A dangerous driving behavior monitoring method, device and electronic equipment

Abstract

The application discloses a kind of dangerous driving behavior monitoring method, comprising: obtaining the real-time driving data of driver end, and the driving order that hits preset driving rule is marked with exception label;Real-time traffic data of current driving path is obtained, and traffic rule is generated according to real-time traffic data;Real-time driving data carrying exception label is detected by traffic rule;If real-time driving data hits traffic rule, the exception label is removed;If real-time driving data does not hit traffic rule, the exception label is converted into dangerous driving label.By the way of marking exception label, first find out those real-time driving data of driver end that exceed normal driving data range, and by calling real-time traffic data, the generation scene of real-time driving data marked as exception label is further verified by traffic rule generated by traffic data, effectively identify the real-time driving data generated under unexpected accident, avoid to bring misjudgment to driver end and cause punishment.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of online car-hailing, and particularly relates to a dangerous driving behavior monitoring method and device and electronic equipment. BACKGROUND

[0002] There are a large number of non-standard driving behaviors in the journey of online car-hailing drivers, such as playing mobile phones while driving, fatigue driving, or speeding, etc. These dangerous driving behaviors bring great safety hazards to the drivers and passengers.

[0003] In the prior art, in order to prevent dangerous driving behaviors of drivers from causing dangerous accidents, an online car-hailing platform usually obtains real-time driving data of online car-hailing drivers, compares the data with normal driving data, identifies abnormal data that is out of the range of normal driving data, analyzes the dangerous driving behaviors of the driver according to the type of abnormal data, and gives a warning or an alarm to the driver according to the different degrees of dangerous driving behaviors. This method for identifying dangerous driving behaviors is difficult to identify the real driving conditions of the driver, and is prone to cause false judgments. SUMMARY

[0004] The present application aims to solve the above technical problems, and provides a dangerous driving behavior monitoring method, device and electronic equipment.

[0005] In order to solve the above problems, the present application is implemented according to the following technical solutions:

[0006] In a first aspect, the present application provides a dangerous driving behavior monitoring method, comprising:

[0007] Obtaining real-time driving data of a driver terminal, and labeling an abnormal tag to a driving order that hits a preset driving rule;

[0008] Obtaining real-time traffic data of a current driving path, and generating a traffic rule according to the real-time traffic data;

[0009] Detecting the real-time driving data carrying the abnormal tag by the traffic rule; if the real-time driving data hits the traffic rule, the abnormal tag is removed; if the real-time driving data does not hit the traffic rule, the abnormal tag is converted into a dangerous driving tag.

[0010] In combination with the first aspect, the present application further provides a first embodiment of the first aspect, which specifically comprises:

[0011] Obtaining real-time driving speed data of a driver terminal;

[0012] Labeling an overspeed abnormal tag to real-time driving speed data that hits an overspeed driving rule; the overspeed driving rule is a driving speed threshold of a current road section;

[0013] obtain road congestion data of the current driving path, and generate congestion road condition rules according to the road congestion data; if the road congestion data of the current driving path exceeds a road congestion threshold, the overspeed abnormality label is converted into an overspeed dangerous driving label.

[0014] With reference to the first aspect, the application further provides a second implementation manner of the first aspect, further comprising:

[0015] If the road congestion data of the current driving path does not exceed the road congestion threshold, the number of overspeed abnormality labels carried in the driving order is obtained;

[0016] If the number of overspeed abnormality labels carried in the driving order is within a number threshold of overspeed abnormality labels, the overspeed abnormality label is removed; if the number of overspeed abnormality labels carried in the driving order exceeds the number threshold of overspeed abnormality labels, an overspeed dangerous driving label is marked for the driving order.

[0017] With reference to the first aspect, the application further provides a third implementation manner of the first aspect, specifically comprising:

[0018] obtain real-time driving acceleration data of the driver side; the value of the acceleration data is a speed change difference value in a preset time period;

[0019] real-time driving speed data that hits the sudden speed change driving rule is marked with a sudden speed change abnormality label; the sudden speed change driving rule is a threshold of the speed change difference value in the preset time period;

[0020] obtain traffic light coordinate data of the current driving path, and generate traffic light road condition recognition rules according to the traffic light coordinate data; if the generation point of the sudden speed change abnormality label is located after the traffic light coordinate, the sudden speed change abnormality label is removed; if the generation point of the sudden speed change abnormality label is located before a traffic light passing time period, the sudden speed change abnormality label is converted into a sudden speed change dangerous driving label.

[0021] With reference to the first aspect, the application further provides a fourth implementation manner of the first aspect, further comprising:

[0022] obtain road congestion data of the current driving path, and generate congestion road condition rules according to the road congestion data; if the road congestion data of the current driving path exceeds a road congestion threshold, the number of sudden speed change abnormality labels carried in the driving order is obtained;

[0023] If the number of sudden speed change abnormality labels carried in the driving order is within a number threshold of sudden speed change abnormality labels, the sudden speed change abnormality label is removed; if the number of sudden speed change abnormality labels carried in the driving order exceeds the number threshold of sudden speed change abnormality labels, a sudden speed change dangerous driving label is marked for the driving order.

[0024] In combination with the first aspect, the present application further provides the fifth implementation form of the first aspect, which specifically comprises:

[0025] obtaining the sudden braking data of the driver terminal;

[0026] labeling the real-time driving speed data that meets the sudden braking driving rule with a sudden braking abnormality label; the sudden braking driving rule is a sudden braking frequency threshold of the current road section;

[0027] obtaining the road congestion data of the current driving path, and generating a congestion road condition rule according to the road congestion data; if the road congestion data of the current driving path exceeds a road congestion threshold, the sudden braking abnormality label is removed; if the road congestion data of the current driving path is within the road congestion threshold, the sudden braking abnormality label is converted into a sudden braking dangerous driving label.

[0028] In combination with the first aspect, the present application further provides the sixth implementation form of the first aspect, which specifically comprises:

[0029] obtaining the voice data of the driver and the passenger;

[0030] labeling the voice data that meets the voice driving rule as a voice abnormality label; the voice driving rule is the voice duration of the driver voice and the passenger voice within a predetermined time;

[0031] obtaining the face image data of the driver and the passenger, and identifying the pupil data in the face image data; if the pupil data of the passenger is directed to the driver, the voice abnormality label is removed; if the pupil data of the passenger is not directed to the driver, the voice abnormality label is converted into a voice dangerous driving label.

[0032] In combination with the first aspect, the present application further provides the seventh implementation form of the first aspect, which further comprises:

[0033] obtaining the weather data of the current path, and obtaining the wading point coordinates of the current path if there is rain data in a preset time period before the current path;

[0034] if the distance between the current driver terminal coordinates and the wading point coordinates is within a preset distance, sending a wading warning information to the driver terminal.

[0035] The second aspect of the present application provides a dangerous driving behavior monitoring device, which comprises:

[0036] an abnormality label labeling module, which is used for obtaining the real-time driving data of the driver terminal, and labeling the driving order that meets the preset driving rule with an abnormality label;

[0037] A road condition rule generation module is configured to acquire real-time road condition data of a current driving path and generate road condition rules according to the real-time road condition data.

[0038] A label conversion module is configured to detect real-time driving data carrying an abnormal label according to the road condition rules, remove the abnormal label if the real-time driving data hits the road condition rules, and convert the abnormal label into a dangerous driving label if the real-time driving data does not hit the road condition rules.

[0039] In a third aspect, the present application provides an electronic device comprising a processor and a memory, wherein the processor is connected to the memory, and the memory stores machine readable instructions executable by the processor, and when the electronic device is running, the machine readable instructions are executed by the processor to perform the steps of the dangerous driving behavior monitoring method according to any one of the first aspect.

[0040] Compared with the prior art, the present application has the following advantages:

[0041] In the embodiments of the present application, the real-time driving data that exceeds the normal driving data range in the driver terminal is first found out by marking an abnormal label, and the real-time driving data marked as the abnormal label is further verified by the road condition rules generated according to the real-time road condition data, so that the real-time driving data generated in an unexpected accident can be effectively identified, and the driver terminal can be prevented from being wrongly judged and punished. BRIEF DESCRIPTION OF DRAWINGS

[0042] The specific embodiments of the present application will be further described in detail below with reference to the accompanying drawings, in which:

[0043] Figure 1 is a flowchart of the dangerous driving behavior monitoring method of the present application

[0044] Figure 2 is a structural schematic diagram of the dangerous driving behavior monitoring device of the present application. DETAILED DESCRIPTION

[0045] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application.

[0046] The preferred embodiments of the present application will be described below in more detail with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0047] The term "includes" and its variants are meant to cover non-exclusive inclusions, i.e., that the listed items are included, but other items are not precluded. The term "or" is meant to be used in the inclusive sense, i.e., "and / or". The term "based on" means "based, at least in part, on". The terms "one example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "a first," "a second," etc. do not require that there be only one of each, but rather, they can mean one or more than one. Other explicit or implicit definitions can also be included below.

[0048] The network car driver is prone to a large number of non-standard driving behaviors during driving, which brings great safety hazards to the driver and the passenger. In order to standardize the driving behavior of the driver, the network car platform usually obtains the driving data of the network car through real-time monitoring, and compares the data with the normal driving data. The data that exceeds the range of the normal driving data is identified as abnormal data, and the dangerous driving behavior of the driver is analyzed according to the type of the abnormal data. The driver is warned or alarmed according to the different degrees of dangerous driving behavior, and the warning method is usually to deduct the score of the driver. The order quantity obtained by the driver with low score is less and the order quality is poor. However, the data obtained by this identification method is only single-dimensional data, which is difficult to judge the real driving condition of the network car driver. Some network car drivers are misjudged to be deducted due to some unexpected accidents on the driving path, which brings great loss to the network car driver.

[0049] Embodiment 1

[0050] As shown in Figure 1 The dangerous driving behavior monitoring method of the present application comprises:

[0051] Step S1: obtaining real-time driving data of the driver end, and marking the driving order that hits the preset driving rule with an abnormal label;

[0052] Step S2: obtaining real-time road condition data of the current driving path, and generating a road condition rule according to the real-time road condition data;

[0053] Step S3: detecting the real-time driving data carrying the abnormal label through the road condition rule; if the real-time driving data hits the road condition rule, the abnormal label is removed; if the real-time driving data does not hit the road condition rule, the abnormal label is converted into a dangerous driving label.

[0054] In this embodiment, by marking the abnormal label, the real-time driving data that exceeds the normal driving data range in the driver terminal is found out, and the real-time driving data marked as an abnormal label is further verified by calling the real-time traffic data and the traffic rules generated by the traffic data, so as to effectively identify the real-time driving data generated in unexpected accidents and avoid misjudgment of the driver terminal.

[0055] In this embodiment, a dangerous driving behavior monitoring method specifically includes:

[0056] Step A1: acquiring real-time driving speed data of the driver terminal;

[0057] Step A2: marking the real-time driving speed data that hits the overspeed driving rule with an overspeed abnormal label; the overspeed driving rule is a driving speed threshold of the current road section;

[0058] Step A3: acquiring road congestion data of the current driving path, and generating congestion traffic rules according to the road congestion data; if the road congestion data of the current driving path exceeds a road congestion threshold, the overspeed abnormal label is converted into an overspeed dangerous driving label.

[0059] In steps A1-A3, the real-time driving speed data of the driver terminal is acquired to identify the overspeed driving data of the driver and mark the overspeed abnormal label, and the detection frequency of the overspeed abnormal label is usually 10s or 15s. Then, the congestion traffic rules generated by the road congestion data of the previous driving path are used to effectively identify the scene of the overspeed driving data generation. If the road congestion data of the current driving path exceeds the road congestion threshold, the overspeed dangerous driving behavior of the ride-hailing driver is effectively identified in the case of a large number of vehicles on the road.

[0060] In a preferred embodiment, it further includes:

[0061] Step A4: if the road congestion data of the current driving path does not exceed the road congestion threshold, the number of overspeed abnormal labels carried in the driving order is acquired;

[0062] Step A5: if the number of overspeed abnormal labels carried in the driving order is within the number threshold of the overspeed abnormal label, the overspeed abnormal label is removed; if the number of overspeed abnormal labels carried in the driving order exceeds the number threshold of the overspeed abnormal label, the driving order is marked with an overspeed dangerous driving label.

[0063] In steps A4-A5, when there are few vehicles on the road, the ride-hailing vehicle can meet the driving requirements of the driver and the passenger at the normal driving speed. However, there will be some unexpected accidents during driving, such as overtaking when parallel to a large truck, and overtaking when giving way to an ambulance or fire truck.

[0064] Generally, the number of overspeed abnormal tags generated by the unexpected accidents in the online car-hailing order is usually less than three, but some online car-hailing drivers or passengers accelerate even in the case of non-congested road to save time, and the overspeed abnormal tag data obtained in this driving state is far more than three. The overspeed driving behavior generated by the unexpected accidents and the overspeed driving behavior under the subjective factors can be effectively identified.

[0065] In an embodiment, a method for monitoring dangerous driving behavior, specifically comprising:

[0066] Step B1: obtaining real-time driving acceleration data of the driver side; the value of the acceleration data is the speed change difference value in a preset time period;

[0067] Step B2: labeling the real-time driving speed data that hits the sudden speed change driving rule with a sudden speed change abnormal tag; the sudden speed change driving rule is a threshold value of the speed change difference value in a preset time period;

[0068] Step B3: obtaining traffic light coordinate data of the current driving path, and generating traffic light road condition recognition rules according to the traffic light coordinate data; if the generation point of the sudden speed change abnormal tag is located within 2m behind the traffic light coordinate, the sudden speed change abnormal tag is removed; if the generation point of the sudden speed change abnormal tag is located within 10m before the traffic light passing time period, the sudden speed change abnormal tag is converted into a sudden speed change dangerous driving tag.

[0069] In steps B1-B3, the real-time driving acceleration data of the driver side is obtained to identify the sudden speed change driving data of the driver and label the sudden speed change abnormal tag. The acceleration data is the speed change difference value per second, and then the traffic light road condition recognition rules generated by the traffic light coordinate data of the previous driving path are used to effectively identify the scene of the sudden speed change driving data. If the generation point of the sudden speed change abnormal tag is located within 2m behind the traffic light coordinate, the sudden speed change abnormal tag is removed. It indicates that the driver is in the process of passing the traffic light, the traffic light suddenly changes from green to yellow, and the driver accelerates through the traffic light to the other side of the intersection in a short time, which can avoid the driver being stuck in the middle of the road and affect the normal driving behavior of vehicles in other directions. If the generation point of the sudden speed change abnormal tag is located within 10m before the traffic light coordinate, it indicates that the driver is suspected of stealing the yellow light, and the sudden speed change abnormal tag is converted into a sudden speed change dangerous driving tag, which effectively identifies the subjective dangerous driving behavior of the driver.

[0070] In a preferred embodiment, it further comprises:

[0071] Step B4: Obtain road congestion data of the current driving path, and generate congestion road condition rules according to the road congestion data; if the road congestion data of the current driving path exceeds the road congestion threshold, obtain the number of sudden change speed abnormality labels carried in the driving order;

[0072] Step B5: If the number of sudden change speed abnormality labels carried in the driving order is within the number threshold of sudden change speed abnormality labels, remove the sudden change speed abnormality label; if the number of sudden change speed abnormality labels carried in the driving order exceeds the number threshold of sudden change speed abnormality labels, mark the driving order with a sudden change speed dangerous driving label.

[0073] In steps B4-B5, when the road is congested, there is a dangerous driving behavior of sudden change speed overtaking by the driver, and for the driver who subjectively exists overtaking, there are multiple overtaking behaviors in the congested road section, and for the driver who objectively exists overtaking, such as overtaking behavior of giving way to an ambulance or a fire truck, generally less than three times, by identifying the number of sudden change speed abnormality labels, the sudden change speed overtaking behavior under subjective and objective factors is effectively identified, the driving order of the driver who subjectively exists sudden change speed dangerous driving behavior is marked with a sudden change speed dangerous driving label, and further warning and punishment are given; and the driving order of the driver who objectively exists sudden change speed dangerous driving behavior cancels the sudden change speed abnormality label.

[0074] In another embodiment, a dangerous driving behavior monitoring method specifically includes:

[0075] Step C1: Obtain sudden braking data of the driver side;

[0076] Step C2: Mark real-time driving speed data that hits the sudden braking driving rule with a sudden braking abnormality label; the sudden braking driving rule is a sudden braking frequency threshold of the current road section;

[0077] Step C3: Obtain road congestion data of the current driving path, and generate congestion road condition rules according to the road congestion data; if the road congestion data of the current driving path exceeds the road congestion threshold, remove the sudden braking abnormality label; if the road congestion data of the current driving path is within the road congestion threshold, convert the sudden braking abnormality label into a sudden braking dangerous driving label.

[0078] In steps C1-C3, by obtaining real-time driving acceleration data of the driver side, sudden change speed driving data of the driver is identified and sudden change speed abnormality label is marked,

[0079] The driver's emergency braking data is obtained and the emergency braking abnormal label is labeled, and the emergency braking driving rule is the number of emergency braking times of the current road section. In a trip, it is inevitable to have pedestrians crossing the road and the front vehicle breaking down without displaying the fault light, and the driver has to brake in emergency. However, the probability of such accidents is low, and the number of emergency braking in a driving order is generally not more than three. As for the emergency braking caused by the driver's fatigue driving and the like, since the driver's driving state is poor, there are a large number of emergency braking behaviors, and the number of emergency braking is effectively identified to identify the driver's emergency braking dangerous driving behavior.

[0080] In still another embodiment, a dangerous driving behavior monitoring method specifically includes:

[0081] Step D1: obtaining voice data of the driver and the passenger;

[0082] Step D2: labeling the voice data hitting the voice driving rule as a voice abnormal label; the voice driving rule is the voice duration of the driver's voice and the passenger's voice within a predetermined time;

[0083] Step D3: obtaining face image data of the driver and the passenger, and identifying the pupil data in the face image data; if the passenger's pupil data is toward the driver, the voice abnormal label is canceled.

[0084] In a real scene, there is a behavior of the driver using two or more mobile phones, only one mobile phone is installed with an app software of a network car-hailing platform, and the other mobile phones are used as mobile phones for making calls. The app software can only monitor the mobile phone installed with the app software, and cannot effectively monitor the other mobile phones, so it is also impossible to effectively monitor the driver's calling behavior during driving.

[0085] In steps D1-D3, when the driver is making a call, the driver usually wears an electronic device such as a Bluetooth headset, and it is difficult to distinguish whether the driver is making a call or communicating with the passenger during voice collection. In this embodiment, the voice data of the driver and the passenger is obtained, if the voice data only contains the driver's voice within 30s, the driver is labeled with a voice abnormal label. Generally, when the driver communicates with the passenger, the driver's voice and the passenger's voice are interlaced, and when the driver makes a call, only the driver's voice can be collected. Some drivers like to tell stories to passengers, and there is also voice data of the driver within 30s. At this time, the face image data of the driver and the passenger is called, when the driver is telling a story, the passenger usually concentrates on listening to the story, and the pupil is toward the driver. At this time, it can be determined that the driver is not making a call, and the voice abnormal label is canceled. If the passenger's pupil is not toward the driver, it is determined that the driver is making a call.

[0086] In a preferred embodiment, in order to further ensure the safe driving of the driver, it further includes:

[0087] Step E1: Obtain current path weather data, if there is rain data in the preset time period before the current path, obtain the coordinates of the wading point of the current path;

[0088] Step E2: If the distance between the current driver terminal coordinates and the wading point coordinates is within the preset distance, send a wading warning message to the driver terminal.

[0089] In steps E1 and E2, after the order is generated, the weather records of the previous three days in the driving path are called in combination with the real-time traffic data, if there is rain or snow weather in the previous three days, the wading point coordinates of the driving path are called, the wading point coordinates are the coordinates of the low-lying place in the traffic, when the driver coordinates and the wading point coordinates are within 200m, the driver is reminded that there is a wading point in front of 200m, and when the driver coordinates and the wading point coordinates are within 50m, the driver is reminded again, so that the driver drives slowly, and when the water in the wading point is serious, another driving path is found.

[0090] The other steps of the dangerous driving behavior monitoring method described in the application refer to the prior art.

[0091] Example 2

[0092] As Figure 2 shown, in a second aspect, the application discloses a dangerous driving behavior monitoring device, which comprises an abnormal label marking module M1, a traffic rule generation module M2 and a label conversion module M3.

[0093] The abnormal label marking module M1 is used to obtain real-time driving data of the driver terminal, and to mark an abnormal label for a driving order that hits a preset driving rule;

[0094] The traffic rule generation module M2 is used to obtain real-time traffic data of the current driving path, and to generate traffic rules according to the real-time traffic data;

[0095] The label conversion module M3 is used to detect real-time driving data carrying an abnormal label through traffic rules; if the real-time driving data hits the traffic rules, the abnormal label is removed; if the real-time driving data does not hit the traffic rules, the abnormal label is converted into a dangerous driving label.

[0096] As described above, the dangerous driving behavior monitoring device described in this embodiment can realize all steps of the dangerous driving behavior monitoring method described in embodiment 1 when it is running, so as to achieve the technical effects achieved in embodiment 1.

[0097] The other structures of the dangerous driving behavior monitoring device described in this embodiment refer to the prior art.

[0098] Example 3

[0099] The application further discloses an electronic device, at least one processor, and a memory connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, and the at least one processor executes the following steps when executing the instructions:

[0100] Real-time driving data of the driver end is acquired, and an abnormal label is marked for a driving order that hits a preset driving rule;

[0101] Real-time traffic data of a current driving path is acquired, and traffic rules are generated according to the real-time traffic data;

[0102] Real-time driving data carrying the abnormal label is detected through the traffic rules, if the real-time driving data hits the traffic rules, the abnormal label is removed, and if the real-time driving data does not hit the traffic rules, the abnormal label is converted into a dangerous driving label.

[0103] Embodiment 4

[0104] The application further discloses a storage medium that stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0105] Real-time driving data of the driver end is acquired, and an abnormal label is marked for a driving order that hits a preset driving rule;

[0106] Real-time traffic data of a current driving path is acquired, and traffic rules are generated according to the real-time traffic data;

[0107] Real-time driving data carrying the abnormal label is detected through the traffic rules, if the real-time driving data hits the traffic rules, the abnormal label is removed, and if the real-time driving data does not hit the traffic rules, the abnormal label is converted into a dangerous driving label.

[0108] The present disclosure can be a method, apparatus, system and / or computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions loaded thereon for executing various aspects of the present disclosure.

[0109] Computer readable storage media can be tangible storage media which can retain and store instructions for use by an instruction execution device. Computer readable storage media can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer readable storage media include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0110] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0111] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0112] While the foregoing has described what are considered to be the best mode and / or other examples, it is understood that various modifications can be made to the embodiments described herein, and that such modifications are intended to be within the scope of this disclosure. One skilled in the art will recognize that the forgoing has been made in a more or less specific context, and that work in an art also includes combinations from other technologies. It is therefore understood that the application can be practiced with modification and alteration, and that the application be limited only by the scope and the spirit of the following claims.

Claims

1. A method for monitoring dangerous driving behavior, characterized in that, include: Obtain real-time driving data from the driver's end and mark abnormal driving orders that match preset driving rules with anomaly tags; Obtain real-time traffic data for the current driving route and generate traffic rules based on the real-time traffic data; Real-time driving data carrying anomaly tags is detected by traffic condition rules; if the real-time driving data matches the traffic condition rules, the anomaly tag is removed; if the real-time driving data does not match the traffic condition rules, the anomaly tag is converted into a dangerous driving tag. Acquire voice data from drivers and passengers; Voice data that matches the voice driving rules are labeled as voice anomalies; the voice driving rules are the duration of driver and passenger voices within a predetermined time. Acquire facial image data of the driver and passengers, and identify the pupil data in the face; If the passenger's pupils are facing the driver, then the voice abnormality label is removed; If the passenger's pupils are not facing the driver, the voice abnormality label is converted into a voice dangerous driving label.

2. The method for monitoring dangerous driving behavior according to claim 1, characterized in that... Specifically, it includes: Obtain real-time driving speed data from the driver's end; The real-time driving speed data that meets the speeding rule is labeled with a speeding anomaly tag; the speeding rule is the driving speed threshold for the current road segment; Obtain road congestion data for the current driving route and generate congestion traffic rules based on the road congestion data; if the road congestion data for the current driving route exceeds the road congestion threshold, convert the speeding abnormal label into a speeding dangerous driving label.

3. The method for monitoring dangerous driving behavior according to claim 2, characterized in that, Also includes: If the road congestion data of the current driving route does not exceed the road congestion threshold, then obtain the number of speeding abnormal tags carried in the driving order; If the number of speeding abnormality tags carried in the driving order is within the threshold for the number of speeding abnormality tags, the speeding abnormality tags are removed; if the number of speeding abnormality tags carried in the driving order exceeds the threshold for the number of speeding abnormality tags, the driving order is marked with a speeding dangerous driving tag.

4. The method for monitoring dangerous driving behavior according to claim 1, characterized in that... Specifically, it includes: Acquire real-time driving acceleration data from the driver's end; the value of the acceleration data is the difference in speed change within a preset time period; The real-time driving speed data that matches the rapid speed change rule is labeled with a rapid speed change anomaly tag; the rapid speed change rule is a threshold value of the speed change difference within a preset time period. Obtain the traffic light coordinate data of the current driving route, and generate traffic light traffic condition recognition rules based on the traffic light coordinate data; if the generation point of the sudden speed change abnormal label is located after the traffic light coordinates, then the sudden speed change abnormal label is removed; if the generation point of the sudden speed change abnormal label is located before the traffic light passage time period, then the sudden speed change abnormal label is converted into a sudden speed change dangerous driving label.

5. The method for monitoring dangerous driving behavior according to claim 4, characterized in that... It also includes: Obtain road congestion data for the current driving route and generate congestion traffic rules based on the road congestion data; if the road congestion data for the current driving route exceeds the road congestion threshold, obtain the number of sudden speed change abnormal tags carried in the driving order; If the number of sudden speed change abnormal tags carried in the driving order is within the threshold for the number of sudden speed change abnormal tags, the sudden speed change abnormal tags are removed; if the number of sudden speed change abnormal tags carried in the driving order exceeds the threshold for the number of sudden speed change abnormal tags, the driving order is marked with a sudden speed change dangerous driving tag.

6. The method for monitoring dangerous driving behavior according to claim 1, characterized in that... Specifically, it includes: Obtain emergency braking data from the driver's end; The real-time driving speed data that matches the emergency braking driving rule is labeled with an emergency braking anomaly tag; the emergency braking driving rule is the threshold number of emergency braking times for the current road segment. Obtain road congestion data for the current driving route and generate congestion traffic rules based on the road congestion data; if the road congestion data for the current driving route exceeds the road congestion threshold, then remove the emergency braking anomaly label; if the road congestion data for the current driving route is within the road congestion threshold, then convert the emergency braking anomaly label into an emergency braking dangerous driving label.

7. The method for monitoring dangerous driving behavior according to claim 1, characterized in that, Also includes: Get the weather data for the current path. If there is rain data for the current path before a preset time period, get the coordinates of the water crossing point for the current path. If the distance between the current driver's coordinates and the coordinates of the water crossing point is within a preset distance, a water crossing alarm message will be sent to the driver's terminal.

8. A device for monitoring dangerous driving behavior, characterized in that, include: An anomaly labeling module is used to obtain real-time driving data from the driver's end and label anomaly tags on driving orders that match preset driving rules. A traffic rule generation module is used to obtain real-time traffic data of the current driving route and generate traffic rules based on the real-time traffic data. The label conversion module is used to detect real-time driving data carrying abnormal labels through traffic rules; if the real-time driving data matches the traffic rules, the abnormal label is removed; if the real-time driving data does not match the traffic rules, the abnormal label is converted into a dangerous driving label; and the driver and passenger's voice data are acquired. Voice data that matches the voice driving rules are labeled as voice anomalies; the voice driving rules are the duration of driver and passenger voices within a predetermined time. Acquire facial image data of the driver and passengers, and identify the pupil data in the face; If the passenger's pupils are facing the driver, then the voice abnormality label is removed; If the passenger's pupils are not facing the driver, the voice abnormality label is converted into a voice dangerous driving label.

9. An electronic device, characterized in that, The device includes a processor and a memory, the processor being connected to the memory, the memory storing machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions being executed by the processor to perform the steps of the method for monitoring dangerous driving behavior as described in any one of claims 1 to 7.

Images