CN109523652A - Processing method, device, equipment and the storage medium of insurance based on driving behavior - Google Patents
Processing method, device, equipment and the storage medium of insurance based on driving behavior Download PDFInfo
- Publication number
- CN109523652A CN109523652A CN201811149959.6A CN201811149959A CN109523652A CN 109523652 A CN109523652 A CN 109523652A CN 201811149959 A CN201811149959 A CN 201811149959A CN 109523652 A CN109523652 A CN 109523652A
- Authority
- CN
- China
- Prior art keywords
- driver
- driving behavior
- driving
- insurance
- information
- 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
Classifications
-
- 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
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The embodiment of the present application provides processing method, device, equipment and the storage medium of a kind of insurance based on driving behavior.The processing method of insurance based on driving behavior of the invention, it include: to obtain driver to drive image and car status information, image is driven to the driver and the car status information is analyzed, determine whether the driving behavior of driver belongs to violation type, if belonging to, the corresponding violation data of driving behavior for then sending the driver to Cloud Server, so that the Cloud Server is based on the violation data and constructs vehicle insurance actuarial model, the vehicle insurance actuarial model is used to determine based on the expense of the insurance of driving behavior.The embodiment of the present application can promote the accuracy of vehicle insurance actuarial model.
Description
Technical field
The invention relates to field of computer technology more particularly to a kind of processing sides of the insurance based on driving behavior
Method, device, equipment and storage medium.
Background technique
Car networking is based on in-vehicle network, inter-vehicle network and vehicle-mounted mobile internet, according to the communication protocol sum number of agreement
The big system with information exchange is communicated wirelessly between vehicle-X (X: vehicle, road, pedestrian and internet etc.) according to interactive standards
Network is that by the integrated network of intelligent traffic management, Intelligent Dynamic information service and Vehicular intelligentization control, is
Typical case of the technology of Internet of things in field of transportation system.
One important application of car networking is the insurance (Usage Based Insurance, UBI) based on driving behavior,
It applies onboard diagnostic system (On-Board Diagnostic, OBD) equipment, global positioning system (Global
Positioning System, GPS) equipment completes the acquisition of vehicle oneself state and environmental information data, as four is anxious, in traveling
Journey, maximum instantaneous velocity and time of trip etc., and data processing is carried out, to construct vehicle insurance actuarial model, the vehicle insurance actuarial
Determination of the module for the insurance premium of insured vehicle.
However, data collected by OBD equipment and GPS device can not reflect the true driving habit of driver, base
Vehicle insurance actuarial model accuracy constructed by this is not high.
Summary of the invention
The embodiment of the present application provides processing method, device, equipment and the storage medium of a kind of insurance based on driving behavior,
With the accuracy of vehicle insurance actuarial model.
In a first aspect, the embodiment of the present application provides a kind of processing method of insurance based on driving behavior, comprising: acquisition is driven
The person of sailing drives image and car status information；Image is driven to the driver and the car status information is analyzed；Really
Whether the driving behavior for determining driver belongs to violation type；If belonging to, the driving row of the driver is sent to Cloud Server
For corresponding violation data, so that the Cloud Server is based on the violation data and constructs vehicle insurance actuarial model, the vehicle insurance is smart
Model is calculated to be used to determine based on the expense of the insurance of driving behavior.
With reference to first aspect, described to drive figure to the driver in a kind of possible implementation of first aspect
Picture and the car status information are analyzed, comprising: are driven image and described using deep learning network to the driver
Car status information is analyzed.
With reference to first aspect or a kind of possible implementation of first aspect, in the alternatively possible reality of first aspect
It is described to drive image to the driver using deep learning network and the car status information is analyzed in existing mode,
It include: that the target object in image of being driven using the algorithm of target detection based on deep learning to the driver is detected,
Determine the position of the target object；According to the position of the target object and the car status information, neural network is used
Model to the driver drive image carry out multi-tag classification, determine the behavior state of the driver.
With reference to first aspect or any possible implementation of first aspect, in the alternatively possible of first aspect
In implementation, whether the driving behavior of the determining driver belongs to unlawful practice, comprising: according to the institute in preset time period
At least one behavior state for stating driver, determines whether the driving behavior of driver belongs to violation type；Wherein, violation type
Driving behavior include any one non-security driving behavior.
With reference to first aspect or any possible implementation of first aspect, in the alternatively possible of first aspect
In implementation, the method also includes: according to the unlawful practice of the driver, generate alarm command；It is sent out to interactive device
The alarm command is sent, the alarm command is for triggering the interactive device to user feedback prompt information.
With reference to first aspect or any possible implementation of first aspect, in the alternatively possible of first aspect
In implementation, the violation data includes the identification information of the driver, the video data of unlawful practice and unlawful practice
Information.
Second aspect, the embodiment of the present application provide a kind of processing method of insurance based on driving behavior, comprising: reception is driven
The corresponding violation data of the driving behavior for the person of sailing；The driving ability description letter of the driver is updated according to the violation data
Breath；Vehicle insurance actuarial model is constructed according to the driving ability description information of the driver, the vehicle insurance actuarial model is for being based on
The expense of the insurance of driving behavior determines.
In conjunction with second aspect, in a kind of possible implementation of second aspect, the violation data includes described drives
The identification information for the person of sailing, the video data of unlawful practice and unlawful practice information, the method also includes: with the driver's
Identification information is major key, and the video data of the unlawful practice and unlawful practice information are stored in database.
In conjunction with a kind of possible implementation of second aspect or second aspect, in the alternatively possible reality of second aspect
In existing mode, the identification information includes face identification information.
The third aspect, the embodiment of the present application provide a kind of processing unit of insurance based on driving behavior, comprising: obtain mould
Block is driven image and car status information for obtaining driver；Analysis module, for driving image and institute to the driver
Car status information is stated to be analyzed；Judgment module, for determining whether the driving behavior of driver belongs to violation type；It sends
Module sends the driving behavior pair of the driver to Cloud Server if the driving behavior for driver belongs to violation type
The violation data answered, so that the Cloud Server is based on the violation data and constructs vehicle insurance actuarial model, the vehicle insurance actuarial mould
Type is used to determine based on the expense of the insurance of driving behavior.
In conjunction with the third aspect, in a kind of possible implementation of the third aspect, the analysis module is used for: using deep
Degree learning network drives image to the driver and the car status information is analyzed.
In conjunction with a kind of possible implementation of the third aspect or the third aspect, in the alternatively possible reality of the third aspect
In existing mode, the analysis module is used for: being driven image using the algorithm of target detection based on deep learning to the driver
In target object detected, determine the position of the target object；According to the position of the target object and the vehicle
Status information, using neural network model to the driver drive image carry out multi-tag classification, determine the driver's
Behavior state.
In conjunction with any possible implementation of the third aspect or the third aspect, in the alternatively possible of the third aspect
In implementation, the judgment module is used for: according at least one behavior state of the driver in preset time period,
Determine whether the driving behavior of driver belongs to violation type；Wherein, the driving behavior of violation type includes any one non-peace
The behavior driven entirely.
In conjunction with any possible implementation of the third aspect or the third aspect, in the alternatively possible of the third aspect
In implementation, described device further include: generation module；The generation module is used for the unlawful practice according to the driver,
Generate alarm command；The sending module is also used to send the alarm command to interactive device, and the alarm command is for touching
Send out interactive device described to user feedback prompt information.
In conjunction with any possible implementation of the third aspect or the third aspect, in the alternatively possible of the third aspect
In implementation, the violation data includes the identification information of the driver, the video data of unlawful practice and unlawful practice
Information.
Fourth aspect, the embodiment of the present application provide a kind of processing unit of insurance based on driving behavior, comprising: receive mould
Block, the corresponding violation data of driving behavior for receiving driver；Processing module, for updating institute according to the violation data
State the driving ability description information of driver；The processing module is also used to describe to believe according to the driving ability of the driver
Breath building vehicle insurance actuarial model, the vehicle insurance actuarial model are used to determine based on the expense of the insurance of driving behavior.
In conjunction with fourth aspect, in a kind of possible implementation of fourth aspect, the violation data includes described drives
The identification information for the person of sailing, the video data of unlawful practice and unlawful practice information, the processing module are also used to: with the driving
The identification information of member is major key, and the video data of the unlawful practice and unlawful practice information are stored in database.
In conjunction with a kind of possible implementation of fourth aspect or fourth aspect, in the alternatively possible reality of fourth aspect
In existing mode, the identification information includes face identification information.
5th aspect, the embodiment of the present application provide a kind of Intelligent treatment equipment, comprising: memory and processor；It is described to deposit
Reservoir is for instructing, so that the processor executes described instruction, to realize that such as first aspect or any of first aspect can
The processing method of insurance based on driving behavior described in the implementation of energy.
6th aspect, the embodiment of the present application provide a kind of Cloud Server, comprising: memory and processor；The memory
For instructing, so that the processor executes described instruction, to realize any possible of such as second aspect or second aspect
The processing method of insurance described in implementation based on driving behavior.
7th aspect, the embodiment of the present application provide a kind of storage medium characterized by comprising the storage medium packet
Include: instruction, described instruction for realizing as described in any possible implementation of first aspect or first aspect based on
The processing method of the insurance of driving behavior, alternatively, described instruction can for realizing any of such as second aspect or second aspect
The processing method of insurance based on driving behavior described in the implementation of energy.
Processing method, device, equipment and the storage medium of the insurance based on driving behavior of the embodiment of the present application, pass through intelligence
Can processing equipment obtain driver and drive image and car status information, Intelligent treatment equipment to the driver drive image and
The car status information is analyzed, and determines whether the driving behavior of driver belongs to violation type, if belonging to, at intelligence
The corresponding violation data of driving behavior that reason equipment sends the driver to Cloud Server, so that the Cloud Server is based on institute
Violation data building vehicle insurance actuarial model is stated, the vehicle insurance actuarial model is used to determine based on the expense of the insurance of driving behavior,
Vehicle insurance actuarial model is constructed based on the violation data to realize, so that vehicle insurance actuarial model accuracy is higher, for example, using should
Vehicle insurance actuarial model determines the expense of insurance, can reduce the expense of the insurance of the user with good driving habit, promoted compared with
The expense of the insurance of the user of poor driving ability and/or driving habit.
Detailed description of the invention
A brief description of the drawings needed to be used in the description of the embodiments or the prior art will be given below.
Fig. 1 is a kind of application scenario diagram schematic diagram for the technical scheme that one embodiment of the application provides；
Fig. 2 is a kind of flow chart of the processing method for insurance based on driving behavior that one embodiment of the application provides；
Fig. 3 is another application scenario diagram schematic diagram for the technical scheme that one embodiment of the application provides；
Fig. 4 is the flow chart of the processing method for another insurance based on driving behavior that one embodiment of the application provides；
Fig. 5 is a kind of schematic diagram of the processing unit 500 for insurance based on driving behavior that one embodiment of the application provides；
Fig. 6 is a kind of schematic diagram for Intelligent treatment equipment 600 that one embodiment of the application provides；
Fig. 7 is a kind of schematic diagram of the processing unit 700 for insurance based on driving behavior that one embodiment of the application provides；
Fig. 8 is a kind of schematic diagram for Cloud Server 800 that one embodiment of the application provides.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description.
Fig. 1 is a kind of application scenario diagram schematic diagram for the technical scheme that one embodiment of the application provides, such as Fig. 1 institute
Show, image capture device and vehicle-state acquisition equipment are connect with Intelligent treatment equipment respectively, Intelligent treatment equipment and cloud service
Device communication connection.Image capture device acquires driver's driving image, and is supplied to the Intelligent treatment equipment of the embodiment of the present application,
Vehicle-state acquires equipment and acquires car status information, which may include mileage travelled, average speed, maximum
Instantaneous velocity, the time of trip, four urgency, real-time position information etc..Wherein, which specifically can be any setting
Have the electronic equipment of camera, for example, monitoring camera head etc., vehicle-state acquisition equipment can specifically include OBD equipment,
GPS device etc..The Intelligent treatment equipment of the embodiment of the present application can drive image to driver and car status information is divided
Analysis, determines whether the driving behavior of driver belongs to violation type, if belonging to, sends driving for the driver to Cloud Server
The corresponding violation data of behavior is sailed, vehicle insurance actuarial model is constructed based on the violation data to realize, so that vehicle insurance actuarial model
Accuracy is higher, for example, determining the expense of insurance using the vehicle insurance actuarial model, can reduce the use with good driving habit
The expense of the insurance at family promotes the expense of the insurance of the user of poor driving ability and/or driving habit.
Above-mentioned communication connection may include the connection of any communication technology such as 3G, 4G, 5G.
" driver's driving image " involved in this paper is used to reflect the real-time driving behavior of driver.
" car status information " involved in this paper is for reflecting vehicle oneself state and vehicle local environment.It specifically may be used
To be collected by OBD equipment, GPS device etc..
" Intelligent treatment equipment " involved in this paper, can also be referred to as artificial intelligence box (AI-Box), at the intelligence
Reason equipment can be vehicle electronic device, and the embodiment of the present application is to its title without specifically limiting.The Intelligent treatment equipment can
To be monitored in real time to the driving behavior of driver.
Fig. 2 is a kind of flow chart of the processing method for insurance based on driving behavior that one embodiment of the application provides, such as
Shown in Fig. 2, the method for the present embodiment may include:
Step 101, Intelligent treatment equipment obtain driver and drive image and car status information.
Image capture device acquires driver's driving image, and is supplied to the Intelligent treatment equipment of the embodiment of the present application, vehicle
State acquisition equipment acquires car status information, and is supplied to the Intelligent treatment equipment of the embodiment of the present application.
Step 102, Intelligent treatment equipment drives image to the driver and the car status information is analyzed, really
Whether the driving behavior for determining driver belongs to violation type.
Wherein, Intelligent treatment equipment uses the car status information as auxiliary, divides driver image of driving
Whether analysis, the driving behavior for monitoring the driver belong to violation type.I.e. by analyzing driver's driving image, know
The driving behavior of other driver, and then determine the driving behavior whether in violation of rules and regulations.
The driving behavior of violation type includes the behavior of any one non-security driving, for example, fatigue driving, middle pumping of driving
Cigarette, drive in make a phone call, drive that middle long-time is absent minded, middle safety belt buckling free of driving, middle both hands of driving leave direction
Disk etc., the present embodiment different one illustrate.
Intelligent treatment equipment can analyze each frame driver image of driving in conjunction with car status information.One kind can
Implementation, Intelligent treatment equipment can be used that deep learning network drives image to driver and car status information is divided
Analysis.
If step 103 belongs to, the driving behavior that Intelligent treatment equipment sends the driver to Cloud Server is corresponding
Violation data.
When the driving behavior of driver belongs to violation type, Intelligent treatment equipment sends the driver's to Cloud Server
The corresponding violation data of driving behavior.
The violation data may include the identification information of the driver, the video data of unlawful practice and unlawful practice letter
Breath.The identification information of the driver can be arbitrarily can be with the information of the unique identification driver, for example, the face mark of driver
Knowledge, phone number of driver etc..The video data of the unlawful practice, which can be, occurs the default of moment including the unlawful practice
The time span of the video data of period, the preset time period can carry out flexible setting according to demand, for example, 30 seconds.It disobeys
Rule behavioural information refers specifically to the information for describing the driving behavior for belonging to violation type, for example, fatigue driving.
Step 104, Cloud Server update the driving ability description information of the driver according to the violation data.
Specifically, Cloud Server receives the violation data that Intelligent treatment equipment is sent, updated according to violation data described in
The driving ability description information of driver.The driving ability description information can be structural body, which can
With to the driver driving ability and driving habit carry out objective description, for example, the drive speed of drive time section, preference,
The probability etc. of various unlawful practices.
Step 105, Cloud Server construct vehicle insurance actuarial model according to the driving ability description information of the driver.
Wherein, the vehicle insurance actuarial model is used to determine based on the expense of the insurance of driving behavior.The vehicle insurance actuarial model
It is to be calculated based on the driving ability description information, since the driving ability description information can reflect the driving ability of driver
And driving habit, it is possible to promote the accuracy of the vehicle insurance actuarial model.
The present embodiment obtains driver by Intelligent treatment equipment and drives image and car status information, and Intelligent treatment is set
It is standby to drive image to the driver and the car status information is analyzed, determine whether the driving behavior of driver belongs to
Violation type, if belonging to, the corresponding violation number of the driving behavior that Intelligent treatment equipment sends the driver to Cloud Server
According to so that the Cloud Server is based on the violation data and constructs vehicle insurance actuarial model, the vehicle insurance actuarial model is for being based on
The expense of the insurance of driving behavior determines, vehicle insurance actuarial model is constructed based on the violation data to realize, so that vehicle insurance actuarial
Model accuracy is higher, for example, determining the expense of insurance using the vehicle insurance actuarial model, can reduce with good driving habit
User insurance expense, promote the expense of the insurance of the user of poor driving ability and/or driving habit.
Fig. 3 is another application scenario diagram schematic diagram for the technical scheme that one embodiment of the application provides, such as Fig. 3
Shown, on the basis of application scenarios shown in Fig. 1, the application scenarios of the present embodiment can also include interactive device, database
And terminal.Wherein, which connect with Intelligent treatment equipment, which can be display screen on vehicle, loudspeaking
The output equipments such as device.The terminal can be the electronic equipments such as computer, mobile phone, tablet computer.
On the basis of the above embodiments, Cloud Server can also disobey this using the identification information of the driver as major key
The video data and unlawful practice information of rule behavior are stored in database as shown in Figure 3.The identification information can be face ID.
When accident occurs for insured vehicle, user can send data to Cloud Server by the terminal and transfer instruction, should
Data transfer the identification information that instruction carries driver, for example, the face ID of driver, Cloud Server is according to the mark of the driver
Know information and obtain corresponding video data from database, and be sent to the terminal, user can identify thing by watching video
Therefore occurrence cause, that is, determine whether that the violation driving behavior due to driver causes the accident, thus to compensation pay-outs
It judges, to constrain the unlawful practice of driver.The user can be the staff of insurance company.
Optionally, Cloud Server can also generate alarm command according to the unlawful practice of driver, send to interactive device
Alarm command, the alarm command is for triggering the interactive device to user feedback prompt information.For example, Cloud Server root
When determining that driver has fatigue driving behavior according to the embodiment of above-described embodiment, alarm command can be generated, the alarm command
Loudspeaker sending prompt tone can be triggered and avoid accident to alert to unlawful practice.
Specific explanations explanation is carried out to above-described embodiment using one embodiment below.
Fig. 4 is the flow chart of the processing method for another insurance based on driving behavior that one embodiment of the application provides,
The executing subject of the present embodiment is Intelligent treatment equipment, as shown in figure 4, the method for the present embodiment may include:
Step 201 obtains driver and drives image and car status information.
Wherein, the explanation of step 201 may refer to the step 101 of embodiment illustrated in fig. 2, and details are not described herein again.
Step 202, the target pair driven in image using the algorithm of target detection based on deep learning to the driver
As being detected, the position of the target object is determined.
Wherein, being somebody's turn to do the algorithm of target detection based on deep learning can be the algorithm of target detection such as faster-rcnn, ssd.
The target object may include each position such as face, hand, body of driver.
Step 203, the position according to the target object and the car status information, using neural network model to institute
State driver drive image carry out multi-tag classification, determine the behavior state of the driver.
Specifically, the neural network model can be any neural network model, which can be to driving
The behavior state of member identified, that is, determines the behavior state of driver, the behavior state of the driver include close one's eyes, open one's mouth,
It makes a phone call in driving.
Step 204, according at least one behavior state of the driver in preset time period, determine driving for driver
Sail whether behavior belongs to violation type.If belonging to violation type, 205 are thened follow the steps, if being not belonging to violation type, executes step
Rapid 201.
Specifically, multiframe driver's driving image can be collected in preset time period, each frame driver is driven respectively
Image is classified, and determines the behavior state of the corresponding driver of each frame image, can be according to the corresponding driving of a frame image
The behavior state of member determines whether the driving behavior of driver belongs to violation type, can also be according to the corresponding driving of multiple image
The behavior state of member determines whether the driving behavior of driver belongs to violation type, to promote recognition correct rate.
For example, the behavior state of the corresponding driver of a frame image is to open one's mouth, the corresponding driver of next frame image
Behavior state be close one's eyes, then can determine that the driver yawns and closes one's eyes, i.e. the driving behavior of the driver is that fatigue is driven
Behavior is sailed, violation type is belonged to.
Step 205, the corresponding violation data of driving behavior for sending the driver to Cloud Server.
Wherein, the explanation of step 205 may refer to the step 103 of embodiment illustrated in fig. 1, and details are not described herein again.
The present embodiment obtains driver by Intelligent treatment equipment and drives image and car status information, and Intelligent treatment is set
It is standby to drive image to the driver and the car status information is analyzed, determine whether the driving behavior of driver belongs to
Violation type, if belonging to, the corresponding violation number of the driving behavior that Intelligent treatment equipment sends the driver to Cloud Server
According to so that the Cloud Server is based on the violation data and constructs vehicle insurance actuarial model, the vehicle insurance actuarial model is for being based on
The expense of the insurance of driving behavior determines, vehicle insurance actuarial model is constructed based on the violation data to realize, so that vehicle insurance actuarial
Model accuracy is higher, for example, determining the expense of insurance using the vehicle insurance actuarial model, can reduce with good driving habit
User insurance expense, promote the expense of the insurance of the user of poor driving ability and/or driving habit.
Determine whether the driving behavior of driver belongs to violation class according to the behavior state of the corresponding driver of multiple image
Type, to promote recognition correct rate.
Fig. 5 is a kind of schematic diagram of the processing unit 500 for insurance based on driving behavior that one embodiment of the application provides,
As shown in figure 5, the device includes:
Module 501 is obtained, is driven image and car status information for obtaining driver；
Analysis module 502, for driving image to the driver and the car status information is analyzed；
Judgment module 503, for determining whether the driving behavior of driver belongs to violation type；
Sending module 504 sends the driving to Cloud Server if the driving behavior for driver belongs to violation type
The corresponding violation data of driving behavior of member, so that the Cloud Server is based on the violation data and constructs vehicle insurance actuarial model,
The vehicle insurance actuarial model is used to determine based on the expense of the insurance of driving behavior.
Optionally, the analysis module 502 is used for: being driven image and described using deep learning network to the driver
Car status information is analyzed.
Optionally, the analysis module 502 is used for: using the algorithm of target detection based on deep learning to the driver
The target object driven in image is detected, and determines the position of the target object；According to the position of the target object and
The car status information, using neural network model to the driver drive image carry out multi-tag classification, determine described in
The behavior state of driver.
Optionally, the judgment module 503, is used for: according at least one row of the driver in preset time period
For state, determine whether the driving behavior of driver belongs to violation type；Wherein, the driving behavior of violation type includes any one
The behavior of the non-security driving of kind.
Optionally, described device further include: generation module 505；The generation module 505 is used for according to the driver's
Unlawful practice generates alarm command；The sending module 504 is also used to send the alarm command, the announcement to interactive device
Alert instruction is for triggering the interactive device to user feedback prompt information.
Optionally, the violation data includes the identification information of the driver, the video data of unlawful practice and violation
Behavioural information.
The processing unit of insurance provided by the present application based on driving behavior can be Intelligent treatment equipment or Intelligent treatment
The inside chip of equipment can be used for executing method and step involved in Intelligent treatment equipment, content in above-described embodiment
Details are not described herein with effect.
Fig. 6 is a kind of schematic diagram for Intelligent treatment equipment 600 that one embodiment of the application provides, as shown in fig. 6, the equipment
It include: memory 601, processor 602 and transceiver 603.
Memory 601 is for instructing, so that processor 602 executes instruction, to realize the above-mentioned guarantor based on driving behavior
The processing method of danger.
Transceiver 603 is communicated for realizing between other equipment.
Processor 602 can be by one or more application specific integrated circuit (Application Specific
Integrated Circuit, ASIC), digital signal processor (Digital Signal Processor, DSP), number letter
Number processing equipment (Digital Signal Processing Device, DSPD), programmable logic device (Programmable
Logic Device, PLD), field programmable gate array (Field-Programmable Gate Array, FPGA), control
Device, microcontroller, microprocessor or other electronic components are realized.
Memory 601 can realize by any kind of volatibility or non-volatile memory device or their combination,
Such as static random access memory (Static Random Access Memory, SRAM), the read-only storage of electrically erasable
Device (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable programmable is only
It reads memory (Erasable Programmable Read-Only Memory, EPROM), programmable read only memory
(Programmable read-only memory, PROM), read-only memory (Read-Only Memory, ROM), magnetic storage
Device, flash memory, disk or CD.
Intelligent treatment equipment provided by the present application can be used for executing in above-described embodiment involved in Intelligent treatment equipment
Details are not described herein for method and step, content and effect.
Fig. 7 is a kind of schematic diagram of the processing unit 700 for insurance based on driving behavior that one embodiment of the application provides,
As shown in fig. 7, the device includes:
Receiving module 701, the corresponding violation data of driving behavior for receiving driver；
Processing module 702, for updating the driving ability description information of the driver according to the violation data；
The processing module 702 is also used to construct vehicle insurance actuarial mould according to the driving ability description information of the driver
Type, the vehicle insurance actuarial model are used to determine based on the expense of the insurance of driving behavior.
Optionally, the violation data includes the identification information of the driver, the video data of unlawful practice and violation
Behavioural information, the processing module 702 are also used to: using the identification information of the driver as major key, by the unlawful practice
Video data and unlawful practice information are stored in database.
Optionally, the identification information includes face identification information.
The processing unit of insurance provided by the present application based on driving behavior can be in Cloud Server or Cloud Server
Portion's chip, can be used for executing method and step involved in Cloud Server in above-described embodiment, and content and effect are herein not
It repeats again.
Fig. 8 is a kind of schematic diagram for Cloud Server 800 that one embodiment of the application provides, as shown in figure 8, the equipment packet
It includes: memory 801, processor 802 and transceiver 803.
Memory 801 is for instructing, so that processor 802 executes instruction, to realize the above-mentioned guarantor based on driving behavior
The processing method of danger.
Transceiver 803 is communicated for realizing between other equipment.
Processor 802 can be by one or more application specific integrated circuit (Application Specific
Integrated Circuit, ASIC), digital signal processor (Digital Signal Processor, DSP), number letter
Number processing equipment (Digital Signal Processing Device, DSPD), programmable logic device (Programmable
Logic Device, PLD), field programmable gate array (Field-Programmable Gate Array, FPGA), control
Device, microcontroller, microprocessor or other electronic components are realized.
Memory 801 can realize by any kind of volatibility or non-volatile memory device or their combination,
Such as static random access memory (Static Random Access Memory, SRAM), the read-only storage of electrically erasable
Device (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable programmable is only
It reads memory (Erasable Programmable Read-Only Memory, EPROM), programmable read only memory
(Programmable read-only memory, PROM), read-only memory (Read-Only Memory, ROM), magnetic storage
Device, flash memory, disk or CD.
Cloud Server provided by the present application can be used for executing method and step involved in Cloud Server in above-described embodiment,
Details are not described herein for its content and effect.
The application also provides a kind of storage medium, comprising: storage medium includes: instruction, is instructed for realizing above-mentioned base
In the processing method of the insurance of driving behavior.Details are not described herein for its content and effect.
The application provides a kind of computer program product, the computer program product include instruction, the instruction for realizing
The processing method of the above-mentioned insurance based on driving behavior.Details are not described herein for its content and effect.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (21)
1. a kind of processing method of the insurance based on driving behavior characterized by comprising
Driver is obtained to drive image and car status information；
Image is driven to the driver and the car status information is analyzed；
Determine whether the driving behavior of driver belongs to violation type；
If belonging to, the corresponding violation data of the driving behavior for sending the driver to Cloud Server, so that the cloud service
Device is based on the violation data and constructs vehicle insurance actuarial model, and the vehicle insurance actuarial model takes for the insurance based on driving behavior
With determination.
2. the method according to claim 1, wherein described drive image and the vehicle shape to the driver
State information is analyzed, comprising:
Image is driven to the driver using deep learning network and the car status information is analyzed.
3. according to the method described in claim 2, it is characterized in that, described drive to the driver using deep learning network
Image and the car status information are analyzed, comprising:
The driver target object in image of driving is detected using the algorithm of target detection based on deep learning, really
The position of the fixed target object；
According to the position of the target object and the car status information, driven using neural network model to the driver
Image carries out multi-tag classification, determines the behavior state of the driver.
4. according to the method described in claim 3, it is characterized in that, whether the driving behavior of the determining driver belongs in violation of rules and regulations
Behavior, comprising:
According at least one behavior state of the driver in preset time period, determine whether the driving behavior of driver belongs to
In violation type；
Wherein, the driving behavior of violation type includes the behavior of any one non-security driving.
5. according to claim 1 to method described in 4, which is characterized in that the method also includes:
According to the unlawful practice of the driver, alarm command is generated；
The alarm command is sent to interactive device, the alarm command is prompted for triggering the interactive device to user feedback
Information.
6. according to claim 1 to method described in 5, which is characterized in that the violation data includes the mark of the driver
Information, the video data of unlawful practice and unlawful practice information.
7. a kind of processing method of the insurance based on driving behavior characterized by comprising
Receive the corresponding violation data of driving behavior of driver；
The driving ability description information of the driver is updated according to the violation data；
Vehicle insurance actuarial model is constructed according to the driving ability description information of the driver, the vehicle insurance actuarial model is for being based on
The expense of the insurance of driving behavior determines.
8. the method according to the description of claim 7 is characterized in that the violation data includes the mark letter of the driver
Breath, the video data of unlawful practice and unlawful practice information, the method also includes:
Using the identification information of the driver as major key, the video data of the unlawful practice and unlawful practice information are stored in number
According to library.
9. according to the method described in claim 8, it is characterized in that, the identification information includes face identification information.
10. a kind of processing unit of the insurance based on driving behavior characterized by comprising
Module is obtained, is driven image and car status information for obtaining driver；
Analysis module, for driving image to the driver and the car status information is analyzed；
Judgment module, for determining whether the driving behavior of driver belongs to violation type；
Sending module sends driving for the driver to Cloud Server if the driving behavior for driver belongs to violation type
The corresponding violation data of behavior is sailed, so that the Cloud Server is based on the violation data and constructs vehicle insurance actuarial model, the vehicle
Dangerous actuarial model is used to determine based on the expense of the insurance of driving behavior.
11. device according to claim 10, which is characterized in that the analysis module is used for:
Image is driven to the driver using deep learning network and the car status information is analyzed.
12. device according to claim 11, which is characterized in that the analysis module is used for:
The driver target object in image of driving is detected using the algorithm of target detection based on deep learning, really
The position of the fixed target object；
According to the position of the target object and the car status information, driven using neural network model to the driver
Image carries out multi-tag classification, determines the behavior state of the driver.
13. device according to claim 12, which is characterized in that the judgment module is used for:
According at least one behavior state of the driver in preset time period, determine whether the driving behavior of driver belongs to
In violation type；
Wherein, the driving behavior of violation type includes the behavior of any one non-security driving.
14. device described in 0 to 13 according to claim 1, which is characterized in that described device further include: generation module；
The generation module is used for the unlawful practice according to the driver, generates alarm command；
The sending module is also used to send the alarm command to interactive device, and the alarm command is for triggering the interaction
Equipment is to user feedback prompt information.
15. device described in 0 to 14 according to claim 1, which is characterized in that the violation data includes the mark of the driver
Know the video data and unlawful practice information of information, unlawful practice.
16. a kind of processing unit of the insurance based on driving behavior characterized by comprising
Receiving module, the corresponding violation data of driving behavior for receiving driver；
Processing module, for updating the driving ability description information of the driver according to the violation data；
The processing module is also used to construct vehicle insurance actuarial model according to the driving ability description information of the driver, described
Vehicle insurance actuarial model is used to determine based on the expense of the insurance of driving behavior.
17. device according to claim 16, which is characterized in that the violation data includes the mark letter of the driver
Breath, the video data of unlawful practice and unlawful practice information, the processing module are also used to:
Using the identification information of the driver as major key, the video data of the unlawful practice and unlawful practice information are stored in number
According to library.
18. device according to claim 17, which is characterized in that the identification information includes face identification information.
19. a kind of Intelligent treatment equipment characterized by comprising
Memory and processor；
The memory is for instructing, so that the processor executes described instruction, to realize such as any one of claim 1~6
The processing method of the insurance based on driving behavior.
20. a kind of Cloud Server characterized by comprising
Memory and processor；
The memory is for instructing, so that the processor executes described instruction, to realize such as any one of claim 7~9
The processing method of the insurance based on driving behavior.
21. a kind of storage medium characterized by comprising the storage medium includes: instruction, and described instruction is for realizing such as
The processing method of insurance according to any one of claims 1 to 9 based on driving behavior.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811149959.6A CN109523652B (en) | 2018-09-29 | 2018-09-29 | Insurance processing method, device and equipment based on driving behaviors and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811149959.6A CN109523652B (en) | 2018-09-29 | 2018-09-29 | Insurance processing method, device and equipment based on driving behaviors and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109523652A true CN109523652A (en) | 2019-03-26 |
| CN109523652B CN109523652B (en) | 2022-03-22 |
Family
ID=65772143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811149959.6A Active CN109523652B (en) | 2018-09-29 | 2018-09-29 | Insurance processing method, device and equipment based on driving behaviors and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109523652B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110126835A (en) * | 2019-04-12 | 2019-08-16 | 中国平安财产保险股份有限公司 | Interference method, device, computer equipment and the storage medium of driving behavior |
| CN111062701A (en) * | 2019-12-18 | 2020-04-24 | 上海博泰悦臻电子设备制造有限公司 | Insurance management method and related device |
| CN111243236A (en) * | 2020-01-17 | 2020-06-05 | 南京邮电大学 | Fatigue driving early warning method and system based on deep learning |
| CN111866032A (en) * | 2019-04-11 | 2020-10-30 | 阿里巴巴集团控股有限公司 | Data processing method and device and computing equipment |
| CN112149511A (en) * | 2020-08-27 | 2020-12-29 | 深圳市点创科技有限公司 | Method, terminal and device for detecting violation of driver based on neural network |
| WO2021063005A1 (en) * | 2019-09-30 | 2021-04-08 | 上海商汤临港智能科技有限公司 | Driving data analysis method and apparatus, electronic device and computer storage medium |
| CN113139403A (en) * | 2020-01-17 | 2021-07-20 | 顺丰科技有限公司 | Violation behavior identification method and device, computer equipment and storage medium |
| CN113792691A (en) * | 2021-09-22 | 2021-12-14 | 平安国际智慧城市科技股份有限公司 | Video identification method, system, device and medium |
| CN114550147A (en) * | 2022-04-26 | 2022-05-27 | 天津大学 | Automobile data acquisition, analysis and processing method and system based on Internet of things |
| CN114627613A (en) * | 2020-12-11 | 2022-06-14 | 深圳酷派技术有限公司 | Irregular driving behavior recognition method and device, storage medium and electronic equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060106515A1 (en) * | 2003-05-06 | 2006-05-18 | Joseph Phelan | Motor vehicle operating data collection and analysis |
| US8595034B2 (en) * | 1996-01-29 | 2013-11-26 | Progressive Casualty Insurance Company | Monitoring system for determining and communicating a cost of insurance |
| KR20140031435A (en) * | 2012-08-28 | 2014-03-13 | (주)나노포인트 | Diagnostic system and method for the analysis of driving behavior |
| CN104732208A (en) * | 2015-03-16 | 2015-06-24 | 电子科技大学 | Video human action reorganization method based on sparse subspace clustering |
| CN104794856A (en) * | 2014-01-22 | 2015-07-22 | 径卫视觉科技（上海）有限公司 | Driver's attention comprehensive evaluation system |
| CN106600427A (en) * | 2016-12-22 | 2017-04-26 | 安徽保腾网络科技有限公司 | Novel vehicle insurance system |
| CN106778538A (en) * | 2016-11-28 | 2017-05-31 | 上海工程技术大学 | Intelligent driving behavior evaluation method based on analytic hierarchy process (AHP) |
| CN107784251A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | The method evaluated based on image recognition technology driving behavior |
| CN108416258A (en) * | 2018-01-23 | 2018-08-17 | 华侨大学 | A kind of multi-human body tracking method based on human body model |
-
2018
- 2018-09-29 CN CN201811149959.6A patent/CN109523652B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8595034B2 (en) * | 1996-01-29 | 2013-11-26 | Progressive Casualty Insurance Company | Monitoring system for determining and communicating a cost of insurance |
| US20060106515A1 (en) * | 2003-05-06 | 2006-05-18 | Joseph Phelan | Motor vehicle operating data collection and analysis |
| KR20140031435A (en) * | 2012-08-28 | 2014-03-13 | (주)나노포인트 | Diagnostic system and method for the analysis of driving behavior |
| CN104794856A (en) * | 2014-01-22 | 2015-07-22 | 径卫视觉科技（上海）有限公司 | Driver's attention comprehensive evaluation system |
| CN104732208A (en) * | 2015-03-16 | 2015-06-24 | 电子科技大学 | Video human action reorganization method based on sparse subspace clustering |
| CN107784251A (en) * | 2016-08-25 | 2018-03-09 | 大连楼兰科技股份有限公司 | The method evaluated based on image recognition technology driving behavior |
| CN106778538A (en) * | 2016-11-28 | 2017-05-31 | 上海工程技术大学 | Intelligent driving behavior evaluation method based on analytic hierarchy process (AHP) |
| CN106600427A (en) * | 2016-12-22 | 2017-04-26 | 安徽保腾网络科技有限公司 | Novel vehicle insurance system |
| CN108416258A (en) * | 2018-01-23 | 2018-08-17 | 华侨大学 | A kind of multi-human body tracking method based on human body model |
Non-Patent Citations (1)
| Title |
|---|
| 王罡: "基于UBI的车辆个性化保险费率厘定模式研究与应用", 《中国优秀硕士学位论文全文数据库 经济与管理学辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111866032A (en) * | 2019-04-11 | 2020-10-30 | 阿里巴巴集团控股有限公司 | Data processing method and device and computing equipment |
| CN110126835A (en) * | 2019-04-12 | 2019-08-16 | 中国平安财产保险股份有限公司 | Interference method, device, computer equipment and the storage medium of driving behavior |
| WO2021063005A1 (en) * | 2019-09-30 | 2021-04-08 | 上海商汤临港智能科技有限公司 | Driving data analysis method and apparatus, electronic device and computer storage medium |
| CN111062701A (en) * | 2019-12-18 | 2020-04-24 | 上海博泰悦臻电子设备制造有限公司 | Insurance management method and related device |
| CN111243236A (en) * | 2020-01-17 | 2020-06-05 | 南京邮电大学 | Fatigue driving early warning method and system based on deep learning |
| CN113139403A (en) * | 2020-01-17 | 2021-07-20 | 顺丰科技有限公司 | Violation behavior identification method and device, computer equipment and storage medium |
| CN112149511A (en) * | 2020-08-27 | 2020-12-29 | 深圳市点创科技有限公司 | Method, terminal and device for detecting violation of driver based on neural network |
| CN114627613A (en) * | 2020-12-11 | 2022-06-14 | 深圳酷派技术有限公司 | Irregular driving behavior recognition method and device, storage medium and electronic equipment |
| CN113792691A (en) * | 2021-09-22 | 2021-12-14 | 平安国际智慧城市科技股份有限公司 | Video identification method, system, device and medium |
| CN113792691B (en) * | 2021-09-22 | 2024-03-22 | 平安国际智慧城市科技股份有限公司 | Video identification method, system, equipment and medium |
| CN114550147A (en) * | 2022-04-26 | 2022-05-27 | 天津大学 | Automobile data acquisition, analysis and processing method and system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109523652B (en) | 2022-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523652A (en) | Processing method, device, equipment and the storage medium of insurance based on driving behavior | |
| US11380193B2 (en) | Method and system for vehicular-related communications | |
| US20210407015A1 (en) | Methods of determining accident cause and/or fault using telematics data | |
| US11375338B2 (en) | Method for smartphone-based accident detection | |
| US20230351888A1 (en) | Method and system for determining traffic-related characteristics | |
| US9990182B2 (en) | Computer platform for development and deployment of sensor-driven vehicle telemetry applications and services | |
| US9714037B2 (en) | Detection of driver behaviors using in-vehicle systems and methods | |
| WO2020042984A1 (en) | Vehicle behavior detection method and apparatus | |
| US10043084B2 (en) | Hierarchical context-aware extremity detection | |
| CN109791678A (en) | It is measured for the dynamic risk based on score and polymerize the intelligent adaptive automotive fittings and its correlation method that have telematics connection search engine | |
| US20100305806A1 (en) | Portable Multi-Modal Emergency Situation Anomaly Detection and Response System | |
| CN108124485A (en) | For the alarm method of limbs conflict behavior, device, storage medium and server | |
| CN107784251A (en) | The method evaluated based on image recognition technology driving behavior | |
| CN104730949A (en) | Affective user interface in an autonomous vehicle | |
| Iqbal et al. | Automatic incident detection in smart city using multiple traffic flow parameters via V2X communication | |
| EP3576037A1 (en) | Vehicle driver monitoring system and method for capturing driver performance parameters | |
| CN109389107A (en) | Vehicle safety processing method, device and computer readable storage medium | |
| RU2684484C1 (en) | Method and cognitive system for video analysis, monitoring, control of driver and vehicle state in real time | |
| Thevendran et al. | Deep Learning & Computer Vision for IoT based Intelligent Driver Assistant System | |
| CN111372197A (en) | Early warning method and related device | |
| KR101620171B1 (en) | system and method for integrating smart care system and eco-managing system | |
| Chintalapati et al. | Accident Prevention-Based Analysis Using IoT-Interfaced LabVIEW Model. | |
| Hong et al. | SLICE-based Trustworthiness Analysis system | |
| CN117274868A (en) | Traffic event identification method and system for video based on large model |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211021 Address after: 100176 101, floor 1, building 1, yard 7, Ruihe West 2nd Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Applicant after: Apollo Zhilian (Beijing) Technology Co.,Ltd. Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Applicant before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |