WO2023015900A1 - 异常驾驶行为检测方法、装置、电子设备和存储介质 - Google Patents

异常驾驶行为检测方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2023015900A1
WO2023015900A1 PCT/CN2022/083014 CN2022083014W WO2023015900A1 WO 2023015900 A1 WO2023015900 A1 WO 2023015900A1 CN 2022083014 W CN2022083014 W CN 2022083014W WO 2023015900 A1 WO2023015900 A1 WO 2023015900A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
driving
abnormal
behavior
state
Prior art date
Application number
PCT/CN2022/083014
Other languages
English (en)
French (fr)
Inventor
刘俊启
Original Assignee
百度在线网络技术（北京）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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Publication of WO2023015900A1 publication Critical patent/WO2023015900A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • 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
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Definitions

  • the present disclosure relates to the field of artificial intelligence, to the field of intelligent transportation technology, and can be used in smart cities and intelligent transportation scenarios, for example, to a method, device, electronic device and storage medium for detecting abnormal driving behavior.
  • Online car-hailing is a service platform based on Internet technology, accessing qualified vehicles and drivers, and providing taxi reservation services by integrating supply and demand information.
  • the present disclosure provides an abnormal driving behavior detection method, device, electronic equipment and storage medium.
  • a method for detecting abnormal driving behavior including:
  • the first user state is compared with the second user state, and abnormal driving behavior of the driving user is detected according to the comparison result.
  • an abnormal driving behavior detection device including:
  • the driving user positioning information acquisition module is configured to receive the first positioning information of the driving user, and determine the first user status of the driving user according to the first positioning information;
  • the vehicle user location information acquisition module is configured to receive the second location information of the vehicle user who is in the same car with the driving user, and determine the second user status of the vehicle user according to the second location information;
  • the abnormal driving behavior detection module is configured to compare the first user state with the second user state, and detect the abnormal driving behavior of the driving user according to the comparison result.
  • an electronic device including:
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the above abnormal driving behavior detection method.
  • a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the above abnormal driving behavior detection method.
  • a computer program product including a computer program, the computer program implements the above abnormal driving behavior detection method when executed by a processor.
  • FIG. 1 is a flow chart of a method for detecting abnormal driving behavior provided by an embodiment of the present disclosure
  • Fig. 2 is a flow chart of another abnormal driving behavior detection method provided by an embodiment of the present disclosure
  • FIG. 3 is a flowchart of another abnormal driving behavior detection method provided by an embodiment of the present disclosure.
  • FIG. 4 is a schematic diagram of an abnormal driving behavior detection system provided by an embodiment of the present disclosure.
  • Fig. 5 is a schematic diagram of an abnormal driving behavior detection device provided by an embodiment of the present disclosure.
  • Fig. 6 is a schematic diagram of an abnormal driving behavior detection module provided by an embodiment of the present disclosure.
  • FIG. 7 is a schematic diagram of a call connection unit provided by an embodiment of the present disclosure.
  • Fig. 8 is a schematic diagram of another abnormal driving behavior detection module provided by an embodiment of the present disclosure.
  • FIG. 9 is a schematic diagram of another abnormal driving behavior detection module provided by an embodiment of the present disclosure.
  • Fig. 10 is a schematic diagram of an abnormal stay behavior detection unit provided by an embodiment of the present disclosure.
  • Fig. 11 is a schematic diagram of another abnormal driving behavior detection device provided by an embodiment of the present disclosure.
  • FIG. 12 is a block diagram of an electronic device for implementing the abnormal driving behavior detection method of the embodiment of the present disclosure.
  • FIG. 1 is a flow chart of a method for detecting abnormal driving behavior provided by an embodiment of the present disclosure. This embodiment may be applicable to obtaining whether a driving user has abnormal driving behavior.
  • the method of this embodiment can be executed by an abnormal driving behavior detection device, which can be implemented in the form of software and/or hardware, and configured in an electronic device with a certain data computing capability, which can be a server or the like.
  • S101 Receive first location information of a driving user, and determine a first user state of the driving user according to the first location information.
  • a driving user is a user who drives a vehicle, for example, a driving user refers to a user who performs a taxi task of transporting a passenger.
  • the first positioning information may refer to the positioning position of the driving user.
  • the first positioning information may be uploaded to the server through the driving user's client.
  • the first user status is used to determine the status of the driving user, where the first user status may include exercise status, identity status, contact status, and the like.
  • S102 Receive second location information of a ride user who is in the same car as the driver user, and determine a second user status of the ride user according to the second location information.
  • a car user is a user who rides in a vehicle driven by the driving user, for example, a car user refers to a user who issues a taxi task.
  • the second positioning information may refer to the positioning position of the riding user.
  • the second positioning information can be uploaded to the server through the client terminal of the passenger.
  • the second user status is used to determine the status of the riding user, wherein the second user status may include motion status, identity status, location transmission status, and the like.
  • the driving user and the riding user are different individuals and use different clients to interact with the server of the abnormal driving behavior detection method provided by the embodiments of the present disclosure.
  • the passenger who rides in the same car as the driving user refers to the user who rides in the same car as the driving user, that is, refers to the riding user associated with the taxi task performed by the driving user.
  • the driving user drives the vehicle, the passenger rides on the vehicle, and the driver drives the vehicle to carry the passenger from the target start position to the target end position, wherein both the target start position and the target end position are specified by the ride user.
  • the driving user and the riding user ride in the same vehicle.
  • the number of ride users is at least one.
  • the taxi task can be a carpooling task.
  • the driving user can transport multiple riders from their respective designated target start locations to the target destination locations. The routes specified by different riders overlap completely or partially. .
  • the client of the driving user and the client of the riding user can periodically upload location information, and the upload period can be set as required, for example, 3 seconds.
  • the first user state is compared with the second user state to obtain a comparison result.
  • the comparison results are used to describe the behavioral differences between the driver user and the ride user during the execution of the taxi task. According to the comparison result, it is detected whether the driving user has abnormal driving behavior.
  • the detection result of abnormal driving behavior includes that the driving user has abnormal driving behavior, or the driving user does not have abnormal driving behavior.
  • the detection result of abnormal driving behavior can also include the type of abnormal driving behavior, for example, dangerous driving behavior or detour driving behavior etc. Among them, the dangerous driving behavior causes the driving user or the passenger to be in danger, and the detour driving behavior causes the passenger to suffer economic losses.
  • the driving user has dangerous driving behavior, which can be that the passenger is in a dangerous state, for example, the driving user performs a dangerous operation on the passenger, or the driving user is in a dangerous state, for example, the passenger performs a dangerous operation on the driving user; or Both the ride user and the driver user are in a dangerous state, for example, a traffic accident occurs.
  • dangerous driving behavior can be that the passenger is in a dangerous state, for example, the driving user performs a dangerous operation on the passenger, or the driving user is in a dangerous state, for example, the passenger performs a dangerous operation on the driving user; or Both the ride user and the driver user are in a dangerous state, for example, a traffic accident occurs.
  • performing an alarm operation may include: sending an alarm message to the official security system, the alarm message includes the information of the driving user, the information of the passenger user, and the latest location information, etc.; sending an alarm message to a designated emergency contact or establishing a call connection; Send an alarm message or establish a call connection to the business personnel of the taxi service system.
  • the positioning information of the driving user and the positioning information of the riding user are obtained respectively, and the user status of the driving user and the user status of the riding user are respectively determined.
  • the user status of the driving user and the user status of the riding user User status which detects the abnormal driving behavior of the driving user to detect the driving safety of the riding user.
  • the technical solution of the present disclosure can detect the abnormal driving behavior of the driving user according to the comparison result of the user states of the two parties, and improves the detection accuracy and detection efficiency of the abnormal driving behavior.
  • Fig. 2 is a flow chart of another abnormal driving behavior detection method provided by an embodiment of the present disclosure, which is described based on the above technical solution, and may be combined with the above optional implementation.
  • the comparing the first user state with the second user state and detecting the abnormal driving behavior of the driving user according to the comparison result includes: comparing the contact state included in the first user state with the second user state Compare the contact state included in the two user states; when the comparison result is that the contact state included in the first user state is different from the contact state included in the second user state, determine that the contact state is the target user in the contactable state ; establishing a call connection with the target user, and obtaining call information of the target user; detecting abnormal driving behavior of the driving user according to the call information.
  • S201 Receive first location information of a driving user, and determine a first user state of the driving user according to the first location information.
  • S202 Receive second location information of a ride user who is in the same car as the driver user, and determine a second user status of the ride user according to the second location information.
  • Contact status is used to determine whether location information is uploaded continuously.
  • the contact status may include an out of contact status or an available status.
  • Comparison results include identical results or different results.
  • the same results include that the contact status included in the first user status and the contact status included in the second user status are both available or out of contact; different results include the contact status included in the first user status and the contact status included in the second user status Among the contact states of , one is in contact state and the other is in contact state.
  • the target user whose contact status is contactable refers to a user who continuously uploads location information, that is, a user who can be contacted.
  • a user in a lost state refers to a user who cannot be contacted.
  • the contact status of the driving user and the contact status of the passenger user are both contactable, and it can be determined that the passenger is in a safe state and no alarm operation is performed; the contact status of the driving user and the contact status of the passenger user are both out of contact State, there are two situations.
  • the first situation is: the vehicle driven by the driving user travels to a location with poor signal quality, and the second situation is: the riding user is in a dangerous state.
  • the result of the comparison is that the contact status included in the first user status is the same as the contact status included in the second user status
  • obtain the latest location information obtain a set of locations marked with poor signal quality
  • obtain a set of locations marked with poor signal quality inquire about the target position matched by the positioning information at the latest moment; in the case that the query result is empty, determine that the passenger is in a dangerous state, and the driving user has dangerous driving behavior in abnormal driving behavior, and perform an alarm operation; If the result is not empty, it is determined that the passenger is in a safe state, and no alarm operation is performed.
  • the distance between the target position and the latest positioning information is less than or equal to the set distance threshold.
  • the established call connection can be a call connection between a standard security user of a security agency and the target user, or a call connection between pre-designated relatives and friends and the target user, or an intelligent robot and the target user. Call connections between target users.
  • the call connection can be implemented through the client.
  • the call connection is used to verify the identity of the target user and to obtain information such as the status of the riding user and the cause of the disconnected user.
  • the initiating party can be prompted to issue a voice of a specified question, so that the target user can answer the specified question, and the call audio can be recorded for the call connection between the initiating party and the target user, and call information can be extracted from the call audio
  • the method of extracting the call information may be methods such as speech recognition; or the target user inputs information for a specified question, and extracts the call information from the input information, and the method of extracting the call information may be a method such as semantic understanding.
  • the call information includes the target user's answer information to the specified question and the target user's voice characteristics. The call information is used to detect the status of the ride user based on the information provided by the target user.
  • a call connection between the intelligent robot and the target user may be established.
  • the intelligent robot pre-generates and plays the voice of the specified question, and waits for the target user to reply, and instructs the target user to say keywords, input specified content or input specified gestures, etc., end the reply to the current question, and play the next specified question until the target user
  • the user replies to complete all specified questions.
  • the reply to the current question will be ended, the next specified question will be played, and the number of times of no reply will be accumulated.
  • the reply method of the target user may be voice, inputting specified content or inputting specified gestures, and the like.
  • the establishing a call connection with the target user includes: establishing a call connection between the target user and a standard security user.
  • a standard security user is a user of a security agency, and may be a business person of a taxi-hailing software, or a police officer, etc.
  • the target user can be contacted manually to detect the safety of the ride and improve the safety of the ride user.
  • the identity characteristics of the target user and the type of the target user are obtained.
  • the standard identity information of the target user can be obtained, the identity characteristics of the target user can be verified according to the standard identity information, and the identity verification result of the target user can be obtained.
  • the type of the target user is used to determine whether the target user is a driving user or a car riding user.
  • the passenger can instruct the server to perform an alarm operation by inputting a specified alarm command. Therefore, it is queried in the call information whether there is information of the specified alarm command, and the query result of the specified alarm command is obtained.
  • the identity verification result of the target user, the type of the target user, and the query result of the specified alarm command can be determined, and based on this, whether the driving user has dangerous driving behavior in abnormal driving behavior can be detected.
  • Verifying the identity characteristics of the target user and obtaining the identity verification result of the target user may include: extracting the voiceprint features from the voice of the target user, comparing them with the standard voiceprint features of the target user, and determining the comparison result; obtaining the target user The user's answering voice to the specified question is recognized as text, compared with the standard answer text, and the comparison result is determined; from the voice of the target user, the gender characteristics of the target user are detected, and compared with the standard gender characteristics of the target user to determine Comparison result: Determine the target user's identity verification result according to at least one of the above comparison results.
  • determining the identity verification result of the target user according to at least one of the above comparison results may include: calculating the identity verification value based on the value and weight corresponding to the comparison result; calculating the comparison result of the identity verification value and the identity verification threshold, And according to the comparison result, the identity verification result is determined. For example, when the identity verification value is greater than or equal to the identity verification threshold, it is determined that the target user’s identity verification result is verified; when the identity verification value is less than the identity verification threshold, it is determined that the target user The result of the identity verification is that the verification fails.
  • the type of the target user when the type of the target user is a driving user and the identity verification result is failed, it is determined that the passenger is in a dangerous state, and the driving user has dangerous driving behavior among abnormal driving behaviors, and an alarm operation is performed.
  • the type of the target user is a driving user and the identity verification result is passed, it is determined that the passenger is in a safe state, the driving user does not have dangerous driving behavior in abnormal driving behavior, and no alarm operation is performed. If the type of the target user is a passenger and the result of the identity verification is not passed, or if the type of the target user is a passenger and a specified alarm instruction is found, determine that the passenger is in danger state, the driving user has dangerous driving behavior in abnormal driving behavior, and performs an alarm operation.
  • the identity verification result is passed, and the query result of the specified alarm command is empty, it is determined that the car user is in a safe state, and the driving user does not have dangerous driving behavior in abnormal driving behavior, No alarm action is performed.
  • the contact status is established as a contactable state
  • the user's call connection and obtain the call information, and detect whether the driving user has abnormal driving behavior based on the call information.
  • the driving user or the driving user loses contact, it can detect whether the driving user has abnormal driving behavior and improve the driving efficiency. safety.
  • Fig. 3 is a flow chart of another abnormal driving behavior detection method provided by an embodiment of the present disclosure, which is described based on the above technical solution, and may be combined with the above optional implementation.
  • the comparing the first user status with the second user status includes: detecting abnormal staying behavior according to the first positioning information and the second positioning information; when there is the abnormal staying behavior Next, compare the first user state with the second user state.
  • S301 Receive first location information of a driving user, and determine a first user state of the driving user according to the first location information.
  • S302. Receive second location information of a ride user who is in the same car as the driver user, and determine a second user status of the ride user according to the second location information.
  • the abnormal stop behavior can refer to the behavior of staying in a position other than the target termination position specified by the user in the abnormal stop state.
  • the abnormal stop state includes a state of no prohibited traffic light, no intersection, no congestion, and the like.
  • the abnormal stop behavior indicates that the vehicle taken by the user is parked at a location other than the destination, and the location is not at an intersection, the vehicle is not waiting for a red or yellow light, and the vehicle is not in a state of congestion.
  • Whether the vehicle stays can be determined according to the first positioning information and the second positioning information. For example, it may be determined that the vehicle stops when it is detected that the first positioning information and the second positioning information are identical and unchanged for a set number of consecutive times.
  • the stop position When detecting that the vehicle stays, detect whether the stop position is the target end position, and if the distance between the stop position and the target end position is greater than or equal to the set distance threshold, it is determined that the stop position is not the target end position; If the distance between the position and the target end position is less than the set distance threshold, it is determined that the stop position is the target end position.
  • detect whether the stop position is at an intersection; detect whether the traffic light near the stop position is a prohibited traffic light; and detect whether the stop position is in a queue of vehicles, etc., and the stop position is not at the intersection 1.
  • the nearby traffic light is not a prohibited traffic light and is not in a queue of vehicles, it is determined that the driving user has an abnormal stop behavior.
  • the set of dangerous locations includes remote locations and locations where the frequency of accidents is greater than or equal to a set frequency threshold.
  • the detecting abnormal staying behavior according to the first positioning information and the second positioning information includes: detecting yaw behavior according to the first positioning information and the second positioning information; In the case of the off-track behavior, send navigation route modification information to the passenger; receive the modification audit result fed back by the passenger for the navigation route modification information; In the case of , the abnormal staying behavior is detected according to the first positioning information and the second positioning information.
  • the driving user drives the vehicle along the navigation route.
  • the driving user determines that the driving user has a veering behavior.
  • the navigation route modification information is used to provide the ride user to detect whether the ride user confirms to change the navigation route.
  • the modification review result is used to determine whether the ride user confirms to change the navigation route. Modify the review result to pass the review, indicating that the ride user confirms to change the navigation route. Modify the audit result to fail the audit, indicating that the ride user confirms not to change the navigation route. In the case that the review fails, it indicates that the user does not want to change the navigation route. At this time, the user may enter a more dangerous state. The detection accuracy of dangerous state.
  • the verification is passed, it is also possible to continue to detect whether there is a yaw behavior according to the first positioning information and the second positioning information, and to accumulate the number of occurrences of the yaw behavior.
  • the number of occurrences of yaw behavior is greater than or equal to a set number threshold, the abnormal staying behavior is detected according to the first positioning information and the second positioning information.
  • the review fails, continue to detect whether there is a yaw behavior based on the first positioning information and the second positioning information, that is, detect whether the first positioning information and the second positioning information return to the initial navigation route, if If there is a yaw behavior, the yaw degree of the yaw behavior is calculated, and if the yaw degree is greater than or equal to a degree threshold, abnormal staying behavior is detected according to the first positioning information and the second positioning information.
  • the yaw degree may be the minimum distance between the yaw position point and the initial navigation route.
  • the positioning information By sending the navigation route revision information to the passenger in the case of yaw behavior, and judging whether the passenger agrees to change the navigation route according to the feedback modification review results, and when the passenger does not agree to change the navigation route, According to the positioning information, detect abnormal staying behavior, and realize whether there is abnormal staying behavior in the environment where the passenger is suspected of risk, so as to detect whether there is abnormal driving behavior, which can eliminate interference factors and improve the detection accuracy of abnormal driving behavior.
  • the driving user will only perform dangerous operations on the passenger when the vehicle is parked. Therefore, in the case that the driving user has an abnormal staying behavior, detecting the user status and making a comparison can improve the detection accuracy of the abnormal driving behavior and eliminate some interference factors. For example, if the driving user enters a route with poor signal quality, causing the user on the vehicle to be out of contact, resulting in false detection results of abnormal driving behavior.
  • the comparing the first user state with the second user state, and detecting the abnormal driving behavior of the driving user according to the comparison result includes: comparing the motion state included in the first user state Comparing with the motion state included in the second user state; detecting the abnormal driving behavior of the driving user according to the comparison result of the motion state.
  • the motion state represents motion information of the user, and the motion state may include motion speed and/or motion direction, and the like.
  • the motion directions of the driver and the passenger are different, indicating that the driver and the passenger are moving in different directions, that is, the passenger leaves the vehicle and moves in a direction different from the driving direction of the vehicle , indicating that the passenger has left the vehicle safely; the driving user and the passenger are moving in the same direction, indicating that the driving user and the passenger are moving in the same direction, that is, the passenger did not leave the vehicle, indicating that the passenger did not leave the vehicle safely, and still In the vehicle, at this time, the passenger is in danger.
  • the motion speeds of the driving user and the riding user are different, indicating that the driving user and the riding user are moving at different speeds.
  • the motion speeds of the two users are non-zero and different, that is, If the driving user leaves the vehicle and moves at a speed different from the driving speed of the vehicle, it indicates that the driving user has left the vehicle safely;
  • the vehicle users move at the same speed, that is, the vehicle user does not leave the vehicle, indicating that the vehicle user has not safely left the vehicle and is still in the vehicle. At this time, the vehicle user is in a dangerous state. In the case that the driving user and the vehicle user have the same movement speed and are zero, it indicates that the two users stay, that is, the vehicle stays.
  • the motion state can include the motion direction and motion speed at the same time, and both the motion direction and motion speed can be judged.
  • the detection operation based on any one of the motion direction and motion speed, it is determined that there is a dangerous driving behavior in the abnormal driving behavior, and then the driving The user has dangerous driving behavior in abnormal driving behavior.
  • the abnormal driving behavior detection method further includes: acquiring historical yaw data of the driving user; and correcting the abnormal driving behavior according to the historical yaw data.
  • the historical yaw data refers to the occurrence frequency of the driving user's yaw behavior.
  • the calculation method of the occurrence frequency is: count the duration of the driving user's execution of multiple taxi tasks, and count the occurrence of yaw behavior in multiple taxi tasks The number of times, calculate the ratio of the number of occurrences to the duration, and determine it as the frequency of occurrence.
  • Historical yaw data is used to correct abnormal driving behavior.
  • abnormal driving behavior may include dangerous driving behavior and detour driving behavior.
  • the dangerous driving behavior of the driving user may be modified into a detour driving behavior.
  • the abnormal driving behavior of the driving user may be directly determined as a detour driving behavior.
  • the abnormal driving behavior can be corrected according to the degree of yaw and the positioning information of the yaw.
  • the yaw degree is greater than or equal to the preset yaw threshold, and the detour driving behavior of the driving user is modified into a dangerous driving behavior;
  • the yaw positioning information is queried from the first positioning information and the second positioning information, and Detect whether the yaw positioning information belongs to the pre-statistic set of dangerous positions, and if the yaw positioning information belongs to the pre-statistic set of dangerous positions, modify the detour driving behavior of the driving user into a dangerous driving behavior.
  • the abnormal driving behavior of the driving user may be directly determined as a dangerous driving behavior.
  • Fig. 4 is a schematic diagram of an abnormal driving behavior detection system provided by an embodiment of the present disclosure.
  • the abnormal driving behavior detection system includes a server 401 , a passenger terminal 402 and a driver terminal 403 .
  • the passenger terminal 402 includes a destination confirmation module, a driving route determination module, a driving route uploading module, a geographic data uploading module, a navigation route switching confirmation module, and the like.
  • the driver terminal 403 includes: a driving route receiving module, a driving navigation module, and a geographical data uploading module.
  • the driving route receiving module pulls the driving route information selected by the passenger from the server 401; the driving navigation module performs route navigation according to the driving route; the geographic data uploading module uploads the current geographic location to the server 401.
  • the server 401 can realize the following functions: perform route planning according to the current location and destination of the passenger to obtain multiple driving routes that can be selected by the user. Realize route synchronization between the driver terminal 403 and the passenger terminal 402; obtain the first location information of the driving user and the second location information of the ride user reported by the client. And store the geographical location information of this trip or the trip information in a short time; according to the first positioning information of the driving user and the second positioning information of the riding user, combined with the driving route reported by the riding user, the current route deviation is carried out. According to the degree of yaw, the user will be prompted and confirmed according to the degree of yaw.
  • the user confirms that the yaw behavior of the driver has not been communicated, it is determined that the current yaw behavior is abnormal; at this time, according to the passenger terminal 402
  • the server 401 performs route planning and returns three routes to the passenger terminal 402: 1, a, b, c, d, e, f, g; 2, a , b1, c1, d, e, f, g; 3, a, b, c, d1, e1, f, g.
  • the ride user selects routes a, b, c, d, e, f, g through the driving route determination module of the passenger terminal 402, and uploads the selected route through the driving route upload module of the passenger terminal 402.
  • the server 401 receives the selected route.
  • the driving route receiving module of the driver terminal 403 pulls the selected route from the server 401, and starts to navigate according to a, b, c, d, e, f, g through the driving navigation module.
  • the driver terminal 403 and the passenger terminal 402 respectively obtain location information in real time through the geographic data upload module and upload it to the server 401 .
  • the server 401 periodically receives the first positioning information and the second positioning information. And detect if yaw behavior occurs.
  • yaw such as a, b1
  • the navigation route modification information is sent to the passenger terminal 402 to prompt the user to yaw, and the driving user may want to change the route; Modify the audit result to confirm to the passenger whether to drive on the new route. If the revised audit result is approved, update the route data; if the modified audit result is not approved, enter the early warning state. In the early warning state, it is detected whether there is an abnormal staying behavior according to the first positioning information and the second positioning information. If there is no abnormal staying behavior, continue to detect whether there is abnormal staying behavior; if there is abnormal staying behavior, compare the first user state and the second user state.
  • the server 401 comparing the first user status with the second user status includes: comparing the contact status of the ride user with the contact status of the driving user. If the result of the comparison is that the contact state of the passenger user is different from that of the driving user, that is, one party loses contact, establish a call connection with the user end that has not lost contact, that is, establish a call connection with the target user whose contact state is contactable. Call connection, and according to the call information during the call connection process, detect whether there is abnormal driving behavior or dangerous driving behavior, and activate the alarm in the case of dangerous driving behavior, which is equivalent to when the mobile phone of the driving user or the car user loses contact , the server 401 actively contacts the other party to confirm the status. When the result of the comparison is that the contact status of the passenger and the driving user are the same and both are out of contact, an alarm is activated.
  • the server 401 comparing the first user state with the second user state includes: comparing the moving direction of the riding user with the moving direction of the driving user.
  • the comparison result is that the direction of motion of the passenger is identical to the direction of motion of the driver, it is determined that there is a dangerous driving behavior and an alarm is started.
  • Comparing the first user state with the second user state by the server 401 includes: comparing the movement speed of the riding user with that of the driving user, and the comparison result shows that the moving speed of the riding user is different from that of the driving user, And when the movement speed of one party is zero, it is determined that there is a dangerous driving behavior, and an alarm is activated.
  • the abnormal driving behavior detection system of the present disclosure can actively sense when the route deviates when driving according to the route preset by the user. In case of dangerous driving behavior, it can quickly call the police, and at the same time, it will have a deterrent effect on the driving user, and will also remind some illegal behaviors. It may be possible to detect illegal behaviors in advance and improve the safety of driving.
  • FIG. 5 is a schematic diagram of an abnormal driving behavior detection device provided by an embodiment of the present disclosure.
  • the embodiment of the present disclosure is suitable for querying roads that connect two areas in the road network and are not recorded in the road network. Condition.
  • the device is implemented by software and/or hardware, and is configured in electronic equipment with certain data computing capabilities.
  • a kind of abnormal driving behavior detection device 500 as shown in Figure 5, comprises: driving user location information acquisition module 501, ride user location information acquisition module 502 and abnormal driving behavior detection module 503; wherein, driving user location information acquisition module 501 , set to receive the first location information of the driving user, and determine the first user state of the driving user; the location information acquisition module 502 of the riding user is set to receive the second positioning information, and determine the second user state of the passenger; the abnormal driving behavior detection module 503 is configured to compare the first user state and the second user state, and detect the driving state according to the comparison result. User's abnormal driving behavior.
  • the positioning information of the driving user and the positioning information of the riding user are obtained respectively, and the user status of the driving user and the user status of the riding user are respectively determined.
  • the technical solution of the present disclosure can detect and predict the abnormal driving behavior of the driving user according to the comparison result of the positioning information of the two parties, and improve the detection accuracy and detection efficiency of the abnormal driving behavior.
  • the abnormal driving behavior detection module 503 includes: a contact status comparison unit 5031 configured to compare the contact status included in the first user status with the contact status included in the second user status;
  • the contactable user determining unit 5032 is configured to determine that the contact state is the target user in the contactable state when the comparison result is that the contact state included in the first user state is different from the contact state included in the second user state;
  • the call connection unit 5033 is configured to establish a call connection with the target user and obtain call information of the target user; the call information processing unit 5034 is configured to detect the abnormal driving behavior of the driving user according to the call information.
  • the call connection unit 5033 includes: an inter-user call establishment subunit 50331 configured to establish a call connection between the target user and a standard security user.
  • the abnormal driving behavior detection module 503 includes: a motion state comparison unit 5035 configured to compare the motion state included in the first user state with the motion state included in the second user state;
  • the motion state comparison result processing unit 5036 is configured to detect the abnormal driving behavior of the driving user according to the motion state comparison result.
  • the abnormal driving behavior detection module 503 also includes: an abnormal staying behavior detection unit 5037, configured to detect abnormal staying behavior according to the first positioning information and the second positioning information;
  • the unit 5038 is configured to compare the first user status with the second user status when the abnormal staying behavior exists.
  • the abnormal stay behavior detection unit 5037 includes: a yaw behavior detection subunit 50371, configured to detect yaw behavior according to the first positioning information and the second positioning information; navigation route modification The information sending subunit 50372 is configured to send navigation route modification information to the passenger in the case of the off-track behavior; the modification review result receiving subunit 50373 is configured to receive the Modification review results fed back from navigation route modification information; yaw review failure result processing subunit 50374, set to information to detect abnormal dwell behavior.
  • the abnormal driving behavior detection device 500 also includes: a historical yaw data acquisition module 504, configured to acquire the historical yaw data of the driving user; an abnormal driving behavior correction module 505, configured to The above-mentioned historical yaw data is used to correct the abnormal driving behavior.
  • the abnormal driving behavior detection device described above can execute the abnormal driving behavior detection method provided by any embodiment of the present disclosure, and has corresponding functional modules and effects for executing the abnormal driving behavior detection method.
  • the acquisition, storage and application of user personal information or vehicle information involved are in compliance with relevant laws and regulations, and do not violate public order and good customs.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • Figure 12 shows a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure.
  • Electronic device 600 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic device 600 may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 600 includes a computing unit 601 that can be loaded into a random access memory (Random Access Memory, RAM) according to a computer program stored in a read-only memory (Read-Only Memory, ROM) 602 or from a storage unit 608. ) 603 to perform various appropriate actions and processes. In the RAM 603, various programs and data necessary for the operation of the device 600 can also be stored.
  • the computing unit 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (Input/Output, I/O) interface 605 is also connected to the bus 604 .
  • the I/O interface 605 includes: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc. ; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 609 allows the device 600 to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.
  • Computing unit 601 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), various dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, various operating Computing units of machine learning model algorithms, digital signal processors (Digital Signal Processing, DSP), and any appropriate processors, controllers, microcontrollers, etc.
  • the computing unit 601 executes a plurality of methods and processes described above, such as an abnormal driving behavior detection method.
  • the abnormal driving behavior detection method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 608 .
  • part or all of the computer program may be loaded and/or installed on the device 600 via the ROM 602 and/or the communication unit 609.
  • the computing unit 601 may be configured in any other appropriate way (for example, by means of firmware) to execute the abnormal driving behavior detection method.
  • Various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that can is a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • a programmable processor that can is a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media examples include one or more wire-based electrical connections, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM, or Flash memory) ), fiber optics, Compact Disc Read-Only Memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • wire-based electrical connections portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM, or Flash memory)
  • fiber optics Compact Disc Read-Only Memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • CD-ROM Compact Disc Read-Only Memory
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display ( Liquid Crystal Display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the computer.
  • a display device e.g., a cathode ray tube (CRT) or a liquid crystal display ( Liquid Crystal Display (LCD) monitor
  • a keyboard and pointing device e.g., a mouse or trackball
  • Other types of devices may also be configured to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (Wide Area Network, WAN), and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.
  • Steps can be reordered, added, or removed using the various forms of flow shown above.
  • steps described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution provided by the present disclosure can be achieved, no limitation is imposed herein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

本文公开异常驾驶行为检测方法、装置、电子设备和存储介质。异常驾驶行为检测方法包括：接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态；接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态；对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。

Description

异常驾驶行为检测方法、装置、电子设备和存储介质
本申请要求在2021年08月10日提交中国专利局、申请号为202110915765.8的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及人工智能领域，涉及智能交通技术领域，可用于智慧城市和智能交通场景下，例如涉及一种异常驾驶行为检测方法、装置、电子设备和存储介质。
背景技术
随着网络技术的发展，网约车服务为用户的出行提供了便利。
网约车是基于互联网技术构建的服务平台，接入符合条件的车辆和驾驶员，通过整合供需信息，提供预约出租汽车的服务。
发明内容
本公开提供了一种异常驾驶行为检测方法、装置、电子设备和存储介质。
根据本公开的一方面，提供了一种异常驾驶行为检测方法，包括：
接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态；
接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态；
对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。
根据本公开的另一方面，提供了一种异常驾驶行为检测装置，包括：
驾驶用户定位信息获取模块，设置为接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态；
乘车用户定位信息获取模块，设置为接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态；
异常驾驶行为检测模块，设置为对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。
根据本公开的另一方面，提供了一种电子设备，包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行上述的异常驾驶行为检测方法。
根据本公开的另一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行上述的异常驾驶行为检测方法。
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现上述的异常驾驶行为检测方法。
附图说明
图1是本公开实施例提供的一种异常驾驶行为检测方法的流程图；
图2是本公开实施例提供的另一种异常驾驶行为检测方法的流程图；
图3是本公开实施例提供的另一种异常驾驶行为检测方法的流程图；
图4是本公开实施例提供的一种异常驾驶行为检测系统的示意图；
图5是本公开实施例提供的一种异常驾驶行为检测装置的示意图；
图6是本公开实施例提供的一种异常驾驶行为检测模块的示意图；
图7是本公开实施例提供的一种通话连接单元的示意图；
图8是本公开实施例提供的另一种异常驾驶行为检测模块的示意图；
图9是本公开实施例提供的另一种异常驾驶行为检测模块的示意图；
图10是本公开实施例提供的一种异常停留行为检测单元的示意图；
图11是本公开实施例提供的另一种异常驾驶行为检测装置的示意图；
图12是用来实现本公开实施例的异常驾驶行为检测方法的电子设备的框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的多种细节以助于理解，应当将它们认为仅仅是示范性的。为了清楚和简明，以下的描述中省略了对公知功能和结构以及与下述实施例相关性低的功能和结构的描述。
图1是本公开实施例提供的一种异常驾驶行为检测方法的流程图，本实施例可以适用于获取驾驶用户是否存在异常驾驶行为的情况。本实施例方法可以由异常驾驶行为检测装置来执行，该装置可采用软件和/或硬件的方式实现，并配置于具有一定数据运算能力的电子设备中，该电子设备可以是服务器等。
S101，接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态。
驾驶用户为驾驶车辆的用户，例如，驾驶用户是指执行运送乘车用户的出租车任务的用户。第一定位信息可以是指驾驶用户的定位位置。第一定位信息可以通过驾驶用户的客户端上传给服务器。第一用户状态用于确定驾驶用户的状态，其中，第一用户状态可以包括运动状态、身份状态和联系状态等。
S102，接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态。
乘车用户为乘坐驾驶用户所驾驶的车辆的用户，例如，乘车用户是指发布出租车任务的用户。第二定位信息可以是指乘车用户的定位位置。第二定位信息可以通过乘车用户的客户端上传给服务器。第二用户状态用于确定乘车用户的状态，其中，第二用户状态可以包括运动状态、身份状态和定位传输状态等。驾驶用户和乘车用户是不同个体，使用不同的客户端，分别与本公开实施例提供的异常驾驶行为检测方法的服务器进行交互。与驾驶用户同车的乘车用户，是指与驾驶用户同乘一辆车的用户，也即是指驾驶用户所执行的出租车任务关联的乘车用户。驾驶用户驾驶车辆，乘车用户乘坐该车辆，驾驶用户通过驾驶车辆搭载乘车用户，从目标起始位置行驶到目标终止位置，其中，目标起始位置和目标终止位置均由乘车用户指定。在行驶过程中，驾驶用户和乘车用户乘坐在同一辆车辆上。其中，乘车用户的数量为至少一个。出租车任务可以为拼车任务，驾驶用户可以在执行拼车任务中，实现将多个乘车用户从各自指定的目标起始位置运输到目标终止位置，不同乘车用户指定的路线完全重叠或部分重叠。
驾驶用户的客户端和乘车用户的客户端可以周期性上传定位信息，上传周期可以根据需要设定，例如是3秒。
S103，对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。
对第一用户状态和第二用户状态进行比较，得到比较结果。比较结果用于描述出租车任务的执行过程中，驾驶用户和乘车用户之间的行为差异。根据比较结果，检测驾驶用户是否存在异常驾驶行为。异常驾驶行为的检测结果包括驾驶用户存在异常驾驶行为，或驾驶用户不存在异常驾驶行为，此外，异常驾驶行为的检测结果还可以包括异常驾驶行为的类型，例如，危险驾驶行为或绕路驾驶行为等，其中，危险驾驶行为导致驾驶用户或乘车用户存在危险，绕路驾驶行为导致乘车用户蒙受经济损失。
驾驶用户存在危险驾驶行为，可以是乘车用户处于危险状态，例如，驾驶用户对乘车用户进行危险操作，也可以是驾驶用户处于危险状态，例如，乘车用户对驾驶用户进行危险操作；或者是乘车用户和驾驶用户均处于危险状态，例如，发生交通事故。
在检测到驾驶用户存在异常驾驶行为中的危险驾驶行为的情况下，执行报警操作。其中，执行报警操作可以包括：向官方安全系统发送报警信息，报警信息包括驾驶用户的信息、乘车用户的信息和最新的定位信息等；向指定的紧急联系人发送报警信息或建立通话连接；向打车服务系统的业务人员发送报警信息或建立通话连接等。
本公开的技术方案中，分别获取驾驶用户的定位信息和乘车用户的定位信息，并分别确定驾驶用户的用户状态和乘车用户的用户状态，通过比较驾驶用户的用户状态和乘车用户的用户状态，检测驾驶用户的异常驾驶行为，以对乘车用户的乘车安全进行检测。本公开的技术方案可以根据两方的用户状态的比较结果检测驾驶用户的异常驾驶行为，提高了异常驾驶行为的检测准确率和检测效率。
图2是本公开实施例提供的另一种异常驾驶行为检测方法的流程图，基于上述技术方案进行说明，并可以与上述可选实施方式进行结合。所述对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为，包括：对所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态进行比较；在比较结果为所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态不同的情况下，确定联系状态为可联系状态的目标用户；与所述目标用户建立通话连接，并获取所述目标用户的通话信息；根据通话信息，检测所述驾驶用户的异常驾驶行为。
S201，接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态。
S202，接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态。
S203，对所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态进行比较。
联系状态用于确定定位信息是否持续上传。联系状态可以包括失联状态或可联系状态。比较结果包括相同结果或不同结果。相同结果包括第一用户状态包括的联系状态和第二用户状态包括的联系状态均为可联系状态，或均为失联状态；不同结果包括第一用户状态包括的联系状态和第二用户状态包括的联系状态中，一个为可联系状态，另一个为失联状态。
S204，在比较结果为所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态不同的情况下，确定联系状态为可联系状态的目标用户。
联系状态为可联系状态的目标用户是指持续上传定位信息的用户，即可以联系的用户。此外，失联状态的用户是指无法联系的用户。
通常，驾驶用户的联系状态和乘车用户的联系状态均为可联系状态，可以确定乘车用户处于安全状态，不执行报警操作；驾驶用户的联系状态和乘车用户的联系状态均为失联状态，存在两种情况，第一种情况是：驾驶用户驾驶的车辆行驶到信号质量差的位置，第二种情况是：乘车用户处于危险状态。可选的，在比较结果为第一用户状态包括的联系状态与第二用户状态包括的联系状态相同的情况下，获取最新时刻的定位信息；获取标注有信号质量差的位置集合；根据该位置集合，查询所述最新时刻的定位信息匹配的目标位置；在查询结果为空的情况下，确定乘车用户处于危险状态，驾驶用户存在异常驾驶行为中的危险驾驶行为，执行报警操作；在查询结果不为空的情况下，确定乘车用户处于安全状态，不执行报警操作。其中，目标位置与最新时刻的定位信息的距离小于或等于设定距离阈值。
S205，与所述目标用户建立通话连接，并获取所述目标用户的通话信息。
建立的通话连接可以是建立安全机构的标准安全用户与该目标用户之间的通话连接，还可以是建立预先指定的亲朋好友与该目标用户之间的通话连接，或者可以是建立智能机器人与该目标用户之间的通话连接。其中，通话连接可以通过客户端实现。通常，通话连接用于校验目标用户的身份以及获取乘车用户的状态和处于失联状态的用户的失联原因等信息。在通话时，可以提示发起通话方发出指定问题的语音，以使目标用户针对指定问题进行回答，可以对发起通话方与目标用户之间的通话连接录制通话音频，并从通话音频中提取通话信息，提取通话信息的方式可以是语音识别等方法；或者目 标用户针对指定问题输入信息，从输入信息中提取通话信息，提取通话信息的方式可以是语义理解等方法。通话信息包括目标用户针对指定问题的回答信息和目标用户的声音特征。通话信息用于根据目标用户提供的信息，检测乘车用户的状态。
示例性的，可以建立智能机器人与该目标用户之间的通话连接。智能机器人预先生成指定问题的语音并播放，并等待目标用户回复，并指示目标用户说出关键词、输入指定内容或输入指定手势等行为，结束当前问题的回复，播放下一个指定问题，直至目标用户回复完成全部指定问题。此外，如果检测到目标用户长时间(例如30秒)无回复，则结束当前问题的回复，播放下一个指定问题，并累计无回复的次数，在无回复的次数大于或等于设定次数阈值的情况下，确定乘车用户处于危险状态，驾驶用户存在异常驾驶行为中的危险驾驶行为，执行报警操作。其中，目标用户的回复方式可以是语音，输入指定内容或输入指定手势等。
可选的，所述与所述目标用户建立通话连接，包括：建立所述目标用户与标准安全用户之间的通话连接。
标准安全用户为安全机构的用户，可以是打车软件的业务人员，还可以是警察人员等。通过建立标准安全用户与目标用户之间的通话连接，可以通过人工方式联系目标用户，以检测乘车安全，提高乘车用户的安全性。
S206，根据通话信息，检测所述驾驶用户的异常驾驶行为。
根据通话信息，获取目标用户的身份特征和目标用户的类型等。可以获取目标用户的标准身份信息，根据标准身份信息对目标用户的身份特征进行校验，获取目标用户的身份校验结果。目标用户的类型用于确定目标用户是驾驶用户还是乘车用户。在通话过程中，乘车用户可以通过输入指定报警指令，以指示服务器执行报警操作。从而，在通话信息中查询是否存在指定报警指令的信息，获取指定报警指令的查询结果。根据通话信息可以确定目标用户的身份校验结果、目标用户的类型和指定报警指令的查询结果，并据此，检测驾驶用户是否存在异常驾驶行为中的危险驾驶行为。
对目标用户的身份特征进行校验，获取目标用户的身份校验结果，可以包括：从目标用户的语音中提取声纹特征，与目标用户的标准声纹特征进行比较，确定比较结果；获取目标用户针对指定问题的回答语音，并识别成文本，与标准答案文本进行比较，确定比较结果；从目标用户的语音中，检测出目标用户的性别特征，并与目标用户的标准性别特征进行比较确定比较结果；根据上述至少一个比较结果，确定目标用户的身份校验结果。其中，根据上述至少一个比较结果，确定目标用户的身份校验结果，可以包括：基于 比较结果对应的数值和权重，计算身份校验数值；计算身份校验数值与身份校验阈值的比较结果，并根据该比较结果，确定身份校验结果。例如，在该身份校验数值大于或等于身份校验阈值的情况下，确定目标用户的身份校验结果为校验通过；在该身份校验数值小于身份校验阈值的情况下，确定目标用户的身份校验结果为校验不通过。
在一个例子中，在目标用户的类型为驾驶用户，且身份校验结果为不通过的情况下，确定乘车用户处于危险状态，驾驶用户存在异常驾驶行为中的危险驾驶行为，执行报警操作。在目标用户的类型为驾驶用户，且身份校验结果为通过的情况下，确定乘车用户处于安全状态，驾驶用户不存在异常驾驶行为中的危险驾驶行为，不执行报警操作。在目标用户的类型为乘车用户，且身份校验结果为不通过的情况下，或者，在目标用户的类型为乘车用户，且查询到指定报警指令的情况下，确定乘车用户处于危险状态，驾驶用户存在异常驾驶行为中的危险驾驶行为，执行报警操作。在目标用户的类型为乘车用户，身份校验结果为通过，指定报警指令的查询结果为空的情况下，确定乘车用户处于安全状态，驾驶用户不存在异常驾驶行为中的危险驾驶行为，不执行报警操作。
根据本公开的技术方案，通过比较驾驶用户的联系状态和乘车用户的联系状态，并在比较驾驶用户的联系状态和乘车用户的联系状态不同的情况下，建立与联系状态为可联系状态的用户的通话连接，并获取通话信息，根据通话信息检测驾驶用户是否存在异常驾驶行为，可以在乘车用户或驾驶用户失联的应用场景中，检测驾驶用户是否存在异常驾驶行为，提高乘车安全性。
图3是本公开实施例提供的另一种异常驾驶行为检测方法的流程图，基于上述技术方案进行说明，并可以与上述可选实施方式进行结合。所述对所述第一用户状态和所述第二用户状态进行比较，包括：根据所述第一定位信息和所述第二定位信息，检测异常停留行为；在存在所述异常停留行为的情况下，对所述第一用户状态和所述第二用户状态进行比较。
S301，接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态。
S302，接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态。
S303，根据所述第一定位信息和所述第二定位信息，检测异常停留行为。
异常停留行为可以是指在异常停留状态下，且在乘车用户指定的目标终 止位置之外的位置进行停留的行为。异常停留状态包括无禁行交通灯、无路口和无拥堵等的状态。异常停留行为表明乘车用户所乘坐的车辆在目的地以外的位置停车，并且该位置并非是在路口的位置，该车辆也不是在等红灯或黄灯，以及该车辆不是处于拥堵状态。可以根据第一定位信息和第二定位信息，确定车辆是否停留。例如，可以在连续设定次数检测到第一定位信息和第二定位信息相同且不变，确定车辆停留。在检测到车辆停留时，检测停留位置是否为目标终止位置，在该停留位置与目标终止位置之间的距离大于或等于设定距离阈值的情况下，确定停留位置不是目标终止位置；在该停留位置与目标终止位置之间的距离小于设定距离阈值的情况下，确定停留位置是目标终止位置。在检测到停留位置不是目标终止位置的情况下，检测停留位置是否在路口；检测停留位置附近的交通灯是否为禁行交通灯；且检测停留位置是否处于车辆拥堵队列等，在停留位置不在路口、附近的交通灯不是禁行交通灯，并且不处于车辆拥堵队列中的情况下，确定驾驶用户存在异常停留行为。此外，还可以检测停留位置是否属于危险位置集合，在停留位置属于危险位置集合的情况下，确定驾驶用户存在异常停留行为。其中，危险位置集合包括偏僻位置和事故发生频率大于或等于设定频率阈值的位置。
可选的，所述根据所述第一定位信息和所述第二定位信息，检测异常停留行为，包括：根据所述第一定位信息和所述第二定位信息，检测偏航行为；在存在所述偏航行为的情况下，向所述乘车用户发送导航路线修改信息；接收所述乘车用户针对所述导航路线修改信息反馈的修改审核结果；在所述修改审核结果为审核不通过的情况下，根据所述第一定位信息和所述第二定位信息，检测异常停留行为。
根据第一定位信息和第二定位信息，检测第一定位信息和第二定位信息是否相同，且第一定位信息和第二定位信息是否属于乘车用户指定的导航路线的点集中。在正常情况下，驾驶用户沿着导航路线驾驶车辆。在第一定位信息和第二定位信息相同，且相同的第一定位信息和第二定位信息不属于乘车用户指定的导航路线的点集的情况下，确定驾驶用户存在偏航行为。
导航路线修改信息用于提供给乘车用户，检测乘车用户是否确认更改导航路线。修改审核结果用于确定乘车用户是否确认更改导航路线。修改审核结果为审核通过，表明乘车用户确认更改导航路线。修改审核结果为审核不通过，表明乘车用户确认不更改导航路线。在审核不通过的情况下，表明乘车用户不想更改导航路线，此时，乘车用户可能会进入比较危险的状态，本实施例根据定位信息检测是否存在异常停留行为，提高了乘车用户的危险状态的检测准确率。
此外，还可以在审核通过的情况下，继续根据第一定位信息和第二定位信息，检测是否存在偏航行为，并累计偏航行为出现的次数。在偏航行为出现的次数大于或等于设定次数阈值时，根据所述第一定位信息和所述第二定位信息，检测异常停留行为。或者，在审核不通过的情况下，继续根据第一定位信息和第二定位信息，检测是否存在偏航行为，也即检测第一定位信息和第二定位信息是否回归到初始导航路线中，如果存在偏航行为，则计算偏航行为的偏航程度，在偏航程度大于或等于程度阈值的情况下，根据所述第一定位信息和所述第二定位信息，检测异常停留行为。其中，偏航程度可以是偏航的位置点与初始导航路线之间的最小距离。
通过在存在偏航行为的情况下，向乘车用户发送导航路线修改信息，并根据反馈的修改审核结果，判断乘车用户是否同意更改导航路线，并在乘车用户不同意更改导航路线时，根据定位信息，检测异常停留行为，实现在乘车用户处于疑似风险的环境下，判断是否存在异常停留行为，从而检测是否存在异常驾驶行为，可以排除干扰因素，提高异常驾驶行为的检测准确率。
S304，在存在所述异常停留行为的情况下，对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。
通常，驾驶用户在停车状态下，才会对乘车用户进行危险操作。从而，在驾驶用户存在异常停留行为的情况下，检测用户状态，并进行比较，可以提高异常驾驶行为的检测准确率，可以排除一些干扰因素。例如，驾驶用户驶入信号质量差的路线中，导致车辆上用户处于失联状态，引起存在异常驾驶行为的错误检测结果。
可选的，所述对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为，包括：对所述第一用户状态包括的运动状态与所述第二用户状态包括的运动状态进行比较；根据运动状态的比较结果，检测所述驾驶用户的异常驾驶行为。
运动状态表示用户的运动信息，运动状态可以包括运动速度和/或运动方向等。
在运动状态包括运动方向的情况下，驾驶用户和乘车用户的运动方向不同，表明驾驶用户和乘车用户朝向不同方向运动，即乘车用户离开车辆并以车辆的行驶方向的不同方向进行运动，表明乘车用户安全离开车辆；驾驶用户和乘车用户运动方向相同，表明驾驶用户和乘车户用朝向相同方向运动，即乘车用户没有离开车辆，表明乘车用户未安全离开车辆，仍在车辆中，此时，乘车用户处于危险状态。在运动方向的比较结果为相同的情况下，确定驾驶用户存在异常驾驶行为中的危险驾驶行为；在运动方向的比较结果为不 同的情况下，确定驾驶用户不存在异常驾驶行为中的危险驾驶行为。
在运动状态包括运动速度的情况下，驾驶用户和乘车用户的运动速度不同，表明驾驶用户和乘车用户以不同速度运动，在两个用户的运动速度非零，且不同的情况下，即乘车用户离开车辆并以与车辆的行驶速度的不同速度进行运动，表明乘车用户安全离开车辆；在驾驶用户和乘车用户的运动速度相同，且非零的情况下，表明驾驶用户和乘车户用以相同速度运动，即乘车用户没有离开车辆，表明乘车用户未安全离开车辆，仍在车辆中，此时，乘车用户处于危险状态。在驾驶用户和乘车用户的运动速度相同，且为零的情况下，表明两个用户停留，即车辆停留。在驾驶用户和乘车用户的运动速度中一个为零，另一个非零的情况下，表明一个用户停留，另外一个用户运动，表明驾驶用户或乘车用户处于危险状态。在运动速度的比较结果为相同且运动速度均非零的情况下，确定驾驶用户存在异常驾驶行为中的危险驾驶行为；在运动速度的比较结果为不同且运动速度均非零的情况下，确定驾驶用户不存在异常驾驶行为中的危险驾驶行为；在运动速度的比较结果为不同且存在一个运动速度为零的情况下，确定驾驶用户存在异常驾驶行为中的危险驾驶行为；在运动速度的比较结果为相同且运动速度均为零的情况下，确定驾驶用户和乘车用户存在停留行为。
运动状态可以同时包括运动方向和运动速度，可以对运动方向和运动速度均进行判断，在根据运动方向和运动速度任一项的检测操作中确定存在异常驾驶行为中的危险驾驶行为，则确定驾驶用户存在异常驾驶行为中的危险驾驶行为。
通过比较乘车用户和驾驶用户之间的运动状态，检测驾驶用户是否存在异常驾驶行为，可以准确根据两方的运动状态的比较结果检测驾驶用户的异常驾驶行为，提高异常驾驶行为的检测准确率。
可选的，异常驾驶行为检测方法还包括：获取所述驾驶用户的历史偏航数据；根据所述历史偏航数据对所述异常驾驶行为进行修正。
历史偏航数据是指驾驶用户偏航行为的出现频率，其中，出现频率的计算方式为：统计驾驶用户执行多个出租车任务的持续时长，并统计多个出租车任务中偏航行为的出现次数，计算出现次数与持续时长的比值，确定为出现频率。历史偏航数据用于对异常驾驶行为进行修正。实际上，异常驾驶行为可以包括危险驾驶行为和绕路驾驶行为。在驾驶用户的偏航行为的频率大于或等于预设频率阈值的情况下，可以将驾驶用户存在的危险驾驶行为修改为绕路驾驶行为。或者，可以直接将驾驶用户存在的异常驾驶行为确定为绕路驾驶行为。
通过根据历史偏航数据对异常驾驶行为进行修正，可以提高异常驾驶行为的检测准确率。
此外，还可以根据偏航程度和偏航的定位信息，对异常驾驶行为进行修正。示例性的，偏航程度大于或等于预设偏航阈值，将驾驶用户存在的绕路驾驶行为修改为危险驾驶行为；从第一定位信息和第二定位信息中查询偏航的定位信息，并检测偏航的定位信息是否属于预先统计的危险位置集合，在偏航的定位信息属于预先统计的危险位置集合的情况下，将驾驶用户存在的绕路驾驶行为修改为危险驾驶行为。或者，可以直接将驾驶用户存在的异常驾驶行为确定为危险驾驶行为。
本公开的技术方案中，通过检测异常停留行为，并在存在异常停留行为的情况下，比较驾驶用户和乘车用户的用户状态，实现在乘车用户处于疑似风险的环境下，判断是否存在异常停留行为，从而检测是否存在异常驾驶行为，可以排除干扰因素，提高异常驾驶行为的检测准确率。
图4是本公开实施例提供的一种异常驾驶行为检测系统的示意图。异常驾驶行为检测系统包括服务器401、乘客端402和司机端403。
乘客端402包括目的地确认模块、行车路径确定模块、行车路线上传模块、地理数据上传模块和导航路线切换确认模块等。
乘车用户通过目的地确认模块输入目的地，确认本次行车的终点；服务器401根据目的地，结合上车地点，为乘车用户推荐多条行车路线，乘车用户通过行车路径确定模块选择其中一条路线；行车路线上传模块将乘车用户选择的路线上传服务器401；地理数据上传模块将当前的地理位置上传到服务器401；导航路线切换确认模块从服务器401获取提示的导航路线修改信息，接收乘车用户输入的确认或否认信息，并将该信息作为修改审核结果，反馈给服务器401。
司机端403包括：行车路径接收模块、行车导航模块和地理数据上传模块等。行车路径接收模块从服务器401拉取乘车用户选择的行车路径信息；行车导航模块按照行车路径进行路径导航；地理数据上传模块将当前的地理位置上传到服务器401。
服务器401可以实现如下功能：根据乘车用户的当前位置及目的地进行路径规划得到多条可供乘车用户选择的行车路线。实现司机端403与乘客端402的路径同步；获取客户端上报的驾驶用户的第一定位信息和乘车用户的第二定位信息。并对本次行程的地理位置信息或者短时间内的行程信息进行 存储；根据驾驶用户的第一定位信息和乘车用户的第二定位信息，结合乘车用户上报的行车路径，进行当前路线偏航的判断，并且根据偏航的程度向乘车用户进行提示及确认，当乘车用户确认驾驶用户的偏航行为未经过沟通，确定当前的偏航行为存在异常；此时，根据乘客端402和司机端403是否离线的用户状态，以及乘客端402和司机端403的运动状态，检测是否存在异常驾驶行为中的危险驾驶行为，并在存在异常驾驶行为中的危险驾驶行为时出发报警行为。
在一个例子中，假设乘车用户从a点到g点，服务器401进行路径规划，并向乘客端402返回三条路线：1、a,b,c,d,e,f,g；2、a,b1,c1,d,e,f,g；3、a,b,c,d1,e1,f,g。乘车用户通过乘客端402的行车路径确定模块选择路线a,b,c,d,e,f,g，并通过乘客端402的行车路线上传模块上传所选的路线。服务器401接收所选路线。司机端403的行车路径接收模块从服务器401拉取该所选路线，并通过行车导航模块开始按a,b,c,d,e,f,g导航。司机端403和乘客端402分别通过地理数据上传模块，实时获取定位信息，上传到服务器401。
服务器401周期性接收第一定位信息和第二定位信息。并检测是否出现偏航行为。当出现偏航(如a,b1)时，向乘客端402发送导航路线修改信息，以提示乘车用户偏航，驾驶用户可能要更换路线；接收乘客端402针对所述导航路线修改信息反馈的修改审核结果，以向乘车用户确认是否按新路线行驶，在修改审核结果为审核通过的情况下，更新路线数据；在修改审核结果为审核不通过的情况下，则进入预警状态。在预警状态下，根据第一定位信息和第二定位信息检测是否存在异常停留行为。在不存在异常停留行为的情况下，继续检测是否存在异常停留行为；在存在异常停留行为的情况下，对第一用户状态和第二用户状态进行比较。
服务器401对第一用户状态和第二用户状态进行比较包括：对乘车用户的联系状态和驾驶用户的联系状态进行比较。在比较结果为乘车用户的联系状态和驾驶用户的联系状态不同的情况下，即一方失联，建立与未失联的用户端的通话连接，即建立与联系状态为可联系状态的目标用户的通话连接，并根据通话连接过程中的通话信息，检测是否存在异常驾驶行为的危险驾驶行为，并在存在危险驾驶行为的情况下，启动报警，相当于是当驾驶用户或乘车用户的手机失联，服务器401主动联系另外一方确认状态。在比较结果为乘车用户的联系状态和驾驶用户的联系状态相同且均为失联状态的情况下，启动报警。
服务器401对第一用户状态和第二用户状态进行比较包括：对乘车用户的运动方向和驾驶用户的运动方向进行比较。在比较结果为乘车用户的运动 方向和驾驶用户的运动方向相同的情况下，确定存在危险驾驶行为，启动报警。
服务器401对第一用户状态和第二用户状态进行比较包括：对乘车用户的运动速度和驾驶用户的运动速度进行比较，在比较结果为乘车用户的运动速度和驾驶用户的运动速度不同，且一方的运动速度为零的情况下，确定存在危险驾驶行为，启动报警。
本公开的异常驾驶行为检测系统，在按照乘车用户预设的路线行驶的情况下，当路线出现偏差时，可主动感知，当路线比较偏僻并且是偏航时，结合车辆的状态在检测到危险驾驶行为时可以快速报警，同时对驾驶用户产生威慑力，也会对于一些不法的行为进行提醒，可能较快速地提前发现不法的行为，提高乘车安全性。
根据本公开的实施例，图5是本公开实施例提供的一种异常驾驶行为检测装置的示意图，本公开实施例适用于查询路网中连通两个区域且未记录在路网中的道路的情况。该装置采用软件和/或硬件实现，并配置于具备一定数据运算能力的电子设备中。
如图5所示的一种异常驾驶行为检测装置500，包括：驾驶用户定位信息获取模块501、乘车用户定位信息获取模块502和异常驾驶行为检测模块503；其中，驾驶用户定位信息获取模块501，设置为接收驾驶用户的第一定位信息，并确定所述驾驶用户的第一用户状态；乘车用户定位信息获取模块502，设置为接收与所述驾驶用户同车的乘车用户的第二定位信息，并确定所述乘车用户的第二用户状态；异常驾驶行为检测模块503，设置为对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。
本公开的技术方案中，分别获取驾驶用户的定位信息和乘车用户的定位信息，并分别确定驾驶用户的用户状态和乘车用户的用户状态，通过比较驾驶用户的用户状态和乘车用户的用户状态，检测驾驶用户的异常驾驶行为，以对乘车用户的乘车安全进行检测。本公开的技术方案可以根据两方的定位信息的比较结果检预测驾驶用户的异常驾驶行为，提高异常驾驶行为的检测准确率和检测效率。
如图6所示，所述异常驾驶行为检测模块503，包括：联系状态比较单元5031，设置为对所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态进行比较；可联系用户确定单元5032，设置为在比较结果为所 述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态不同的情况下，确定联系状态为可联系状态的目标用户；通话连接单元5033，设置为与所述目标用户建立通话连接，并获取所述目标用户的通话信息；通话信息处理单元5034，设置为根据通话信息，检测所述驾驶用户的异常驾驶行为。
如图7所示，所述通话连接单元5033，包括：用户间通话建立子单元50331，设置为建立所述目标用户与标准安全用户之间的通话连接。
如图8所示，所述异常驾驶行为检测模块503，包括：运动状态比较单元5035，设置为对所述第一用户状态包括的运动状态与所述第二用户状态包括的运动状态进行比较；运动状态比较结果处理单元5036，设置为根据运动状态的比较结果，检测所述驾驶用户的异常驾驶行为。
如图9所示，所述异常驾驶行为检测模块503，还包括：异常停留行为检测单元5037，设置为根据所述第一定位信息和所述第二定位信息，检测异常停留行为；用户状态比较单元5038，设置为在存在所述异常停留行为的情况下，对所述第一用户状态和所述第二用户状态进行比较。
如图10所示，所述异常停留行为检测单元5037，包括：偏航行为检测子单元50371，设置为根据所述第一定位信息和所述第二定位信息，检测偏航行为；导航路线修改信息发送子单元50372，设置为在存在所述偏航行为的情况下，向所述乘车用户发送导航路线修改信息；修改审核结果接收子单元50373，设置为接收所述乘车用户针对所述导航路线修改信息反馈的修改审核结果；偏航审核不通过结果处理子单元50374，设置为在所述修改审核结果为审核不通过的情况下，根据所述第一定位信息和所述第二定位信息，检测异常停留行为。
如图11所示，所述异常驾驶行为检测装置500，还包括：历史偏航数据获取模块504，设置为获取所述驾驶用户的历史偏航数据；异常驾驶行为修正模块505，设置为根据所述历史偏航数据对所述异常驾驶行为进行修正。
上述异常驾驶行为检测装置可执行本公开任意实施例所提供的异常驾驶行为检测方法，具备执行异常驾驶行为检测方法相应的功能模块和效果。
本公开的技术方案中，所涉及的用户个人信息或车辆信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
图12示出了可以用来实施本公开的实施例的示例电子设备600的示意性 框图。电子设备600旨在表示多种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备600还可以表示多种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图12所示，设备600包括计算单元601，其可以根据存储在只读存储器(Read-Only Memory，ROM)602中的计算机程序或者从存储单元608加载到随机访问存储器(Random Access Memory，RAM)603中的计算机程序，来执行多种适当的动作和处理。在RAM 603中，还可存储设备600操作所需的多种程序和数据。计算单元601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(Input/Output，I/O)接口605也连接至总线604。
设备600中的多个部件连接至I/O接口605，包括：输入单元606，例如键盘、鼠标等；输出单元607，例如多种类型的显示器、扬声器等；存储单元608，例如磁盘、光盘等；以及通信单元609，例如网卡、调制解调器、无线通信收发机等。通信单元609允许设备600通过诸如因特网的计算机网络和/或多种电信网络与其他设备交换信息/数据。
计算单元601可以是多种具有处理和计算能力的通用和/或专用处理组件。计算单元601的一些示例包括但不限于中央处理单元(Central Processing Unit，CPU)、图形处理单元(Graphics Processing Unit，GPU)、多种专用的人工智能(Artificial Intelligence，AI)计算芯片、多种运行机器学习模型算法的计算单元、数字信号处理器(Digital Signal Processing，DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元601执行上文所描述的多个方法和处理，例如异常驾驶行为检测方法。例如，在一些实施例中，异常驾驶行为检测方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元608。在一些实施例中，计算机程序的部分或者全部可以经由ROM 602和/或通信单元609而被载入和/或安装到设备600上。当计算机程序加载到RAM 603并由计算单元601执行时，可以执行上文描述的异常驾驶行为检测方法的一个或多个步骤。备选地，在其他实施例中，计算单元601可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行异常驾驶行为检测方法。
本文中以上描述的系统和技术的多种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产 品(Application Specific Standard Parts，ASSP)、芯片上的系统(System on Chip，SoC)、复杂可编程逻辑设备(Complex Programmable Logic Device，CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。多种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、RAM、ROM、可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：设置为向用户显示信息的显示装置(例如，阴极射线管(Cathode Ray Tube，CRT)或者液晶显示器(Liquid Crystal Display，LCD)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以设置为提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、 或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(Local Area Network，LAN)、广域网(Wide Area Network，WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，也可以为分布式系统的服务器，或者是结合了区块链的服务器。
可以使用上面所示的多种形式的流程，重新排序、增加或删除步骤。例如，本公开中记载的多个步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开提供的技术方案所期望的结果，本文在此不进行限制。

Claims (17)

  1. 一种异常驾驶行为检测方法，包括：
    接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态；
    接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态；
    对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。
  2. 根据权利要求1所述的方法，其中，所述对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为，包括：
    对所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态进行比较；
    在比较结果为所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态不同的情况下，确定联系状态为可联系状态的目标用户；
    与所述目标用户建立通话连接，并获取所述目标用户的通话信息；
    根据所述通话信息，检测所述驾驶用户的异常驾驶行为。
  3. 根据权利要求2所述的方法，其中，所述与所述目标用户建立通话连接，包括：
    建立所述目标用户与标准安全用户之间的通话连接。
  4. 根据权利要求1所述的方法，其中，所述对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为，包括：
    对所述第一用户状态包括的运动状态与所述第二用户状态包括的运动状态进行比较；
    根据运动状态的比较结果，检测所述驾驶用户的异常驾驶行为。
  5. 根据权利要求1所述的方法，其中，所述对所述第一用户状态和所述第二用户状态进行比较，包括：
    根据所述第一定位信息和所述第二定位信息，检测异常停留行为；
    在存在所述异常停留行为的情况下，对所述第一用户状态和所述第二用户状态进行比较。
  6. 根据权利要求5所述的方法，其中，所述根据所述第一定位信息和所述第二定位信息，检测异常停留行为，包括：
    根据所述第一定位信息和所述第二定位信息，检测偏航行为；
    在存在所述偏航行为的情况下，向所述乘车用户发送导航路线修改信息；
    接收所述乘车用户针对所述导航路线修改信息反馈的修改审核结果；
    在所述修改审核结果为审核不通过的情况下，根据所述第一定位信息和所述第二定位信息，检测所述异常停留行为。
  7. 根据权利要求1所述的方法，还包括：
    获取所述驾驶用户的历史偏航数据；
    根据所述历史偏航数据对所述异常驾驶行为进行修正。
  8. 一种异常驾驶行为检测装置，包括：
    驾驶用户定位信息获取模块，设置为接收驾驶用户的第一定位信息，并根据所述第一定位信息确定所述驾驶用户的第一用户状态；
    乘车用户定位信息获取模块，设置为接收与所述驾驶用户同车的乘车用户的第二定位信息，并根据所述第二定位信息确定所述乘车用户的第二用户状态；
    异常驾驶行为检测模块，设置为对所述第一用户状态和所述第二用户状态进行比较，并根据比较结果检测所述驾驶用户的异常驾驶行为。
  9. 根据权利要求8所述的装置，其中，所述异常驾驶行为检测模块，包括：
    联系状态比较单元，设置为对所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态进行比较；
    可联系用户确定单元，设置为在比较结果为所述第一用户状态包括的联系状态与所述第二用户状态包括的联系状态不同的情况下，确定联系状态为可联系状态的目标用户；
    通话连接单元，设置为与所述目标用户建立通话连接，并获取所述目标用户的通话信息；
    通话信息处理单元，设置为根据所述通话信息，检测所述驾驶用户的异常驾驶行为。
  10. 根据权利要求9所述的装置，其中，所述通话连接单元，包括：
    用户间通话建立子单元，设置为建立所述目标用户与标准安全用户之间的通话连接。
  11. 根据权利要求8所述的装置，其中，所述异常驾驶行为检测模块，包括：
    运动状态比较单元，设置为对所述第一用户状态包括的运动状态与所述第二用户状态包括的运动状态进行比较；
    运动状态比较结果处理单元，设置为根据运动状态的比较结果，检测所述驾驶用户的异常驾驶行为。
  12. 根据权利要求11所述的装置，其中，所述异常驾驶行为检测模块，还包括：
    异常停留行为检测单元，设置为根据所述第一定位信息和所述第二定位信息，检测异常停留行为；
    用户状态比较单元，设置为在存在所述异常停留行为的情况下，对所述第一用户状态和所述第二用户状态进行比较。
  13. 根据权利要求12所述的装置，其中，所述异常停留行为检测单元，包括：
    偏航行为检测子单元，设置为根据所述第一定位信息和所述第二定位信息，检测偏航行为；
    导航路线修改信息发送子单元，设置为在存在所述偏航行为的情况下，向所述乘车用户发送导航路线修改信息；
    修改审核结果接收子单元，设置为接收所述乘车用户针对所述导航路线修改信息反馈的修改审核结果；
    偏航审核不通过结果处理子单元，设置为在所述修改审核结果为审核不通过的情况下，根据所述第一定位信息和所述第二定位信息，检测所述异常停留行为。
  14. 根据权利要求8所述的装置，还包括：
    历史偏航数据获取模块，设置为获取所述驾驶用户的历史偏航数据；
    异常驾驶行为修正模块，设置为根据所述历史偏航数据对所述异常驾驶行为进行修正。
  15. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述 至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-7中任一项所述的异常驾驶行为检测方法。
  16. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行根据权利要求1-7中任一项所述的异常驾驶行为检测方法。
  17. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-7中任一项所述的异常驾驶行为检测方法。
PCT/CN2022/083014 2021-08-10 2022-03-25 异常驾驶行为检测方法、装置、电子设备和存储介质 WO2023015900A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110915765.8 2021-08-10
CN202110915765.8A CN113657632B (zh) 2021-08-10 2021-08-10 异常驾驶行为检测方法、装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2023015900A1 true WO2023015900A1 (zh) 2023-02-16

Family

ID=78479425

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/083014 WO2023015900A1 (zh) 2021-08-10 2022-03-25 异常驾驶行为检测方法、装置、电子设备和存储介质

Country Status (2)

Country Link
CN (1) CN113657632B (zh)
WO (1) WO2023015900A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113657632B (zh) * 2021-08-10 2023-11-07 百度在线网络技术（北京）有限公司 异常驾驶行为检测方法、装置、电子设备和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791009A (zh) * 2016-11-28 2017-05-31 北京奇虎科技有限公司 协助用户安全出行的方法及相关设备
CN111064841A (zh) * 2018-10-16 2020-04-24 北京嘀嘀无限科技发展有限公司 消息发送方法、装置及服务器
CN112017463A (zh) * 2020-07-17 2020-12-01 盛威时代科技集团有限公司 智能化的网约车管理方法
CN112183245A (zh) * 2020-09-11 2021-01-05 广州宸祺出行科技有限公司 一种监测网约车司机异常行为并告警的方法、装置及电子设备
CN112389448A (zh) * 2020-11-23 2021-02-23 重庆邮电大学 一种基于车辆状态和驾驶员状态的异常驾驶行为识别方法
CN113657632A (zh) * 2021-08-10 2021-11-16 百度在线网络技术（北京）有限公司 异常驾驶行为检测方法、装置、电子设备和存储介质

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20150044064A (ko) * 2013-10-15 2015-04-24 조성훈 스마트기기를 이용한 편리하고 안전한 택시이용방법
CN106056839B (zh) * 2016-06-30 2018-12-25 武汉斑马快跑科技有限公司 网约车安全监测系统及方法
US9919648B1 (en) * 2016-09-27 2018-03-20 Robert D. Pedersen Motor vehicle artificial intelligence expert system dangerous driving warning and control system and method
CN109697844B (zh) * 2017-10-20 2020-11-17 北京嘀嘀无限科技发展有限公司 状态信息处理方法及装置
CN110447214B (zh) * 2018-03-01 2022-04-15 北京嘀嘀无限科技发展有限公司 一种识别驾驶行为的系统、方法、装置和存储介质
CN108810804B (zh) * 2018-06-13 2020-06-09 车城智行信息技术(成都)有限公司 一种基于网约车平台的智能防护方法及其系统
CN108765930B (zh) * 2018-06-26 2021-02-09 上海掌门科技有限公司 行车监控方法及设备
CN111147671A (zh) * 2018-11-02 2020-05-12 北京嘀嘀无限科技发展有限公司 信息处理方法、装置、服务器及计算机可读存储介质
CN110782625A (zh) * 2018-12-17 2020-02-11 北京嘀嘀无限科技发展有限公司 乘车安全报警方法、装置、电子设备及存储介质
CN109859089A (zh) * 2019-01-31 2019-06-07 平安科技（深圳）有限公司 预警用户乘车安全方法、装置、计算机设备和存储介质
CN111598368B (zh) * 2019-02-21 2023-09-05 北京嘀嘀无限科技发展有限公司 基于行程结束后停留异常的风险识别方法、系统及装置
CN110049096A (zh) * 2019-03-01 2019-07-23 深圳市华慧云科技有限公司 网约顺风车行程监控和紧急信息发送方法
CN110070889A (zh) * 2019-03-15 2019-07-30 深圳壹账通智能科技有限公司 车辆监控方法、装置及存储介质、服务器
CN111859104A (zh) * 2020-03-31 2020-10-30 北京嘀嘀无限科技发展有限公司 一种乘客状态判断方法、装置、电子设备和存储介质
CN111953789A (zh) * 2020-08-17 2020-11-17 广西云森科技有限公司 基于语音识别的网约车异常驾驶环境监督系统及方法
CN113038383A (zh) * 2021-02-01 2021-06-25 丰桔出行(北京)科技有限公司 一种网约车安全监测系统及方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106791009A (zh) * 2016-11-28 2017-05-31 北京奇虎科技有限公司 协助用户安全出行的方法及相关设备
CN111064841A (zh) * 2018-10-16 2020-04-24 北京嘀嘀无限科技发展有限公司 消息发送方法、装置及服务器
CN112017463A (zh) * 2020-07-17 2020-12-01 盛威时代科技集团有限公司 智能化的网约车管理方法
CN112183245A (zh) * 2020-09-11 2021-01-05 广州宸祺出行科技有限公司 一种监测网约车司机异常行为并告警的方法、装置及电子设备
CN112389448A (zh) * 2020-11-23 2021-02-23 重庆邮电大学 一种基于车辆状态和驾驶员状态的异常驾驶行为识别方法
CN113657632A (zh) * 2021-08-10 2021-11-16 百度在线网络技术（北京）有限公司 异常驾驶行为检测方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
CN113657632B (zh) 2023-11-07
CN113657632A (zh) 2021-11-16

Similar Documents

Publication Publication Date Title
US10255648B2 (en) Self-driving vehicle systems and methods
US11899449B1 (en) Autonomous vehicle extended reality environments
US10268192B1 (en) Self-driving vehicle systems and methods
US20210312809A1 (en) Apparatus and method for safety improvement by collaborative autonomous vehicles
US10466057B1 (en) Self-driving vehicle systems and methods
US10794714B2 (en) Self-driving vehicle systems and methods
US10775783B2 (en) System for asymmetric just-in-time human intervention in automated vehicle fleets
JP2022084758A (ja) 車両監視方法、装置、電子機器、記憶媒体、コンピュータプログラム、クラウド制御プラットフォームおよび車路連携システム
US11215987B2 (en) Exception situation playback for tele-operators
KR102176223B1 (ko) 네트워크 서비스와 연관하여 안전 동작들을 수행하기 위한 시스템 및 방법
US20190318631A1 (en) Providing inter-vehicle data communications for vehicular drafting operations
US8712681B2 (en) High safety vehicular transportation system and operational method thereof
CN103454930B (zh) 减少驾驶员口语对话期间的分心
CN109345829A (zh) 无人车的监控方法、装置、设备及存储介质
WO2023015900A1 (zh) 异常驾驶行为检测方法、装置、电子设备和存储介质
US20220335535A1 (en) Traffic accident processing method and apparatus, device, storage medium and program product
WO2021138341A1 (en) Pattern-based adaptation model for detecting contact information requests in a vehicle
US20210097983A1 (en) Method for monitoring spoken communication in rail traffic and associated train control system
JP2021163498A (ja) 交通マネージャ輸送手段
CN114644030A (zh) 一种列车自动监控系统
KR20200027231A (ko) 차량과 응급 구난자의 연결 방법 및 시스템
KR20200115879A (ko) 열차통합무선망 기반 열차무선방호시스템
CN113183983B (zh) 控制车辆的方法、装置、电子设备、存储介质及程序产品
WO2021153382A1 (ja) 情報処理方法、及び、情報処理システム
CN114616139A (zh) 通过听觉信号的拼车的行程认证

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: 22854905

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22854905

Country of ref document: EP

Kind code of ref document: A1