CN111081021A - Driving safety control method, driving safety device, mobile terminal and support - Google Patents
Driving safety control method, driving safety device, mobile terminal and support Download PDFInfo
- Publication number
- CN111081021A CN111081021A CN201911399035.6A CN201911399035A CN111081021A CN 111081021 A CN111081021 A CN 111081021A CN 201911399035 A CN201911399035 A CN 201911399035A CN 111081021 A CN111081021 A CN 111081021A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driving
- real
- reflecting
- time data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 206010039203 Road traffic accident Diseases 0.000 claims abstract description 66
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 41
- 238000012549 training Methods 0.000 claims description 22
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 11
- 230000006855 networking Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 235000019504 cigarettes Nutrition 0.000 description 2
- 230000001939 inductive effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000192 social effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/161—Decentralised systems, e.g. inter-vehicle communication
Landscapes
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of vehicle networking and discloses a driving safety control method, a driving safety device, a mobile terminal and a support, wherein the driving safety control method comprises the following steps: acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process; and inputting the obtained real-time data reflecting the indexes of the vehicle running state into a pre-trained safety model, and obtaining whether the vehicle runs at risk from the output result of the pre-trained safety model. In the embodiment, real-time data of indexes reflecting the vehicle running state in the running process is collected, real-time safety prediction is carried out on the basis of the pre-trained safety model, and when the vehicle runs dangerously, a driver is reminded to take measures in time so as to adjust the running state of the vehicle, avoid or reduce traffic accidents, and further reduce life and property losses.
Description
Technical Field
The invention relates to the technical field of vehicle networking, in particular to a driving safety control method, a driving safety device, a mobile terminal and a support.
Background
At present, the holding capacity of household automobiles is very high, and the travel of people is very convenient. However, due to the fact that the number of vehicles is large, the road is complex, and the like, traffic accidents frequently occur, and personal and property losses are caused. In the driving process, the driving state of the vehicle is closely related to the driving behavior habit of the driver, and when the driver takes some improper driving behaviors, the driving state of the vehicle also changes correspondingly, for example, the driver steps on an accelerator to control the vehicle to run at high speed, or rotates a steering wheel to control the vehicle to make a sharp turn, and the like, and under the condition, traffic accidents are easily caused. How to assist a driver to drive safely and avoid or reduce traffic accidents is very important, so that the loss of lives and property is reduced.
Disclosure of Invention
The invention provides a driving safety control method, a driving safety device, a mobile terminal and a support, which are used for providing driving safety guidance for a driver, avoiding or reducing traffic accidents and further reducing life and property losses.
In a first aspect, an embodiment of the present invention provides a driving safety control method, where the driving safety control method includes:
acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process;
inputting the real-time data of the index reflecting the vehicle running state into a pre-trained safety model, and obtaining whether there is driving danger from the output result of the pre-trained safety model;
the pre-trained safety model is a model obtained by training a constructed convolutional neural network by using historical data of the index reflecting the vehicle running state within a set time before a traffic accident occurs; when a vehicle enters a set road section, weighting the acquired real-time data of the index reflecting the vehicle running state according to the corresponding relation between the historical traffic accident occurring on the set road section and the index reflecting the vehicle running state, and inputting the weighted real-time data into a pre-trained safety model for prediction.
In the embodiment, real-time data of indexes reflecting the vehicle running state in the running process is collected, real-time safety prediction is carried out on the basis of the pre-trained safety model, and when the vehicle runs dangerously, a driver is reminded to take measures in time so as to adjust the running state of the vehicle, avoid or reduce traffic accidents, and further reduce life and property losses.
Optionally, the index reflecting the vehicle driving state includes one or more of speed, turning angle and acceleration.
Optionally, if the vehicle is predicted to have driving danger according to the real-time data of the index reflecting the driving state of the vehicle, voice reminding is performed.
Optionally, the output result of the pre-trained security model includes: the risk of occurrence of major traffic accidents, the risk of medium traffic accidents, the risk of low traffic accidents and the risk of no traffic accidents.
Optionally, when the vehicle is predicted to have driving danger according to the real-time data of the index reflecting the vehicle driving state, the current time and the current location are marked on a map system of the mobile terminal and stored.
Optionally, the real-time data reflecting the index of the environment in the vehicle is obtained, and the real-time data reflecting the index of the environment in the vehicle and the real-time data reflecting the index of the driving state of the vehicle are used as the input data of the pre-trained model.
Optionally, the index reflecting the environment in the vehicle includes one or more of temperature, humidity, and noise.
In a second aspect, an embodiment of the present invention further provides a driving safety device, including:
the data acquisition module is used for acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process;
the prediction module is used for inputting the real-time data of the index reflecting the vehicle running state into a pre-trained safety model and obtaining whether the driving danger exists from the output result of the pre-trained safety model;
the pre-trained safety model is obtained by training the constructed convolutional neural network by using historical data of the index reflecting the vehicle running state within a set time before a traffic accident occurs.
In the embodiment, the real-time data of the indexes reflecting the vehicle running state in the running process is collected, and the real-time safety prediction is carried out on the basis of the pre-trained safety model, so that the safe driving of a driver is assisted, the occurrence of traffic accidents is avoided or reduced, and the life and property loss is reduced.
In a third aspect, an embodiment of the present invention further provides a mobile terminal, including any one of the driving safety devices described above.
In a fourth aspect, an embodiment of the present invention further provides a support, including a base and a tray for fixing the mobile terminal, where the tray is rotatably connected to the base; the base is fixed in the carriage, be equipped with collection system and communication device in the base, wherein:
the acquisition device is used for measuring real-time data of indexes reflecting the running state of the vehicle;
and the communication device is used for sending the real-time data of the index reflecting the vehicle running state, which is measured by the acquisition device, to the mobile terminal.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a driving safety control method according to an embodiment of the present invention;
FIG. 2 is a flow chart of training a security model according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a constructed convolutional neural network according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a bracket according to an embodiment of the present invention;
FIG. 5 is a diagram of an internal circuit of a base according to an embodiment of the present invention;
fig. 6 is a schematic view of an application scenario of the driving safety method according to the embodiment of the present invention;
fig. 7 is an information diagram of an early warning point according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a driving safety control method, which is used for providing driving safety guide for a driver, avoiding or reducing traffic accidents and further reducing life and property loss.
As shown in fig. 1, the driving safety control method includes:
step S101: acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process;
step S102: inputting the obtained real-time data reflecting the indexes of the vehicle running state into a pre-trained safety model, and obtaining whether the vehicle runs at risk from the output result of the pre-trained safety model;
the pre-trained safety model is obtained by training a constructed convolutional neural network by using historical data of indexes reflecting the vehicle running state within a set time before a traffic accident occurs, wherein the historical data refers to: in a traffic accident caused by the active driving behavior of a driver, the historical data of the index reflecting the driving state of the vehicle driven by the driver is reflected, the active driving behavior of the driver means that the driver actively takes some improper driving behaviors, such as the active accelerated driving, the high-speed driving and the like of the driver, and the historical data of the index reflecting the driving state of the vehicle of the past party identified by the traffic accident can be understood in a certain layer.
The driving state of the vehicle is closely related to the driving behavior habit of the driver, and when the driver takes some improper driving behavior during driving, the driving state of the vehicle also changes correspondingly, and traffic accidents can be caused. The driving safety control method can provide safety guide for a driver by acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process and carrying out real-time safety prediction based on a safety model trained in advance, and remind the driver to take measures in time so as to adjust the driving state of the vehicle, thereby avoiding or reducing the occurrence of traffic accidents.
In order to enhance the warning effect on the accident-prone road section, a GPS system can be combined, when a vehicle enters a set road section, the obtained real-time data of the index reflecting the vehicle running state is weighted according to the corresponding relation between the historical traffic accident occurring on the set road section and the index reflecting the vehicle running state, and the weighted real-time data is input into a pre-trained safety model for prediction. Specifically, when most of the historical traffic accidents occurring in a certain road section are caused by overspeed driving of a driver, the weight of the speed index can be increased, and then whether driving danger exists or not can be predicted by adopting weighted real-time data.
In a specific embodiment, the index reflecting the driving state of the vehicle includes one or more of speed, turning angle and acceleration (when the acceleration index is positive, the vehicle is accelerated, and when the acceleration index is negative, the vehicle is decelerated), the three types of indexes are closely related to whether the vehicle is safely driven in the driving process, and traffic accidents are easily caused when the vehicle is driven at high speed, turns sharply, accelerates suddenly or decelerates suddenly, so that the safety prediction is performed by monitoring the three types of indexes and based on the obtained real-time data and a pre-trained safety model, if the driving danger of the vehicle is predicted according to the real-time data of the index reflecting the driving state of the vehicle, the driver is prompted by voice, or a warning lamp can be set to warn the driver to guide the driver to take measures in time, so as to adjust the driving state of the vehicle, thereby avoiding or reducing the occurrence of traffic accidents. Furthermore, the driving state of the driver can be evaluated according to the prediction result of the pre-trained safety model and by combining the current road condition information, weather information and the like, so that the driver is warned to drive carefully.
The output results of the pre-trained security model include: the risk of traffic accidents is present, and the risk of traffic accidents is absent; alternatively, the obtained output results of the security model may be trained to include: there is a risk of occurrence of a major traffic accident, there is a risk of occurrence of a medium traffic accident, there is a risk of occurrence of a low traffic accident, and there is no risk of occurrence of a traffic accident.
As shown in fig. 2, the pre-trained security model can be obtained by:
step S201: constructing a convolutional neural network;
as shown in fig. 3, the constructed convolutional neural network includes an input layer, two convolutional layers for feature extraction of input data, two pooling layers for sampling features, and a full-link layer as an output layer, and the convolutional layers and the pooling layers alternately appear in the network; and the full connection layer is responsible for connecting the extracted features, and finally, a final classification result is obtained through a classifier.
Step S202: setting and initializing parameters of the convolutional neural network;
step S203: training the convolutional neural network by using historical data of indexes reflecting the vehicle running state within set time before an accident occurs until the convolutional neural network is converged, and determining parameters of the convolutional neural network after training is completed;
the training of the convolutional neural network by using historical data of indexes reflecting the vehicle running state within a set time before a traffic accident specifically comprises the following steps: firstly, preprocessing the data, including intercepting the most effective historical data of one end time in the set time, and converting the one-dimensional time sequence data into a two-dimensional array; secondly, training the convolutional neural network by adopting the preprocessed data until the convolutional neural network is converged.
During training, if the convolutional neural network is trained by using the marked historical data of the index reflecting the vehicle running state within the set time before any traffic accident occurs, the output result based on the trained convolutional neural network model comprises the following steps: there is a risk of a traffic accident occurring, there is no risk of a traffic accident occurring. Further, if the traffic accidents are classified into major traffic accidents, medium traffic accidents and low traffic accidents according to the severity, and the marked historical data of the indexes reflecting the vehicle running states within the set time before the occurrence of the three traffic accidents are respectively trained on the convolutional neural network until the convolutional neural network converges, the output result of the convolutional neural network model after the training is completed comprises: there is a risk of occurrence of a major traffic accident, there is a risk of occurrence of a medium traffic accident, there is a risk of occurrence of a low traffic accident, and there is no risk of occurrence of a traffic accident.
Step S204: and adopting the trained convolutional neural network model as a pre-trained safety model.
The environment in the vehicle will have a certain influence on the driving of the driver, such as excessive noise in the vehicle and excessive temperature, which will have an adverse effect on the normal driving of the driver, and when the driver takes inappropriate driving operation, there is a possibility of traffic accidents, and therefore, the environment in the vehicle is also an important factor for inducing traffic accidents. Therefore, when model training is carried out, the convolutional neural network can be trained by adopting historical data reflecting indexes of the environment in the vehicle within set time before a traffic accident and historical data reflecting the driving state of the vehicle together until the convolutional neural network converges, and the obtained convolutional neural network model is used as a pre-trained safety model. Therefore, when the real-time prediction is carried out, the real-time data reflecting the indexes of the environment in the vehicle and the real-time data reflecting the indexes of the running state of the vehicle are obtained, the two types of data are used as input data of a pre-trained safety model, the influence of the environment in the vehicle on safe running is further synthesized, and whether the running risk exists is obtained from the output result of the pre-trained safety model. Specifically, the index reflecting the environment in the vehicle includes one or more of temperature, humidity, and noise.
The driving safety control method further comprises the following steps: when the driving danger of the vehicle is predicted according to the real-time data of the index reflecting the driving state of the vehicle, the current time and the current place are marked on a map system of the mobile terminal and stored to form an early warning point information graph, so that a driver can know the health degree of the past driving conveniently, and can share the WeChat or the microblog and other social software through the Internet, the social effect is improved, and the social demand of a user is met.
The embodiment of the present invention further provides a driving safety device, including:
the data acquisition module is used for acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process;
the prediction module is used for inputting the real-time data of the index reflecting the vehicle running state into a pre-trained safety model and obtaining whether the driving danger exists from the output result of the pre-trained safety model;
the pre-trained safety model is obtained by training the constructed convolutional neural network by using historical data of indexes reflecting the vehicle running state within set time before an accident occurs.
In order to enhance the warning effect on the accident-prone road section, when the vehicle enters the set road section, the prediction module is specifically configured to weight the acquired real-time data of the index reflecting the vehicle driving state according to the corresponding relationship between the historical traffic accident occurring on the set road section and the index reflecting the vehicle driving state, and input the weighted real-time data into a pre-trained safety model for prediction.
In a specific embodiment, the index reflecting the driving state of the vehicle comprises speed, turning angle, acceleration or deceleration, the three indexes are closely related to whether the vehicle is safely driven or not in the driving process, and the vehicle is easy to cause traffic accidents when the vehicle is driven at high speed, makes a sharp turn, accelerates rapidly or decelerates rapidly.
In order to remind a driver of taking measures in time to adjust the running state of the vehicle, the driving safety device further comprises an alarm module used for carrying out voice reminding when the prediction module predicts that the vehicle has driving danger. Or, a warning lamp can be arranged to warn the driver.
In this driving safety device, the output result of the safety model trained in advance includes: the risk of traffic accidents is present, and the risk of traffic accidents is absent; alternatively, the obtained output results of the security model may be trained to include: there is a risk of occurrence of a major traffic accident, there is a risk of occurrence of a medium traffic accident, there is a risk of occurrence of a low traffic accident, and there is no risk of occurrence of a traffic accident. In a specific embodiment, the pre-trained security model is obtained by:
step S201: constructing a convolutional neural network;
step S202: setting and initializing parameters of a convolutional neural network;
step S203: training the convolutional neural network by using historical data of indexes reflecting the vehicle running state within set time before an accident occurs until the convolutional neural network is converged, and determining parameters of the convolutional neural network after training is completed;
step S204: the trained convolutional neural network model is a pre-trained safety model.
The environment in the vehicle will have a certain influence on the driving of the driver, such as excessive noise in the vehicle and excessive temperature, which will have an adverse effect on the normal driving of the driver, and when the driver takes inappropriate driving operation, there is a possibility of traffic accidents, and therefore, the environment in the vehicle is also an important factor for inducing traffic accidents. Therefore, when model training is carried out, the convolutional neural network can be trained by adopting historical data reflecting indexes of the environment in the vehicle within set time before a traffic accident and historical data reflecting the driving state of the vehicle together until the convolutional neural network converges, and the obtained convolutional neural network model is used as a pre-trained safety model. Therefore, when the real-time prediction is carried out, the real-time data reflecting the indexes of the environment in the vehicle can be obtained through the data acquisition module, the real-time data reflecting the indexes of the environment in the vehicle and the real-time data reflecting the driving state of the vehicle are used as the input data of the pre-trained safety model together with the prediction module, the influence of the environment in the vehicle on safe driving is further synthesized, and whether the driving risk exists or not is obtained from the output result of the pre-trained safety model. Specifically, the index reflecting the environment in the vehicle includes one or more of temperature, humidity, and noise.
In order to enhance the social contact, the safe driving system further comprises a display module, and the display module is used for displaying and storing the real-time data reflecting the index of the driving state of the vehicle, the current time and the current place on a map system of the mobile terminal when the prediction module predicts that the vehicle has a driving danger, so as to form an early warning point information map.
The embodiment of the invention also provides a mobile terminal which comprises the driving safety device. The mobile terminal can be a mobile phone, a tablet and other terminal equipment.
An embodiment of the present invention further provides a cradle, as shown in fig. 4, including a base 10 and a tray 20 for fixing the mobile terminal, where the tray 20 is rotatably connected to the base 10, and specifically, the tray 20 can rotate in a universal direction with respect to the base 10; base 10 is fixed in the carriage, is equipped with collection system and communication device in the base 10, wherein:
the acquisition device is used for acquiring real-time data of indexes reflecting the running state of the vehicle;
and the communication device is used for transmitting the real-time data of the indexes reflecting the vehicle running state, which are measured by the acquisition device, to the mobile terminal.
In the embodiment, based on the rigidity requirement of the support, the acquisition device, the communication device and the like are integrated in the base of the support to acquire real-time data reflecting indexes of the driving state of the vehicle in the driving process and upload the real-time data to the mobile terminal; the mobile terminal carries out real-time data analysis based on the pre-trained safety model downloaded from the cloud end, and provides safe driving guide service for a driver.
The base 10 has certain structural strength, and can fixed mounting in a certain position, avoids rocking and the inaccurate or too big problem of interference of data collection that leads to, if can adopt 3M to glue to fix on the mesa that somewhere is smooth relatively in the cockpit. The base 10 is internally provided with an integrated circuit board which supports satellite positioning, a gyroscope, an acceleration sensor, a temperature and humidity sensor, a noise sensor and a Bluetooth communication module, and a circuit diagram inside the base 10 is shown in figure 5. The system comprises a satellite positioning device, an acceleration sensor, a temperature and humidity sensor and a noise sensor, wherein the satellite positioning device is used for acquiring a driving track, the gyroscope is used for acquiring turning data of a vehicle, the acceleration sensor is used for acquiring acceleration and deceleration data of the vehicle, and the temperature and humidity sensor and the noise sensor are respectively used for acquiring temperature, humidity and noise in the vehicle; the Bluetooth communication module realizes data transmission with the mobile terminal, and besides Bluetooth communication, data transmission with the mobile terminal can be realized in the forms of data lines, WIFI and the like; the integrated circuit board is provided with a storage unit which supports short-term storage of monitoring data.
In addition, the support also has a charging function, supports wireless charging and USB charging, and provides convenience conditions for charging of the mobile terminal. The charging power source is an automobile cigarette lighter, and the voltage range meets 12-24V of output voltage of the cigarette lighter of common automobile types; as shown in the circuit diagram of fig. 5, after passing through the power protection unit, the vehicle-mounted power supply supports wireless charging through the output power supply processed by the DC/DC module1, and the output power supply supplies power to the MCU after being processed by the next stage power supply unit DC/DC module3, thereby ensuring that the main control logic works normally; after passing through the power protection unit, the vehicle-mounted power supply is processed by the power processing unit DC/DC module2 to supply power to the USB charging unit.
Referring to fig. 6, the mobile terminal receives the monitoring data reported by the bluetooth communication module and provides a safe driving guide and content sharing for the driver, that is, the navigation positioning data, the speed increase (decrease) speed and the turning angle obtained by the mobile terminal are calculated by the safety model to obtain a safety result, which is used as a driving guide to remind the driver of the current driving health (whether there is a possibility of danger); and after the early warning information is generated every time, an early warning point with current position information and current vehicle running state information (including running speed information, plus (minus) speed information, turning angle information and the like) is displayed on the map, and an early warning point information graph shown in the graph 7 is formed through accumulation, so that a driver can know the health degree of the past driving conveniently. Based on the data, the driver can set shared content on social software to enhance social performance, for example, health degree data or in-vehicle environment data are loaded on a map in cooperation with satellite positioning data to be made into small H5 pages, and the small H5 pages are shared on WeChat or microblog and other social applications through the Internet to increase social effects and meet social requirements of some users.
After receiving the new safety model upgrading notification of the driving safety cloud, the mobile terminal can refresh the local safety model; when an accident occurs, the mobile terminal can report each data information collected by the sensor in a specified time period before the accident occurrence point to the driving safety cloud.
The driving safety cloud is responsible for model training and historical accident data management, and the driving safety cloud regularly refreshes the safety model based on artificial intelligence algorithm, and the mobile terminal of being convenient for downloads the update, specifically includes:
A) data preprocessing: the mobile terminal uploads the data 10 minutes before the accident occurrence point to a driving safety cloud, quality inspection personnel of a driving safety cloud platform check the validity of the reported data through tools (namely, the data are historical data of indexes reflecting the driving state of a vehicle driven by a driver in a traffic accident caused by the active driving behavior of the driver), and the most effective 6 minutes are intercepted from the historical data to serve as model training data, namely, the data are the data for leaving an insurance, and the marking work of a data block for leaving the insurance is completed;
collecting 576 groups of data in 6 minutes, wherein each group of data comprises the running speed, the turning angle, the acceleration or the deceleration of the vehicle, and storing the 576 groups of data which are continuous on a time axis into a 24-3 matrix, namely forming 3 24-24 two-dimensional matrixes;
B) model training: constructing a convolutional neural network based on a deep learning algorithm framework, referring to fig. 4, wherein the convolutional neural network comprises an input layer, two convolutional layers, two pooling layers and a full-connection layer, inputting 24-by-24 matrixes of 3 channels into the convolutional neural network, and training the convolutional neural network until the convolutional neural network is converged, so that the determination of parameters of a convolutional neural network model after the training is completed is realized;
C) after the trained and converged convolutional neural network model is artificially checked, tested and confirmed, available updating information is issued, and the mobile terminal can decide to update the model of the application end.
In the embodiment, the real-time data of the indexes reflecting the vehicle running state in the running process is collected, and real-time safety prediction is carried out on the basis of the pre-trained safety model, so that the safe driving of a driver is assisted, traffic accidents are avoided or reduced, and the life and property loss is reduced.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A driving safety control method is characterized by comprising the following steps:
acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process;
inputting the real-time data of the index reflecting the vehicle running state into a pre-trained safety model, and obtaining whether there is driving danger from the output result of the pre-trained safety model;
the pre-trained safety model is a model obtained by training a constructed convolutional neural network by using historical data of the index reflecting the vehicle running state within a set time before a traffic accident occurs; when a vehicle enters a set road section, weighting the acquired real-time data of the index reflecting the vehicle running state according to the corresponding relation between the historical traffic accident occurring on the set road section and the index reflecting the vehicle running state, and inputting the weighted real-time data into a pre-trained safety model for prediction.
2. The driving safety control method according to claim 1, wherein the index reflecting the driving state of the vehicle includes one or more of a speed, a turning angle, and an acceleration.
3. The driving safety control method according to claim 1, further comprising:
and if the vehicle is predicted to have driving danger according to the real-time data of the index reflecting the driving state of the vehicle, carrying out voice reminding.
4. The driving safety control method according to claim 1, wherein the output result of the pre-trained safety model comprises: there is a risk of occurrence of a major traffic accident, there is a risk of occurrence of a medium traffic accident, there is a risk of occurrence of a low traffic accident, and there is no risk of occurrence of a traffic accident.
5. The driving safety control method according to claim 1, further comprising:
and when the vehicle is predicted to have driving danger according to the real-time data of the index reflecting the vehicle driving state, marking the real-time data of the index reflecting the vehicle driving state, the current time and the current place on a map system of the mobile terminal and storing the data.
6. The driving safety control method according to claim 1, further comprising:
and acquiring real-time data reflecting indexes of the environment in the automobile, and inputting the real-time data reflecting the indexes of the environment in the automobile into the pre-trained safety model.
7. The driving safety control method according to claim 1, wherein the index reflecting the environment in the vehicle includes one or more of temperature, humidity, and noise.
8. A driving safety device, comprising:
the data acquisition module is used for acquiring real-time data of indexes reflecting the driving state of the vehicle in the driving process;
the prediction module is used for inputting the real-time data of the index reflecting the vehicle running state into a pre-trained safety model and obtaining whether the driving danger exists from the output result of the pre-trained safety model;
the pre-trained safety model is obtained by training the constructed convolutional neural network by using historical data of the index reflecting the vehicle running state within a set time before a traffic accident occurs.
9. A mobile terminal, characterized in that it comprises a driving safety device according to claim 8.
10. A cradle comprising a base and a tray for holding the mobile terminal of claim 9, the tray being pivotally connected to the base; the base is fixed in the carriage, be equipped with collection system and communication device in the base, wherein:
the acquisition device is used for measuring real-time data of indexes reflecting the running state of the vehicle;
and the communication device is used for sending the real-time data of the index reflecting the vehicle running state, which is measured by the acquisition device, to the mobile terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911399035.6A CN111081021B (en) | 2019-12-30 | 2019-12-30 | Driving safety control method, driving safety device, mobile terminal and support |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911399035.6A CN111081021B (en) | 2019-12-30 | 2019-12-30 | Driving safety control method, driving safety device, mobile terminal and support |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111081021A true CN111081021A (en) | 2020-04-28 |
| CN111081021B CN111081021B (en) | 2021-12-10 |
Family
ID=70320161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911399035.6A Active CN111081021B (en) | 2019-12-30 | 2019-12-30 | Driving safety control method, driving safety device, mobile terminal and support |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111081021B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149908A (en) * | 2020-09-28 | 2020-12-29 | 深圳壹账通智能科技有限公司 | Vehicle driving prediction method, system, computer device and readable storage medium |
| CN113436365A (en) * | 2021-06-25 | 2021-09-24 | 中科富创(北京)智能***技术有限公司 | Vehicle-mounted edge computing gateway equipment and system |
| CN114995164A (en) * | 2022-08-03 | 2022-09-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
| CN116226787A (en) * | 2023-05-04 | 2023-06-06 | 中汽信息科技(天津)有限公司 | Commercial vehicle danger probability prediction method, equipment and medium |
| CN117389256A (en) * | 2023-12-11 | 2024-01-12 | 青岛盈智科技有限公司 | Early warning method for truck vehicle state in transportation process |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496000A (en) * | 2011-11-14 | 2012-06-13 | 电子科技大学 | Urban traffic accident detection method |
| CN102800136A (en) * | 2011-05-25 | 2012-11-28 | 株式会社审调社 | Drive evaluation system, drive evaluation program, and drive evaluation method |
| CN106323321A (en) * | 2016-10-21 | 2017-01-11 | 思建科技有限公司 | Vehicle navigation real-time correction method and vehicle navigation real-time correction system |
| CN106446914A (en) * | 2016-09-28 | 2017-02-22 | 天津工业大学 | Road detection based on superpixels and convolution neural network |
| WO2018116189A1 (en) * | 2016-12-20 | 2018-06-28 | Ratti Jayant | On-demand roadway stewardship system |
| CN108280991A (en) * | 2017-01-05 | 2018-07-13 | 大唐高鸿信息通信研究院（义乌）有限公司 | The vehicle traffic accident prediction technique of vehicle-mounted short haul connection net |
| CN108860165A (en) * | 2018-05-11 | 2018-11-23 | 深圳市图灵奇点智能科技有限公司 | Vehicle assistant drive method and system |
| CN109362235A (en) * | 2016-05-29 | 2019-02-19 | 微软技术许可有限责任公司 | Classify to the affairs at network accessible storage device |
-
2019
- 2019-12-30 CN CN201911399035.6A patent/CN111081021B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102800136A (en) * | 2011-05-25 | 2012-11-28 | 株式会社审调社 | Drive evaluation system, drive evaluation program, and drive evaluation method |
| CN102496000A (en) * | 2011-11-14 | 2012-06-13 | 电子科技大学 | Urban traffic accident detection method |
| CN109362235A (en) * | 2016-05-29 | 2019-02-19 | 微软技术许可有限责任公司 | Classify to the affairs at network accessible storage device |
| CN106446914A (en) * | 2016-09-28 | 2017-02-22 | 天津工业大学 | Road detection based on superpixels and convolution neural network |
| CN106323321A (en) * | 2016-10-21 | 2017-01-11 | 思建科技有限公司 | Vehicle navigation real-time correction method and vehicle navigation real-time correction system |
| WO2018116189A1 (en) * | 2016-12-20 | 2018-06-28 | Ratti Jayant | On-demand roadway stewardship system |
| CN108280991A (en) * | 2017-01-05 | 2018-07-13 | 大唐高鸿信息通信研究院（义乌）有限公司 | The vehicle traffic accident prediction technique of vehicle-mounted short haul connection net |
| CN108860165A (en) * | 2018-05-11 | 2018-11-23 | 深圳市图灵奇点智能科技有限公司 | Vehicle assistant drive method and system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149908A (en) * | 2020-09-28 | 2020-12-29 | 深圳壹账通智能科技有限公司 | Vehicle driving prediction method, system, computer device and readable storage medium |
| CN112149908B (en) * | 2020-09-28 | 2023-09-08 | 深圳壹账通智能科技有限公司 | Vehicle driving prediction method, system, computer device, and readable storage medium |
| CN113436365A (en) * | 2021-06-25 | 2021-09-24 | 中科富创(北京)智能***技术有限公司 | Vehicle-mounted edge computing gateway equipment and system |
| CN114995164A (en) * | 2022-08-03 | 2022-09-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
| CN114995164B (en) * | 2022-08-03 | 2022-12-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
| CN116226787A (en) * | 2023-05-04 | 2023-06-06 | 中汽信息科技(天津)有限公司 | Commercial vehicle danger probability prediction method, equipment and medium |
| CN117389256A (en) * | 2023-12-11 | 2024-01-12 | 青岛盈智科技有限公司 | Early warning method for truck vehicle state in transportation process |
| CN117389256B (en) * | 2023-12-11 | 2024-03-08 | 青岛盈智科技有限公司 | Early warning method for truck vehicle state in transportation process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111081021B (en) | 2021-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111081021B (en) | Driving safety control method, driving safety device, mobile terminal and support | |
| CN107776574B (en) | Driving mode switching method and device for automatic driving vehicle | |
| US20170101093A1 (en) | Collision prediction system | |
| US8818697B2 (en) | Vehicles for communicating vehicle parameters to a networked server | |
| CN110782111B (en) | Risk assessment method and system | |
| US20170129497A1 (en) | System and method for assessing user attention while driving | |
| CN110471411A (en) | Automatic Pilot method and servomechanism | |
| CN111260482B (en) | Information processing terminal, computer-readable storage medium, and control method | |
| SE527692C2 (en) | Procedure in a communication network to distribute driving information for vehicles and systems implementing the procedure | |
| US11225264B2 (en) | Realtime driver assistance system | |
| CA3112557A1 (en) | Determining driver and vehicle characteristics based on an edge-computing device | |
| CN111325437B (en) | Abnormal driving behavior recognition method and device and electronic equipment | |
| US11657659B2 (en) | Systems and methods for analyzing wireless telematics data of a vehicle engaged in an extended period of travel | |
| US11454967B2 (en) | Systems and methods for collecting vehicle data to train a machine learning model to identify a driving behavior or a vehicle issue | |
| US10984657B2 (en) | System and method for vehicle-to-vehicle statistic challenges | |
| US11377111B1 (en) | Systems and methods for detecting vehicle mass changes | |
| US20200175474A1 (en) | Information processing system, program, and control method | |
| EP4137950A1 (en) | Methods and systems for providing results of an autonomous vehicle simulation | |
| Akhtar et al. | Mobile application for safe driving | |
| US20230316411A1 (en) | Deductible Determination System | |
| US10556596B2 (en) | Driver scoring and safe driving notifications | |
| CN115209374B (en) | Motor vehicle alarm system based on third party call center | |
| CN115203457B (en) | Image retrieval method, device, vehicle, storage medium and chip | |
| CN110660217B (en) | Method and device for detecting information security | |
| CN111199655A (en) | Intelligent automobile interconnection exchange safety system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |