WO2025001968A1 - 驾驶状态监测方法、装置、设备、存储介质及产品 - Google Patents

驾驶状态监测方法、装置、设备、存储介质及产品 Download PDF

Info

Publication number
WO2025001968A1
WO2025001968A1 PCT/CN2024/100465 CN2024100465W WO2025001968A1 WO 2025001968 A1 WO2025001968 A1 WO 2025001968A1 CN 2024100465 W CN2024100465 W CN 2024100465W WO 2025001968 A1 WO2025001968 A1 WO 2025001968A1
Authority
WO
WIPO (PCT)
Prior art keywords
driver
fatigue
reminder
state
level
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/CN2024/100465
Other languages
English (en)
French (fr)
Inventor
汪勇泉
高敏
王友兰
韦彩霞
刘金平
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.)
Chery Automobile Co Ltd
Original Assignee
Chery Automobile 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 Chery Automobile Co Ltd filed Critical Chery Automobile Co Ltd
Publication of WO2025001968A1 publication Critical patent/WO2025001968A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V40/174—Facial expression recognition
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W2040/0872—Driver physiology
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B60W2050/143—Alarm means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B60W2050/146—Display means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/229—Attention level, e.g. attentive to driving, reading or sleeping

Definitions

  • the present application relates to the field of vehicle technology, and in particular to a driving status monitoring method, device, equipment, storage medium and product.
  • the embodiments of the present application provide a driving status monitoring method, device, equipment, storage medium and product, which can promptly remind the user when the user is driving fatigued, thereby ensuring the user's driving safety and reducing the incidence of traffic accidents.
  • the technical solution is as follows:
  • a driving state monitoring method comprising:
  • the cloud server is used to determine a target account of the driver based on the facial features, and obtain account data of the target account, wherein the account data includes reminder configuration information corresponding to the abnormal driving state;
  • the fatigue information including a fatigue state and a fatigue level corresponding to the fatigue state
  • the fatigue state is fatigue
  • the driver is reminded based on the first reminder method.
  • the determining the driver's fatigue information based on the eye closing frequency and the eye closing duration includes:
  • the eye-closing frequency reaches the first frequency and the eye-closing duration is greater than the first duration but less than the second duration, determining that the driver's fatigue state is fatigue and the fatigue level is the first level;
  • the eye-closing frequency reaches a second frequency and the eye-closing duration is greater than the second duration but less than a third duration, determining that the driver's fatigue state is fatigue and the fatigue level is a second level;
  • the eyes closing frequency reaches the third frequency and the eyes closing duration is greater than the third duration, it is determined that the driver's fatigue state is fatigue and the fatigue level is the third level; wherein the third frequency is less than the second frequency, the second frequency is less than the first frequency, and the fatigue degrees corresponding to the first level, the second level and the third level increase respectively.
  • the method further includes:
  • the driver is reminded based on the second reminder method.
  • the method further includes:
  • the driver is reminded based on the third reminder method.
  • the method further includes:
  • the vehicle is ventilated based on the ventilation method.
  • the account data of the target account further includes the identity information of the driver; and the method further includes:
  • a voice message is broadcasted or music is recommended to the driver.
  • the account data of the target account further includes vehicle body configuration data; and the method further includes:
  • the position of the main driver's seat and the position of the rearview mirror are adjusted.
  • a driving state monitoring device comprising:
  • a first acquisition module used to acquire a facial image of a driver of the vehicle
  • the extraction module is used to extract the facial features of the driver based on the facial image and send the facial features to the cloud server; wherein the cloud server is used to determine the driver based on the facial features.
  • the target account of the driver and obtaining account data of the target account, wherein the account data includes reminder configuration information corresponding to the abnormal driving state;
  • a receiving module used for receiving the account data of the target account sent by the cloud server
  • a first determination module configured to determine, based on the facial image, the frequency and duration of eye closure of the driver within a first preset duration
  • a second determination module is used to determine the driver's fatigue information based on the eye closing frequency and the eye closing duration, wherein the fatigue information includes a fatigue state and a fatigue level corresponding to the fatigue state;
  • a second acquisition module is used to acquire a first correspondence between a fatigue level and a reminder method from the reminder configuration information corresponding to the abnormal driving state when the fatigue state is fatigue;
  • a third determining module configured to determine, based on the fatigue level corresponding to the fatigue state, a first reminder method corresponding to the fatigue level from the first corresponding relationship
  • a reminder module is used to remind the driver based on the first reminder method.
  • the second determination module is used to determine that the driver's fatigue state is fatigue and the fatigue level is the first level when the eye-closing frequency reaches a first frequency and the eye-closing duration is greater than the first duration but less than the second duration; to determine that the driver's fatigue state is fatigue and the fatigue level is the second level when the eye-closing frequency reaches a second frequency and the eye-closing duration is greater than the second duration but less than a third duration; to determine that the driver's fatigue state is fatigue and the fatigue level is the third level when the eye-closing frequency reaches a third frequency and the eye-closing duration is greater than the third duration; wherein the third frequency is less than the second frequency, the second frequency is less than the first frequency, and the fatigue degrees corresponding to the first level, the second level and the third level increase in sequence.
  • the device further includes:
  • a fourth determination module configured to determine an actual gaze area of the driver's sight based on the face image
  • a fifth determination module configured to determine that the driver is in a distracted state when the actual gaze area does not match the theoretical gaze area
  • a third acquisition module used to acquire a second corresponding relationship between the abnormal state and the reminder method from the reminder configuration information corresponding to the abnormal driving state;
  • a fourth acquisition module configured to acquire a second reminder method corresponding to the distraction state from the second corresponding relationship
  • the reminding module is further used to remind the driver based on the second reminding method.
  • the device further includes:
  • a first detection module configured to detect the driver's hands based on the face image
  • a sixth determination module configured to determine the distance between the driver's hand and the ear when it is detected that the driver's hand is holding the electronic device
  • a seventh determination module configured to determine that the driver is in a talking state when the distance is less than a preset distance
  • a fifth acquisition module configured to acquire a third reminder method corresponding to the call status from the second corresponding relationship
  • the reminding module is further used to remind the driver based on the third reminding method.
  • the device further includes:
  • a second detection module is used to detect the driver's mouth when it is detected that the driver's hand is holding a smoking object
  • an eighth determination module configured to determine that the driver is in a smoking state when it is detected that the smoking object is contained in the driver's mouth;
  • an eighth determination module configured to obtain the smoke concentration in the vehicle, and determine the environment in which the vehicle is located when the smoke concentration is greater than a preset concentration
  • a ninth determination module configured to determine a ventilation mode based on the environment in which the vehicle is located
  • a ventilation module is used to ventilate the vehicle based on the ventilation method.
  • the account data of the target account further includes the identity information of the driver; and the device further includes:
  • a tenth determination module configured to determine the driver's emotion type based on the facial features
  • a sixth acquisition module configured to acquire the identity information of the driver from the account data of the target account when the emotion type of the driver is a positive emotion
  • a recommendation module is used to broadcast a voice message or recommend music to the driver based on the positive emotion and the identity information.
  • the account data of the target account further includes vehicle body configuration data; and the device further includes:
  • a seventh acquisition module used to acquire the position information of the main driver's seat and the position information of the rearview mirror from the vehicle body configuration data
  • An adjustment module is used to adjust the position of the main driver's seat and the position of the rearview mirror based on the position information of the main driver's seat and the position information of the rearview mirror.
  • a control device which includes a processor and a memory, wherein at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement any of the above-mentioned driving status monitoring methods.
  • a computer-readable storage medium in which at least one program code is stored.
  • the at least one program code is loaded and executed by a processor to implement any of the above-mentioned driving state monitoring methods.
  • a computer program product wherein at least one program code is stored in the computer program product, and the at least one program code is loaded and executed by a processor to implement any of the above-mentioned driving state monitoring methods.
  • the embodiment of the present application provides a driving status monitoring method.
  • the account data of the driver's target account is obtained from the cloud server, and the account data includes reminder configuration information corresponding to the abnormal driving state, that is, the reminder method adapted to the driver in the abnormal driving state is obtained.
  • the reminder method adapted to the user in the fatigue state is obtained to remind the driver, which can improve the reminder effect, thereby ensuring the user's safe driving, and further reducing the incidence of traffic accidents.
  • FIG1 is a schematic diagram of an implementation environment of a driving state monitoring method provided in an embodiment of the present application.
  • FIG2 is a flow chart of a driving state monitoring method provided in an embodiment of the present application.
  • FIG. 3 is a schematic diagram of an interaction between a control device and a cloud server provided in an embodiment of the present application
  • FIG4 is a schematic diagram of a control device performing data processing through a DMS provided in an embodiment of the present application.
  • FIG5 is a schematic diagram of the structure of a driving state monitoring device provided in an embodiment of the present application.
  • FIG6 is a structural block diagram of a control device provided in an embodiment of the present application.
  • the information including but not limited to user device information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.
  • the facial images, emotion types, account data, etc. involved in this application are all obtained with full authorization.
  • FIG. 1 is a schematic diagram of an implementation environment of a driving status monitoring method provided in an embodiment of the present application, and the implementation environment includes: a camera module 10, a control device 11, a cloud server 12 and a T-BOX 13 (Telematics BOX, information processor), wherein the camera module 10, the control device 11 and the T-BOX 13 are located in the same vehicle, and the vehicle can be a fuel vehicle, an electric vehicle or a hybrid vehicle, which is not specifically limited.
  • a camera module 10 a control device 11, a cloud server 12 and a T-BOX 13 (Telematics BOX, information processor)
  • the vehicle can be a fuel vehicle, an electric vehicle or a hybrid vehicle, which is not specifically limited.
  • the camera module 10 can capture the driver's facial image and send the facial image to the control device 11.
  • the control device 11 extracts the facial features in the facial image and sends the facial features to the T-BOX 13.
  • the T-BOX 13 forwards the facial features to the cloud server 12.
  • the cloud server 12 compares the facial features with the facial features stored in the cloud database, determines the target account corresponding to the facial features, obtains the account data of the target account, and sends the account data of the target account to the control device 11 through the T-BOX 13.
  • the control device 11 receives and stores the account data of the target account locally.
  • the target account is the driver's
  • the target account data is the account registered by the driver in the cloud server, and the account data of the target account is the relevant data associated with the target account; for example, the account data of the target account includes reminder configuration information corresponding to the abnormal driving state, and the abnormal driving state refers to the driving state where a traffic accident may occur.
  • the reminder configuration information corresponding to the abnormal driving state includes a first correspondence between the fatigue level and the reminder method, and the reminder configuration information corresponding to the abnormal driving state also includes a second correspondence between the abnormal state and the reminder method;
  • the account data of the target account also includes the driver's identity information, and the account data of the target account also includes the position information of the main driver's seat and the position information of the rearview mirror.
  • control device 11 After the control device 11 obtains the facial image, it can determine the driver's driving status based on the facial image, which driving status includes: fatigue state, distracted state, call state, smoking state, etc. According to the driver's driving status, the corresponding reminder method is obtained from the account data of the target account, and then the driver is reminded based on the obtained reminder method.
  • the control device 11 can be a vehicle computer or a vehicle controller.
  • the vehicle computer is the abbreviation of the vehicle infotainment product, including the vehicle computer host and the display screen.
  • the cloud server 12 can be at least one of a server, a server cluster composed of multiple servers, a cloud computing platform and a virtualization center.
  • the camera module 10 is a camera for shooting the driver in the main driving seat.
  • T-BOX13 provides network transmission capability to realize data transmission between the control device 11 and the cloud server 12.
  • control device can monitor the driver's fatigue state, distraction state, talking state and smoking state, and remind the driver through the reminder method corresponding to the monitored state.
  • FIG2 is a flow chart of a driving state monitoring method provided by an embodiment of the present application, which is executed by a control device. Referring to FIG2 , the method includes:
  • Step 201 The control device obtains a facial image of the driver of the vehicle.
  • the driver is the person who drives the vehicle, that is, the person sitting in the main driver's seat.
  • the camera module can collect facial images in real time or periodically.
  • the collected facial images are sent to the control device.
  • the control device receives the facial images sent by the camera module.
  • the camera module When the camera module is in the on state, the camera module can directly capture images.
  • the control device When the camera module is in the off state, the control device can display a status monitoring option on the display screen. In response to detecting a trigger operation of the status monitoring option, the control device sends an on/off message to the camera module. The camera module starts up and then collects facial images in real time or periodically.
  • the control device After the control device acquires the facial image, it determines the clarity and completeness of the facial image. If the clarity or completeness does not meet the requirements, it displays or voice broadcasts a prompt message to remind the user to adjust the posture, and then the camera module re-takes the driver's facial image, and then determines whether the clarity and completeness of the re-taken facial image meet the requirements, until a facial image with clarity and completeness that meets the requirements is captured, so that the camera module captures a facial image that meets the requirements. If the clarity and completeness meet the requirements, the subsequent steps are executed.
  • Step 202 The control device extracts the driver's facial features based on the facial image and sends the facial features to the cloud server.
  • the control device extracts facial features from the facial image and sends the facial features to the cloud server through T-BOX.
  • the cloud server compares the facial features with multiple facial features stored in the cloud database, and searches for target facial features that match the facial features from the multiple facial features.
  • the cloud server finds the target facial features that match the facial features, the cloud server determines the target account corresponding to the target facial features based on the correspondence between the facial features and the accounts, and then obtains the account data of the target account from the cloud database, and sends the account data of the target account to the control device through T-BOX.
  • the process can be seen in Figure 3.
  • the target account is the account registered by the driver in the cloud server, and the account data of the target account is the relevant data associated with the target account; for example, the account data of the target account includes the reminder configuration information corresponding to the abnormal driving state, which refers to the driving state where a traffic accident may occur, and the reminder configuration information corresponding to the abnormal driving state includes the first correspondence between the fatigue level and the reminder method, and the reminder configuration information corresponding to the abnormal driving state also includes the second correspondence between the abnormal state and the reminder method; the account data of the target account also includes the identity information of the driver, and the identity information of the driver includes the gender and age of the driver; the account data of the target account also includes the body configuration data, which includes the position information of the main driver's seat and the position information of the rearview mirror, and the body configuration data also includes the height information of the steering wheel and other personalized driving habit setting information, such as the brightness of the interior atmosphere light, the music style type, HUD (Head Up Display), ADAS (Advanced Driving Assistance System), audio host, etc., without
  • the control device can extract facial features from the facial image itself, or it can
  • the DMS transmits the facial image to the visual perception service module through the ZMQ communication method.
  • the visual perception service module extracts facial features from the facial image and returns the facial features to the DMS.
  • the DMS then transmits the facial features to the control device, which then transmits the facial features to the cloud server through the T-BOX.
  • the DMS can also obtain the body configuration data and transmit the body configuration data to the visual perception service module, which is processed by the visual perception service module.
  • the data is CAN (Controller Area Network) data, see Figure 4.
  • the cloud server does not find the target facial feature that matches the facial feature, the cloud server returns a first notification message to the control device through T-BOX.
  • the control device displays a registration interface based on the first notification message, and registers the account data of the target account in the cloud server based on the registration interface.
  • the process of registering the target account's account data in the cloud server based on the registration interface by the control device may be as follows: the driver triggers the registration interface displayed by the control device, the registration interface includes multiple registration options, and the driver may enter registration information in the multiple registration options.
  • the control device sends the registration information to the cloud server via the T-BOX, and the cloud server generates the target account and the account data of the target account based on the registration information, and then establishes the corresponding relationship between the facial features and the target account and stores the account data of the target account.
  • the driver can also actively register account data when driving the vehicle for the first time.
  • the registration process is the same as the above registration process and will not be repeated here.
  • a correspondence between facial features and accounts is pre-established in the cloud server, and the corresponding account is determined based on the facial features.
  • the account data of the corresponding account can also be obtained through the facial features.
  • Step 203 The control device receives the account data of the target account sent by the cloud server, where the account data includes reminder configuration information corresponding to the abnormal driving status.
  • the cloud server After the cloud server obtains the account data of the target account, it sends the account data of the target account to the control device through T-BOX, and the control device receives and stores the account data of the target account locally.
  • control device stores the account data of the target account locally, and can subsequently obtain the corresponding reminder method directly from the local account data without the need to interact with the cloud server, which greatly shortens the time.
  • the cloud server when the cloud server sends the target account's account data to the control device, it can also send the corresponding relationship between the target facial features and the target account to the control device.
  • the control device stores the corresponding relationship between the target facial features and the target account locally, so that the next time the driver drives the vehicle, he can directly compare the facial features locally without interacting with the cloud server, further shortening the time.
  • the control device can delete the less frequently used account data and the corresponding relationship between the account and the facial features at regular intervals.
  • Step 204 The control device determines the frequency and duration of eye closure of the driver within a first preset time period based on the facial image.
  • the control device collects facial images in real time or periodically; therefore, the control device acquires multiple facial images. For each facial image, the control device determines the degree of eye closure of the driver in the facial image, and determines whether the driver has closed his eyes based on the degree of eye closure. If the driver has closed his eyes, the control device determines the frequency and duration of eye closure of the driver within a first preset time period based on multiple facial images before and after the facial image.
  • the control device may determine the eye closing frequency and the eye closing duration by itself or through the DMS, and there is no specific limitation on this.
  • the first preset duration may be set and changed as needed, for example, the first preset duration is 30s or 40s, and there is no specific limitation on this.
  • Step 205 The control device determines the driver's fatigue information based on the eye closing frequency and the eye closing duration, where the fatigue information includes a fatigue state and a fatigue level corresponding to the fatigue state.
  • the control device determines that the driver's fatigue state is fatigue and the fatigue level is a first level.
  • the control device determines that the driver's fatigue state is fatigue and the fatigue level is the second level.
  • the control device determines that the driver's fatigue state is fatigue and the fatigue level is the third level.
  • the third frequency is less than the second frequency, and the second frequency is less than the first frequency.
  • the fatigue levels corresponding to the first level, the second level, and the third level increase in sequence, that is, the fatigue level of the third level is greater than the fatigue level of the second level, and the fatigue level of the second level is greater than the fatigue level of the first level.
  • the third level is severe fatigue
  • the second level is moderate fatigue
  • the first level is mild fatigue.
  • the first frequency, the second frequency, the third frequency, the first duration, the second duration and the third duration can all be set and changed as needed.
  • the first frequency is 9 times
  • the second frequency is 3 times
  • the third frequency is 2 times
  • the first duration is 1s
  • the second duration is 3s
  • the third duration is 5s.
  • the control device determines that the driver is slightly fatigued. If the driver's eye closing frequency reaches 3 times within 30s, and the eye closing duration each time is greater than 3s but less than 4s, the control device determines that the driver is moderately fatigued. If the driver's eye closing frequency reaches 2 times within 30s, and the eye closing duration each time is greater than 5s, the control device determines that the driver is severely fatigued.
  • control device may first execute steps 202-203 and then execute steps 204-205, or may first execute steps 204-205 and then execute steps 202-203, and there is no specific limitation on this.
  • Step 206 When the driver's fatigue state is fatigue, the control device obtains a first correspondence between the fatigue level and the reminder method from the reminder configuration information corresponding to the abnormal driving state.
  • the control device stores the account data of the target account locally.
  • the control device obtains a first corresponding relationship from the account data of the target account stored locally.
  • the first corresponding relationship is a corresponding relationship between fatigue level and reminder method. Different fatigue levels correspond to different reminder methods.
  • the reminder method corresponding to the same fatigue level in the first correspondence may be the default reminder method of the control device, and the same fatigue level may correspond to one or more reminder methods.
  • the reminder method corresponding to the same fatigue level in the first correspondence is an effective reminder method, and the effective reminder method is a reminder method that can alleviate the driver's fatigue level, and the effective reminder method may be one or more.
  • different accounts correspond to different reminder methods in the first corresponding relationship, that is, different drivers correspond to different reminder methods when they are driving fatigued, because some reminder methods are effective for the first object, and some reminder methods are effective for the second object.
  • the effective reminder method for the first driver is to control the device to simulate other people to have a virtual conversation with him
  • the effective reminder method for the second driver is to control the device to control the knocking device to knock the driver.
  • control device establishes a corresponding relationship between the fatigue level and the reminder method according to the effective reminder method corresponding to the driver, so as to effectively remind the driver when the driver is driving fatigued. To effectively relieve the driver's fatigue.
  • Step 207 The control device determines a first reminder method corresponding to the fatigue level from the first corresponding relationship based on the fatigue level corresponding to the fatigue state.
  • the control device randomly selects a reminder method or selects a reminder method in sequence from the reminder methods corresponding to the fatigue level in the first corresponding relationship based on the fatigue level.
  • the reminder methods corresponding to the first level include sounding an alarm and opening windows for ventilation
  • the reminder methods corresponding to the second level include the control device simulating a virtual conversation with other people
  • the reminder methods corresponding to the third level include the control device controlling the spraying device to spray liquid in the direction of the driver, and the control device taking over the steering wheel to control the vehicle's driving.
  • the spraying device can be set on one side of the main driver's seat, and the knocking device can be set inside the backrest of the main driver's seat.
  • the control device randomly selects one reminder method from the two reminder methods corresponding to the first level.
  • the control device determines an effective reminder method corresponding to the fatigue level from the first corresponding relationship based on the fatigue level.
  • the effective reminder method corresponding to the first level is opening the window for ventilation
  • the effective reminder method corresponding to the second level is the control device simulating other people to have a virtual conversation with them
  • the effective reminder method corresponding to the third level is the control device controlling the spraying device to spray liquid in the direction of the driver.
  • the control device selects the effective reminder method corresponding to the second level.
  • Step 208 The control device reminds the driver based on the first reminder method.
  • the control device when the driver is driving the vehicle for the first time, the control device reminds the driver based on the first reminder method corresponding to the fatigue level, and then determines whether the driver's fatigue level is relieved within the second preset time period, that is, whether the fatigue level decreases.
  • the control device uses the reminder method as a valid reminder method and updates the first corresponding relationship based on the valid reminder method.
  • the control device reselects the first reminder method from the reminder methods corresponding to the fatigue level, and reminds the driver based on the reselected first reminder method until a valid reminder method is selected.
  • the control device will remind the driver based on the effective reminder method, and then determine whether the driver's fatigue level is relieved within the second preset time period, that is, whether the fatigue level has decreased. If the driver's fatigue level has decreased, no other operations are required. If the driver's fatigue level has not decreased, and there are multiple effective reminder methods corresponding to the fatigue level, the control device will reselect the effective reminder method, and remind the driver based on the reselected effective reminder method until an effective reminder method that can reduce the driver's fatigue level is selected. If the driver's fatigue level has not decreased, and there is only one effective reminder method corresponding to the fatigue level, the control device will select the first reminder method from the default reminder method to remind the driver.
  • the process of the control device determining whether the driver's fatigue level is alleviated within the second preset time period is the same as the process of determining the driver's fatigue state, which will not be repeated here.
  • the control device when the control device takes over the steering wheel, the control device controls the vehicle driving to remind the driver.
  • the control device may first output a voice message to remind the driver that the control device is about to take over the steering wheel, and then the control device controls the vehicle driving.
  • the control device may control the vehicle to travel according to the type of road it is on. For example, if the vehicle is on a highway, the control device may determine the location of the service area closest to the current location and control the vehicle to travel to the service area. For another example, if the vehicle is on a city road, the control device may determine the parking lot or parking area closest to the current location and control the vehicle to travel to the parking lot or parking area.
  • the embodiment of the present application provides a driving status monitoring method.
  • the account data of the driver's target account is obtained from the cloud server, and the account data includes reminder configuration information corresponding to the abnormal driving state, that is, the reminder method adapted to the driver in the abnormal driving state is obtained.
  • the reminder method adapted to the user in the fatigue state is obtained to remind the driver, which can improve the reminder effect, thereby ensuring the user's safe driving, and further reducing the incidence of traffic accidents.
  • the user first registers an account through face recognition when using the vehicle for the first time, and can automatically log in and call up the set account data when getting on the vehicle later.
  • the user's age, gender, and driving behavior can be automatically identified, and judgments can be made in combination with scene brain technology, and the user can be reminded through voice broadcasts, phone calls, music, etc. These active reminder behaviors can enhance driving safety and provide effective driving pleasure.
  • the control device can determine the actual gaze area of the driver's line of sight based on the face image; when the actual gaze area does not match the theoretical gaze area, determine that the driver is in a distracted state; obtain a second correspondence between the abnormal state and the reminder method from the reminder configuration information corresponding to the abnormal driving state; obtain a second reminder method corresponding to the distracted state from the second correspondence; and remind the driver based on the second reminder method.
  • the control device extracts eye features from the face image, determines the driver's line of sight direction based on the eye features, and determines the actual gaze area based on the line of sight direction; then determines whether the actual gaze area is the theoretical gaze area. If the actual gaze area is the theoretical gaze area, it is determined that the driver is not in a distracted state. If the actual gaze area is not the theoretical gaze area, that is, the actual gaze area does not match the theoretical gaze area, it is determined that the driver is in a distracted state.
  • the theoretical gaze area may be set and changed as needed.
  • the theoretical gaze area may be a rearview mirror, a front windshield, a reflector, an instrument panel, etc., and no specific limitation is made to this.
  • control device can determine the actual gaze area based on the driver's head posture direction, and then determine whether the driver is in a distracted state based on the actual gaze area.
  • the control device When the driver is in a distracted state, the control device obtains a second corresponding relationship from the reminder configuration information corresponding to the abnormal driving state, where the second corresponding relationship is a corresponding relationship between the abnormal state and the reminder method, and one abnormal state corresponds to one or more reminder methods.
  • the control device obtains a second reminder method corresponding to the distracted state from the second corresponding relationship, and reminds the driver based on the second reminder method.
  • the control device directly reminds the driver based on the second reminder method.
  • the control device can randomly select one reminder method from the multiple second reminder methods to remind the driver. After reminding the driver through the selected second reminder method, determine whether the driver is still in a distracted state. If the driver is still in a distracted state, reselect the second reminder method from multiple second reminder methods until the driver changes from a distracted state to a non-distracted state after the driver is reminded based on the second reminder method; if the driver is no longer distracted, mark the second reminder method, and subsequently use the second reminder method to remind the driver first.
  • the second reminder method can be set and changed as needed, and there is no specific limitation on this.
  • the control device detects the driver's hand based on the face image; when it is detected that the driver's hand is holding the electronic device, the distance between the driver's hand and the ear is determined; when the distance is less than a preset distance, it is determined that the driver is in a call state; a third reminder method corresponding to the call state is obtained from the second corresponding relationship; the driver is reminded based on the third reminder method; when the distance is not less than the preset distance, it is determined that the driver is not in a call state,
  • the control device detects the driver's hands based on the facial image; if it is detected that the driver's hands are holding a smoking object, the driver's mouth is detected; if it is detected that the smoking object is in the driver's mouth, it is determined that the driver is in a smoking state; a fourth reminder method corresponding to the smoking state is obtained from the second corresponding relationship; and the driver is reminded based on the fourth reminder method.
  • control device can also obtain the smoke concentration in the vehicle, and when the smoke concentration is greater than a preset concentration, determine the environment in which the vehicle is located; determine the ventilation method based on the environment in which the vehicle is located; and ventilate the vehicle based on the ventilation method.
  • the control device detects the driver's hand state from the face image, and when the driver's hand is detected and the hand is holding an object, it determines whether the object is a smoking object. If the object is a smoking object, the driver's mouth is detected; if the smoking object is detected in the driver's mouth, it is determined that the driver is in a smoking state.
  • the control device can also input the face image into the recognition model, and score the driver's smoking behavior through the recognition model. If the score exceeds the second scoring threshold, it is determined that the driver is in a smoking state; if the score does not exceed the second scoring threshold, it is determined that the driver is not in a smoking state.
  • the process of the control device reminding the driver based on the third reminder method or the fourth reminder method is the same as the process of reminding the driver based on the second reminder method, which will not be repeated here.
  • the control device can also detect the smoke concentration through the sensor in the vehicle, and determine the environment of the vehicle when the smoke concentration is greater than the preset concentration.
  • Different environments correspond to different ventilation methods. Ventilation is performed based on the corresponding ventilation method to improve the air quality in the vehicle. For example, if the vehicle is in a rainy or snowy environment, the ventilation method can be to turn on the air conditioner. If the vehicle is in a sunny environment, the ventilation method can be to open the window for ventilation.
  • the account data of the target account also includes the identity information of the driver; accordingly, the control device can also broadcast or recommend to the driver according to the driver's emotion type and identity information.
  • the process can be: the control device determines the driver's emotion type based on facial features; when the driver's emotion type is positive, the driver's identity information is obtained from the account data of the target account; based on the positive emotion and identity information, a voice message is broadcast to the driver or music is recommended.
  • control device determines the driver's mouth features based on facial features.
  • the driver's mouth features are upturned corners of the mouth, slightly open mouth, or open mouth with teeth exposed, it is determined that the driver is in a happy state, that is, the driver's emotion type is positive emotion.
  • the control device obtains the driver's identity information, the identity information includes gender, age, etc. Based on the positive emotion and identity information, the control device recommends music that matches the positive emotion and identity information to the driver, or broadcasts a voice message that matches the positive emotion and identity information.
  • the account data of the target account also includes the vehicle body configuration data; accordingly, the control device can also automatically adjust the position of the seat and the rearview mirror.
  • the process can be: the control device obtains the position information of the main driver's seat and the position information of the rearview mirror from the vehicle body configuration data; based on the position information of the main driver's seat and the position information of the rearview mirror, the position of the main driver's seat and the position of the rearview mirror are adjusted.
  • the vehicle body configuration data stores the corresponding main driver's seat position information and rearview mirror position information when the driver drove the vehicle in the past.
  • the control device automatically adjusts the main driver's seat position and rearview mirror position information based on the historically stored main driver's seat position information and rearview mirror position information.
  • the driver can manually adjust the position of the main driver's seat and the position of the rearview mirror, and the control device stores the position of the main driver's seat and the position of the rearview mirror.
  • the position of the main driver's seat and the position of the rearview mirror can be automatically adjusted to meet the driver's needs.
  • control device may also obtain the height of the steering wheel from the account data of the target account, and automatically adjust the height of the steering wheel based on the obtained steering wheel height after the driver gets in the vehicle.
  • the control device can also heat the main driver's seat.
  • the process can be: when the vehicle is powered on, the control device obtains the temperature outside the vehicle, and when the temperature is less than the preset temperature, the heating function of the main driver's seat is turned on; when the temperature is not less than the preset temperature, the heating function of the main driver's seat is not turned on.
  • the control device displays an interactive interface, and a function button for turning on heating is displayed on the interactive interface. In response to detecting that the function button for turning on heating is triggered, the control device turns on the heating function of the main driver's seat.
  • control device After the control device turns on the heating function of the main driver's seat, it can output a voice message and/or display a message pop-up box on the interactive interface, so that the user knows that the heating function has been turned on.
  • the main driver's seat can also support more seat posture adjustments. In addition to the regular adjustments of level, height and backrest, it also supports adjustments in the directions of leg rest, shoulder, etc. to achieve a comfortable sitting posture. It also supports heating, ventilation, massage, memory and other functions.
  • fatigue perception, gaze perception, distraction perception, behavior perception and other algorithms can be used to monitor the driver's driving state, and the driver can be reminded in time when the driver is in an abnormal driving state, thereby ensuring the driver's safe driving.
  • control device can also take the initiative to care for the driver.
  • the driver can actively ventilate to improve the air quality in the car.
  • it can also automatically adjust the driver's commonly used settings according to the driver's driving habits, thereby improving the user experience.
  • FIG5 is a schematic diagram of the structure of a driving state monitoring device provided in an embodiment of the present application.
  • the device includes:
  • a first acquisition module 501 is used to acquire a facial image of a driver of a vehicle
  • Extraction module 502 for extracting the driver's facial features based on the facial image, and sending the facial features to the cloud server.
  • the receiving module 503 is used to receive the account data of the target account sent by the cloud server;
  • a first determination module 504 is used to determine the frequency and duration of eye closure of the driver within a first preset time period based on the face image;
  • a second determination module 505 is used to determine the driver's fatigue information based on the eye closing frequency and the eye closing duration, where the fatigue information includes a fatigue state and a fatigue level corresponding to the fatigue state;
  • the second acquisition module 506 is used to acquire a first correspondence between a fatigue level and a reminder method from the account data of the target account when the driver is driving fatigued;
  • a third determining module 507 configured to determine, based on the fatigue level corresponding to the fatigue state, a first reminder method corresponding to the fatigue level from the first corresponding relationship;
  • the reminder module 508 is configured to remind the driver based on a first reminder method.
  • the second determination module 505 is used to determine that the driver's fatigue state is fatigue and the fatigue level is the first level when the eye-closing frequency reaches a first frequency and the eye-closing duration is greater than the first duration but less than the second duration; determine that the driver's fatigue state is fatigue and the fatigue level is the second level when the eye-closing frequency reaches a second frequency and the eye-closing duration is greater than the second duration but less than a third duration; determine that the driver's fatigue state is fatigue and the fatigue level is the third level when the eye-closing frequency reaches a third frequency and the eye-closing duration is greater than the third duration; wherein the third frequency is less than the second frequency, the second frequency is less than the first frequency, and the fatigue degrees corresponding to the first level, the second level and the third level increase in sequence.
  • the device further includes:
  • a fourth determination module used to determine the actual gaze area of the driver's line of sight based on the face image
  • a fifth determination module configured to determine that the driver is in a distracted state when the actual gaze area does not match the theoretical gaze area
  • a third acquisition module is used to acquire a second corresponding relationship between the abnormal state and the reminder method from the reminder configuration information corresponding to the abnormal driving state;
  • a fourth acquisition module used for acquiring a second reminder method corresponding to the distraction state from the second corresponding relationship
  • the reminding module 508 is further configured to remind the driver based on the second reminding method.
  • the device further includes:
  • a first detection module used for detecting the driver's hands based on the face image
  • a sixth determination module configured to determine the distance between the driver's hand and the ear when it is detected that the driver's hand is holding the electronic device
  • a seventh determination module configured to determine that the driver is in a call state when the distance is less than a preset distance
  • a fifth acquisition module used to acquire a third reminder method corresponding to the call status from the second corresponding relationship
  • the reminding module 508 is further configured to remind the driver based on a third reminding method.
  • the device further includes:
  • the second detection module is used to detect the driver's mouth when it is detected that the driver's hand is holding a smoking object
  • an eighth determination module configured to determine that the driver is in a smoking state when a smoking object is detected in the driver's mouth
  • an eighth determination module for obtaining the smoke concentration in the vehicle, and determining the environment in which the vehicle is located when the smoke concentration is greater than a preset concentration
  • a ninth determination module for determining a ventilation mode based on the environment in which the vehicle is located
  • the ventilation module is used for ventilating the vehicle based on a ventilation mode.
  • the account data of the target account further includes the identity information of the driver; and the device further includes:
  • a tenth determination module for determining the driver's emotion type based on facial features
  • a sixth acquisition module configured to acquire the driver's identity information from the account data of the target account when the driver's emotion type is positive emotion
  • the recommendation module is used to broadcast voice messages or recommend music to the driver based on positive emotions and identity information.
  • the account data of the target account further includes vehicle body configuration data; and the device further includes:
  • a seventh acquisition module used to acquire the position information of the main driver's seat and the position information of the rearview mirror from the vehicle body configuration data
  • the adjustment module is used to adjust the position of the main driver's seat and the position of the rearview mirror based on the position information of the main driver's seat and the position information of the rearview mirror.
  • the embodiment of the present application provides a driving status monitoring device.
  • the account data of the driver's target account is obtained from the cloud server based on face recognition technology, and the account data Including reminder configuration information corresponding to abnormal driving status, that is, obtaining reminder methods suitable for drivers in abnormal driving status.
  • the reminder method suitable for the user in the fatigue state is obtained to remind the driver, which can improve the reminder effect, thereby ensuring the user's safe driving and reducing the incidence of traffic accidents.
  • the driving state monitoring device provided in the above embodiment only uses the division of the above functional modules as an example when performing driving state monitoring.
  • the above functions can be assigned to different functional modules as needed, that is, the internal structure of the control device is divided into different functional modules to complete all or part of the functions described above.
  • the driving state monitoring device provided in the above embodiment and the driving state monitoring method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
  • the structural block diagram of the control device can be seen in FIG6 .
  • the control device 600 may have relatively large differences due to different configurations or performances, and may include a processor (central processing unit, CPU) 601 and a memory 602, wherein the memory 602 stores at least one program code, and the at least one program code is loaded and executed by the processor 601 to implement the driving state monitoring method in the above embodiment.
  • the control device 600 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output.
  • the control device 600 may also include other components for implementing device functions, which will not be described in detail here.
  • a computer-readable storage medium which stores at least one program code, which is loaded and executed by a processor to implement the driving state monitoring method in the above embodiment.
  • the storage medium can be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium can be a ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk and optical data storage device, etc.
  • a computer program product is further provided.
  • the computer program product stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the above The driving state monitoring method in the above embodiment.
  • the computer program product involved in the embodiments of the present application may be deployed and executed on a control device, or on multiple control devices located at one location, or on multiple control devices distributed at multiple locations and interconnected by a communication network.
  • Multiple control devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种驾驶状态监测方法，属于车辆技术领域，该驾驶状态监测方法从驾驶员的人脸图像中提取驾驶员的人脸特征，向云服务器发送人脸特征，通过云服务器确定人脸特征对应的目标账号，获取目标账号的账号数据，账号数据包括异常驾驶状态对应的提醒配置信息。并且，根据人脸图像确定驾驶员的疲劳状态，在驾驶员疲劳驾驶时，从异常驾驶状态对应的提醒配置信息中获取与疲劳等级对应的提醒方式，通过该提醒方式提醒驾驶员，从而保障用户的驾驶安全性，进而降低交通事故的发生率。还公开了一种驾驶状态监测装置、一种控制设备、一种计算机可读存储介质以及一种计算机程序产品。

Description

驾驶状态监测方法、装置、设备、存储介质及产品
本申请要求于2023年6月29日提交的申请号为202310789333.6、发明名称为“驾驶状态监测方法、装置、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及车辆技术领域，特别涉及一种驾驶状态监测方法、装置、设备、存储介质及产品。
背景技术
随着车辆使用量的不断增加，交通事故的发生率也在不断增长。其中，发生交通事故很重要的一个因素就是疲劳驾驶。当用户长时间驾驶车辆时，会出现精神困倦、四肢无力、注意力不集中以及判断力下降等情况，而这些情况均会影响用户在驾驶车辆过程中的安全性，从而造成交通事故。因此，如何保障用户的驾驶安全性，从而降低交通事故的发生率，便成为了本领域一个亟待解决的问题。
发明内容
本申请实施例提供了一种驾驶状态监测方法、装置、设备、存储介质及产品，可以在用户疲劳驾驶时，及时提醒用户，从而保障用户的驾驶安全性，降低交通事故的发生率。所述技术方案如下：
一方面，提供了一种驾驶状态监测方法，所述方法包括：
获取车辆的驾驶员的人脸图像；
基于所述人脸图像，提取所述驾驶员的人脸特征，向云服务器发送所述人脸特征；其中，所述云服务器用于基于所述人脸特征，确定所述驾驶员的目标账号，获取所述目标账号的账号数据，所述账号数据包括异常驾驶状态对应的提醒配置信息；
接收所述云服务器发送的所述目标账号的账号数据；
基于所述人脸图像，确定所述驾驶员在第一预设时长内的闭眼频率和闭眼 时长；
基于所述闭眼频率和所述闭眼时长，确定所述驾驶员的疲劳信息，所述疲劳信息包括疲劳状态和疲劳状态对应的疲劳等级；
在所述疲劳状态为疲劳的情况下，从所述异常驾驶状态对应的提醒配置信息中获取疲劳等级与提醒方式的第一对应关系；
基于所述疲劳状态对应的疲劳等级，从所述第一对应关系中确定所述疲劳等级对应的第一提醒方式；
基于所述第一提醒方式提醒所述驾驶员。
在一种可能的实现方式中，所述基于所述闭眼频率和所述闭眼时长，确定所述驾驶员的疲劳信息，包括：
在所述闭眼频率达到第一频率，且闭眼时长大于第一时长但小于第二时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第一等级；
在所述闭眼频率达到第二频率，且闭眼时长大于所述第二时长但小于第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第二等级；
在所述闭眼频率达到第三频率，且所述闭眼时长大于所述第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第三等级；其中，所述第三频率小于所述第二频率，所述第二频率小于所述第一频率，所述第一等级、所述第二等级和所述第三等级分别对应的疲劳程度依次增大。
在另一种可能的实现方式中，所述方法还包括：
基于所述人脸图像，确定所述驾驶员视线的实际注视区域；
在所述实际注视区域与理论注视区域不匹配的情况下，确定所述驾驶员处于分心状态；
从所述异常驾驶状态对应的提醒配置信息中获取异常状态与提醒方式的第二对应关系；
从所述第二对应关系中获取所述分心状态对应的第二提醒方式；
基于所述第二提醒方式提醒所述驾驶员。
在另一种可能的实现方式中，所述方法还包括：
基于所述人脸图像，对所述驾驶员的手部进行检测；
在检测到所述驾驶员的手部持握电子设备的情况下，确定所述驾驶员的手部与耳部之间的距离；
在所述距离小于预设距离的情况下，确定所述驾驶员处于通话状态；
从所述第二对应关系中获取所述通话状态对应的第三提醒方式；
基于所述第三提醒方式提醒所述驾驶员。
在另一种可能的实现方式中，所述方法还包括：
在检测到所述驾驶员的手部持握发烟物体的情况下，对所述驾驶员的嘴部进行检测；
在检测到所述发烟物体含在所述驾驶员的嘴部的情况下，确定所述驾驶员处于抽烟状态；
获取所述车辆内的烟雾浓度，在所述烟雾浓度大于预设浓度的情况下，确定所述车辆所处环境；
基于所述车辆所处环境，确定通风方式；
基于所述通风方式对所述车辆进行通风。
在另一种可能的实现方式中，所述目标账号的账号数据还包括所述驾驶员的身份信息；所述方法还包括：
基于所述人脸特征，确定所述驾驶员的情绪类型；
在所述驾驶员的情绪类型为正面情绪的情况下，从所述目标账号的账号数据中获取所述驾驶员的身份信息；
基于所述正面情绪和所述身份信息，为所述驾驶员播报语音消息或者推荐音乐。
在另一种可能的实现方式中，所述目标账号的账号数据还包括车身配置数据；所述方法还包括：
从所述车身配置数据中获取主驾驶座椅的位置信息以及后视镜的位置信息；
基于所述主驾驶座椅的位置信息以及所述后视镜的位置信息，调整所述主驾驶座椅的位置和所述后视镜的位置。
另一方面，提供了一种驾驶状态监测装置，所述装置包括：
第一获取模块，用于获取车辆的驾驶员的人脸图像；
提取模块，用于基于所述人脸图像，提取所述驾驶员的人脸特征，向云服务器发送所述人脸特征；其中，所述云服务器用于基于所述人脸特征，确定所 述驾驶员的目标账号，获取所述目标账号的账号数据，所述账号数据包括异常驾驶状态对应的提醒配置信息；
接收模块，用于接收所述云服务器发送的所述目标账号的账号数据；
第一确定模块，用于基于所述人脸图像，确定所述驾驶员在第一预设时长内的闭眼频率和闭眼时长；
第二确定模块，用于基于所述闭眼频率和所述闭眼时长，确定所述驾驶员的疲劳信息，所述疲劳信息包括疲劳状态和疲劳状态对应的疲劳等级；
第二获取模块，用于在所述疲劳状态为疲劳的情况下，从所述异常驾驶状态对应的提醒配置信息中获取疲劳等级与提醒方式的第一对应关系；
第三确定模块，用于基于所述疲劳状态对应的疲劳等级，从所述第一对应关系中确定所述疲劳等级对应的第一提醒方式；
提醒模块，用于基于所述第一提醒方式提醒所述驾驶员。
在一种可能的实现方式中，所述第二确定模块，用于在所述闭眼频率达到第一频率，且闭眼时长大于第一时长但小于第二时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第一等级；在所述闭眼频率达到第二频率，且闭眼时长大于所述第二时长但小于第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第二等级；在所述闭眼频率达到第三频率，且所述闭眼时长大于所述第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第三等级；其中，所述第三频率小于所述第二频率，所述第二频率小于所述第一频率，所述第一等级、所述第二等级和所述第三等级分别对应的疲劳程度依次增大。
在另一种可能的实现方式中，所述装置还包括：
第四确定模块，用于基于所述人脸图像，确定所述驾驶员视线的实际注视区域；
第五确定模块，用于在所述实际注视区域与理论注视区域不匹配的情况下，确定所述驾驶员处于分心状态；
第三获取模块，用于从所述异常驾驶状态对应的提醒配置信息中获取异常状态与提醒方式的第二对应关系；
第四获取模块，用于从所述第二对应关系中获取所述分心状态对应的第二提醒方式；
所述提醒模块，还用于基于所述第二提醒方式提醒所述驾驶员。
在另一种可能的实现方式中，所述装置还包括：
第一检测模块，用于基于所述人脸图像，对所述驾驶员的手部进行检测；
第六确定模块，用于在检测到所述驾驶员的手部持握电子设备的情况下，确定所述驾驶员的手部与耳部之间的距离；
第七确定模块，用于在所述距离小于预设距离的情况下，确定所述驾驶员处于通话状态；
第五获取模块，用于从所述第二对应关系中获取所述通话状态对应的第三提醒方式；
所述提醒模块，还用于基于所述第三提醒方式提醒所述驾驶员。
在另一种可能的实现方式中，所述装置还包括：
第二检测模块，用于在检测到所述驾驶员的手部持握发烟物体的情况下，对所述驾驶员的嘴部进行检测；
第八确定模块，用于在检测到所述发烟物体含在所述驾驶员的嘴部的情况下，确定所述驾驶员处于抽烟状态；
第八确定模块，用于获取所述车辆内的烟雾浓度，在所述烟雾浓度大于预设浓度的情况下，确定所述车辆所处环境；
第九确定模块，用于基于所述车辆所处环境，确定通风方式；
通风模块，用于基于所述通风方式对所述车辆进行通风。
在另一种可能的实现方式中，所述目标账号的账号数据还包括所述驾驶员的身份信息；所述装置还包括：
第十确定模块，用于基于所述人脸特征，确定所述驾驶员的情绪类型；
第六获取模块，用于在所述驾驶员的情绪类型为正面情绪的情况下，从所述目标账号的账号数据中获取所述驾驶员的身份信息；
推荐模块，用于基于所述正面情绪和所述身份信息，为所述驾驶员播报语音消息或者推荐音乐。
在另一种可能的实现方式中，所述目标账号的账号数据还包括车身配置数据；所述装置还包括：
第七获取模块，用于从所述车身配置数据中获取主驾驶座椅的位置信息以及后视镜的位置信息；
调整模块，用于基于所述主驾驶座椅的位置信息以及所述后视镜的位置信息，调整所述主驾驶座椅的位置和所述后视镜的位置。
另一方面，提供了一种控制设备，所述控制设备包括处理器和存储器，所述存储器中存储有至少一条程序代码，所述至少一条程序代码由所述处理器加载并执行，以实现上述任一项所述的驾驶状态监测方法。
另一方面，提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有至少一条程序代码，所述至少一条程序代码由处理器加载并执行，以实现上述任一项所述的驾驶状态监测方法。
另一方面，提供了一种计算机程序产品，所述计算机程序产品中存储有至少一条程序代码，所述至少一条程序代码由处理器加载并执行，以实现上述任一项所述的驾驶状态监测方法。
本申请实施例提供了一种驾驶状态监测方法，当驾驶员驾驶车辆时，基于人脸识别技术，从云服务器中获取驾驶员的目标账号的账号数据，而账号数据包括异常驾驶状态对应的提醒配置信息，也即获取到适配于驾驶员在异常驾驶状态下的提醒方式。而当基于人脸识别技术识别到驾驶员疲劳驾驶时，基于该驾驶员的异常状态对应的提醒配置信息，获取到驾驶员在疲劳状态下适配于用户的提醒方式对驾驶员进行提醒，能够提高提醒的效果，从而保障用户的安全驾驶，进而降低交通事故的发生率。
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的，并不能限制本公开。
附图说明
图1是本申请实施例提供的一种驾驶状态监测方法的实施环境的示意图；
图2是本申请实施例提供的一种驾驶状态监测方法的流程图；
图3是本申请实施例提供的一种控制设备与云服务器之间交互的示意图；
图4是本申请实施例提供的一种控制设备通过DMS进行数据处理的示意图；
图5是本申请实施例提供的一种驾驶状态监测装置的结构示意图；
图6是本申请实施例提供的一种控制设备的结构框图。
具体实施方式
为使本申请的技术方案和优点更加清楚，下面对本申请实施方式作进一步地详细描述。
本申请的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们的任意变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
需要说明的是，本申请所涉及的信息(包括但不限于用户设备信息、用户个人信息等)、数据(包括但不限于用于分析的数据、存储的数据、展示的数据等)以及信号，均为经用户授权或者经过各方充分授权的，且相关数据的收集、使用和处理需要遵守相关国家和地区的相关法律法规和标准。例如，本申请中涉及到的人脸图像、情绪类型、账号数据等都是在充分授权的情况下获取的。
图1是本申请实施例提供的一种驾驶状态监测方法的实施环境的示意图，该实施环境包括：摄像模组10、控制设备11、云服务器12和T-BOX13(Telematics BOX，信息处理器)，其中，摄像模组10、控制设备11和T-BOX13位于同一车辆中，该车辆可以为燃油车辆、电动车辆或者混动车辆，对此不作具体限定。
在本申请实施例中，摄像模组10可以采集驾驶员的人脸图像，向控制设备11发送人脸图像。控制设备11提取人脸图像中的人脸特征，向T-BOX13发送人脸特征，T-BOX13向云服务器12转发人脸特征，云服务器12将该人脸特征与云端数据库中存储的人脸特征进行比对，确定该人脸特征对应的目标账号，获取目标账号的账号数据，通过T-BOX13向控制设备11发送目标账号的账号数据，控制设备11接收并在本地存储目标账号的账号数据，目标账号为该驾驶 员在云服务器中注册的账号，目标账号的账号数据为目标账号关联的相关数据；例如，目标账号的账号数据包括异常驾驶状态对应的提醒配置信息，异常驾驶状态是指可能发生交通事故的驾驶状态，异常驾驶状态对应的提醒配置信息包括疲劳等级与提醒方式的第一对应关系，异常驾驶状态对应的提醒配置信息还包括异常状态与提醒方式的第二对应关系；目标账号的账号数据还包括驾驶员的身份信息，目标账号的账号数据还包括主驾驶座椅的位置信息以及后视镜的位置信息。
并且，控制设备11获取人脸图像后，可以基于人脸图像确定驾驶员的驾驶状态，该驾驶状态包括：疲劳状态、分心状态、通话状态、抽烟状态等，根据驾驶员的驾驶状态，从目标账号的账号数据中获取相应的提醒方式，进而基于获取到的提醒方式提醒驾驶员。
其中，控制设备11可以为车机或者整车控制器，车机为车载信息娱乐产品的简称，包括车机主机和显示屏幕。云服务器12可以为一台服务器、由多台服务器组成的服务器集群、云计算平台和虚拟化中心中的至少一种。摄像模组10为拍摄位于主驾驶座椅上的驾驶员的摄像头。T-BOX13提供网络传输能力，实现控制设备11与云服务器12之间的数据传输。
在本申请实施例中，控制设备可以监测驾驶员的疲劳状态、分心状态、通话状态以及抽烟状态，并通过监测到的状态对应的提醒方式提醒驾驶员。下面先介绍一下对疲劳状态的监测过程。
图2是本申请实施例提供的一种驾驶状态监测方法的流程图，由控制设备执行，参见图2，该方法包括：
步骤201：控制设备获取车辆的驾驶员的人脸图像。
驾驶员为驾驶车辆的人员，也即位于主驾驶座椅上的人员。
本步骤中，摄像模组可以实时或者周期性采集人脸图像，在采集到人脸图像的情况下，向控制设备发送采集的人脸图像，相应的，控制设备接收摄像模组发送的人脸图像。
其中，在摄像模组处于开启状态的情况下，则摄像模组可以直接采集图像。在摄像模组处于关闭状态的情况下，则控制设备可以在显示屏幕上显示状态监测选项，响应于检测到状态监测选项的触发操作，控制设备向摄像模组发送开 启指令，摄像模组进行启动，然后实时或周期性采集人脸图像。
在本申请实施例中，控制设备获取人脸图像后，确定人脸图像的清晰度和完整度，在清晰度或者完整度不符合要求的情况下，则显示或者语音播报提示消息，以提醒用户调整姿势，然后摄像模组重新拍摄驾驶员的人脸图像，然后确定重新拍摄的人脸图像的清晰度和完整度是否符合要求，直到拍摄到清晰度和完整度符合要求的人脸图像为止，从而使得摄像模组拍摄出符合要求的人脸图像。在清晰度和完整度符合要求的情况下，则执行后续步骤。
步骤202：控制设备基于人脸图像，提取驾驶员的人脸特征，向云服务器发送人脸特征。
控制设备从人脸图像中提取人脸特征，通过T-BOX向云服务器发送人脸特征。云服务器将该人脸特征与云端数据库中存储的多个人脸特征进行比对，从多个人脸特征中查找与该人脸特征匹配的目标人脸特征。在云服务器查找到与该人脸特征匹配的目标人脸特征的情况下，则云服务器基于人脸特征与账号的对应关系，确定目标人脸特征对应的目标账号，进而从云端数据库中获取目标账号的账号数据，通过T-BOX向控制设备发送目标账号的账号数据，该过程可以参见图3。
目标账号为该驾驶员在云服务器中注册的账号，目标账号的账号数据为目标账号关联的相关数据；例如，目标账号的账号数据包括异常驾驶状态对应的提醒配置信息，异常驾驶状态是指可能发生交通事故的驾驶状态，异常驾驶状态对应的提醒配置信息包括疲劳等级与提醒方式的第一对应关系，异常驾驶状态对应的提醒配置信息还包括异常状态与提醒方式的第二对应关系；目标账号的账号数据还包括驾驶员的身份信息，驾驶员的身份信息包括驾驶员的性别、年龄等；目标账号的账号数据还包括车身配置数据，车身配置数据包括主驾驶座椅的位置信息以及后视镜的位置信息，车身配置数据还包括方向盘的高度信息以及其他个性化驾驶习惯设置信息，例如，车内氛围灯的亮度、音乐风格类型、HUD(Head Up Display，抬头显示)、ADAS(Advanced Driving Assistance System，高级驾驶辅助系统)、音响主机等，对此不作具体限定。音响主机能够给用户提供蓝牙、手机互连、导航、语音、电话、音乐、视频、游戏、生活服务、小程序等功能。
其中，控制设备可以自身从人脸图像中提取人脸特征，也可以将人脸图像 传递给DMS(Driver Monitor System，驾驶疲劳检测系统)，DMS将人脸图像通过ZMQ的通讯方式传递给视觉感知服务模块，视觉感知服务模块从人脸图像中提取人脸特征，将人脸特征返回给DMS，DMS再传递给控制设备，控制设备再通过T-BOX传递给云服务器。并且，DMS还可以获取车身配置数据，将车身配置数据传递给视觉感知服务模块，由视觉感知服务模块进行处理，该数据为CAN(Controller Area Network，控制器局域网)数据，参见图4。
例如，请继续参见图3，在云服务器没有查找到与该人脸特征匹配的目标人脸特征的情况下，则云服务器通过T-BOX向控制设备返回第一通知消息，控制设备基于第一通知消息，显示注册界面，基于注册界面在云服务器中注册目标账号的账号数据。
其中，控制设备基于注册界面在云服务器中注册目标账号的账号数据过程可以为：驾驶员触发控制设备显示的注册界面，注册界面包括多个注册选项，驾驶员可以在多个注册选项中输入注册信息。响应于获取到注册信息，控制设备通过T-BOX向云服务器发送注册信息，云服务器基于注册信息，生成目标账号以及目标账号的账号数据，然后建立人脸特征与目标账号的对应关系以及存储目标账号的账号数据。
当然，驾驶员也可以在第一次驾驶车辆时主动注册账号数据，该注册过程与上述注册过程同理，这里不再赘述。
在本申请实施例中，在云服务器中预先建立人脸特征与账号的对应关系，根据人脸特征确定相应的账号，这样当用户驾驶其他车辆时，通过人脸特征也可以获取对应账号的账号数据，在用户驾驶其他车辆的过程中，当用户出现疲劳状态或者其他非正常状态时，也可以通过该用户对应的提醒方式提醒用户，从而提高用户驾驶过程中的安全性。
步骤203：控制设备接收云服务器发送的目标账号的账号数据，账号数据包括异常驾驶状态对应的提醒配置信息。
云服务器获取目标账号的账号数据后，通过T-BOX向控制设备发送目标账号的账号数据，控制设备接收并在本地存储目标账号的账号数据。
在本申请实施例中，控制设备在本地存储目标账号的账号数据，后续可以直接从本地的账号数据中获取相应的提醒方式，无需再与云服务器进行交互，大大缩短了时间。
另外，云服务器向控制设备发送目标账号的账号数据时，还可以向控制设备发送目标人脸特征与目标账号的对应关系，控制设备在本地存储目标人脸特征与目标账号的对应关系，这样当下次驾驶员驾驶本车辆时，可以直接从本地进行人脸特征的比对，无需再与云服务器交互，进一步缩短了时间。为避免本地存储数据量过多，影响设备的处理速度，控制设备可以每隔一定时间删除使用频率较少的账号数据及账号与人脸特征的对应关系。
步骤204：控制设备基于人脸图像，确定驾驶员在第一预设时长内的闭眼频率和闭眼时长。
在步骤201中控制设备实时或者周期性采集人脸图像；因此，控制设备会获取到多个人脸图像。对于每个人脸图像，控制设备确定该人脸图像中驾驶员的眼睛闭合度，根据眼睛闭合度，确定驾驶员是否闭眼，在驾驶员闭眼的情况下，基于该人脸图像前后相邻的多个人脸图像，确定驾驶员在第一预设时长内的闭眼频率和闭眼时长。
其中，控制设备可以自身确定闭眼频率和闭眼时长，也可以通过DMS确定闭眼频率和闭眼时长，对此不作具体限定。并且，第一预设时长可以根据需要进行设置并更改，例如，第一预设时长为30s或者40s，对此不作具体限定。
步骤205：控制设备基于闭眼频率和闭眼时长，确定驾驶员的疲劳信息，疲劳信息包括疲劳状态和疲劳状态对应的疲劳等级。
在一种可能的实现方式中，在闭眼频率达到第一频率，且闭眼时长大于第一时长但小于第二时长的情况下，控制设备确定驾驶员的疲劳状态为疲劳，且疲劳等级为第一等级。
在另一种可能的实现方式中，在闭眼频率达到第二频率，且闭眼时长大于第二时长但小于第三时长的情况下，控制设备确定驾驶员的疲劳状态为疲劳，且疲劳等级为第二等级。
在另一种可能的实现方式中，在闭眼频率达到第三频率，且闭眼时长大于第三时长的情况下，控制设备确定驾驶员的疲劳状态为疲劳，且疲劳等级为第三等级。
上述三种实现方式中，第三频率小于第二频率，第二频率小于第一频率。并且，第一等级、第二等级和第三等级分别对应的疲劳程度依次增大，也即第三等级的疲劳程度大于第二等级的疲劳程度，第二等级的疲劳程度大于第一等 级的疲劳程度。例如，第三等级为重度疲劳，第二等级为中度疲劳，第一等级为轻度疲劳。
其中，第一频率、第二频率、第三频率、第一时长、第二时长和第三时长均可以根据需要进行设置并更改，例如，第一频率为9次，第二频率为3次，第三频率为2次，第一时长为1s，第二时长为3s，第三时长为5s。相应的，在30s内驾驶员的闭眼频率达到9次，且每次的闭眼时长大于1s但小于2s的情况下，则控制设备确定驾驶员出现轻度疲劳。在30s内驾驶员的闭眼频率达到3次，且每次的闭眼时长大于3s但小于4s的情况下，则控制设备确定驾驶员出现中度疲劳。在30s内驾驶员的闭眼频率达到2次，且每次的闭眼时长大于5s的情况下，则控制设备确定驾驶员出现重度疲劳。
在本申请实施例中，控制设备可以先执行步骤202-203，再执行步骤204-205，也可以先执行步骤204-205，再执行步骤202-203，对此不作具体限定。
步骤206：在驾驶员的疲劳状态为疲劳的情况下，控制设备从异常驾驶状态对应的提醒配置信息中获取疲劳等级与提醒方式的第一对应关系。
控制设备在本地存储目标账号的账号数据，在驾驶员出现疲劳驾驶的情况下，从本地存储的目标账号的账号数据中获取第一对应关系，第一对应关系为疲劳等级与提醒方式的对应关系，不同的疲劳等级对应不同的提醒方式。
其中，在驾驶员第一次驾驶本车辆的情况下，则第一对应关系中同一疲劳等级对应的提醒方式可以为控制设备默认的提醒方式，且同一疲劳等级可以对应一种或多种提醒方式。在驾驶员非首次驾驶本车辆的情况下，则第一对应关系中同一疲劳等级对应的提醒方式为有效提醒方式，有效提醒方式为驾驶员的疲劳程度可以得到缓解的提醒方式，有效提醒方式可以为一种或者多种。
在本申请实施例中，不同的账号对应第一对应关系中不同的提醒方式，也即不同的驾驶员出现疲劳驾驶时，对应不同的提醒方式，这是由于有的提醒方式对第一对象有效，有的提醒方式对第二对象有效。例如，当第一驾驶员和第二驾驶员均处于中度疲劳时，对第一驾驶员的有效提醒方式为控制设备模拟其他人员与其进行虚拟通话，而对第二驾驶员的有效提醒方式为控制设备控制敲击装置敲击驾驶员。
在本申请实施例中，控制设备根据驾驶员对应的有效提醒方式建立疲劳等级与提醒方式的对应关系，从而在驾驶员出现疲劳驾驶时，有效提醒驾驶员， 以有效缓解驾驶员的疲劳状态。
步骤207：控制设备基于疲劳状态对应的疲劳等级，从第一对应关系中确定疲劳等级对应的第一提醒方式。
在驾驶员第一次驾驶本车辆的情况下，则控制设备基于疲劳等级，从第一对应关系中该疲劳等级对应的提醒方式中随机选择一种提醒方式或者按照顺序选择一种提醒方式。
例如，第一等级对应的提醒方式包括发出警报和开窗通风，第二等级对应的提醒方式包括控制设备模拟其他人员与其进行虚拟通话，以及控制设备控制敲击装置敲击驾驶员的背部，第三等级对应的提醒方式包括控制设备控制喷洒装置向驾驶员所处方向喷洒液体，以及控制设备接管方向盘，控制车辆行驶。其中，喷洒装置可以设置在主驾驶座椅的一侧，敲击装置可以设置在主驾驶座椅靠背的内部。则当驾驶员的疲劳等级为第一等级时，控制设备从第一等级对应的两种提醒方式中随机选择一种提醒方式。
在驾驶员非首次驾驶本车辆的情况下，则控制设备基于疲劳等级，从第一对应关系中确定该疲劳等级对应的有效提醒方式。
其中，第一等级对应的有效提醒方式为开窗通风，第二等级对应的有效提醒方式为控制设备模拟其他人员与其进行虚拟通话，第三等级对应的有效提醒方式为控制设备控制喷洒装置向驾驶员所处方向喷洒液体。则当驾驶员的疲劳等级为第二等级时，控制设备选择第二等级对应的有效提醒方式。
上述仅是列举了几种提醒方式，在实际应用中，还可以通过其他提醒方式提醒驾驶员，例如，播放音乐或者增大音乐音量等，对此不作具体限定。
步骤208：控制设备基于第一提醒方式提醒驾驶员。
在本申请实施例中，在驾驶员第一次驾驶本车辆的情况下，则控制设备基于疲劳等级对应的第一提醒方式提醒驾驶员后，确定第二预设时长内驾驶员的疲劳程度是否得到缓解，也即疲劳等级是否下降。在驾驶员的疲劳等级下降的情况下，例如，从中度疲劳缓解为轻度疲劳，或者从轻度疲劳变为清醒，则控制设备将该提醒方式作为有效提醒方式，基于该有效提醒方式更新第一对应关系。在驾驶员的疲劳等级未下降的情况下，则控制设备从该疲劳等级对应的提醒方式中重新选择第一提醒方式，基于重新选择的第一提醒方式提醒驾驶员，直到选择出有效提醒方式为止。
在驾驶员非首次驾驶本车辆的情况下，则控制设备基于有效提醒方式提醒驾驶员后，确定第二预设时长内驾驶员的疲劳程度是否得到缓解，也即疲劳等级是否下降。在驾驶员的疲劳等级下降的情况下，则无需进行其他操作。在驾驶员的疲劳等级未下降的情况下，且该疲劳等级对应的有效提醒方式为多种，则控制设备重新选择有效提醒方式，基于重新选择的有效提醒方式提醒驾驶员，直到选择出能够使驾驶员的疲劳等级下降的有效提醒方式为止。在驾驶员的疲劳等级未下降，且该疲劳等级对应的有效提醒方式为一种，则控制设备从默认的提醒方式中选择第一提醒方式来提醒驾驶员。
其中，控制设备确定第二预设时长内驾驶员的疲劳程度是否得到缓解的过程与确定驾驶员的疲劳状态的过程同理，这里不再赘述。
在本申请实施例中，在控制设备接管方向盘的情况下，由控制设备控制车辆行驶的提醒方式来提醒驾驶员。例如，控制设备可以先输出语音消息，以提醒驾驶员即将由控制设备接管方向盘，然后由控制设备控制车辆行驶。
其中，控制设备可以根据所处道路类型，控制车辆行驶。例如，车辆所处道路为高速公路，则控制设备可以确定距离当前位置最近的服务区所在的位置，控制车辆向服务区行驶。再如，车辆所处道路为城市道路，则控制设备可以确定距离当前位置最近的停车场或者允许停车区域，控制车辆向停车场或者允许停车区域行驶。
本申请实施例提供了一种驾驶状态监测方法，当驾驶员驾驶车辆时，基于人脸识别技术，从云服务器中获取驾驶员的目标账号的账号数据，而账号数据包括异常驾驶状态对应的提醒配置信息，也即获取到适配于驾驶员在异常驾驶状态下的提醒方式。而当基于人脸识别技术识别到驾驶员疲劳驾驶时，基于该驾驶员的异常状态对应的提醒配置信息，获取到驾驶员在疲劳状态下适配于用户的提醒方式对驾驶员进行提醒，能够提高提醒的效果，从而保障用户的安全驾驶，进而降低交通事故的发生率。
在本申请实施例中，用户在第一次使用车辆的时候先通过人脸识别注册账号，后续上车可以自动无感登录并调出已设置的账号数据。在日常驾驶过程中，可以自动识别用户年龄、性别、驾驶行为，并结合场景大脑技术进行判断，通过播报语音、电话、音乐等方式来提醒用户。这些主动式提醒行为可以增强驾驶安全，并提供有效的驾驶乐趣。
接下来介绍一下对分心状态的监测过程。
在本申请实施例中，控制设备可以基于人脸图像，确定驾驶员视线的实际注视区域；在实际注视区域与理论注视区域不匹配的情况下，确定驾驶员处于分心状态；从异常驾驶状态对应的提醒配置信息中获取异常状态与提醒方式的第二对应关系；从第二对应关系中获取分心状态对应的第二提醒方式；基于第二提醒方式提醒驾驶员。
该实现方式中，控制设备从人脸图像中提取眼部特征，根据眼部特征确定驾驶员的视线方向，根据视线方向确定视线的实际注视区域；然后确定该实际注视区域是否为理论注视区域，在实际注视区域为理论注视区域的情况下，则确定驾驶员未处于分心状态，在实际注视区域不是理论注视区域的情况下，也即实际注视区域与理论注视区域不匹配，则确定驾驶员处于分心状态。
其中，理论注视区域可以根据需要进行设置并更改，例如，理论注视区域为后视镜、前风挡、反光镜、仪表盘等，对此不作具体限定。
在控制设备根据眼部特征无法确定驾驶员的实际视线方向的情况下，则控制设备可以根据驾驶员的头姿方向确定实际注视区域，进而基于实际注视区域确定驾驶员是否处于分心状态。
在驾驶员处于分心状态的情况下，控制设备从异常驾驶状态对应的提醒配置信息中获取第二对应关系，第二对应关系为异常状态与提醒方式的对应关系，一种异常状态对应一种或多种提醒方式。控制设备从第二对应关系中获取分心状态对应的第二提醒方式，基于第二提醒方式提醒驾驶员。
在分心状态对应的第二提醒方式为一种的情况下，则控制设备直接基于该第二提醒方式提醒驾驶员。在分心状态对应的第二提醒方式为多种的情况下，则控制设备可以从多种第二提醒方式中随机选择一种提醒方式提醒驾驶员。在通过选择的第二提醒方式提醒驾驶员后，确定驾驶员是否仍处于分心状态，在驾驶员仍处于分心状态的情况下，则重新从多个第二提醒方式中选择第二提醒方式，直到选择出基于该第二提醒方式提醒驾驶员后驾驶员由分心状态更改为未分心状态为止；在驾驶员不再分心的情况下，则标记该第二提醒方式，后续优先采用该第二提醒方式提醒驾驶员。其中，第二提醒方式可以根据需要进行设置并更改，对此不作具体限定。
下面介绍一下通话状态的监测过程。
在本申请实施例中，控制设备基于人脸图像，对驾驶员的手部进行检测；在检测到驾驶员的手部持握电子设备的情况下，确定驾驶员的手部与耳部之间的距离；在该距离小于预设距离的情况下，确定驾驶员处于通话状态；从第二对应关系中获取通话状态对应的第三提醒方式；基于第三提醒方式提醒驾驶员；在该距离不小于预设距离的情况下，确定驾驶员未处于通话状态，
该实现方式中，控制设备从人脸图像中检测驾驶员的手部，在检测到驾驶员的手部，且手部持握物体的情况下，确定该物体是否为电子设备，在该物体为电子设备，则确定驾驶员的手部持握电子设备。这种情况下，控制设备确定驾驶员的手部与耳部之间的距离，在该距离小于预设距离的情况下，则确定驾驶员处于通话状态。或者，控制设备也可以将人脸图像输入识别模型中，通过识别模型对驾驶员的通话行为进行评分，在评分超过第一评分阈值的情况下，确定驾驶员处于通话状态；在评分未超过第一评分阈值的情况下，确定驾驶员未处于通话状态。
接下来介绍一下抽烟状态的监测过程。
在本申请实施例中，控制设备基于人脸图像，对驾驶员的手部进行检测；在检测到驾驶员的手部持握发烟物体的情况下，对驾驶员的嘴部进行检测；在检测到发烟物体含在驾驶员的嘴部的情况下，确定驾驶员处于抽烟状态；从第二对应关系中获取抽烟状态对应的第四提醒方式；基于第四提醒方式提醒驾驶员。
并且，控制设备还可以获取车辆内的烟雾浓度，在烟雾浓度大于预设浓度的情况下，确定车辆所处环境；基于车辆所处环境，确定通风方式；基于通风方式对车辆进行通风。
该实现方式中，控制设备从人脸图像中检测驾驶员的手部状态，在检测到驾驶员的手部，且手部持握物体的情况下，确定该物体是否为发烟物体，在该物体为发烟物体的情况下，则对驾驶员的嘴部进行检测；在检测到发烟物体含在驾驶员的嘴部的情况下，则确定驾驶员处于抽烟状态。或者，控制设备也可以将人脸图像输入识别模型中，通过识别模型对驾驶员的抽烟行为进行评分，在评分超过第二评分阈值的情况下，确定驾驶员处于抽烟状态；在评分未超过第二评分阈值的情况下，确定驾驶员未处于抽烟状态。
需要说明的一点是，控制设备基于第三提醒方式或第四提醒方式提醒驾驶员的过程与基于第二提醒方式提醒驾驶员的过程同理，这里不再赘述。
并且，在驾驶员处于抽烟状态的情况下，控制设备还可以通过车辆内的传感器检测烟雾浓度，在烟雾浓度大于预设浓度的情况下，确定车辆所处环境。不同的环境，对应不同的通风方式。基于相应的通风方式进行通风，从而提升车内空气质量。例如，车辆所处环境为雨天或者雪天，则通风方式可以为开启空调。车辆所处环境为晴天，则通风方式可以为开窗通风。
在本申请实施例中，目标账号的账号数据还包括驾驶员的身份信息；相应的，控制设备还可以根据驾驶员的情绪类型和身份信息为驾驶员进行播报或者推荐。该过程可以为：控制设备基于人脸特征，确定驾驶员的情绪类型；在驾驶员的情绪类型为正面情绪的情况下，从目标账号的账号数据中获取驾驶员的身份信息；基于正面情绪和身份信息，为驾驶员播报语音消息或者推荐音乐。
该实现方式中，控制设备基于人脸特征，确定驾驶员的嘴部特征，在驾驶员的嘴部特征为嘴角上扬、嘴巴微张或者处于张开状态露出牙齿的情况下，则确定驾驶员处于开心状态，也即驾驶员的情绪类型为正面情绪。
在驾驶员的情绪类型为正面情绪的情况下，控制设备获取驾驶员的身份信息，身份信息包括性别、年龄等，控制设备基于正面情绪和身份信息，为驾驶员推荐与正面情绪和身份信息相匹配的音乐，或者播报与正面情绪和身份信息相匹配的语音消息。
在本申请实施例中，目标账号的账号数据还包括车身配置数据；相应的，控制设备还可以自动调节座椅以及后视镜的位置。该过程可以为：控制设备从车身配置数据中获取主驾驶座椅的位置信息以及后视镜的位置信息；基于主驾驶座椅的位置信息以及后视镜的位置信息，调整主驾驶座椅的位置和后视镜的位置。
该实现方式中，在驾驶员非首次驾驶本车辆的情况下，车身配置数据中存储了驾驶员历史驾驶本车时，对应的主驾驶座椅的位置信息以及后视镜的位置信息。在驾驶员上车后，控制设备基于历史存储的主驾驶座椅的位置信息和后视镜的位置信息，自动调整主驾驶座椅的位置和后视镜的位置。
在驾驶员首次驾驶本车辆的情况下，则驾驶员可以手动调整主驾驶座椅的位置和后视镜的位置，控制设备存储主驾驶座椅的位置和后视镜的位置，这样 驾驶员下次驾驶本车辆时，就可以自动调整主驾驶座椅的位置和后视镜的位置，从而满足驾驶员的需求。
在本申请实施例中，控制设备也可以从目标账号的账号数据中获取方向盘的高度，在驾驶员上车后，基于获取到的方向盘高度，自动调整方向盘的高度。
在本申请实施例中，控制设备也可以对主驾驶座椅进行加热。该过程可以为：在车辆处于上电状态的情况下，控制设备获取车辆外部的温度，在该温度小于预设温度的情况下，则开启主驾驶座椅的加热功能，；在该温度不低于预设温度的情况下，则不开启主驾驶座椅的加热功能。或者在车辆处于上电状态的情况下，控制设备显示交互界面，交互界面上显示开启加热的功能按钮，响应于检测到开启加热的功能按钮被触发的触发操作，控制设备开启主驾驶座椅的加热功能。
其中，控制设备开启主驾驶座椅的加热功能后，可以输出语音消息和/或在交互界面显示消息弹框，从而使用户知晓已开启加热功能。
主驾驶座椅还可以支持更多的座椅姿态调节，除了水平、高度、靠背常规调节，还支持腿托、肩部等方向调节来实现舒适坐姿，同时支持加热、通风、按摩、记忆等功能。
在本申请实施例中，可以采用疲劳感知、注视感知、分心感知、行为感知等算法来监测驾驶员的驾驶状态，在驾驶员处于异常驾驶状态时，及时提醒驾驶员，从而保障驾驶员的安全驾驶。
并且，还可以利用图像感知、语音信号处理、语音识别、场景大脑等核心技术，达到预测、主动推荐、语音对话、行为举止等新一代车载人工智能服务。如在驾驶员处于开心状态的情况下，控制设备还可以主动关怀驾驶员，在驾驶员处于抽烟状态的情况下，主动通风，达到提升车内空气质量的目的。另外，还可以根据驾驶员的驾车习惯，自动调整驾驶员常用的设置项，从而提升用户体验。
图5是本申请实施例提供的一种驾驶状态监测装置的结构示意图，参见图5，该装置包括：
第一获取模块501，用于获取车辆的驾驶员的人脸图像；
提取模块502，用于基于人脸图像，提取驾驶员的人脸特征，向云服务器发 送人脸特征；其中，云服务器用于基于人脸特征，确定驾驶员的目标账号，获取目标账号的账号数据，账号数据包括异常驾驶状态对应的提醒配置信息；
接收模块503，用于接收云服务器发送的目标账号的账号数据；
第一确定模块504，用于基于人脸图像，确定驾驶员在第一预设时长内的闭眼频率和闭眼时长；
第二确定模块505，用于基于闭眼频率和闭眼时长，确定驾驶员的疲劳信息，疲劳信息包括疲劳状态和疲劳状态对应的疲劳等级；
第二获取模块506，用于在驾驶员出现疲劳驾驶的情况下，从目标账号的账号数据中获取疲劳等级与提醒方式的第一对应关系；
第三确定模块507，用于基于疲劳状态对应的疲劳等级，从第一对应关系中确定疲劳等级对应的第一提醒方式；
提醒模块508，用于基于第一提醒方式提醒驾驶员。
在一种可能的实现方式中，第二确定模块505，用于在闭眼频率达到第一频率，且闭眼时长大于第一时长但小于第二时长的情况下，确定驾驶员的疲劳状态为疲劳，且疲劳等级为第一等级；在闭眼频率达到第二频率，且闭眼时长大于第二时长但小于第三时长的情况下，确定驾驶员的疲劳状态为疲劳，且疲劳等级为第二等级；在闭眼频率达到第三频率，且闭眼时长大于第三时长的情况下，确定驾驶员的疲劳状态为疲劳，且疲劳等级为第三等级；其中，第三频率小于第二频率，第二频率小于第一频率，第一等级、第二等级和第三等级分别对应的疲劳程度依次增大。
在另一种可能的实现方式中，装置还包括：
第四确定模块，用于基于人脸图像，确定驾驶员视线的实际注视区域；
第五确定模块，用于在实际注视区域与理论注视区域不匹配的情况下，确定驾驶员处于分心状态；
第三获取模块，用于从异常驾驶状态对应的提醒配置信息中获取异常状态与提醒方式的第二对应关系；
第四获取模块，用于从第二对应关系中获取分心状态对应的第二提醒方式；
提醒模块508，还用于基于第二提醒方式提醒驾驶员。
在另一种可能的实现方式中，装置还包括：
第一检测模块，用于基于人脸图像，对驾驶员的手部进行检测；
第六确定模块，用于在检测到驾驶员的手部持握电子设备的情况下，确定驾驶员的手部与耳部之间的距离；
第七确定模块，用于在距离小于预设距离的情况下，确定驾驶员处于通话状态；
第五获取模块，用于从第二对应关系中获取通话状态对应的第三提醒方式；
提醒模块508，还用于基于第三提醒方式提醒驾驶员。
在另一种可能的实现方式中，装置还包括：
第二检测模块，用于在检测到驾驶员的手部持握发烟物体的情况下，对驾驶员的嘴部进行检测；
第八确定模块，用于在检测到发烟物体含在驾驶员的嘴部的情况下，确定驾驶员处于抽烟状态；
第八确定模块，用于获取车辆内的烟雾浓度，在烟雾浓度大于预设浓度的情况下，确定车辆所处环境；
第九确定模块，用于基于车辆所处环境，确定通风方式；
通风模块，用于基于通风方式对车辆进行通风。
在另一种可能的实现方式中，目标账号的账号数据还包括驾驶员的身份信息；装置还包括：
第十确定模块，用于基于人脸特征，确定驾驶员的情绪类型；
第六获取模块，用于在驾驶员的情绪类型为正面情绪的情况下，从目标账号的账号数据中获取驾驶员的身份信息；
推荐模块，用于基于正面情绪和身份信息，为驾驶员播报语音消息或者推荐音乐。
在另一种可能的实现方式中，目标账号的账号数据还包括车身配置数据；装置还包括：
第七获取模块，用于从车身配置数据中获取主驾驶座椅的位置信息以及后视镜的位置信息；
调整模块，用于基于主驾驶座椅的位置信息以及后视镜的位置信息，调整主驾驶座椅的位置和后视镜的位置。
本申请实施例提供了一种驾驶状态监测装置，当驾驶员驾驶车辆时，基于人脸识别技术，从云服务器中获取驾驶员的目标账号的账号数据，而账号数据 包括异常驾驶状态对应的提醒配置信息，也即获取到适配于驾驶员在异常驾驶状态下的提醒方式。而当基于人脸识别技术识别到驾驶员疲劳驾驶时，基于该驾驶员的异常状态对应的提醒配置信息，获取到驾驶员在疲劳状态下适配于用户的提醒方式对驾驶员进行提醒，能够提高提醒的效果，从而保障用户的安全驾驶，进而降低交通事故的发生率。
需要说明的是，上述实施例提供的驾驶状态监测装置在进行驾驶状态监测时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将控制设备的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的驾驶状态监测装置与驾驶状态监测方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
控制设备的结构框图可以参见图6，该控制设备600可因配置或性能不同而产生比较大的差异，可以包括处理器(central processing units，CPU)601和存储器602，其中，该存储器602中存储有至少一条程序代码，该至少一条程序代码由该处理器601加载并执行以实现上述实施例中的驾驶状态监测方法。当然，该控制设备600还可以具有有线或无线网络接口、键盘以及输入输出接口等部件，以便进行输入输出，该控制设备600还可以包括其他用于实现设备功能的部件，在此不做赘述。
在示例性实施例中，还提供了一种计算机可读存储介质，该计算机可读介质存储有至少一条程序代码，该至少一条程序代码由处理器加载并执行，以实现上述实施例中的驾驶状态监测方法。可选地，存储介质可以是非临时性计算机可读存储介质，例如，非临时性计算机可读存储介质可以是ROM(Read-Only Memory，只读存储器)、RAM(Random Access Memory，随机存取存储器)、CD-ROM(Compact Disc Read-Only Memory，只读光盘)、磁带、软盘和光数据存储设备等。
在示例性实施例中，还提供了一种计算机程序产品，该计算机程序产品存储有至少一条程序代码，该至少一条程序代码由处理器加载并执行，以实现上 述实施例中的驾驶状态监测方法。
在示例性实施例中，本申请实施例所涉及的计算机程序产品可被部署在一个控制设备上执行，或者在位于一个地点的多个控制设备上执行，又或者，在分布在多个地点且通过通信网络互连的多个控制设备上执行，分布在多个地点且通过通信网络互连的多个控制设备可以组成区块链系统。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，该程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
以上所述仅是为了便于本领域的技术人员理解本申请的技术方案，并不用以限制本申请。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (17)

  1. 一种驾驶状态监测方法，其特征在于，所述方法包括：
    获取车辆的驾驶员的人脸图像；
    基于所述人脸图像，提取所述驾驶员的人脸特征，向云服务器发送所述人脸特征；其中，所述云服务器用于基于所述人脸特征，确定所述驾驶员的目标账号，获取所述目标账号的账号数据，所述账号数据包括异常驾驶状态对应的提醒配置信息；
    接收所述云服务器发送的所述目标账号的账号数据；
    基于所述人脸图像，确定所述驾驶员在第一预设时长内的闭眼频率和闭眼时长；
    基于所述闭眼频率和所述闭眼时长，确定所述驾驶员的疲劳信息，所述疲劳信息包括疲劳状态和疲劳状态对应的疲劳等级；
    在所述疲劳状态为疲劳的情况下，从所述异常驾驶状态对应的提醒配置信息中获取疲劳等级与提醒方式的第一对应关系；
    基于所述疲劳状态对应的疲劳等级，从所述第一对应关系中确定所述疲劳等级对应的第一提醒方式；
    基于所述第一提醒方式提醒所述驾驶员。
  2. 根据权利要求1所述的方法，其特征在于，所述基于所述闭眼频率和所述闭眼时长，确定所述驾驶员的疲劳信息，包括：
    在所述闭眼频率达到第一频率，且闭眼时长大于第一时长但小于第二时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第一等级；
    在所述闭眼频率达到第二频率，且闭眼时长大于所述第二时长但小于第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第二等级；
    在所述闭眼频率达到第三频率，且所述闭眼时长大于所述第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第三等级；其中，所述第三频率小于所述第二频率，所述第二频率小于所述第一频率，所述第一等级、所述第二等级和所述第三等级分别对应的疲劳程度依次增大。
  3. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    基于所述人脸图像，确定所述驾驶员视线的实际注视区域；
    在所述实际注视区域与理论注视区域不匹配的情况下，确定所述驾驶员处于分心状态；
    从所述异常驾驶状态对应的提醒配置信息中获取异常状态与提醒方式的第二对应关系；
    从所述第二对应关系中获取所述分心状态对应的第二提醒方式；
    基于所述第二提醒方式提醒所述驾驶员。
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    基于所述人脸图像，对所述驾驶员的手部进行检测；
    在检测到所述驾驶员的手部持握电子设备的情况下，确定所述驾驶员的手部与耳部之间的距离；
    在所述距离小于预设距离的情况下，确定所述驾驶员处于通话状态；
    从所述第二对应关系中获取所述通话状态对应的第三提醒方式；
    基于所述第三提醒方式提醒所述驾驶员。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    在检测到所述驾驶员的手部持握发烟物体的情况下，对所述驾驶员的嘴部进行检测；
    在检测到所述发烟物体含在所述驾驶员的嘴部的情况下，确定所述驾驶员处于抽烟状态；
    获取所述车辆内的烟雾浓度，在所述烟雾浓度大于预设浓度的情况下，确定所述车辆所处环境；
    基于所述车辆所处环境，确定通风方式；
    基于所述通风方式对所述车辆进行通风。
  6. 根据权利要求1所述的方法，其特征在于，所述目标账号的账号数据还包括所述驾驶员的身份信息；所述方法还包括：
    基于所述人脸特征，确定所述驾驶员的情绪类型；
    在所述驾驶员的情绪类型为正面情绪的情况下，从所述目标账号的账号数据中获取所述驾驶员的身份信息；
    基于所述正面情绪和所述身份信息，为所述驾驶员播报语音消息或者推荐音乐。
  7. 根据权利要求1所述的方法，其特征在于，所述目标账号的账号数据还包括车身配置数据；所述方法还包括：
    从所述车身配置数据中获取主驾驶座椅的位置信息以及后视镜的位置信息；
    基于所述主驾驶座椅的位置信息以及所述后视镜的位置信息，调整所述主驾驶座椅的位置和所述后视镜的位置。
  8. 一种驾驶状态监测装置，其特征在于，所述装置包括：
    第一获取模块，用于获取车辆的驾驶员的人脸图像；
    提取模块，用于基于所述人脸图像，提取所述驾驶员的人脸特征，向云服务器发送所述人脸特征；其中，所述云服务器用于基于所述人脸特征，确定所述驾驶员的目标账号，获取所述目标账号的账号数据，所述账号数据包括异常驾驶状态对应的提醒配置信息；
    接收模块，用于接收所述云服务器发送的所述目标账号的账号数据；
    第一确定模块，用于基于所述人脸图像，确定所述驾驶员在第一预设时长内的闭眼频率和闭眼时长；
    第二确定模块，用于基于所述闭眼频率和所述闭眼时长，确定所述驾驶员的疲劳状态；
    第二获取模块，用于在所述驾驶员出现疲劳驾驶的情况下，从所述异常驾驶状态对应的提醒配置信息中获取疲劳等级与提醒方式的第一对应关系；
    第三确定模块，用于基于所述疲劳状态对应的疲劳等级，从所述第一对应关系中确定所述疲劳等级对应的提醒方式；
    提醒模块，用于基于所述提醒方式，提醒所述驾驶员。
  9. 根据权利要求8所述的装置，其特征在于，所述第二确定模块，用于在所 述闭眼频率达到第一频率，且闭眼时长大于第一时长但小于第二时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第一等级；在所述闭眼频率达到第二频率，且闭眼时长大于所述第二时长但小于第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第二等级；在所述闭眼频率达到第三频率，且所述闭眼时长大于所述第三时长的情况下，确定所述驾驶员的疲劳状态为疲劳，且疲劳等级为第三等级；其中，所述第三频率小于所述第二频率，所述第二频率小于所述第一频率，所述第一等级、所述第二等级和所述第三等级分别对应的疲劳程度依次增大。
  10. 根据权利要求8所述的装置，其特征在于，所述装置还包括：
    第四确定模块，用于基于所述人脸图像，确定所述驾驶员视线的实际注视区域；
    第五确定模块，用于在所述实际注视区域与理论注视区域不匹配的情况下，确定所述驾驶员处于分心状态；
    第三获取模块，用于从所述异常驾驶状态对应的提醒配置信息中获取异常状态与提醒方式的第二对应关系；
    第四获取模块，用于从所述第二对应关系中获取所述分心状态对应的第二提醒方式；
    所述提醒模块，还用于基于所述第二提醒方式提醒所述驾驶员。
  11. 根据权利要求10所述的装置，其特征在于，所述装置还包括：
    第一检测模块，用于基于所述人脸图像，对所述驾驶员的手部进行检测；
    第六确定模块，用于在检测到所述驾驶员的手部持握电子设备的情况下，确定所述驾驶员的手部与耳部之间的距离；
    第七确定模块，用于在所述距离小于预设距离的情况下，确定所述驾驶员处于通话状态；
    第五获取模块，用于从所述第二对应关系中获取所述通话状态对应的第三提醒方式；
    所述提醒模块，还用于基于所述第三提醒方式提醒所述驾驶员。
  12. 根据权利要求11所述的装置，其特征在于，所述装置还包括：
    第二检测模块，用于在检测到所述驾驶员的手部持握发烟物体的情况下，对所述驾驶员的嘴部进行检测；
    第八确定模块，用于在检测到所述发烟物体含在所述驾驶员的嘴部的情况下，确定所述驾驶员处于抽烟状态；
    第八确定模块，用于获取所述车辆内的烟雾浓度，在所述烟雾浓度大于预设浓度的情况下，确定所述车辆所处环境；
    第九确定模块，用于基于所述车辆所处环境，确定通风方式；
    通风模块，用于基于所述通风方式对所述车辆进行通风。
  13. 根据权利要求8所述的装置，其特征在于，所述目标账号的账号数据还包括所述驾驶员的身份信息；所述装置还包括：
    第十确定模块，用于基于所述人脸特征，确定所述驾驶员的情绪类型；
    第六获取模块，用于在所述驾驶员的情绪类型为正面情绪的情况下，从所述目标账号的账号数据中获取所述驾驶员的身份信息；
    推荐模块，用于基于所述正面情绪和所述身份信息，为所述驾驶员播报语音消息或者推荐音乐。
  14. 根据权利要求8所述的装置，其特征在于，所述目标账号的账号数据还包括车身配置数据；所述装置还包括：
    第七获取模块，用于从所述车身配置数据中获取主驾驶座椅的位置信息以及后视镜的位置信息；
    调整模块，用于基于所述主驾驶座椅的位置信息以及所述后视镜的位置信息，调整所述主驾驶座椅的位置和所述后视镜的位置。
  15. 一种控制设备，其特征在于，所述控制设备包括处理器和存储器，所述存储器中存储有至少一条程序代码，所述至少一条程序代码由所述处理器加载并执行，以实现如权利要求1至7任一项所述的驾驶状态监测方法。
  16. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存 储有至少一条程序代码，所述至少一条程序代码由处理器加载并执行，以实现如权利要求1至7任一项所述的驾驶状态监测方法。
  17. 一种计算机程序产品，其特征在于，所述计算机程序产品存储有至少一条程序代码，所述至少一条程序代码由处理器加载并执行，以实现如权利要求1至7任一项所述的驾驶状态监测方法。
PCT/CN2024/100465 2023-06-29 2024-06-20 驾驶状态监测方法、装置、设备、存储介质及产品 Ceased WO2025001968A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202310789333.6 2023-06-29
CN202310789333.6A CN116985819A (zh) 2023-06-29 2023-06-29 驾驶状态监测方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2025001968A1 true WO2025001968A1 (zh) 2025-01-02

Family

ID=88531049

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/100465 Ceased WO2025001968A1 (zh) 2023-06-29 2024-06-20 驾驶状态监测方法、装置、设备、存储介质及产品

Country Status (2)

Country Link
CN (1) CN116985819A (zh)
WO (1) WO2025001968A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116985819A (zh) * 2023-06-29 2023-11-03 奇瑞汽车股份有限公司 驾驶状态监测方法、装置、设备及存储介质
CN121224752A (zh) * 2024-06-28 2025-12-30 比亚迪股份有限公司 车辆提醒方法、计算机可读存储介质、电子设备及车辆

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10163163B1 (en) * 2012-12-17 2018-12-25 State Farm Mutual Automobile Insurance Company System and method to adjust insurance rate based on real-time data about potential vehicle operator impairment
CN111950398A (zh) * 2020-07-27 2020-11-17 上海仙豆智能机器人有限公司 一种疲劳驾驶处理方法、装置及计算机存储介质
CN114987500A (zh) * 2022-05-31 2022-09-02 深圳市航盛电子股份有限公司 驾驶员状态监控方法、终端设备及存储介质
CN115366907A (zh) * 2022-08-12 2022-11-22 重庆长安汽车股份有限公司 驾驶员的状态异常提醒方法、装置、车辆及存储介质
CN116985819A (zh) * 2023-06-29 2023-11-03 奇瑞汽车股份有限公司 驾驶状态监测方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10163163B1 (en) * 2012-12-17 2018-12-25 State Farm Mutual Automobile Insurance Company System and method to adjust insurance rate based on real-time data about potential vehicle operator impairment
CN111950398A (zh) * 2020-07-27 2020-11-17 上海仙豆智能机器人有限公司 一种疲劳驾驶处理方法、装置及计算机存储介质
CN114987500A (zh) * 2022-05-31 2022-09-02 深圳市航盛电子股份有限公司 驾驶员状态监控方法、终端设备及存储介质
CN115366907A (zh) * 2022-08-12 2022-11-22 重庆长安汽车股份有限公司 驾驶员的状态异常提醒方法、装置、车辆及存储介质
CN116985819A (zh) * 2023-06-29 2023-11-03 奇瑞汽车股份有限公司 驾驶状态监测方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN116985819A (zh) 2023-11-03

Similar Documents

Publication Publication Date Title
EP3067827B1 (en) Driver distraction detection system
KR102909636B1 (ko) 양방향 차내 가상 개인 비서
WO2025001968A1 (zh) 驾驶状态监测方法、装置、设备、存储介质及产品
JP7299840B2 (ja) 情報処理装置および情報処理方法
EP3657465A1 (en) Vehicle control device and vehicle control method
CN111754729A (zh) 疲劳驾驶提示装置及提示方法
US11490843B2 (en) Vehicle occupant health monitor system and method
JP2019021229A (ja) 車両制御装置および車両制御方法
CN112568904B (zh) 车辆交互方法、装置、计算机设备及存储介质
CN113491519A (zh) 基于情感-认知负荷的数字助理
CN113665528A (zh) 自主车辆安全系统和方法
US20200247422A1 (en) Inattentive driving suppression system
CN114821966A (zh) 疲劳驾驶预警方法、装置、终端及疲劳驾驶预警系统
WO2020066757A1 (ja) 危険運転防止装置
CN111783550A (zh) 驾驶人情绪的监控调节方法及系统
CN111532280A (zh) 一种基于操作感知的车辆控制系统及方法
CN118289021A (zh) 基于多源数据融合的驾驶安全系统及智控方法
CN111292493A (zh) 一种振动提醒方法、装置、电子设备及系统
CN117864046A (zh) 检测车辆操作者汽车压力和/或焦虑并通过车厢环境实施补救措施的系统和方法
CN111243235A (zh) 驾驶辅助方法及装置
JP7537259B2 (ja) 注目対象共有装置、注目対象共有方法
CN117836853A (zh) 一种信息播报方法、通行状态提示方法、装置及车辆
CN115140063B (zh) 一种疲劳驾驶的应对方法、终端及汽车
KR20220005290A (ko) 인캐빈 안전센서 및 그 서비스 플랫폼 제공 방법
CN121425262A (zh) 车辆风险提示方法、装置、设备、存储介质以及程序产品

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: 24830614

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE