WO2020010715A1 - 电子装置、驾驶行为评分方法及存储介质 - Google Patents

电子装置、驾驶行为评分方法及存储介质 Download PDF

Info

Publication number
WO2020010715A1
WO2020010715A1 PCT/CN2018/107728 CN2018107728W WO2020010715A1 WO 2020010715 A1 WO2020010715 A1 WO 2020010715A1 CN 2018107728 W CN2018107728 W CN 2018107728W WO 2020010715 A1 WO2020010715 A1 WO 2020010715A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
driving behavior
user
model
travel
Prior art date
Application number
PCT/CN2018/107728
Other languages
English (en)
French (fr)
Inventor
吴壮伟
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2020010715A1 publication Critical patent/WO2020010715A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME 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
    • G07C5/00Registering or indicating the working of vehicles
    • G07C5/08Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0808Diagnosing performance data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • G06F18/232Non-hierarchical techniques
    • G06F18/2321Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks

Definitions

  • the present application relates to the field of driving behavior safety, and in particular, to an electronic device, a driving behavior scoring method, and a storage medium.
  • sensors such as acceleration sensors and gravity sensors are commonly used to collect three parameters of longitudinal acceleration, lateral acceleration, and vertical acceleration during driving, and determine whether driving behavior is safe by setting corresponding acceleration thresholds, or by calculating The average of each acceleration is used to score the driving behavior.
  • vehicles travel in different geographic situations, which correspond to different safe speed values. Therefore, if the influence of altitude data is not considered, the driving behavior of the driver cannot be accurately and comprehensively based on the speed data alone, and it cannot effectively help users avoid danger.
  • the present application proposes an electronic device, a driving behavior scoring method, and a storage medium, which can accurately and comprehensively understand the driving behavior of the driver, and thus can effectively help users avoid danger.
  • the present application proposes an electronic device including a memory and a processor connected to the memory, where the processor is configured to execute a driving behavior scoring program stored on the memory.
  • the driving behavior scoring program is executed by the processor, the following steps are implemented:
  • A1. Obtain and perform statistics on a user's terminal positioning data, and determine travel data of the user according to a statistical result of the terminal positioning data, the travel data including travel route data and speed data on a corresponding travel route; the travel route The data includes at least the altitude data of the starting point, the ending point and the passing point;
  • A2 Analyze the travel data according to a predetermined target travel mode determination method to determine a target travel mode, where the target travel mode is a driving mode;
  • the present application also proposes a driving behavior scoring method, which is characterized in that the method includes the following steps:
  • the travel data includes travel route data and speed data on a corresponding travel route; the travel route The data includes at least the altitude data of the starting point, the ending point and the passing point;
  • the present application also proposes a computer-readable storage medium storing a driving behavior scoring program, and the driving behavior scoring program may be executed by at least one processor to enable all The at least one processor executes the steps of the driving behavior scoring method according to any one of claims 6-9.
  • the electronic device, driving behavior scoring method, and storage medium proposed in the present application obtain terminal statistics of a user's terminal and perform statistics, and determine travel data of the user according to a statistical result of the terminal positioning data, where the travel data includes travel route data And the speed data on the corresponding travel route; the travel route data includes at least the altitude data of the starting point, the end point, and the passing point; and the target travel mode is determined from the travel data according to a predetermined target travel mode determination method,
  • the target travel mode is a driving mode; a driving behavior score analysis is performed on the travel data corresponding to the target travel mode according to a pre-trained user driving behavior scoring model to obtain a user's driving behavior score.
  • FIG. 1 is a schematic diagram of an optional hardware architecture of an electronic device proposed by the present application.
  • FIG. 2 is a schematic diagram of a program module of a driving behavior scoring program in an embodiment of the electronic device of the present application
  • FIG. 3 is an implementation flowchart of a preferred embodiment of a driving behavior scoring method of the present application.
  • FIG. 1 is a schematic diagram of an optional hardware architecture of an electronic device provided by the present application.
  • the electronic device 10 may include, but is not limited to, a memory 11, a processor 12, and a network interface 13 which may communicate with each other through a communication bus 14.
  • FIG. 1 only shows the electronic device 10 with components 11-14, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.
  • the memory 11 includes at least one type of computer-readable storage medium.
  • the computer-readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a random access memory (RAM), and a static memory.
  • the memory 11 may be an internal storage unit of the electronic device 10, such as a hard disk or a memory of the electronic device 10.
  • the memory 11 may also be an outsourced storage device of the electronic device 10, such as a plug-in hard disk, a smart memory card (SMC), and a secure digital (SD) device. ) Cards, flash cards, etc.
  • the memory 11 may also include both the internal storage unit of the electronic device 10 and its outsourced storage device.
  • the memory 11 is generally used to store an operating system and various application software installed on the electronic device 10, such as a user driving behavior scoring program.
  • the memory 11 can also be used to temporarily store various types of data that have been output or will be output.
  • the processor 12 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is generally used to control the overall operation of the electronic device 10.
  • the processor 12 is configured to run program code or process data stored in the memory 11, such as a running driving behavior scoring program of a user.
  • the network interface 13 may include a wireless network interface or a wired network interface.
  • the network interface 13 is generally used to establish a communication connection between the electronic device 10 and other electronic devices.
  • the communication bus 14 is used to implement a communication connection between the components 11-13.
  • FIG. 1 only shows the electronic device 10 having components 11-14 and a human-machine recognition program based on a dynamic picture, but it should be understood that it is not required to implement all the illustrated components, and more or less can be implemented instead. s component.
  • the electronic device 10 may further include a user interface (not shown in FIG. 1).
  • the user interface may include a display, an input unit such as a keyboard, and the user interface may further include a standard wired interface, a wireless interface, and the like.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED touch device, or the like.
  • the display may also be referred to as a display screen or a display unit for displaying information processed in the electronic device 10 and a user interface for displaying visualization.
  • A. Obtain and perform statistics on a user's terminal positioning data, and determine travel data of the user according to a statistical result of the terminal positioning data, where the travel data includes travel route data and speed data on a corresponding travel route; the travel route The data includes at least the altitude data of the starting point, the ending point and the passing point;
  • the terminal positioning data specifically includes a user's terminal identification, terminal location information, terminal movement acceleration, and corresponding time information.
  • the terminal identification may be a terminal ’s MAC address
  • the terminal location information includes a start point, an end point, and a way point.
  • the terminal is typically a device held by a user such as a mobile phone and a tablet for travel.
  • the obtained terminal positioning data of the user is used as the basic data of the user's travel data to perform statistics, and according to the statistical result, the user's travel route data and acceleration data on the corresponding travel route are determined.
  • the travel route data includes at least the altitude data of the starting point, the ending point, and the passing point.
  • the acceleration data of the movement on the travel route can be calculated according to time and location information in the user's terminal positioning data.
  • the speed data on the travel route may be at least one of speed, acceleration, angle, and angular velocity. It can also be obtained in real time by sensors built in the terminal. Among them, the sensors built in the terminal can collect speed characteristic data such as the speed, acceleration, angle, and angular velocity of the user's travel in real time, and can also collect GPS positioning data in real time.
  • the acceleration of movement can be calculated based on the time and location information in the user's terminal positioning data, and the travel mode can be initially determined based on the movement acceleration.
  • this judgment method may be misjudged.
  • the method for determining a predetermined target travel mode includes: obtaining a user travel route data model, and the user travel route data model includes at least two clusters.
  • each of the clustering clusters corresponds to an estimated travel mode; based on the travel route data and the user travel route data model, obtain at least one of the starting points from the at least two clustering clusters, An end point and a target cluster class corresponding to at least one geographical location between the start point and the end point; and based on the evaluation travel method corresponding to the target cluster class cluster, a target travel mode is obtained.
  • the target travel mode is a driving mode.
  • the user travel route data model is a model trained in advance to identify a travel mode corresponding to the current user travel data.
  • the user travel data model is obtained based on training user travel data and stored in a predetermined database.
  • the predetermined database may be a database such as MySQL or Oracle.
  • the terminal device recognizes the travel mode, it can be obtained from the predetermined database.
  • the user travel data model is a model obtained by performing cluster processing on the training user travel data by using a K-means clustering algorithm.
  • the training user travel data is travel data obtained by the user during the travel and used to train the user travel data model.
  • the travel data includes, but is not limited to, acceleration data, speed data, angle, and angular velocity data collected by the user at any time during the travel. At least one of.
  • the K-means clustering algorithm is a clustering algorithm based on distance evaluation similarity, that is, the closer the two objects are, the larger the similarity is.
  • the evaluated travel mode refers to the travel mode corresponding to the training user travel data in each cluster.
  • the user travel data model obtained by clustering using the K-means clustering algorithm includes at least two clustering clusters, and each clustering cluster corresponds to an estimated travel mode.
  • Each of the clusters includes a centroid user travel data, and the travel mode corresponding to the centroid user travel data is an evaluation travel mode.
  • the trained user travel data model includes at least seven clustering clusters, and each clustering cluster represents walking, cycling, light riding, bus, car, railway, and airplane, that is, each cluster Class clusters represent a way of travel. The smaller the centroid clustering of the training trip data to the clustering cluster, the more likely the training trip data belongs to the traveling mode corresponding to the clustering cluster.
  • the pre-trained user driving behavior scoring model is a neural network model.
  • the user driving behavior scoring model includes a training process and a test process of the model.
  • the training process of the model includes: collecting driving behavior data of the user within a preset time period, and dividing the collected driving behavior data into a preset proportion of training sample set and test sample set; substituting the data in the training sample set into The neural network model is trained to obtain the trained user driving behavior scoring model; the driving behavior data in the test sample set is substituted into the trained user driving behavior scoring model.
  • the test is determined to pass; otherwise, the test fails, and a training sample set needs to be added for further training until the test passes.
  • the driving behavior data of the user includes the altitude data of the passing point of the driving route and the corresponding speed data.
  • different driving safety speed thresholds are preset according to the altitude of the geographical location.
  • the altitude data can be obtained by the built-in air pressure sensor inside the terminal, and the altitude value can be obtained by converting the air pressure value, or can be obtained by the GPS sensor, which obtains the geospatial information of the user's location. , And further obtain the latitude, longitude, altitude and other information of the location based on the geospatial information.
  • the electronic device proposed by the present application firstly obtains user terminal positioning data and performs statistics, and determines the user's travel data according to a statistical result of the terminal positioning data, where the travel data includes travel route data And the speed data on the corresponding travel route; the travel route data includes at least the altitude data of the starting point, the end point, and the passing point; and then, analyzing the travel data according to a predetermined target travel mode determination method to determine the target travel Mode, the target travel mode is a driving mode; finally, a driving behavior score analysis is performed on the travel data corresponding to the target travel mode according to a pre-trained user driving behavior scoring model to obtain a user's driving behavior score.
  • a driving behavior score analysis is performed on the travel data corresponding to the target travel mode according to a pre-trained user driving behavior scoring model to obtain a user's driving behavior score.
  • the user driving behavior scoring program of the present application may be described by a program module having the same function according to different functions implemented by each part thereof.
  • FIG. 2 is a schematic diagram of a program module of a driving behavior scoring program for a user in an embodiment of the electronic device of the present application.
  • the user driving behavior scoring program can be divided into a prompt information acquisition module 201, a determination module 202, and a scoring module 203 according to different functions implemented by its various parts.
  • the program module referred to in the present application refers to a series of computer program instruction segments capable of performing specific functions, and is more suitable for describing the execution process of the user driving behavior scoring program in the electronic device 10 than the program.
  • the functions or operation steps implemented by the modules 201-203 are similar to the above, which will not be described in detail here.
  • the obtaining module 201 is configured to obtain user terminal positioning data and perform statistics, and determine a user's travel data according to a statistical result of the terminal positioning data, where the travel data includes travel route data and speed data on a corresponding travel route;
  • the travel route data includes at least altitude data of a start point, an end point, and a passing point;
  • the determination module 202 is configured to analyze the travel data according to a predetermined target travel mode determination method to determine a target travel mode, and the target travel mode is driving the way;
  • the scoring module 203 is configured to perform driving behavior scoring analysis on the travel data corresponding to the target travel mode according to a pre-trained user driving behavior scoring model to obtain a user's driving behavior score.
  • this application also proposes a driving behavior scoring method, as shown in FIG. 3.
  • the driving behavior scoring method includes the following steps:
  • S301 Obtain and perform statistics on a user's terminal positioning data, and determine travel data of the user according to a statistical result of the terminal positioning data, where the travel data includes travel route data and speed data on a corresponding travel route; the travel route The data includes at least the altitude data of the starting point, the ending point and the passing point;
  • the terminal positioning data specifically includes a user's terminal identification, terminal location information, terminal movement acceleration, and corresponding time information.
  • the terminal identification may be a terminal ’s MAC address
  • the terminal location information includes a start point, an end point, and a way point.
  • the terminal is typically a device held by a user such as a mobile phone and a tablet for travel.
  • the terminal positioning data of the user obtained is used as the basic data of the user's travel data to perform statistics, and the user's travel route data and acceleration data on the corresponding travel route are determined according to the statistical results.
  • the travel route data includes at least the altitude data of the starting point, the ending point, and the passing point.
  • the acceleration data of the movement on the travel route can be calculated according to time and location information in the user's terminal positioning data.
  • the speed data on the travel route may be at least one of speed, acceleration, angle, and angular velocity. It can also be obtained in real time by sensors built in the terminal. Among them, the sensors built in the terminal can collect speed characteristic data such as the speed, acceleration, angle, and angular velocity of the user's travel in real time, and can also collect GPS positioning data in real time.
  • the acceleration of movement can be calculated based on the time and location information in the user's terminal positioning data, and the travel mode can be initially determined based on the movement acceleration.
  • this judgment method may be misjudged.
  • the method for determining a predetermined target travel mode includes: obtaining a user travel route data model, and the user travel route data model includes at least two clusters.
  • each of the clustering clusters corresponds to an estimated travel mode; based on the travel route data and the user travel route data model, obtain at least one of the starting points from the at least two clustering clusters, An end point and a target cluster class corresponding to at least one geographical location between the start point and the end point; and based on the evaluation travel method corresponding to the target cluster class cluster, a target travel mode is obtained.
  • the target travel mode is a driving mode.
  • the user travel route data model is a model trained in advance to identify a travel mode corresponding to the current user travel data.
  • the user travel data model is obtained based on training user travel data and stored in a predetermined database.
  • the predetermined database may be a database such as MySQL or Oracle.
  • the terminal device recognizes the travel mode, it can be obtained from the predetermined database.
  • the user travel data model is a model obtained by performing cluster processing on the training user travel data by using a K-means clustering algorithm.
  • the training user travel data is travel data obtained by the user during the travel and used to train the user travel data model.
  • the travel data includes, but is not limited to, acceleration data, speed data, angle, and angular velocity data collected by the user at any time during the travel. At least one of.
  • the K-means clustering algorithm is a clustering algorithm based on distance evaluation similarity, that is, the closer the two objects are, the larger the similarity is.
  • the evaluated travel mode refers to the travel mode corresponding to the training user travel data in each cluster.
  • the user travel data model obtained by clustering using the K-means clustering algorithm includes at least two clustering clusters, and each clustering cluster corresponds to an estimated travel mode.
  • Each of the clusters includes a centroid user travel data, and the travel mode corresponding to the centroid user travel data is an evaluation travel mode.
  • the trained user travel data model includes at least seven clustering clusters, and each clustering cluster represents walking, cycling, light riding, bus, car, railway, and airplane, that is, each cluster Class clusters represent a way of travel. The smaller the centroid clustering of the training trip data to the clustering cluster, the more likely the training trip data belongs to the traveling mode corresponding to the clustering cluster.
  • S303 Perform driving behavior score analysis on the travel data corresponding to the target travel mode according to the pre-trained user driving behavior scoring model to obtain a user's driving behavior score.
  • the pre-trained user driving behavior scoring model is a neural network model.
  • the user driving behavior scoring model includes a training process and a testing process of the model, and the training process of the model includes collecting driving behavior data of the user within a preset time period, and dividing the collected driving behavior data into a preset ratio.
  • Training sample set and test sample set substituting the data in the training sample set into the neural network model for training to obtain the trained user driving behavior scoring model; substituting the driving behavior data in the test sample set into the trained user driving behavior scoring model If the error between the driving behavior score output by the user ’s driving behavior model and the predetermined driving behavior score of the user is less than a preset error threshold, the test is determined to pass, otherwise the test fails , You need to increase the training sample set and further training until the test passes.
  • the driving behavior data of the user includes the altitude data of the passing point of the driving route and the corresponding speed data.
  • different driving safety speed thresholds are preset according to the altitude of the geographical location.
  • the altitude data can be obtained by the built-in air pressure sensor inside the terminal, and the altitude value can be obtained by converting the air pressure value, or can be obtained by the GPS sensor, which obtains the geospatial information of the user's location. , And further obtain the latitude, longitude, altitude and other information of the location based on the geospatial information.
  • the driving behavior scoring method proposed in the present application firstly obtains terminal statistics of a user and performs statistics, and determines travel data of the user according to a statistical result of the terminal positioning data, where the travel data includes travel Route data and speed data on the corresponding travel route; the travel route data includes at least the altitude data of the starting point, the end point, and the passing point; and then, analyzing the travel data according to a predetermined target travel mode determination method to determine the A target travel mode, which is a driving mode; finally, a driving behavior score analysis is performed on the travel data corresponding to the target travel mode according to a pre-trained user driving behavior scoring model to obtain a user's driving behavior score.
  • a predetermined target travel mode determination method to determine the A target travel mode, which is a driving mode
  • a driving behavior score analysis is performed on the travel data corresponding to the target travel mode according to a pre-trained user driving behavior scoring model to obtain a user's driving behavior score.
  • this application also proposes a computer-readable storage medium, where the computer-readable storage medium stores a driving behavior scoring program, and when the driving behavior scoring program is executed by a processor, the following operations are implemented:
  • driving behavior scoring analysis is performed on the travel data corresponding to the target travel mode to obtain the user's driving behavior score.
  • the methods in the above embodiments can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware, but in many cases the former is better.
  • Implementation Based on such an understanding, the technical solution of this application that is essentially or contributes to the existing technology can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, The optical disc) includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the embodiments of the present application.
  • a terminal device which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Biology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请公开了一种电子装置、驾驶行为评分方法及存储介质,所述方法:通过获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;根据预先确定的目标出行方式确定方法,从所述出行数据中确定出目标出行方式,所述目标出行方式为驾驶方式;根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。能够准确全面的了解驾驶员的驾驶行为,进而能有效地帮助用户避免危险。

Description

电子装置、驾驶行为评分方法及存储介质
本申请要求于2018年7月13日提交中国专利局,申请号为201810768315.9、发明名称为“电子装置、驾驶行为评分方法及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及驾驶行为安全领域,尤其涉及一种电子装置、驾驶行为评分方法及存储介质。
背景技术
随着人们生活水平的日益提高,机动车辆的数量也越来越多,在驾驶车辆过程中,不安全的驾驶行为会带来很多安全隐患,造成巨大的财产和人员损失。因此,在车险领域,若能准确地知道驾驶员的驾驶行为,并对存在不良驾驶行为的驾驶员提出安全预警,并要求其进行改善已经成为一个不可忽视的问题。
目前,通常借助于传感器,例如加速度传感器和重力传感器来分别采集行车过程中的纵向加速度、横向加速度、及垂直加速度三个参数,并通过设置对应的加速度阈值来判断驾驶行为是否安全,或者通过计算各个加速度的平均值来对驾驶行为进行评分。然而,车辆在不同的地理形势中行驶,其对应有不同的安全速度值。因此,若不考虑海拔数据的影响,仅依据速度数据不能准确全面的了解驾驶员的驾驶行为,也不能有效地帮助用户避免危险。
发明内容
有鉴于此,本申请提出一种电子装置、驾驶行为评分方法及存储介质,能够准确全面的了解驾驶员的驾驶行为,进而能有效地帮助用户避免危险。
首先,为实现上述目的,本申请提出一种电子装置,所述电子装置包括存储器、及与所述存储器连接的处理器,所述处理器用于执行所述存储器上存储的驾驶行为评分程序,所述驾驶行为评分程序被所述处理器执行时实现如下步骤:
A1、获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
A2、根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
A3、根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
此外,为实现上述目的,本申请还提出一种驾驶行为评分方法,其特征在于,所述方法包括如下步骤:
S1、获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
S2、根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
S3、根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
此外,为实现上述目的,本申请还提出一种计算机可读存储介质,所述计算机可读存储介质存储有驾驶行为评分程序,所述驾驶行为评分程序可被至少一个处理器执行,以使所述至少一个处理器执行如权利要求6-9中任一项所述的驾驶行为评分方法的步骤。
本申请所提出的电子装置、驾驶行为评分方法及存储介质,通过获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;根据预先确定的目标出行方式确定方法,从所述出行数据中确定出目标出行方式,所述目标出行方式为驾驶方式;根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。能够准确全面的了解驾驶员的驾驶行为,进而能有效地帮助用户避免危险。
附图说明
图1是本申请提出的电子装置一可选的硬件架构的示意图;
图2是本申请电子装置一实施例中驾驶行为评分程序的程序模块示意图;
图3是本申请驾驶行为评分方法较佳实施例的实施流程图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
需要说明的是,在本申请中涉及“第一”、“第二”等的描述仅用于描述目的,而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该 特征。另外,各个实施例之间的技术方案可以相互结合,但是必须是以本领域普通技术人员能够实现为基础,当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在,也不在本申请要求的保护范围之内。
参阅图1所示,是本申请提出的电子装置一可选的硬件架构示意图。本实施例中,电子装置10可包括,但不仅限于,可通过通信总线14相互通信连接存储器11、处理器12、网络接口13。需要指出的是,图1仅示出了具有组件11-14的电子装置10,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
其中,存储器11至少包括一种类型的计算机可读存储介质,计算机可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中,存储器11可以是电子装置10的内部存储单元,例如电子装置10的硬盘或内存。在另一些实施例中,存储器11也可以是电子装置10的外包存储设备,例如电子装置10上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。当然,存储器11还可以既包括电子装置10的内部存储单元也包括其外包存储设备。本实施例中,存储器11通常用于存储安装于电子装置10的操作系统和各类应用软件,例如用户驾驶行为评分程序等。此外,存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器12在一些实施例中可以是中央处理器(Central Processing Unit,CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。处理器12通常用于控制电子装置10的总体操作。本实施例中,处理器12用于运行存储器11中存储的程序代码或者处理数据,例如运行的用户驾驶行为评分程序等。
网络接口13可包括无线网络接口或有线网络接口,网络接口13通常用于在电子装置10与其他电子设备之间建立通信连接。
通信总线14用于实现组件11-13之间的通信连接。
图1仅示出了具有组件11-14以及基于动态图片的人机识别程序的电子装置10,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
可选地,电子装置10还可以包括用户接口(图1中未示出),用户接口可以包括显示器、输入单元比如键盘,其中,用户接口还可以包括标准的有线接口、无线接口等。
可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED触摸器等。
进一步地,显示器也可称为显示屏或显示单元,用于显示在电子装置10中处理信息以及用于显示可视化的用户界面。
在一实施例中,存储器11中存储的用户驾驶行为评分程序被处理器12执行时,实现如下操作:
A、获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
示例性的,所述终端定位数据具体包括用户的终端标识、终端位置信息、终端移动的加速度以及对应的时间信息,例如终端标识可以是终端的MAC地址,终端位置信息包括起点、终点、途径点以及在起点、终点、途经点的经纬度数据、海波数据等。其中,终端典型的是手机、平板电脑等用户出行是持有的设备。
上述操作中,获取的用户的终端定位数据,作为用户出行数据的基础数据进行统计,根据统计结果,确定用户的出行路线数据以及在对应的出行路 线上的加速度数据。其中,出行路线数据至少包括起点、终点以及途经点的海拔数据。所述出行路线上移动的加速度数据可以根据用户的终端定位数据中的时间和位置信息计算得到。进一步地,所述出行路线上的速度数据可以是速度、加速度、角度和角速度中的至少一种。其也可以通过终端中内置的传感器实时采集得到,其中,终端中内置的传感器可以实时采集用户出行的速度、加速度、角度、角速度等速度特征数据,也可以实时采集GPS定位数据等。
B、根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
可以理解的是,常见的用户出行可以有多种选择,例如可以是驾车、步行、骑自行车、公交车或者地铁等。通常,可以根据用户的终端定位数据中的时间和位置信息,计算出移动的加速度,并根据移动加速度可以初步判断出行方式。但是这种判断方式有可能出现误判,在本实施例中,所述预先确定的目标出行方式确定方法包括:获取用户出行路线数据模型,所述用户出行路线数据模型包括至少两个聚类类簇,每一所述聚类类簇对应一评估出行方式;基于所述出行路线数据和所述用户出行路线数据模型,从所述至少两个聚类类簇中获取与至少一个所述起点、终点以及所述起点与终点之间的至少一个地理位置相对应的目标聚类类簇;基于所述目标聚类类簇对应的评估出行方法,获取目标出行方式。在本实施例中,所述目标出行方式为驾驶方式。
具体地,所述用户出行路线数据模型为预先训练好的用于识别当前用户出行数据对应的出行方式的模型。该用户出行数据模型基于训练用户出行数据得到并存储在预先确定的数据库中,具体地,预先确定的数据库可以是MySQL、Oracle等数据库,在终端设备进行出行方式识别时,可以从预先确定的数据库中调取该用户出行数据模型。本实施例中,用户出行数据模型是通过K-means聚类算法对训练用户出行数据进行聚类处理之后获得的模型。 该训练用户出行数据是用户在出行时获取的用于训练用户出行数据模型的出行数据,该出行数据包括但不限于用户在出行时的任意时刻采集到的加速度数据、速度数据、角度和角速度数据中的至少一个。其中,K-means聚类算法是一种基于距离评估相似度的聚类算法,即两个对象的距离越近,其相似度越大的聚类算法。评估出行方式是指每一聚类类簇中训练用户出行数据所对应的出行方式。
具体地,采用K-means聚类算法进行聚类后获取的用户出行数据模型包括至少两个聚类类簇,每一聚类类簇对应一评估出行方式。其中,每一聚类类簇包括一质心用户出行数据,质心用户出行数据对应的出行方式为评估出行方式。本实施例中,该训练好的用户出行数据模型至少包括七个聚类类簇,每个聚类类簇分别代表步行、自行车、轻骑、公共汽车、轿车、铁路和飞机,即每个聚类类簇代表一种出行方式。训练出行数据到聚类类簇的质心聚类越小,则该训练出行数据越有可能属于该聚类类簇对应的出行方式。
C、根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
具体地,预先训练完成的用户驾驶行为评分模型为神经网络模型。所述用户驾驶行为评分模型包括模型的训练过程和测试过程。所述模型的训练过程包括,采集预设时间段内该用户的驾驶行为数据,并将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型;将测试样本集中的驾驶行为数据代入训练完成的用户驾驶行为评分模型,若该用户驾驶行为模型输出的驾驶行为评分与预先确定的该用户的驾驶行为评分之间的误差小于预设误差阈值的概率小于预设的概率阈值,则确定测试通过,否则,测试不通过,需要增加训练样本集,进一步进行训练,直至测试通过为止。
具体地,用户驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据,通常根据地理位置的海拔高度不同,预设有不同的行驶安全速度阈值。具体地,海拔数据可以通过终端内部内置的气压传感器获取到用户所在位置的气压值,并将该气压值通过换算得到海拔高度,也可以通过GPS传感器获取,GPS传感器获取用户所在位置的地理空间信息,进一步根据地理空间信息得到所在位置的经纬度、海拔等信息。
由上述事实施例可知,本申请提出的电子装置,首先,通过获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;然后,根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;最后,根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。能够准确全面的了解驾驶员的驾驶行为,进而能有效地帮助用户避免危险。
此外,本申请的用户驾驶行为评分程序依据其各部分所实现的功能不同,可用具有相同功能的程序模块进行描述。请参阅图2所示,是本申请电子装置一实施例中用户驾驶行为评分程序的程序模块示意图。本实施例中,用户驾驶行为评分程序依据其各部分所实现的功能的不同,可以被分割成提示信息获取模块201、确定模块202以及评分模块203。由上面的描述可知,本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段,比程序更适合于描述用户驾驶行为评分程序在电子装置10中的执行过程。所述模块201-203所实现的功能或操作步骤均与上文类似,此处不再详述,示例性地,例如其中:
获取模块201用于获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据 以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;确定模块202用于根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
评分模块203用于根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。此外,本申请还提出一种驾驶行为评分方法,请参阅图3所示,所述驾驶行为评分方法包括如下步骤:
S301、获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
示例性的,所述终端定位数据具体包括用户的终端标识、终端位置信息、终端移动的加速度以及对应的时间信息,例如终端标识可以是终端的MAC地址,终端位置信息包括起点、终点、途径点以及在起点、终点、途经点的经纬度数据、海波数据等。其中,终端典型的是手机、平板电脑等用户出行是持有的设备。
上述操作中,获取的用户的终端定位数据,作为用户出行数据的基础数据进行统计,根据统计结果,确定用户的出行路线数据以及在对应的出行路线上的加速度数据。其中,出行路线数据至少包括起点、终点以及途经点的海拔数据。所述出行路线上移动的加速度数据可以根据用户的终端定位数据中的时间和位置信息计算得到。进一步地,所述出行路线上的速度数据可以是速度、加速度、角度和角速度中的至少一种。其也可以通过终端中内置的传感器实时采集得到,其中,终端中内置的传感器可以实时采集用户出行的速度、加速度、角度、角速度等速度特征数据,也可以实时采集GPS定位数据等。
S302、根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
可以理解的是,常见的用户出行可以有多种选择,例如可以是驾车、步行、骑自行车、公交车或者地铁等。通常,可以根据用户的终端定位数据中的时间和位置信息,计算出移动的加速度,并根据移动加速度可以初步判断出行方式。但是这种判断方式有可能出现误判,在本实施例中,所述预先确定的目标出行方式确定方法包括:获取用户出行路线数据模型,所述用户出行路线数据模型包括至少两个聚类类簇,每一所述聚类类簇对应一评估出行方式;基于所述出行路线数据和所述用户出行路线数据模型,从所述至少两个聚类类簇中获取与至少一个所述起点、终点以及所述起点与终点之间的至少一个地理位置相对应的目标聚类类簇;基于所述目标聚类类簇对应的评估出行方法,获取目标出行方式。在本实施例中,所述目标出行方式为驾驶方式。
具体地,所述用户出行路线数据模型为预先训练好的用于识别当前用户出行数据对应的出行方式的模型。该用户出行数据模型基于训练用户出行数据得到并存储在预先确定的数据库中,具体地,预先确定的数据库可以是MySQL、Oracle等数据库,在终端设备进行出行方式识别时,可以从预先确定的数据库中调取该用户出行数据模型。本实施例中,用户出行数据模型是通过K-means聚类算法对训练用户出行数据进行聚类处理之后获得的模型。该训练用户出行数据是用户在出行时获取的用于训练用户出行数据模型的出行数据,该出行数据包括但不限于用户在出行时的任意时刻采集到的加速度数据、速度数据、角度和角速度数据中的至少一个。其中,K-means聚类算法是一种基于距离评估相似度的聚类算法,即两个对象的距离越近,其相似度越大的聚类算法。评估出行方式是指每一聚类类簇中训练用户出行数据所对应的出行方式。
具体地,采用K-means聚类算法进行聚类后获取的用户出行数据模型包括至少两个聚类类簇,每一聚类类簇对应一评估出行方式。其中,每一聚类类簇包括一质心用户出行数据,质心用户出行数据对应的出行方式为评估出行方式。本实施例中,该训练好的用户出行数据模型至少包括七个聚类类簇,每个聚类类簇分别代表步行、自行车、轻骑、公共汽车、轿车、铁路和飞机,即每个聚类类簇代表一种出行方式。训练出行数据到聚类类簇的质心聚类越小,则该训练出行数据越有可能属于该聚类类簇对应的出行方式。
S303、根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
具体地,预先训练完成的用户驾驶行为评分模型为神经网络模型。所述用户驾驶行为评分模型包括模型的训练过程和测试过程,所述模型的训练过程包括,采集预设时间段内该用户的驾驶行为数据,并将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型;将测试样本集中的驾驶行为数据代入训练完成的用户驾驶行为评分模型,若该用户驾驶行为模型输出的驾驶行为评分与预先确定的该用户的驾驶行为评分之间的误差小于预设误差阈值的概率小于预设的概率阈值,则确定测试通过,否则,测试不通过,需要增加训练样本集,进一步进行训练,直至测试通过为止。
具体地,用户驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据,通常根据地理位置的海拔高度不同,预设有不同的行驶安全速度阈值。具体地,海拔数据可以通过终端内部内置的气压传感器获取到用户所在位置的气压值,并将该气压值通过换算得到海拔高度,也可以通过GPS传感器获取,GPS传感器获取用户所在位置的地理空间信息,进一步根据地理空间信息得到所在位置的经纬度、海拔等信息。
由上述事实施例可知,本申请提出的驾驶行为评分方法,首先,通过获 取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;然后,根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;最后,根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。能够准确全面的了解驾驶员的驾驶行为,进而能有效地帮助用户避免危险。
此外,本申请还提出一种计算机可读存储介质,所述计算机可读存储介质上存储有驾驶行为评分程序,所述驾驶行为评分程序被处理器执行时实现如下操作:
获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
本申请计算机可读存储介质具体实施方式与上述电子装置以及驾驶行为评分方法各实施例基本相同,在此不作累述。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体 现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种电子装置,其特征在于,所述电子装置包括存储器、及与所述存储器连接的处理器,所述处理器用于执行所述存储器上存储的驾驶行为评分程序,所述驾驶行为评分程序被所述处理器执行时实现如下步骤:
    A1、获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
    A2、根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
    A3、根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
  2. 如权利要求1所述的电子装置,其特征在于,在所述步骤A2中,所述根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式的步骤,包括:
    获取用户出行路线数据模型,所述用户出行路线数据模型包括至少两个聚类类簇,每一所述聚类类簇对应一评估出行方式;
    基于所述出行路线数据和所述用户出行路线数据模型,从所述至少两个聚类类簇中获取与至少一个所述起点、终点以及所述起点与终点之间的至少一个地理位置相对应的目标聚类类簇;
    基于所述目标聚类类簇对应的评估出行方法,获取目标出行方式。
  3. 如权利要求2所述的电子装置,其特征在于,所述获取用户出行数据路线模型之前,还包括如下步骤:
    基于训练用户出行数据训练所述用户出行路线数据模型,将训练完成的用户出行路线模型存储在预先确定的数据库中;
    所述获取用户出行路线数据模型,包括:从所述预先确定的数据库中获 取所述用户出行路线数据模型。
  4. 如权利要求1所述的电子装置,其特征在于,在所述步骤A3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  5. 如权利要求2所述的电子装置,其特征在于,在所述步骤A3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  6. 如权利要求3所述的电子装置,其特征在于,在所述步骤A3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  7. 如权利要求4-6任一项所述的电子装置,其特征在于,所述模型的测试过程包括:
    将测试样本集中的驾驶行为数据代入训练完成的用户驾驶行为评分模型;
    若该用户驾驶行为模型输出的驾驶行为评分与预先确定的该用户的驾驶行为评分之间的误差,小于预设误差阈值的概率小于预设的概率阈值,则确定测试通过,否则,测试不通过,重复执行上述步骤E、F、G。
  8. 一种驾驶行为评分方法,其特征在于,所述方法包括如下步骤:
    S1、获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
    S2、根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
    S3、根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
  9. 如权利要求8所述的驾驶行为评分方法,其特征在于,在所述步骤S2中,
    所述根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式的步骤,包括:
    获取用户出行路线数据模型,所述用户出行路线数据模型包括至少两个聚类类簇,每一所述聚类类簇对应一评估出行方式;
    基于所述出行路线数据和所述用户出行路线数据模型,从所述至少两个聚类类簇中获取与至少一个所述起点、终点以及所述起点与终点之间的至少一个地理位置相对应的目标聚类类簇;
    基于所述目标聚类类簇对应的评估出行方法,获取目标出行方式。
  10. 如权利要求9所述的驾驶行为评分方法,其特征在于,所述获取用户出行数据路线模型之前,还包括如下步骤:
    基于训练用户出行数据训练所述用户出行路线数据模型,将训练完成的用户出行路线模型存储在预先确定的数据库中;
    所述获取用户出行路线数据模型,包括:从所述预先确定的数据库中获取所述用户出行路线数据模型。
  11. 如权利要求8所述的驾驶行为评分方法,其特征在于,在所述步骤S3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  12. 如权利要求9所述的驾驶行为评分方法,其特征在于,在所述步骤A3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  13. 如权利要求10所述的驾驶行为评分方法,其特征在于,在所述步骤A3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用 户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  14. 如权利要求11-13任一项所述的驾驶行为评分方法,其特征在于,所述模型的测试过程包括:
    将测试样本集中的驾驶行为数据代入训练完成的用户驾驶行为评分模型;
    若该用户驾驶行为模型输出的驾驶行为评分与预先确定的该用户的驾驶行为评分之间的误差,小于预设误差阈值的概率小于预设的概率阈值,则确定测试通过,否则,测试不通过,重复执行上述步骤E、F、G。
  15. 一种计算机可读存储介质,所述计算机可读存储介质存储有驾驶行为评分程序,所述驾驶行为评分程序可被至少一个处理器执行,以使所述至少一个处理器执行如下步骤:
    S1、获取用户的终端定位数据并进行统计,根据所述终端定位数据的统计结果确定用户的出行数据,所述出行数据包括出行路线数据以及在对应的出行路线上的速度数据;所述出行路线数据至少包括起点、终点以及途经点的海拔数据;
    S2、根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式,所述目标出行方式为驾驶方式;
    S3、根据预先训练完成的用户驾驶行为评分模型对目标出行方式对应的出行数据进行驾驶行为评分分析,以得到用户的驾驶行为的评分。
  16. 如权利要求15所述的计算机可读存储介质,其特征在于,在所述步 骤S2中,
    所述根据预先确定的目标出行方式确定方法分析所述出行数据,以确定出目标出行方式的步骤,包括:
    获取用户出行路线数据模型,所述用户出行路线数据模型包括至少两个聚类类簇,每一所述聚类类簇对应一评估出行方式;
    基于所述出行路线数据和所述用户出行路线数据模型,从所述至少两个聚类类簇中获取与至少一个所述起点、终点以及所述起点与终点之间的至少一个地理位置相对应的目标聚类类簇;
    基于所述目标聚类类簇对应的评估出行方法,获取目标出行方式。
  17. 如权利要求15所述的计算机可读存储介质,其特征在于,所述获取用户出行数据路线模型之前,还包括如下步骤:
    基于训练用户出行数据训练所述用户出行路线数据模型,将训练完成的用户出行路线模型存储在预先确定的数据库中;
    所述获取用户出行路线数据模型,包括:从所述预先确定的数据库中获取所述用户出行路线数据模型。
  18. 如权利要求16所述的计算机可读存储介质,其特征在于,在所述步骤S3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  19. 如权利要求16所述的计算机可读存储介质,其特征在于,在所述步骤A3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述 用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
  20. 如权利要求17所述的计算机可读存储介质,其特征在于,在所述步骤A3中,所述预先训练完成的用户驾驶行为评分模型为神经网络模型,所述用户驾驶行为评分模型包括模型的训练过程和测试过程;所述模型的训练过程包括:
    E、采集预设时间段内该用户的驾驶行为数据,所述驾驶行为数据包括行驶路线途经点的海拔数据以及对应的速度数据;
    F、将采集到的驾驶行为数据分为预设比例的训练样本集和测试样本集;
    G、将训练样本集中的数据代入神经网络模型,进行训练,得到训练完成的用户驾驶行为评分模型。
PCT/CN2018/107728 2018-07-13 2018-09-26 电子装置、驾驶行为评分方法及存储介质 WO2020010715A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810768315.9 2018-07-13
CN201810768315.9A CN108986255A (zh) 2018-07-13 2018-07-13 电子装置、驾驶行为评分方法及存储介质

Publications (1)

Publication Number Publication Date
WO2020010715A1 true WO2020010715A1 (zh) 2020-01-16

Family

ID=64537298

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/107728 WO2020010715A1 (zh) 2018-07-13 2018-09-26 电子装置、驾驶行为评分方法及存储介质

Country Status (2)

Country Link
CN (1) CN108986255A (zh)
WO (1) WO2020010715A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111680058A (zh) * 2020-04-24 2020-09-18 合肥湛达智能科技有限公司 一种基于嵌入式终端的多目标跟踪及行为分析检测方法
CN114162142A (zh) * 2021-12-17 2022-03-11 广州小鹏自动驾驶科技有限公司 行驶路径的评分方法、装置、车辆及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111833480B (zh) * 2019-04-12 2022-04-15 比亚迪股份有限公司 驾驶行为检测方法、装置和车辆
CN111860928B (zh) * 2020-01-21 2024-07-02 北京嘀嘀无限科技发展有限公司 一种行车规划的制定方法、装置、电子设备及存储介质
CN113901627A (zh) * 2020-06-22 2022-01-07 阿里巴巴集团控股有限公司 路线安全性评估方法和装置、电子设备以及计算机可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104158846A (zh) * 2014-07-16 2014-11-19 深圳市凯伦圣科技有限公司 一种驾驶行为分析方法及系统
CN104599545A (zh) * 2014-05-19 2015-05-06 腾讯科技(深圳)有限公司 用于行车过程中的行车状态监测方法、装置和导航设备
CN104601640A (zh) * 2014-05-07 2015-05-06 腾讯科技(深圳)有限公司 驾驶信息处理方法、客户端及系统
CN105894610A (zh) * 2015-11-11 2016-08-24 乐卡汽车智能科技(北京)有限公司 数据处理方法、装置及系统
CN107784597A (zh) * 2017-09-19 2018-03-09 平安科技(深圳)有限公司 出行方式识别方法、装置、终端设备及存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104648283B (zh) * 2015-01-12 2017-03-22 重庆嗨驾科技有限公司 车辆驾驶行为分析评价系统
CN106585635B (zh) * 2016-11-25 2019-05-10 东软集团股份有限公司 驾驶行为评分方法和装置
CN107918963A (zh) * 2017-11-16 2018-04-17 百度在线网络技术(北京)有限公司 用于车辆的信息生成方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104601640A (zh) * 2014-05-07 2015-05-06 腾讯科技(深圳)有限公司 驾驶信息处理方法、客户端及系统
CN104599545A (zh) * 2014-05-19 2015-05-06 腾讯科技(深圳)有限公司 用于行车过程中的行车状态监测方法、装置和导航设备
CN104158846A (zh) * 2014-07-16 2014-11-19 深圳市凯伦圣科技有限公司 一种驾驶行为分析方法及系统
CN105894610A (zh) * 2015-11-11 2016-08-24 乐卡汽车智能科技(北京)有限公司 数据处理方法、装置及系统
CN107784597A (zh) * 2017-09-19 2018-03-09 平安科技(深圳)有限公司 出行方式识别方法、装置、终端设备及存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111680058A (zh) * 2020-04-24 2020-09-18 合肥湛达智能科技有限公司 一种基于嵌入式终端的多目标跟踪及行为分析检测方法
CN111680058B (zh) * 2020-04-24 2023-09-26 合肥湛达智能科技有限公司 一种基于嵌入式终端的多目标跟踪及行为分析检测方法
CN114162142A (zh) * 2021-12-17 2022-03-11 广州小鹏自动驾驶科技有限公司 行驶路径的评分方法、装置、车辆及存储介质
CN114162142B (zh) * 2021-12-17 2024-05-31 广州小鹏自动驾驶科技有限公司 行驶路径的评分方法、装置、车辆及存储介质

Also Published As

Publication number Publication date
CN108986255A (zh) 2018-12-11

Similar Documents

Publication Publication Date Title
WO2020010715A1 (zh) 电子装置、驾驶行为评分方法及存储介质
US11375338B2 (en) Method for smartphone-based accident detection
CN108860162B (zh) 电子装置、基于用户驾驶行为的安全预警方法及存储介质
CN109032103B (zh) 无人驾驶车辆的测试方法、装置、设备及存储介质
US9650052B2 (en) Driving diagnosis method and driving diagnosis apparatus
CN110765807B (zh) 驾驶行为分析、处理方法、装置、设备和存储介质
JP2020530578A (ja) 運転行為の採点方法及び装置
CN106985814A (zh) 用于自动激活自主驻车的系统和方法
KR20220047732A (ko) 차량 감시 방법 및 장치, 전자 기기, 저장 매체 및 컴퓨터 프로그램, 클라우드 제어 플랫폼 및 차량 도로 협조 시스템
US11106969B2 (en) Method and apparatus for driver identification leveraging telematics data
US10679434B2 (en) Device diagnostic apparatus, device diagnostic system and device diagnostic methods
WO2020107894A1 (zh) 一种驾驶行为评分方法、装置及计算机可读存储介质
CN108520571B (zh) 利用加速度计判断车辆行驶状态的算法和装置
EP3272612B1 (en) Method and system for vehicle speed profile generation
CN113095125B (zh) 基于场景连续性来诊断感知系统
CN112330964B (zh) 路况信息监测方法和装置
CN113460062A (zh) 驾驶行为分析系统
CN108286973B (zh) 一种行驶数据校验方法及装置、及混合导航系统
EP3382570A1 (en) Method for characterizing driving events of a vehicle based on an accelerometer sensor
CN114943956A (zh) 多场景下的驾驶分心识别方法、系统及车辆
CN111860512B (zh) 一种车辆识别方法、装置、电子设备及计算机可读存储介质
CN113192340B (zh) 高速公路施工车辆的识别方法、装置、设备及存储介质
CN109146694B (zh) 电子装置、用户车险优惠级别确定方法及存储介质
WO2020010712A1 (zh) 电子装置、用户骗保风险预警方法及存储介质
CN112533208A (zh) 模型训练方法、虚假终端识别方法和装置、电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18926235

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18926235

Country of ref document: EP

Kind code of ref document: A1