to the vehicle travel geographic location information; the traffic status information is represented by the vehicle travel time information
  • the traffic conditions corresponding to the geographic location information of the vehicle at the corresponding point in time After receiving the second query request, the second server performs the query according to the second query request, obtains the corresponding traffic status information, and sends the traffic status information to the cloud platform. In this way, the cloud platform can receive the traffic status information sent by the second server.
  • the driving data may include driver behavior data and corresponding driver images when the driver behavior data is acquired; for the implementation of determining the credibility of the driving data, in another example, Including: Determine the credibility of the driver's behavior data based on the driver's image.
  • the DMS can collect driver images in real time, and when it is determined to send alarm data, it can send the alarm data and the corresponding driver image when the alarm data is acquired to the cloud platform.
  • the driver image sent by the on-board device DMS reflects the real driver's status. Therefore, by introducing a reconfirmation processing mechanism for the alarm data, the probability of false alarms and false alarms by the on-board equipment can be reduced to a certain extent, so that the alarm
  • the data analysis result is more objective and reliable.
  • the reliability of the alarm data is determined based on the driver's image, which can reduce the misjudgment rate of the driver's behavior data and help accurately determine the risk level of driving behavior. For example, the alarm data reported by the in-vehicle device indicates that the driver is yawning and the driver is in a fatigued driving state.
  • the database is also pre-established with a mapping relationship between the driver’s facial features and the team identity. Accordingly, at least two drivers corresponding to the same team identity can be determined according to the mapping relationship.
  • the same in-vehicle device can upload the driver’s facial features and the identity of the vehicle fleet to the cloud platform; in this way, the cloud platform can establish in the database based on the driver’s facial features and fleet identity sent by the same in-vehicle device The mapping relationship between the driver’s facial features and the team logo.
  • the facial features of all drivers of the same fleet can be determined by establishing the above-mentioned mapping relationship in the database; further combining the driver evaluation results corresponding to the facial features of each driver, the same fleet can be obtained
  • the driver evaluation results corresponding to all the drivers of the driver can be evaluated separately for each driver of each fleet, which is conducive to understanding the driver behavior of each fleet.
  • the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process.
  • the specific execution order of each step should be based on its function and possibility.
  • the inner logic is determined.
  • FIG. 4 is a schematic diagram of the composition structure of a driving data analysis device according to an embodiment of the disclosure.
  • the device includes: a receiving module 401, a first processing module 402, an acquiring module 403, and a second processing module 404, wherein,
  • the receiving module 401 is configured to receive a driver data analysis request, where the driver data analysis request includes the facial feature requested to be analyzed; and the first processing module 402 is configured to determine that the facial feature corresponds to the facial feature in the database.
  • the matched driver’s facial features the database stores the correspondence between the driver’s facial features and driving data; the acquisition module 403 is used to acquire the information corresponding to the determined driver’s facial features in the database Driving data; The second processing module 404 is used to analyze the acquired driving data to obtain driver evaluation results corresponding to the driver's facial features.
  • the second processing module 404 is configured to determine the danger level of the driving behavior according to the driving data; according to the mapping relationship between the predetermined danger level and the evaluation weight, obtain and The evaluation weight corresponding to the determined danger level; according to the determined danger level and the corresponding evaluation weight, the driver evaluation result corresponding to the facial feature of the driver is determined.
  • the driving data includes driver behavior data and/or vehicle driving data
  • the driver behavior data includes at least one of the following: yawning, calling, drinking, smoking, Make-up and the driver is not in the driving position
  • the vehicle driving data includes at least one of the following: lane departure warning, forward collision warning, speeding warning, pedestrian presence in front of the vehicle, backward collision warning, and obstacle warning in front of the vehicle.
  • the first processing module 402 is further configured to receive driving data and facial features of the driver sent by the on-board equipment installed on the vehicle; establish the received driver's facial features in the database.
  • the corresponding relationship between the facial features of the driver and the received driving data, or the corresponding relationship between the facial features of the driver matching the facial features of the received driver and the received driving data is established in the database.
  • the second processing module 404 is configured to determine the credibility of the driving data; according to the driving data that is determined to be credible or the credibility exceeds a set threshold Driving data to determine the dangerous level of the driving behavior.
  • the driving data includes vehicle driving data
  • the vehicle driving data includes vehicle driving geographic location information and vehicle driving time information
  • the second processing module 404 is configured to obtain the Weather condition information and/or traffic condition information corresponding to the vehicle driving time information and the vehicle driving geographic location information
  • the credibility of the driving data is determined according to the weather condition information and/or the traffic condition information.
  • the second processing module 404 is configured to send a first query request to a first server that provides weather services, and the first query request is used to query the vehicle travel time information And weather condition information of the geographic location information of the vehicle; receiving the weather condition information sent by the first server.
  • the second processing module 404 is configured to send a second query request to a second server that provides traffic status information, and the second query request is used to query the travel time of the vehicle Information and traffic condition information of the vehicle driving geographic location information; receiving the traffic condition information sent by the second server.
  • the driving data includes driver behavior data and corresponding driver images when the driver behavior data is acquired; the second processing module 404 is configured to The image determines the credibility of the driver's behavior data.
  • the facial feature of the driver is a feature extracted from a facial image of the driver.
  • the database is also pre-established with a mapping relationship between the facial features of the driver and the team identification; the second processing module 404 is further configured to, according to the mapping relationship, Determine at least two driver facial features corresponding to the same team identifier; and obtain a team evaluation result according to a driver evaluation result corresponding to each driver's facial feature in the at least two driver facial features.
  • the receiving module 401, the first processing module 402, the acquiring module 403, and the second processing module 404 can all be implemented by a processor in a vehicle-mounted data terminal or a cloud platform.
  • the aforementioned processors can be ASIC, DSP, DSPD, At least one of PLD, FPGA, CPU, controller, microcontroller, and microprocessor.
  • the functional modules in this embodiment may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be realized in the form of hardware or software function module.
  • the integrated unit is implemented in the form of a software function module and is not sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this embodiment is essentially or It is said that the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can A personal computer, a server, or a network device, etc.) or a processor (processor) executes all or part of the steps of the method described in this embodiment.
  • the aforementioned storage media include: U disk, mobile hard disk, read only memory (Read Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes.
  • the computer program instructions corresponding to a driving data analysis method in this embodiment can be stored on storage media such as optical disks, hard disks, and USB flash drives.
  • storage media such as optical disks, hard disks, and USB flash drives.
  • FIG. 5 shows an electronic device 50 provided by an embodiment of the present disclosure, which may include: a memory 51 and a processor 52; wherein the memory 51 is used to store a computer Programs and data; the processor 52 is configured to execute a computer program stored in the memory to implement any data analysis method of the foregoing embodiments.
  • the aforementioned memory 51 may be a volatile memory (volatile memory), such as RAM; or a non-volatile memory (non-volatile memory), such as ROM, flash memory, or hard disk (Hard Disk). Drive, HDD) or Solid-State Drive (SSD); or a combination of the foregoing types of memories, and provide instructions and data to the processor 52.
  • volatile memory volatile memory
  • non-volatile memory non-volatile memory
  • ROM read-only memory
  • flash memory read-only memory
  • HDD hard disk
  • SSD Solid-State Drive
  • the aforementioned processor 52 may be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor. It can be understood that, for different devices, the electronic devices used to implement the above-mentioned processor functions may also be other, which is not specifically limited in the embodiments of the present disclosure.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the embodiment of the present disclosure also provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a processor, it implements any of the driving data analysis methods described in the embodiments of the present disclosure.
  • the embodiments of the present disclosure also provide a computer program product, including computer program instructions, which enable a computer to implement any one of the driving data analysis methods described in the embodiments of the present disclosure when executed by a computer.
  • the technical solution of the present invention essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes a number of instructions to enable a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the method described in each embodiment of the present invention.
  • a terminal which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Library & Information Science (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种驾驶数据分析方法、装置、电子设备和计算机存储介质，该方法包括：接收驾驶员数据分析请求，所述驾驶员数据分析请求包括请求分析的脸部特征（101）；在数据库中确定与所述脸部特征匹配的驾驶员脸部特征，所述数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系（102）；获取所述数据库中与确定的驾驶员脸部特征对应的驾驶数据（103）；分析获取的所述驾驶数据，得到与所述驾驶员脸部特征对应的驾驶员评估结果（104）。

Description

驾驶数据分析方法、装置、电子设备和计算机存储介质
相关申请的交叉引用
本公开基于申请号为201910945671.8、申请日为2019年9月30日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以引入方式并入本公开。
技术领域
本公开涉及车辆系统的数据分析技术，尤其涉及一种驾驶数据分析方法、装置、电子设备和计算机存储介质。
背景技术
车辆出行在我们生活中已经非常普及。无论是企业内部运营的车队，还是面向公众的普遍客运服务的车队，通常涉及到多个驾驶员，需要对驾驶员实行准人管理，以保证交通安全和服务质量。此外，除了交通行业之外的保险等行业，也需要对每个驾驶员进行评估报备，以确定相应的投保策略。
发明内容
本公开实施例期望提供驾驶数据分析的技术方案。
本公开实施例提供了一种驾驶数据分析方法，所述方法包括：接收驾驶员数据分析请求，所述驾驶员数据分析请求包括请求分析的脸部特征；在数据库中确定与所述脸部特征匹配的驾驶员脸部特征，所述数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系；获取所述数据库中与确定的驾驶员脸部特征对应的驾驶数据；分析获取的所述驾驶数据，得到与所 述驾驶员脸部特征对应的驾驶员评估结果。
本公开实施例还提供了一种驾驶数据分析装置，所述装置包括接收模块、第一处理模块、获取模块和第二处理模块，其中，所述接收模块，用于接收驾驶员数据分析请求，所述驾驶员数据分析请求包括请求分析的脸部特征；所述第一处理模块，用于在数据库中确定与所述脸部特征匹配的驾驶员脸部特征，所述数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系；所述获取模块，用于获取所述数据库中与确定的驾驶员脸部特征对应的驾驶数据；所述第二处理模块，用于分析获取的所述驾驶数据，得到与所述驾驶员脸部特征对应的驾驶员评估结果。
本公开实施例还提供了一种电子设备，包括处理器和用于存储能够在处理器上运行的计算机程序的存储器；其中，所述处理器用于运行所述计算机程序以执行上述任意一种驾驶数据分析方法。
本公开实施例还提供了一种计算机存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述任意一种驾驶数据分析方法。
本公开实施例还提供了一种计算机程序产品，包括计算机程序指令，该计算机程序指令使得计算机执行时实现上述任意一种驾驶数据分析方法。
本公开实施例提出的驾驶数据分析方法、装置、电子设备和计算机存储介质中，接收驾驶员数据分析请求，所述驾驶员数据分析请求包括请求分析的脸部特征；在数据库中确定与所述脸部特征匹配的驾驶员脸部特征，所述数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系；获取所述数据库中与确定的驾驶员脸部特征对应的驾驶数据；分析获取的所述驾驶数据，得到与所述驾驶员脸部特征对应的驾驶员评估结果。如此，在本公开实施例中，可以根据驾驶员脸部特征，确定出与驾驶员脸部特征对应的驾驶数据，进而进行数据分析；可以从驾驶员的角度，对驾驶员相关的驾 驶数据进行分析，进而可以实现对驾驶员驾驶行为的准确评估，以为驾驶员管理、车队管理、保险管理等应用场景提供更为准确的驾驶员评估数据。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1为本公开实施例的驾驶数据分析方法的流程示意图；
图2为本公开实施例中报警数据统计结果示意图；
图3为本公开实施例的一个应用场景结构示意图；
图4为本公开实施例的驾驶数据分析装置的组成结构示意图；
图5为本公开实施例的电子设备的结构示意图。
具体实施方式
以下结合附图及实施例，对本公开实施例进行进一步详细说明。应当理解，此处所提供的实施例仅仅用以解释本公开实施例，并不用于限定本公开实施例。另外，以下所提供的实施例是用于实施本公开的部分实施例，而非提供实施本公开的全部实施例，在不冲突的情况下，本公开实施例记载的技术方案可以任意组合的方式实施。
需要说明的是，在本公开实施例中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的方法或者装置不仅包括所明确记载的要素，而且还包括没有明确列出的其他要素，或者是还包括为实施方法或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个......”限定的要素，并不排除在包括该要素的方法或者装置中还存在另外的相关要素(例如方法中的步骤或者装置中的单元，例 如的单元可以是部分电路、部分处理器、部分程序或软件等等)。
例如，本公开实施例提供的驾驶数据分析方法包含了一系列的步骤，但是本公开实施例提供的驾驶数据分析方法不限于所记载的步骤，同样地，本公开实施例提供的驾驶数据分析装置包括了一系列模块，但是本公开实施例提供的装置不限于包括所明确记载的模块，还可以包括为获取相关信息、或基于信息进行处理时所需要设置的模块。
本文中术语“和/或”，仅仅是一种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。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
本公开实施例的应用场景可以是车载设备和云平台组成的计算机系统中，并可以与众多其它通用或专用计算系统环境或配置一起操作。示例性的，车载设备可以是安装在车辆上的驾驶员监控系统(Driver Monitor System，DMS)、高级辅助驾驶系统(Advanced Driving Assistant System，ADAS)或其他设备，云平台可以是包括小型计算机系统或大型计算机系统的分布式云计算技术环境等等。
车载设备、云平台等可以在由计算机系统执行的计算机系统可执行指令(诸如程序模块)的一般语境下描述。通常，程序模块可以包括例程、程序、目标程序、组件、逻辑、数据结构等等，它们执行特定的任务或者实现特定的抽象数据类型。在云平台中，任务是由通过通信网络链接的远程处理设备执行的。在云平台中，程序模块可以位于包括存储设备的本地或远程计算系统存储介质上。
本实施例中，车载设备可以与车辆的传感器、定位装置等通信连接， 车载设备可以通过通信连接获取车辆的传感器采集的数据、以及定位装置上报的地理位置信息等。示例性的，车辆的传感器可以是毫米波雷达、激光雷达、摄像头等设备中的至少一种；定位装置可以是基于以下至少一种定位系统的用于提供定位服务的装置：全球定位系统(Global Positioning System，GPS)、北斗卫星导航系统或伽利略卫星导航系统。
在本公开的一些实施例中，提出了一种驾驶数据分析方法，本公开实施例可以应用于驾驶行为分析、车辆运营管理、驾驶员管理、商业行为分析等领域。本公开实施例的驾驶数据分析方法可以应用于与车载设备形成通信连接的云平台中。图1为本公开实施例的驾驶数据分析方法的流程示意图，如图1所示，该流程可以包括：
步骤101：接收驾驶员数据分析请求，驾驶员数据分析请求包括请求分析的脸部特征。
本公开实施例中，请求分析的脸部特征可以是从驾驶员脸部图像提取出的特征。在实际应用中，车载设备或第三方设备在获取到驾驶员脸部图像后，可以采用人脸识别算法从驾驶员脸部图像中提取出驾驶员脸部特征。第三方设备可以是提供第三方服务的外部设备，外部设备可以与云平台通信连接；示例性的，外部设备可以是计算机等电子设备。本公开实施例并不对第三方服务的种类进行限定，示例性地，第三方服务可以是商业分析服务、校车服务或其它第三方服务。需要说明的是，本公开实施例中不对人脸识别算法的种类进行限定。
在实际应用中，车载设备或第三方设备在获取驾驶员脸部特征后，可以生成驾驶员数据分析请求，并向云平台发送驾驶员数据分析请求。
步骤102：在数据库中确定与脸部特征匹配的驾驶员脸部特征，数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系。
本实施例中，数据库可在云平台中预先建立。在实际应用中，车辆上 设置的车载设备可以向云平台发送驾驶数据和驾驶员脸部特征；云平台可以根据接收到车载设备发送的驾驶数据和驾驶员脸部特征，在数据库中建立接收到的驾驶员脸部特征和驾驶数据之间的对应关系。由于驾驶员脸部特征不易伪造，基于驾驶员脸部特征建立其与待分析的驾驶数据之间的关系，有利于提高分析结果的准确性和不易篡改性。
在实际应用中，在数据库中建立驾驶员脸部特征和驾驶数据之间的对应关系后，如果云平台接收到请求分析的脸部特征，则可以通过特征比对，在数据库中确定与请求分析的脸部特征匹配的驾驶员脸部特征。
步骤103：获取数据库中与确定的驾驶员脸部特征对应的驾驶数据。
在实际应用中，在确定驾驶员脸部特征后，可以根据数据库中存储的对应关系，获取与确定的驾驶员脸部特征对应的驾驶数据。
步骤104：分析获取的所述驾驶数据，得到与所述驾驶员脸部特征对应的驾驶员评估结果。
本实施例中，对驾驶数据的分析可以是对驾驶员行车行为的安全性进行分析。示例性的，得到的驾驶员评估结果可以表征驾驶员行车行为的安全性。需要说明的是，上述内容仅仅是对驾驶数据分析进行了示例性说明，本公开实施例中，驾驶数据分析的内容并不局限于此。
在实际应用中，步骤101至步骤104可以基于云平台的处理器等实现，上述处理器可以为特定用途集成电路(Application Specific Integrated Circuit，ASIC)、数字信号处理器(Digital Signal Processor，DSP)、数字信号处理装置(Digital Signal Processing Device，DSPD)、可编程逻辑装置(Programmable Logic Device，PLD)、现场可编程门阵列(Field Programmable Gate Array，FPGA)、中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器中的至少一种。
可以看出，在本公开实施例中，可以根据驾驶员脸部特征，确定出与 驾驶员脸部特征对应的驾驶数据，进而进行数据分析；可以从驾驶员的角度，对驾驶员相关的驾驶数据进行分析，进而可以实现对驾驶员驾驶行为的准确评估，以为驾驶员管理、车队管理、保险管理等应用场景提供更为准确的驾驶员评估数据。
本实施例中，在车载设备向云平台发送驾驶员数据分析请求的情况下，请求分析的脸部特征是从车载摄像头拍摄的驾驶员脸部图像中提取出的特征；因而，基于请求分析的脸部特征获取驾驶数据并进行分析，可以针对车辆实际的驾驶员，进行准确的行为评估，即分析得出的驾驶员评估结果可以反映车辆当前驾驶员的驾驶行为。
在本公开的一些可选实施例中，驾驶数据可以包括驾驶员行为数据和/或车辆行驶数据；驾驶员行为数据包括以下至少之一：打哈欠、打电话、喝水、抽烟、化妆、驾驶员不在驾驶位置；车辆行驶数据包括以下至少之一：车道偏离预警、前向碰撞预警、超速预警、车辆前方出现行人、后向碰撞预警、车辆前方障碍物预警。也就是说，驾驶员行为数据和/或车辆行驶数据可以是报警数据。需要说明的是，上述内容仅仅是对驾驶员行为数据和车辆行驶数据进行了示例性说明，本公开实施例中，驾驶员行为数据和车辆行驶数据的内容并不局限于此。
实际应用中，DMS可以在获取驾驶员行为数据后，向云平台发送驾驶员行为数据；ADAS可以在获取车辆行驶数据后，向云平台发送车辆行驶数据。其中，DMS可以设置在车辆上，DMS包括车载摄像头，车载摄像头的图像采集方向朝向车舱内；DMS可以对车载摄像头拍摄到的驾驶员图像进行分析，根据分析结果确定驾驶员行为是需要报警的行为时，可以生成上述驾驶员行为数据。驾驶员行为数据表示需要报警的行为，例如，可以是打哈欠、打电话、喝水、抽烟、化妆等分心驾驶行为。ADAS可以设置在车辆上，ADAS可以包括摄像头，摄像头安装在车辆上但图像采集方向 朝向车外，ADAS可以根据摄像头采集的车外环境图像进行分析，根据分析结果确定车辆行驶行为是需要报警的行为时，可以生成上述车辆行驶数据，车辆行驶数据表示需要报警的车辆行驶行为，例如，可以是车道偏离、前向碰撞、超速、车辆前方出现行人等。
可以理解地，由于驾驶员脸部特征反映了一个驾驶员特有的生物特征，因而在本公开实施例中，通过将驾驶员脸部特征与驾驶数据建立对应关系，可以筛选出同一个驾驶员的驾驶员行为数据和/或车辆行驶数据，实现对同一个驾驶员的驾驶员行为数据和/或车辆行驶数据进行分析，即，能够单独针对每个驾驶员进行数据分析，有利于了解每个驾驶员的行车行为。进一步地，在车载设备向云平台发送驾驶员数据分析请求的情况下，请求分析的脸部特征是从车载摄像头拍摄的驾驶员脸部图像中提取出的脸部特征，因而，基于请求分析的脸部特征获取驾驶员行为数据和/或车辆行驶数据，并进行分析，可以针对车辆实际的驾驶员，进行准确的行为评估，即，分析得出的驾驶员评估结果可以反映车辆当前驾驶员的驾驶行为。
在驾驶数据包括驾驶员行为数据和车辆行驶数据的情况下，可以综合考虑同一个驾驶员的驾驶行为和车辆行驶行为，能够更加全面地分析同一个驾驶员的行为，分析结果更加客观和准确。
在一些可选实施例中，车载设备可以将驾驶数据和驾驶员脸部特征一同发送至云平台。示例性地，DMS可以将驾驶员数据和驾驶员脸部特征一同发送至云平台；ADAS可以将车辆数据和驾驶员脸部特征一同发送至云平台。其中，驾驶员数据可以包括驾驶员行为数据，车辆数据包括车辆行驶数据。
在一个示例中，云平台在接收到DMS发送的驾驶员行为数据和驾驶员脸部特征，并接收到ADAS发送的车辆行驶数据和驾驶员脸部特征；可以对DMS和ADAS发送的驾驶员脸部特征进行比对，将比对成功的驾驶员脸 部特征对应的驾驶员行为数据和车辆行驶数据进行关联，得到包括驾驶员行为数据和车辆行驶数据的驾驶数据。
在另一个示例中，驾驶员数据还可包括DMS的第一设备标识，车辆数据还包括ADAS的第二设备标识。其中，DMS的第一设备标识可以是DMS的ID或DMS的其它标识信息，第一设备标识用于唯一标识DMS；ADAS的第二设备标识可以是ADAS的ID或ADAS的其它标识信息，第二设备标识用于唯一标识ADAS。
云平台在接收到驾驶员数据和车辆数据后，可以根据数据库中建立的设备标识和车辆标识之间的第一映射关系，分别确定第一设备标识和第二设备标识各自对应的车辆标识。
本公开实施例中，车辆标识可以是车辆的车牌号或其它标识信息，DMS在向云平台发送驾驶员数据时，可以将车辆标识一并发送至云平台；相应的，ADAS在向云平台发送车辆数据时，可以将车辆标识一并发送至云平台。
在实际应用中，云平台在接收到DMS和ADAS发送的数据后，可以根据DMS发送的数据中携带的车辆标识、以及ADAS发送的数据中携带的车辆标识，在数据库中建立设备标识和车辆标识之间的对应关系；其中，设备标识和车辆标识之间的对应关系可包括：第一设备标识和车辆标识之间的对应关系、以及第二设备标识与车辆标识之间的对应关系。
显然，在数据库中建立设备标识和车辆标识之间的对应关系之后，再接收到第一设备标识和第二设备标识时，可以根据该对应关系在数据库中查找到第一设备标识和第二设备标识各自对应的车辆标识；响应于第一设备标识和第二设备标识对应于相同车辆标识，可以确定接收到的驾驶员行为数据和车辆行驶数据对应于相同车辆。此时，可以将接收到的驾驶员行为数据和车辆行驶数据进行关联，得到包括驾驶员行为数据和车辆行驶数 据的驾驶数据。
本公开实施例中，云平台在接收到车载设备发送的驾驶数据和驾驶员脸部特征后，可以在数据库中建立接收到的驾驶员脸部特征和接收到的驾驶数据之间的对应关系；或者，在数据库中建立和接收到的驾驶员脸部特征匹配的驾驶员脸部特征与接收到的驾驶数据之间的对应关系，示例性的，可以在数据库中存储的驾驶员脸部特征中，先确定与接收到的驾驶员脸部特征匹配的驾驶员脸部特征，再在数据库中建立和接收到的驾驶员脸部特征匹配的驾驶员脸部特征与接收到的驾驶数据之间的对应关系。
可以理解，通过在数据库中建立驾驶员脸部特征与驾驶数据的对应关系，便于在后续接收到驾驶员脸部特征后，确定出与驾驶员脸部特征对应的驾驶数据，进而有利于从驾驶员的角度，对驾驶员相关的驾驶数据进行分析，进而可以实现对驾驶员驾驶行为的准确评估。
对于分析获取的驾驶数据，得到驾驶员的评估结果的实现方式，示例性地可以包括：根据驾驶数据确定行车行为的危险等级；根据预先确定的危险等级和评估权重之间的映射关系，获取与确定的危险等级对应的评估权重；根据确定的危险等级及其对应的评估权重，确定与驾驶员脸部特征对应的驾驶员评估结果。
示例性的，可以预先划分行车行为的多个危险等级，针对每个危险等级设置相应的评估权重；每个危险等级对应的评估权重可以根据实际需求设置，不同危险等级对应的评估权重不同。例如，对于重度危险行为，评估权重可以为-10，对于中度危险行为，评估权重可以为-5；对于轻度危险行为，评估权重可以为-2；对于单位时间内无危险行为的情况，评估权重可以为2。
本公开实施例中，在确定数据库中的驾驶数据后，可以确定驾驶数据表征的各种行车行为，进而可以针对每种行车行为对应的危险等级，进行 评分；再将各种行车行为对应的评分进行求和，得到驾驶员评估结果。实际应用中，驾驶员评估结果可以作为单位或个人绩效管理依据。在一个示例中，驾驶员评估结果的数值越高，说明驾驶员行车行为更安全。
可以理解地，各种行车行为的危险等级可以根据实际应用需求进行设置，因而，根据行车行为的危险等级确定驾驶员评估结果的方式，有利于得到准确的驾驶员评估结果，可以准确地评估驾驶员行车行为的安全性。
对于根据驾驶数据确定行车行为的危险等级的实现方式，示例性地可以包括：确定驾驶数据的可信度；根据确定为可信的驾驶数据或者可信度超过设定阈值的驾驶数据，确定行车行为的危险等级。
本实施例中，设定阈值可以根据实际应用需求设置。在实际实施时，在确定驾驶数据的可信度后，根据驾驶数据的可信度，判断驾驶数据是否为可信的驾驶数据，或者驾驶数据的可信度是否超过设定阈值；当驾驶数据为可信的驾驶数据或者驾驶数据的可信度超过设定阈值时，再根据驾驶数据确定行车行为的危险等级；当驾驶数据为不可信的驾驶数据或者驾驶数据的可信度未超过设定阈值时，不确定行车行为的危险等级。
可以理解地，本公开实施例中，在驾驶数据为可信的驾驶数据或者驾驶数据的可信度超过设定阈值的基础上，确定行车行为的危险等级，可以排除不可信或可信度较低的驾驶数据。具体地，在驾驶数据为报警数据时，通过引入对报警数据的再次确认处理机制，一定程度上可以减少车载设备误报、错报的概率，使得对报警数据的分析结果更为客观和可靠；进而通过排除不可信或可信度较低的报警数据，有利于准确地评估驾驶员的驾驶行为，进而有利于准确评估行车行为的危险等级。
在本公开的一些可选实施例中，驾驶数据包括车辆行驶数据，车辆行驶数据包括车辆行驶地理位置信息和车辆行驶时间信息；对于确定驾驶数据的可信度的实现方式，在一个示例中可以包括：获取车辆行驶时间信息 和车辆行驶地理位置信息对应的天气状况信息和/或交通状况信息；根据天气状况信息和/或交通状况信息确定驾驶数据的可信度。
本公开实施例中，车辆行驶地理位置信息用于表示车辆当前的地理位置，车辆行驶地理位置信息的表现形式可以是经纬度数据或其它种类的地理位置数据。在实际应用中，ADAS可以从车辆的定位装置中获取车辆行驶地理位置信息。车辆行驶时间信息表示发送车辆行驶数据的时间点。在ADAS将车辆行驶数据发送到云平台后，云平台可以获取车辆行驶时间信息和车辆行驶地理位置信息。
本示例中，天气状况信息包括但不限于下雨、下雪、晴天、夜晚、阴天等情况；交通状况信息包括但不限于上坡、下坡、转弯、道路平整、道路不平整、道路通畅、堵车、出现车祸等。
可以理解地，天气状况信息和/或交通状况信息是影响驾驶员行为的重要因素，因而通过引入对报警数据的再次确认处理机制，一定程度上可以减少车载设备误报、错报的概率，使得对报警数据的分析结果更为客观和可靠，例如，在根据天气状况信息和/或交通状况信息确定驾驶数据的可信度、并根据驾驶数据的可信度确定行车行为的危险等级的情况下，通过排除不可信或可信度较低的报警数据，有利于准确地评估驾驶员的驾驶行为，进而有利于准确评估行车行为的危险等级。
本公开实施例中，在驾驶员行为数据为报警数据，和/或车辆行驶数据为报警数据时，DMS和/或ADAS可以将报警数据发送至云平台，云平台在接收到报警数据时，可以对报警数据进行核实和统计分析，参照图2为本公开实施例中报警数据统计结果示意图。
在本公开的一些可选实施例中，云平台在接收到报警数据时，可以根据天气状况信息和/或交通状况信息对报警数据进行核实。在第一个具体的示例中，报警数据表示车辆超速时，如果交通状况信息表示车辆行驶当前 位置出现堵车，则可以确定报警数据为不可信的数据。在第二个具体的示例中，报警数据表示车辆前方出向车祸时，如果交通状况信息表示车辆行驶当前位置未出现车祸，则可以确定报警数据为不可信的数据。在第三个具体的实例中，报警数据表示车道偏离时，如果交通状况信息表示车辆行驶当前位置所在区域存在交通管制，则可以确定报警数据的可信度较低，例如，可以将报警数据的可信度置为低于设定值的可信度值。通过引入对报警数据的再次确认处理机制，一定程度上可以减少车载设备误报、错报的概率，使得对报警数据的分析结果更为客观和可靠。
图3为本公开实施例的一个应用场景结构示意图，参照图3所示，获取车辆行驶时间信息和车辆行驶地理位置信息对应的天气状况信息的一种实现方式可以是：云平台在接收到车载设备发送的车辆行驶时间信息和车辆行驶地理位置信息后，可以向提供天气服务的第一服务器发送第一查询请求，第一查询请求用于查询车辆行驶时间信息和车辆行驶地理位置信息对应的天气状况信息；天气状况信息表征在车辆行驶时间信息对应的时间点下、在车辆行驶地理位置信息对应的地理位置对应的天气状况。第一服务器在接收到第一查询请求后，根据第一查询请求进行查询，得到对应的天气状况信息，向云平台发送天气状况信息。这样，云平台可以接收到第一服务器发送的天气状况信息。
参照图3所示，获取所车辆行驶时间信息和车辆行驶地理位置信息对应的交通状况信息的一种实现方式可以是：云平台在接收到车载设备发送的车辆行驶时间信息和车辆行驶地理位置信息后，可以向提供交通状况信息的第二服务器发送第二查询请求，第二查询请求用于查询车辆行驶时间信息和车辆行驶地理位置信息对应的交通状况信息；交通状况信息表征在车辆行驶时间信息对应的时间点下、在车辆行驶地理位置信息对应的交通状况。第二服务器在接收到第二查询请求后，根据第二查询请求进行查询， 得到对应的交通状况信息，向云平台发送交通状况信息。这样，云平台可以接收到第二服务器发送的交通状况信息。
在本公开的一些可选实施例中，驾驶数据可以包括驾驶员行为数据以及驾驶员行为数据获取时对应的驾驶员图像；对于确定驾驶数据的可信度的实现方式，在另一个示例中可以包括：根据驾驶员图像确定驾驶员行为数据的可信度。
在实际应用中，DMS可以实时采集驾驶员图像，在确定发送报警数据时，可以将报警数据和报警数据获取时对应的驾驶员图像发送至云平台。
可以理解地，车载设备DMS发送的驾驶员图像反映了真实的驾驶员状态，因而通过引入对报警数据的再次确认处理机制，一定程度上可以减少车载设备误报、错报的概率，使得对报警数据的分析结果更为客观和可靠，具体根据驾驶员图像确定报警数据的可信度，可以降低驾驶员行为数据的误判率，有利于准确地判断行车行为的危险等级。例如，车载设备上报的报警数据表示驾驶员出现打哈欠的疲劳驾驶状态，但是通过对车载设备联通报警数据一并上报的当时的驾驶员图像的分析，表明当时驾驶员并未打哈欠，则可以确定该条报警数据为不可信的驾驶数据；或者，确定该条报警数据的可信度较低，进而通过排除不可信或可信度较低的报警数据，有利于准确地评估驾驶员的驾驶行为，进而有利于准确评估行车行为的危险等级。
在本公开的一些可选实施例中，数据库中还预先建立有驾驶员脸部特征和车队标识之间的映射关系，相应地，可以根据该映射关系，确定对应相同车队标识的至少两个驾驶员脸部特征；根据至少两个驾驶员脸部特征中各驾驶员脸部特征对应的驾驶员评估结果，得到车队评估结果。
在实际应用中，同一车载设备可以将驾驶员脸部特征和车辆所属车队的标识上传至云平台；这样，云平台可以根据同一车载设备发送的驾驶员 脸部特征和车队标识，在数据库中建立驾驶员脸部特征和车队标识之间的映射关系。
可以理解，在本公开实施例中，通过数据库中建立上述映射关系，可以确定同一车队的所有驾驶员的脸部特征；进一步结合各驾驶员脸部特征对应的驾驶员评估结果，可以得到同一车队的所有驾驶员对应的驾驶员评估结果，进而能够单独针对每个车队的各驾驶员进行评估，有利于了解每个车队的驾驶员行为。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
在前述实施例提出的驾驶数据分析方法的基础上，本公开实施例提出了一种驾驶数据分析装置。图4为本公开实施例的驾驶数据分析装置的组成结构示意图，如图4所示，所述装置包括：接收模块401、第一处理模块402、获取模块403和第二处理模块404，其中，所述接收模块401，用于接收驾驶员数据分析请求，所述驾驶员数据分析请求包括请求分析的脸部特征；所述第一处理模块402，用于在数据库中确定与所述脸部特征匹配的驾驶员脸部特征，所述数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系；所述获取模块403，用于获取所述数据库中与确定的驾驶员脸部特征对应的驾驶数据；所述第二处理模块404，用于分析获取的所述驾驶数据，得到与所述驾驶员脸部特征对应的驾驶员评估结果。
在本公开的一些可选实施例中，所述第二处理模块404，用于根据所述驾驶数据确定行车行为的危险等级；根据预先确定的危险等级和评估权重之间的映射关系，获取与确定的危险等级对应的评估权重；根据确定的危险等级及其对应的评估权重，确定与所述驾驶员脸部特征对应的驾驶员评估结果。
在本公开的一些可选实施例中，所述驾驶数据包括驾驶员行为数据和/或车辆行驶数据，所述驾驶员行为数据包括以下至少之一：打哈欠、打电话、喝水、抽烟、化妆、驾驶员不在驾驶位置；所述车辆行驶数据包括以下至少之一：车道偏离预警、前向碰撞预警、超速预警、车辆前方出现行人、后向碰撞预警、车辆前方障碍物预警。
在本公开的一些可选实施例中，所述第一处理模块402，还用于接收车辆上设置的车载设备发送的驾驶数据和驾驶员脸部特征；在数据库中建立接收到的驾驶员脸部特征和接收到的驾驶数据之间的对应关系，或者，在数据库中建立和接收到的驾驶员脸部特征匹配的驾驶员脸部特征与接收到的驾驶数据之间的对应关系。
在本公开的一些可选实施例中，所述第二处理模块404，用于确定所述驾驶数据的可信度；根据确定为可信的驾驶数据或者所述可信度超过设定阈值的驾驶数据，确定所述行车行为的危险等级。
在本公开的一些可选实施例中，所述驾驶数据包括车辆行驶数据，所述车辆行驶数据包括车辆行驶地理位置信息和车辆行驶时间信息；所述第二处理模块404，用于获取所述车辆行驶时间信息和所述车辆行驶地理位置信息对应的天气状况信息和/或交通状况信息；根据所述天气状况信息和/或所述交通状况信息确定所述驾驶数据的可信度。
在本公开的一些可选实施例中，所述第二处理模块404，用于向提供天气服务的第一服务器发送第一查询请求，所述第一查询请求用于查询所述车辆行驶时间信息和所述车辆行驶地理位置信息的天气状况信息；接收所述第一服务器发送的所述天气状况信息。
在本公开的一些可选实施例中，所述第二处理模块404，用于向提供交通状况信息的第二服务器发送第二查询请求，所述第二查询请求用于查询所述车辆行驶时间信息和所述车辆行驶地理位置信息的交通状况信息；接 收所述第二服务器发送的所述交通状况信息。
在本公开的一些可选实施例中，所述驾驶数据包括驾驶员行为数据以及所述驾驶员行为数据获取时对应的驾驶员图像；所述第二处理模块404，用于根据所述驾驶员图像确定所述驾驶员行为数据的可信度。
在本公开的一些可选实施例中，所述驾驶员脸部特征是从驾驶员脸部图像提取的特征。
在本公开的一些可选实施例中，所述数据库中还预先建立有驾驶员脸部特征和车队标识之间的映射关系；所述第二处理模块404，还用于根据所述映射关系，确定对应相同车队标识的至少两个驾驶员脸部特征；根据所述至少两个驾驶员脸部特征中各驾驶员脸部特征对应的驾驶员评估结果，得到车队评估结果。
在实际应用中，接收模块401、第一处理模块402、获取模块403和第二处理模块404均可以利用车载数据终端或云平台中的处理器实现，上述处理器可以为ASIC、DSP、DSPD、PLD、FPGA、CPU、控制器、微控制器、微处理器中的至少一种。
另外，在本实施例中的各功能模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
所述集成的单元如果以软件功能模块的形式实现并非作为独立的产品进行销售或使用时，可以存储在一个计算机可读取存储介质中，基于这样的理解，本实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或processor(处理器)执行 本实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
具体的，本实施例中的一种驾驶数据分析方法对应的计算机程序指令可以被存储在光盘，硬盘，U盘等存储介质上，当存储介质中的与一种驾驶数据分析方法对应的计算机程序指令被一电子设备读取或被执行时，实现前述实施例的任意一种驾驶数据分析方法。
基于前述实施例相同的技术构思，参见图5，其示出了本公开实施例提供的一种电子设备50，可以包括：存储器51和处理器52；其中，所述存储器51，用于存储计算机程序和数据；所述处理器52，用于执行所述存储器中存储的计算机程序，以实现前述实施例的任意一种数据分析方法。
在实际应用中，上述存储器51可以是易失性存储器(volatile memory)，例如RAM；或者非易失性存储器(non-volatile memory)，例如ROM，快闪存储器(flash memory)，硬盘(Hard Disk Drive，HDD)或固态硬盘(Solid-State Drive，SSD)；或者上述种类的存储器的组合，并向处理器52提供指令和数据。
上述处理器52可以为ASIC、DSP、DSPD、PLD、FPGA、CPU、控制器、微控制器、微处理器中的至少一种。可以理解地，对于不同的设备，用于实现上述处理器功能的电子器件还可以为其它，本公开实施例不作具体限定。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提供了一种计算机存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现本公开实施例上述任意一种驾驶数据分 析方法。
本公开实施例还提供了一种计算机程序产品，包括计算机程序指令，该计算机程序指令使得计算机执行时实现本公开实施例上述任意一种驾驶数据分析方法。
上文对各个实施例的描述倾向于强调各个实施例之间的不同之处，其相同或相似之处可以互相参考，为了简洁，本文不再赘述。
本公开所提供的各方法实施例中所揭露的方法，在不冲突的情况下可以任意组合，得到新的方法实施例。
本公开所提供的各产品实施例中所揭露的特征，在不冲突的情况下可以任意组合，得到新的产品实施例。
本公开所提供的各方法或设备实施例中所揭露的特征，在不冲突的情况下可以任意组合，得到新的方法实施例或设备实施例。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本发明各个实施例所述的方法。
上面结合附图对本发明的实施例进行了描述，但是本发明并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本发明的启示下，在不脱离本发明宗旨和权利要求所保护的范围情况下，还可做出很多形式，这些均属于本发明的保护之内。

Claims (15)

  1. 一种驾驶数据分析方法，包括：
    接收驾驶员数据分析请求，所述驾驶员数据分析请求包括请求分析的脸部特征；
    在数据库中确定与所述脸部特征匹配的驾驶员脸部特征，所述数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系；
    获取所述数据库中与确定的所述驾驶员脸部特征对应的驾驶数据；
    分析获取的所述驾驶数据，得到与所述驾驶员脸部特征对应的驾驶员评估结果。
  2. 根据权利要求1所述的方法，其中，所述分析获取的所述驾驶数据，得到所述驾驶员的评估结果，包括：
    根据所述驾驶数据确定行车行为的危险等级；
    根据预先确定的危险等级和评估权重之间的映射关系，获取与确定的危险等级对应的评估权重；
    根据确定的危险等级及其对应的评估权重，确定与所述驾驶员脸部特征对应的驾驶员评估结果。
  3. 根据权利要求1所述的方法，其中，所述驾驶数据包括驾驶员行为数据和/或车辆行驶数据，所述驾驶员行为数据包括以下至少之一：打哈欠、打电话、喝水、抽烟、化妆、驾驶员不在驾驶位置；所述车辆行驶数据包括以下至少之一：车道偏离预警、前向碰撞预警、超速预警、车辆前方出现行人、后向碰撞预警、车辆前方障碍物预警。
  4. 根据权利要求3所述的方法，其中，所述获取所述数据库中与确定的驾驶员脸部特征对应的驾驶数据之前，还包括：
    接收车辆上设置的车载设备发送的驾驶数据和驾驶员脸部特征；
    在数据库中建立接收到的驾驶员脸部特征和接收到的驾驶数据之间的 对应关系，或者，在数据库中建立和接收到的驾驶员脸部特征匹配的驾驶员脸部特征与接收到的驾驶数据之间的对应关系。
  5. 根据权利要求2至4任一项所述的方法，其中，所述根据所述驾驶数据确定行车行为的危险等级，包括：
    确定所述驾驶数据的可信度；
    根据确定为可信的驾驶数据或者所述可信度超过设定阈值的驾驶数据，确定所述行车行为的危险等级。
  6. 根据权利要求5所述的方法，其中，所述驾驶数据包括车辆行驶数据，所述车辆行驶数据包括车辆行驶地理位置信息和车辆行驶时间信息；
    确定所述驾驶数据的可信度，包括：
    获取所述车辆行驶时间信息和所述车辆行驶地理位置信息对应的天气状况信息和/或交通状况信息；
    根据所述天气状况信息和/或所述交通状况信息确定所述驾驶数据的可信度。
  7. 根据权利要求6所述的方法，其中，所述获取所述车辆行驶时间信息和所述车辆行驶地理位置信息对应的天气状况信息，包括：
    向提供天气服务的第一服务器发送第一查询请求，所述第一查询请求用于查询所述车辆行驶时间信息和所述车辆行驶地理位置信息的天气状况信息；
    接收所述第一服务器发送的所述天气状况信息。
  8. 根据权利要求6所述的方法，其中，所述获取所述车辆行驶时间信息和所述车辆行驶地理位置信息对应的交通状况信息，包括：
    向提供交通状况信息的第二服务器发送第二查询请求，所述第二查询请求用于查询所述车辆行驶时间信息和所述车辆行驶地理位置信息的交通状况信息；
    接收所述第二服务器发送的所述交通状况信息。
  9. 根据权利要求5所述的方法，其中，所述驾驶数据包括驾驶员行为数据以及所述驾驶员行为数据获取时对应的驾驶员图像；
    确定所述驾驶数据的可信度，包括：根据所述驾驶员图像确定所述驾驶员行为数据的可信度。
  10. 根据权利要求1至9任一项所述的方法，其中，所述驾驶员脸部特征是从驾驶员脸部图像提取的特征。
  11. 根据权利要求1至10任一项所述的方法，其中，所述数据库中还预先建立有驾驶员脸部特征和车队标识之间的映射关系，所述方法还包括：
    根据所述映射关系，确定对应相同车队标识的至少两个驾驶员脸部特征；
    根据所述至少两个驾驶员脸部特征中各驾驶员脸部特征对应的驾驶员评估结果，得到车队评估结果。
  12. 一种驾驶数据分析装置，所述装置包括接收模块、第一处理模块、获取模块和第二处理模块，其中，
    所述接收模块，用于接收驾驶员数据分析请求，所述驾驶员数据分析请求包括请求分析的脸部特征；
    所述第一处理模块，用于在数据库中确定与所述脸部特征匹配的驾驶员脸部特征，所述数据库存储有驾驶员脸部特征和驾驶数据之间的对应关系；
    所述获取模块，用于获取所述数据库中与确定的驾驶员脸部特征对应的驾驶数据；
    所述第二处理模块，用于分析获取的所述驾驶数据，得到与所述驾驶员脸部特征对应的驾驶员评估结果。
  13. 一种电子设备，包括处理器和用于存储能够在处理器上运行的计 算机程序的存储器；其中，
    所述处理器用于运行所述计算机程序以执行权利要求1至11任一项所述的方法。
  14. 一种计算机存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现权利要求1至11任一项所述的方法。
  15. 一种计算机程序产品，包括计算机程序指令，该计算机程序指令使得计算机执行如权利要求1至11任一项所述的方法。
PCT/CN2020/092603 2019-09-30 2020-05-27 驾驶数据分析方法、装置、电子设备和计算机存储介质 WO2021063005A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020217030885A KR20210129190A (ko) 2019-09-30 2020-05-27 운전 데이터 분석 방법, 장치, 전자 기기 및 컴퓨터 저장 매체
JP2021556962A JP2022526509A (ja) 2019-09-30 2020-05-27 運転データの分析方法、装置、電子機器およびコンピュータ記憶媒体

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910945671.8A CN110737688B (zh) 2019-09-30 2019-09-30 驾驶数据分析方法、装置、电子设备和计算机存储介质
CN201910945671.8 2019-09-30

Publications (1)

Publication Number Publication Date
WO2021063005A1 true WO2021063005A1 (zh) 2021-04-08

Family

ID=69268577

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/092603 WO2021063005A1 (zh) 2019-09-30 2020-05-27 驾驶数据分析方法、装置、电子设备和计算机存储介质

Country Status (4)

Country Link
JP (1) JP2022526509A (zh)
KR (1) KR20210129190A (zh)
CN (1) CN110737688B (zh)
WO (1) WO2021063005A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114274967A (zh) * 2021-12-30 2022-04-05 上海商汤临港智能科技有限公司 智能驾驶车辆的管理方法、装置、计算机设备及存储介质
CN115333938A (zh) * 2022-07-19 2022-11-11 岚图汽车科技有限公司 一种车辆安全防护控制方法及相关设备
CN115953858A (zh) * 2022-11-29 2023-04-11 摩尔线程智能科技(北京)有限责任公司 一种基于车载dms的驾驶评分方法、装置及电子设备

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110717436A (zh) * 2019-09-30 2020-01-21 上海商汤临港智能科技有限公司 数据分析方法、装置、电子设备和计算机存储介质
CN110737688B (zh) * 2019-09-30 2023-04-07 上海商汤临港智能科技有限公司 驾驶数据分析方法、装置、电子设备和计算机存储介质
CN113554370A (zh) * 2020-04-23 2021-10-26 中国石油化工股份有限公司 危化品运输车辆安全风险评估方法及装置
CN112132475A (zh) * 2020-09-27 2020-12-25 上海应用技术大学 司机驾驶安全绩效考核方法及系统
CN112398814B (zh) * 2020-10-26 2023-07-04 易显智能科技有限责任公司 一种基于大数据的驾驶行为数据防篡改方法及装置
CN113263993B (zh) * 2021-05-17 2023-08-15 深圳市元征科技股份有限公司 故障预警方法、装置、通信设备及存储介质
CN113506447B (zh) * 2021-08-16 2022-08-16 深圳市沅欣智能科技有限公司 一种基于物联网的园区智慧通行控制方法及相关装置
CN114095898A (zh) * 2021-11-04 2022-02-25 武汉极目智能技术有限公司 一种基于车联网运营控制中心的交互方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105206052A (zh) * 2015-09-21 2015-12-30 张力 一种驾驶行为分析方法及设备
CN105894609A (zh) * 2015-11-11 2016-08-24 乐卡汽车智能科技（北京）有限公司 数据处理方法、装置及车险系统
CN105930771A (zh) * 2016-04-13 2016-09-07 乐视控股（北京）有限公司 一种驾驶行为评分方法及装置
CN109523652A (zh) * 2018-09-29 2019-03-26 百度在线网络技术（北京）有限公司 基于驾驶行为的保险的处理方法、装置、设备及存储介质
CN109754595A (zh) * 2017-11-01 2019-05-14 阿里巴巴集团控股有限公司 车辆风险的评估方法、装置及接口设备
CN110737688A (zh) * 2019-09-30 2020-01-31 上海商汤临港智能科技有限公司 驾驶数据分析方法、装置、电子设备和计算机存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101211428A (zh) * 2006-12-27 2008-07-02 厦门雅迅网络股份有限公司 一种驾驶员习惯统计、分析方法
JP4941752B2 (ja) * 2007-08-15 2012-05-30 オムロン株式会社 運転支援装置および方法、並びに、プログラム
JP4995046B2 (ja) * 2007-11-21 2012-08-08 株式会社日立製作所 自動車保険料設定システム
CN104732785A (zh) * 2015-01-09 2015-06-24 杭州好好开车科技有限公司 一种驾驶行为分析和提醒的方法及系统
CN105654753A (zh) * 2016-01-08 2016-06-08 北京乐驾科技有限公司 一种智能车载安全驾驶辅助方法及系统
JP6261637B2 (ja) * 2016-03-17 2018-01-17 ヤフー株式会社 保険条件決定装置、保険条件決定方法、およびプログラム
CN106297340A (zh) * 2016-08-17 2017-01-04 上海电机学院 一种行驶车辆安全监测预警系统与方法
CN108438001A (zh) * 2018-03-15 2018-08-24 东南大学 一种基于时间序列聚类分析的异常驾驶行为判别方法
CN109002757A (zh) * 2018-06-04 2018-12-14 上海商汤智能科技有限公司 驾驶管理方法和系统、车载智能系统、电子设备、介质
CN109326134A (zh) * 2018-12-03 2019-02-12 北京远特科技股份有限公司 谨慎驾驶提醒方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105206052A (zh) * 2015-09-21 2015-12-30 张力 一种驾驶行为分析方法及设备
CN105894609A (zh) * 2015-11-11 2016-08-24 乐卡汽车智能科技（北京）有限公司 数据处理方法、装置及车险系统
CN105930771A (zh) * 2016-04-13 2016-09-07 乐视控股（北京）有限公司 一种驾驶行为评分方法及装置
CN109754595A (zh) * 2017-11-01 2019-05-14 阿里巴巴集团控股有限公司 车辆风险的评估方法、装置及接口设备
CN109523652A (zh) * 2018-09-29 2019-03-26 百度在线网络技术（北京）有限公司 基于驾驶行为的保险的处理方法、装置、设备及存储介质
CN110737688A (zh) * 2019-09-30 2020-01-31 上海商汤临港智能科技有限公司 驾驶数据分析方法、装置、电子设备和计算机存储介质

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114274967A (zh) * 2021-12-30 2022-04-05 上海商汤临港智能科技有限公司 智能驾驶车辆的管理方法、装置、计算机设备及存储介质
CN114274967B (zh) * 2021-12-30 2024-04-12 上海商汤临港智能科技有限公司 智能驾驶车辆的管理方法、装置、计算机设备及存储介质
CN115333938A (zh) * 2022-07-19 2022-11-11 岚图汽车科技有限公司 一种车辆安全防护控制方法及相关设备
CN115333938B (zh) * 2022-07-19 2024-03-26 岚图汽车科技有限公司 一种车辆安全防护控制方法及相关设备
CN115953858A (zh) * 2022-11-29 2023-04-11 摩尔线程智能科技(北京)有限责任公司 一种基于车载dms的驾驶评分方法、装置及电子设备

Also Published As

Publication number Publication date
JP2022526509A (ja) 2022-05-25
KR20210129190A (ko) 2021-10-27
CN110737688B (zh) 2023-04-07
CN110737688A (zh) 2020-01-31

Similar Documents

Publication Publication Date Title
WO2021063005A1 (zh) 驾驶数据分析方法、装置、电子设备和计算机存储介质
WO2021063006A1 (zh) 驾驶预警方法、装置、电子设备和计算机存储介质
US9583000B2 (en) Vehicle-based abnormal travel event detecting and reporting
US9940530B2 (en) Platform for acquiring driver behavior data
US9253251B2 (en) System and method for determining a vehicle proximity to a selected address
US9786171B2 (en) Systems and methods for detecting and distributing hazard data by a vehicle
US10696257B2 (en) Automatic crowd sensing and reporting system for road incidents
US9836965B2 (en) Move over slow drivers
US10203217B2 (en) Traffic citation delivery based on type of traffic infraction
US12014423B1 (en) Using vehicle data, geographic area type data, and vehicle collision data in determining an indication of whether a vehicle in a vehicle collision is a total loss
US8031084B2 (en) Method and system for infraction detection based on vehicle traffic flow data
US20160280132A1 (en) Method and system for providing a collision alert
US11741763B2 (en) Systems and methods for system generated damage analysis
WO2021063004A1 (zh) 数据分析方法、装置、电子设备和计算机存储介质
JP2018018214A5 (zh)
KR20130108928A (ko) 차량 사고 정보 수집 방법, 이를 위한 장치 및 차량 사고 정보 수집 시스템
KR101066081B1 (ko) 차량 탑재형 스마트 정보 판독 시스템 및 방법
US20200005562A1 (en) Method for ascertaining illegal driving behavior by a vehicle
US20180096433A1 (en) Calculation of Differential for Insurance Rates
US20210323577A1 (en) Methods and systems for managing an automated driving system of a vehicle
EP3291199A1 (en) Move over slow drivers
CN115131958B (zh) 拥堵路况推送方法、装置、电子设备和存储介质
US20240061917A1 (en) Driving record authentication method, electronic device, storage medium
CA2977386A1 (en) Process for improving vehicle driver behavior
CN114613150A (zh) 一种违停行为确定方法及存储介质

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: 20870650

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021556962

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20217030885

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20870650

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20870650

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 20.10.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20870650

Country of ref document: EP

Kind code of ref document: A1