CN110648075A - Driving safety assessment method and device - Google Patents
Driving safety assessment method and deviceDownload PDFInfo
- Publication number
- CN110648075A CN110648075ACN201910923281.0ACN201910923281ACN110648075ACN 110648075 ACN110648075 ACN 110648075ACN 201910923281 ACN201910923281 ACN 201910923281ACN 110648075 ACN110648075 ACN 110648075A
- Authority
- CN
- China
- Prior art keywords
- driving
- driver
- information
- data
- violation
- 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.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本申请涉及安全评估领域，具体而言，涉及一种驾驶安全评估方法及装置。The present application relates to the field of safety assessment, and in particular, to a driving safety assessment method and device.
背景技术Background technique
在交通行业，驾驶员的驾驶安全管理是极其重要的一环。安全管理的核心就是找出容易出问题的极小一部分驾驶员，以便采取对应的措施。In the transportation industry, driving safety management of drivers is an extremely important part. The core of safety management is to identify the very small number of drivers who are prone to problems, so that corresponding measures can be taken.
现有技术中，存在多种对驾驶员的行为进行判断的方法。例如，判断驾驶员的心理测评的各项指标是否符合对应的要求。或者根据驾驶员的生理状况来判断其各项生理指标是否满足对应的要求。再或者根据驾驶员的各项驾驶技能的指标来判断驾驶员的驾驶安全性。In the prior art, there are many methods for judging the driver's behavior. For example, it is determined whether each index of the driver's psychological evaluation meets the corresponding requirements. Or according to the physiological condition of the driver, it is judged whether various physiological indicators of the driver meet the corresponding requirements. Furthermore, the driving safety of the driver is judged according to the indicators of various driving skills of the driver.
现有技术中的这些判断方法，只是根据驾驶员的心理、生理、驾驶技能的各项指标独立来判断驾驶员的驾驶安全性，这种方式中，并未考虑到不同指标之间的关联性对驾驶员驾驶行为安全性的影响，因此，现有技术对驾驶安全性的判断结果并不够准确，这样就不能准确地了解驾驶员的状况。These judging methods in the prior art only judge the driving safety of the driver independently according to various indicators of the driver's psychology, physiology and driving skills. In this method, the correlation between different indicators is not considered. Influence on the safety of the driver's driving behavior, therefore, the judgment result of the driving safety in the prior art is not accurate enough, so that the driver's condition cannot be accurately understood.
发明内容SUMMARY OF THE INVENTION
为了至少克服现有技术中的上述不足，本申请的目的之一在于提供一种驾驶安全评估方法，所述方法包括：In order to at least overcome the above-mentioned deficiencies in the prior art, one of the purposes of the present application is to provide a driving safety assessment method, the method comprising:
获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据，所述基础信息包括心理数据、生理数据和驾驶技能数据，所述心理数据是表征驾驶员心理状态的信息，所述生理数据是表征驾驶员的生理健康状态的信息，所述驾驶技能数据包括所述驾驶员获取驾照的时间、驾龄、是否定期审核驾照、学历、年龄；所述安全驾驶记录数据是用于表征所述驾驶员是否安全驾驶的信息，所述驾驶违章及事故数据是用于表征所述驾驶员发生的安全事故的信息；Obtain the basic information of the driver to be evaluated, safe driving record data and driving violation and accident data, the basic information includes psychological data, physiological data and driving skill data, the psychological data is the information representing the driver's psychological state, the Physiological data is information that characterizes the driver's physiological health status, and the driving skill data includes the time when the driver obtained a driver's license, driving experience, whether the driver's license is regularly reviewed, education, and age; the safe driving record data is used to characterize all The information on whether the driver is safe to drive, and the driving violation and accident data is the information used to characterize the safety accident occurred by the driver;
将所述基础信息、所述安全驾驶记录数据和所述驾驶违章及事故数据，或者将所述基础信息和所述安全驾驶记录数据输入预先训练好的驾驶安全评估模型，以对所述待评估驾驶员进行画像；Input the basic information, the safe driving record data and the driving violation and accident data, or input the basic information and the safe driving record data into a pre-trained driving safety evaluation model to evaluate the to-be-evaluated portrait of the driver;
根据所述待评估驾驶员的画像获得所述待评估驾驶员的驾驶安全等级，所述驾驶安全等级为驾驶员驾驶的安全程度；Obtaining the driving safety level of the to-be-evaluated driver according to the portrait of the to-be-evaluated driver, where the driving safety level is the safety level of the driver's driving;
根据所述驾驶安全等级进行报警。The alarm is issued according to the driving safety level.
可选地，在所述获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据的步骤前，所述方法还包括：Optionally, before the step of acquiring the basic information of the driver to be evaluated, the safe driving record data and the driving violation and accident data, the method further includes:
获取包括多个训练样本的训练样本集，所述训练样本包括驾驶员的基础信息、安全驾驶记录数据、驾驶违章及事故数据和用于表征驾驶的安全程度的标签；acquiring a training sample set including a plurality of training samples, the training samples including the basic information of the driver, safe driving record data, driving violation and accident data, and labels used to characterize the safety degree of driving;
将所述训练样本集输入预先配置好的初始训练模型进行模型训练；Inputting the training sample set into a preconfigured initial training model for model training;
获得驾驶安全评估模型。Get a driving safety assessment model.
所述将所述多个训练样本输入预先训练好的初始训练模型进行模型训练的步骤中，对初始训练模型进行训练的方法为分类聚类或相关性分析法，所述分类聚类或相关性分析法包括神经网络算法、Aprori算法、FP-growth算法、K-means算法中的至少一种。In the step of inputting the plurality of training samples into the pre-trained initial training model for model training, the method for training the initial training model is classification clustering or correlation analysis method. The analysis method includes at least one of neural network algorithm, Aprori algorithm, FP-growth algorithm and K-means algorithm.
可选地，所述方法还包括：Optionally, the method further includes:
获取所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据；Obtain the new basic information, new safe driving record data and new driving violation and accident data or new driver's basic information, safe driving record data and driving violation and accident data corresponding to the training sample;
根据所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据更新所述训练样本集；According to the corresponding driver's new basic information, new safe driving record data and new driving violation and accident data or new driver's basic information, safe driving record data and driving violation and accident data, update the training sample training sample set;
根据更新后的训练样本集调整所述驾驶安全评估模型。The driving safety evaluation model is adjusted according to the updated training sample set.
可选地，所述心理数据包括心理疾病测评量表和心理测评报告，所述心理疾病测评量表包括抑郁症测评量表或者暴躁症测评量表；Optionally, the psychological data includes a psychological disease assessment scale and a psychological assessment report, and the psychological disease assessment scale includes a depression assessment scale or an irritable disorder assessment scale;
所述生理数据包括所述驾驶员的历史患病信息、体检信息、反应速度和实时生理信息，所述实时生理信息包括脉搏、血糖、心率、血压和酒精测试结果；The physiological data includes the driver's historical disease information, physical examination information, reaction speed and real-time physiological information, where the real-time physiological information includes pulse, blood sugar, heart rate, blood pressure and alcohol test results;
所述安全驾驶记录数据包括超速信息、驾驶信息、行为信息、车辆状态信息；The safe driving record data includes speeding information, driving information, behavior information, and vehicle status information;
所述超速信息包括历史超速次数和每次超速的严重程度；The speeding information includes the historical speeding times and the severity of each speeding;
所述驾驶信息包括急刹车信息、急加速信息、急转向信息和开门滑行信息、闯红灯信息、不避让行人信息；The driving information includes sudden braking information, sudden acceleration information, sudden turning information, sliding door opening information, red light running information, and pedestrian not avoiding information;
所述行为信息包括疲劳驾驶信息、打手机信息、双眼长时间不目视前方信息、双手脱离方向盘信息、不保持安全车距信息和停靠站点距离信息。The behavior information includes information on fatigued driving, information on cell phone use, information on not looking ahead with both eyes for a long time, information on hands off the steering wheel, information on not maintaining a safe vehicle distance, and information on stopping site distance.
可选地，所述获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据的具体步骤包括：Optionally, the specific steps of obtaining the basic information of the driver to be evaluated, the safe driving record data and the driving violation and accident data include:
从第三方平台获取心理疾病测评量表、心理测评报告、历史患病信息和体检信息；Obtain mental illness assessment scales, psychological assessment reports, historical disease information and physical examination information from third-party platforms;
从智能穿戴设备获取所述待评估驾驶员的实时生理信息；Obtain the real-time physiological information of the driver to be evaluated from the smart wearable device;
从GPS装置中获取所述待评估驾驶员的超速信息；Obtain the speeding information of the driver to be evaluated from the GPS device;
从CAN总线装置获取所述待评估驾驶员的驾驶信息；Obtain the driving information of the driver to be evaluated from the CAN bus device;
从包括ADAS装置和/或DSM装置的智能视频分析设备获取驾驶员的待评估驾驶员的行为信息。The driver's behavior information of the driver to be evaluated is obtained from the intelligent video analysis device including the ADAS device and/or the DSM device.
本申请的另一目的在于提供一种驾驶安全评估装置，所述装置包括：Another object of the present application is to provide a driving safety assessment device, the device comprising:
获取模块，用于获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据，所述基础信息包括心理数据、生理数据和驾驶技能数据，所述心理数据是表征驾驶员心理状态的信息，所述生理数据是表征驾驶员的生理健康状态的信息，所述驾驶技能数据包括所述驾驶员获取驾照的时间、驾龄、是否定期审核驾照、学历、年龄，所述安全驾驶记录数据是用于表征所述驾驶员是否安全驾驶的信息，所述驾驶违章及事故数据是用于表征所述驾驶员发生的安全事故的信息；The acquisition module is used to acquire the basic information of the driver to be evaluated, safe driving record data and driving violation and accident data, the basic information includes psychological data, physiological data and driving skill data, the psychological data is to represent the psychological state of the driver The physiological data is the information that characterizes the physiological health status of the driver, the driving skill data includes the time when the driver obtained the driver's license, driving experience, whether the driver's license is regularly reviewed, education, age, and the safe driving record data is the information used to characterize whether the driver is driving safely, and the driving violation and accident data is the information used to characterize the safety accident occurred by the driver;
输入模块，用于将所述基础信息、所述安全驾驶记录数据和所述驾驶违章及事故数据，或者将所述基础信息和所述安全驾驶记录数据输入预先训练好的驾驶安全评估模型，以对所述待评估驾驶员进行画像；The input module is used to input the basic information, the safe driving record data and the driving violation and accident data, or input the basic information and the safe driving record data into a pre-trained driving safety evaluation model, so as to Make a portrait of the driver to be evaluated;
评估模块，用于根据所述待评估驾驶员的画像获得所述待评估驾驶员的驾驶安全等级，所述驾驶安全等级为驾驶员驾驶的安全程度；An evaluation module, configured to obtain the driving safety level of the driver to be evaluated according to the portrait of the driver to be evaluated, and the driving safety level is the safety level of the driver's driving;
报警模块，用于根据所述驾驶安全等级进行报警。The alarm module is used for alarming according to the driving safety level.
可选地，所述装置还包括训练模块，在获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据的步骤前，所述训练模块具体用于：Optionally, the device further includes a training module, which is specifically used for:
获取包括多个训练样本的训练样本集，所述训练样本包括驾驶员的基础信息、安全驾驶记录数据、驾驶违章及事故数据和用于表征驾驶的安全程度的标签；acquiring a training sample set including a plurality of training samples, the training samples including the basic information of the driver, safe driving record data, driving violation and accident data, and labels used to characterize the safety degree of driving;
将所述训练样本集输入预先配置好的初始训练模型进行模型训练；Inputting the training sample set into a preconfigured initial training model for model training;
获得驾驶安全评估模型。Get a driving safety assessment model.
所述将所述多个训练样本输入预先训练好的初始训练模型进行模型训练的步骤中，对初始训练模型进行训练的方法为分类聚类或相关性分析法，所述分类聚类或相关性分析法包括神经网络算法、Aprori算法、FP-growth算法、K-means算法中的至少一种算法。In the step of inputting the plurality of training samples into the pre-trained initial training model for model training, the method for training the initial training model is classification clustering or correlation analysis method. The analysis method includes at least one of the neural network algorithm, the Aprori algorithm, the FP-growth algorithm, and the K-means algorithm.
可选地，所述装置还包括调整模块，用于获取所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据；Optionally, the device further includes an adjustment module for acquiring new basic information of the driver corresponding to the training sample, new safe driving record data and new driving violation and accident data or new basic information of the driver. , safe driving record data and driving violation and accident data;
根据所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据更新所述训练样本集；According to the corresponding driver's new basic information, new safe driving record data and new driving violation and accident data or new driver's basic information, safe driving record data and driving violation and accident data, update the training sample training sample set;
根据更新后的训练样本集调整所述驾驶安全评估模型。The driving safety evaluation model is adjusted according to the updated training sample set.
相对于现有技术而言，本申请具有以下有益效果：Compared with the prior art, the present application has the following beneficial effects:
本申请中，将待评估驾驶员的基础信息、所述安全驾驶记录数据和所述驾驶违章及事故数据，或者将所述基础信息和所述安全驾驶记录数据同时输入驾驶安全评估模型以对待评估驾驶员进行画像，从而获得待评估驾驶员的驾驶安全等级。该驾驶安全评估模型可以综合驾驶员的心理、生理和驾驶技能数据、安全驾驶记录数据、驾驶违章及事故数据等多方面的数据来同时对驾驶员的驾驶安全性进行评估，因此，其评判结果更加准确。根据该评判结果进行报警，能够及时将发现驾驶危险性高的驾驶员，减少事故发生。In this application, the basic information of the driver to be evaluated, the safe driving record data and the driving violation and accident data, or the basic information and the safe driving record data are simultaneously input into the driving safety evaluation model to be evaluated The driver is profiled to obtain the driving safety level of the driver to be evaluated. The driving safety evaluation model can simultaneously evaluate the driving safety of the driver by integrating the data of the driver's psychology, physiology and driving skills, safe driving record data, driving violation and accident data. more precise. According to the judgment result, an alarm is issued, and the driver with high driving risk can be found in time, thereby reducing the occurrence of accidents.
附图说明Description of drawings
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本申请的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。In order to illustrate the technical solutions of the embodiments of the present application more clearly, the following drawings will briefly introduce the drawings that need to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore do not It should be regarded as a limitation of the scope, and for those of ordinary skill in the art, other related drawings can also be obtained according to these drawings without any creative effort.
图1是本申请实施例提供的驾驶安全评估设备的结构示意框图；1 is a schematic structural block diagram of a driving safety assessment device provided by an embodiment of the present application;
图2是本申请实施例提供的驾驶安全评估方法的流程示意图一；FIG. 2 is a schematic flowchart 1 of a driving safety assessment method provided by an embodiment of the present application;
图3是本申请实施例提供的驾驶安全评估方法的流程示意图二；3 is a second schematic flowchart of a driving safety assessment method provided by an embodiment of the present application;
图4是本申请实施例提供的驾驶安全评估装置的结构示意框图。FIG. 4 is a schematic block diagram of the structure of a driving safety assessment device provided by an embodiment of the present application.
图标：100-驾驶安全评估设备；110-驾驶安全评估装置；111-获取模块；112-输入模块；113-评估模块；114-报警模块；115-训练模块；116-调整模块；120-存储器；130-处理器。Icons: 100-driving safety evaluation equipment; 110-driving safety evaluation device; 111-acquisition module; 112-input module; 113-evaluation module; 114-alarm module; 115-training module; 116-adjustment module; 120-memory; 130 - Processor.
具体实施方式Detailed ways
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. The components of the embodiments of the present application generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.
因此，以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围，而是仅仅表示本申请的选定实施例。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。Thus, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the application as claimed, but is merely representative of selected embodiments of the application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.
在本申请的描述中，还需要说明的是，除非另有明确的规定和限定，术语“设置”、“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本申请中的具体含义。In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "arrangement", "installation", "connection" and "connection" should be interpreted in a broad sense, for example, it may be a fixed connection, It can also be a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or the internal communication between the two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood in specific situations.
在交通行业，驾驶员的驾驶行为安全管理是极其重要的一环。安全管理的核心就是及时发现容易出问题的5％的驾驶员，从而便于进行针对性的教育、处置或者转岗等后续动作。对于一个驾驶员而言，其驾驶安全行为会受到多种因素的影响，例如心理因素、生理因素和年龄、驾龄以及安全驾驶的记录等。In the transportation industry, the safety management of driver's driving behavior is an extremely important part. The core of safety management is to identify 5% of drivers who are prone to problems in time, so as to facilitate follow-up actions such as targeted education, disposal or job transfer. For a driver, his driving safety behavior will be affected by many factors, such as psychological factors, physiological factors and age, driving experience and record of safe driving.
现有技术中，在判断驾驶员的驾驶行为安全性时，一般是单独地获取心理、生理或者驾驶技能数据等方面中的一种数据，然后由单独的安全管理系统根据获取的数据进行判断，甚至给出报警等。例如，对于GPS超速，会根据路段限速值给出一般、严重超速等界定，从而采取相应的措施。发明人经过研究发现，在判断驾驶员的驾驶安全性时，驾驶员的心理因素、生理因素和驾驶技能因素之间会相互影响，现有技术中的这种方案，只是简单地将各类数据分开来进行判断，判断结果并不够准确。In the prior art, when judging the safety of the driver's driving behavior, one type of data in psychological, physiological or driving skill data is generally obtained separately, and then a separate safety management system judges according to the obtained data. Even give an alarm etc. For example, for GPS speeding, the general and serious speeding will be defined according to the speed limit value of the road section, and corresponding measures will be taken. Through research, the inventor found that when judging the driving safety of the driver, the driver's psychological factors, physiological factors and driving skill factors will affect each other. This solution in the prior art simply combines various data Separate judgments are made, and the judgment results are not accurate enough.
请参见图1，所述驾驶安全评估设备100包括驾驶安全评估装置110、存储器120和处理器130，存储器120和处理器130相互之间直接或间接电性连接，用于实现数据交互。例如，这些元件相互之间可通过一条或多条通讯总线或信号线实现电性连接。所述驾驶安全评估装置110包括至少一个可以软件或固件(firmware)的形式存储于所述存储器120中或固化在所述驾驶安全评估设备100的操作系统(operating system，OS)中的软件功能模块。所述处理器130用于执行所述存储器120中存储的可执行模块，例如所述驾驶安全评估装置110所包括的软件功能模块及计算机程序等。Referring to FIG. 1 , the driving
请参见图2，图2是可应用于上述驾驶安全评估设备100的驾驶安全评估方法的流程示意图，所述方法包括步骤S110-步骤S140。以下对各个步骤进行详细阐述。Please refer to FIG. 2 . FIG. 2 is a schematic flowchart of a driving safety assessment method applicable to the above driving
步骤S110，获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据，所述基础信息包括心理数据、生理数据和驾驶技能数据，所述心理数据是表征驾驶员心理状态的信息，所述生理数据是表征驾驶员生理健康状态的信息，所述安全驾驶记录数据是用于表征所述驾驶员是否安全驾驶的信息，所述驾驶违章及事故数据是用于表征所述驾驶员发生的安全事故的信息。Step S110, obtain the basic information of the driver to be evaluated, safe driving record data and driving violation and accident data, the basic information includes psychological data, physiological data and driving skill data, and the psychological data is the information representing the driver's psychological state , the physiological data is the information that characterizes the driver's physiological health state, the safe driving record data is the information used to characterize whether the driver is driving safely, the driving violation and accident data is used to characterize the driver Information about security incidents that occurred.
可选地，本实施例中，所述心理数据包括心理疾病测评量表和心理测评报告，心理疾病测评量表是用于记录驾驶员是否患有心理疾病的表，所述心理疾病测评量表可以包括抑郁症测评量表或者暴躁症测评量表，心理疾病测评量表中，也可以包括失眠、焦虑和抑郁症这三项疾病的数据记录，心理测评报告是对脑部功能区活跃度、脑电波等心理测评方法测评结果的数据记录表；所述生理数据包括所述驾驶员的历史患病信息、体检信息、反应速度和实时生理信息，历史患病信息是记录驾驶员历史患病状态的信息，历史患病信息可以是电子病历，在具体获取时，可以由人工输入，也可以从第三方平台，例如医院等获取。体检信息是记录驾驶员体检结果的信息，例如，可以包括驾驶员体检的血压大小、血脂浓度、血糖浓度等各项指标，体检信息可以由人工输入，也可以从第三方平台，例如医院等获取。所述实时生理信息包括脉搏、心率、血糖、血压和酒精测试结果，实时生理信息可以由能够采集脉搏、血糖心率、血压和酒精测试结果的设备采集，例如驾驶员所佩戴的智能穿戴设备，所述智能穿戴设备可以是健康手环。Optionally, in this embodiment, the psychological data includes a psychological disease assessment scale and a psychological assessment report, and the psychological disease assessment scale is a table used to record whether the driver suffers from a psychological disease, and the psychological disease assessment scale is used. It can include the Depression Assessment Scale or the Irritable Disorder Assessment Scale, and the Mental Illness Assessment Scale, as well as the data records of the three diseases of insomnia, anxiety and depression. A data record table for the evaluation results of psychological evaluation methods such as brain waves; the physiological data includes the driver's historical disease information, physical examination information, reaction speed and real-time physiological information, and the historical disease information is a record of the driver's historical disease state The historical disease information can be an electronic medical record, which can be manually input or obtained from a third-party platform, such as a hospital. The physical examination information is the information that records the results of the driver's physical examination. For example, it can include various indicators such as blood pressure, blood lipid concentration, and blood glucose concentration of the driver's physical examination. The physical examination information can be manually input or obtained from third-party platforms, such as hospitals, etc. . The real-time physiological information includes pulse, heart rate, blood sugar, blood pressure and alcohol test results, and the real-time physiological information can be collected by a device capable of collecting pulse, blood sugar heart rate, blood pressure and alcohol test results, such as a smart wearable device worn by a driver. The smart wearable device can be a health bracelet.
所述驾驶技能数据包括所述驾驶员获取驾照的时间、驾龄、是否定期审核驾照、学历、年龄；所述安全驾驶记录数据包括超速信息、驾驶信息、行为信息、车辆状态信息。The driving skill data includes the time when the driver obtained the driver's license, driving experience, whether the driver's license is regularly reviewed, education, and age; the safe driving record data includes speeding information, driving information, behavior information, and vehicle status information.
所述超速信息用于表征与驾驶员超速相关的信息，所述超速信息包括历史超速次数和每次超速的严重程度；所述超速信息中还可以包括当前车辆所处路段的限速值、当前速度和超速的比例。超速的严重程度可以为实际驾驶速度超出限速值的比例，比例越高超速越严重。所述驾驶信息包括急刹车信息、急加速信息、急转向信息、开门滑行信息、开门滑行信息、闯红灯信息和不避让行人信息，急刹车信息是用于表征驾驶员是否存在急刹车的行为的信息，也就是驾驶员刹车过程中，车辆速度的变化率是否超过第一预设变化率。急加速信息是用于表征驾驶员是否存在急加速的信息，也就是驾驶员加速过程中，车辆速度的变化率是否超过第二预设变化率。急转向信息是用于表征驾驶员是否存在急转向的信息，也就是驾驶员转向过程中，车辆转向角度的变化率是否超过第三预设变化率。开门滑行信息也就是表征驾驶员在滑行过程中是否开车门的信息。闯红灯信息是表征驾驶员是否存在闯红灯和/或闯红灯的次数等信息。不避让行人信息是表征驾驶员是否存在不避让行人和/或不避让行人的次数等信息。当然，本实施例中，所述驾驶信息还可以包括所述驾驶信息包括油门的开度、刹车的开度、转向的角度。所述行为信息包括疲劳驾驶信息、打手机信息、双眼长时间不目视前方信息、双手脱离方向盘信息、不保持安全车距信息和停靠站点距离信息。其中，所述疲劳驾驶信息可以包括表征所述驾驶员是否打哈欠的数据、表征所述驾驶员的眼睛闭合程度的数据、所述驾驶员是否说话的数据、所述驾驶员是否脱离方向盘的数据中的至少一项。打手机信息包括表征驾驶员是否打手机。双眼长时间不目视前方信息用于表征驾驶员是否在预设时间长度内未目视前方。双手脱离方向盘信息用于表征驾驶员是否双手脱离方向盘。不保持安全车距信息用于表征驾驶员与前车距离是否小于安全车距。停靠站点距离信息用于表征驾驶员停车时是否距离站点超过预设距离。本实施例中，所述安全驾驶记录数据还可以包括所述车辆状态信息，所述车辆状态信息包括车道偏离信息、碰撞信息以及路况信息，车道偏离信息为车辆偏离车道或者车道边线方向的信息，碰撞信息是车辆是否与其他物体发生碰撞的信息。路况信息是指道路上的车辆密度等信息。The speeding information is used to represent the information related to the speeding of the driver, and the speeding information includes the number of times of speeding in history and the severity of each speeding; The ratio of speed to overspeed. The severity of the speeding can be the ratio of the actual driving speed exceeding the speed limit value, and the higher the ratio, the more serious the speeding. The driving information includes sudden braking information, sudden acceleration information, sudden turning information, door sliding information, door sliding information, red light running information, and information about not giving way to pedestrians. , that is, whether the rate of change of the vehicle speed exceeds the first preset rate of change during the braking process of the driver. The rapid acceleration information is information used to represent whether the driver has rapid acceleration, that is, whether the rate of change of the vehicle speed exceeds the second preset rate of change during the driver's acceleration process. The sharp steering information is information used to represent whether the driver has a sharp steering, that is, whether the rate of change of the steering angle of the vehicle exceeds the third preset rate of change during the driver's steering process. The sliding information with the door open is also the information representing whether the driver opens the door during sliding. The red light running information is information indicating whether the driver has run a red light and/or the number of times of running a red light. The non-avoidance pedestrian information is information indicating whether the driver has non-avoidance pedestrians and/or the number of times of non-avoidance pedestrians. Of course, in this embodiment, the driving information may further include that the driving information includes the opening degree of the accelerator, the opening degree of the brake, and the steering angle. The behavior information includes information on fatigued driving, information on cell phone use, information on not looking ahead with both eyes for a long time, information on hands off the steering wheel, information on not maintaining a safe vehicle distance, and information on stopping site distance. The fatigue driving information may include data indicating whether the driver yawns, data indicating the degree of eye closure of the driver, data indicating whether the driver speaks, and data indicating whether the driver is off the steering wheel at least one of. The cell phone information includes characterizing whether the driver is using a cell phone. The information that both eyes do not look ahead for a long time is used to represent whether the driver does not look ahead for a preset period of time. The hands off steering wheel information is used to represent whether the driver's hands off the steering wheel. The information about not keeping the safe distance is used to represent whether the distance between the driver and the vehicle in front is less than the safe distance. The parking site distance information is used to represent whether the driver is more than a preset distance from the stop when parking. In this embodiment, the safe driving record data may further include the vehicle status information, the vehicle status information includes lane departure information, collision information, and road condition information, and the lane departure information is the information that the vehicle deviates from the lane or the direction of the lane edge, The collision information is information on whether the vehicle collides with other objects. The road condition information refers to information such as vehicle density on the road.
本实施例中，所述当前生理数据还可以包括所述驾驶员的酒精测试结果，该酒精测试结果可以由酒精测试仪测量获得。In this embodiment, the current physiological data may further include an alcohol test result of the driver, and the alcohol test result may be measured and obtained by an alcohol tester.
本实施例中，驾驶员的超速信息可以从GPS装置中获取，获取驾驶员的行为信息的步骤可以如下：由车辆内设置的智能视频分析设备来获取驾驶员行为信息，例如，智能视频分析设备可以包括ADAS(Advanced Driving Assistant System，高级驾驶辅助系统)装置和/或DSM(驾驶员监控系统)装置。采集驾驶室内的图像信息，然后由处理器130对该图像信息进行处理从而获得该驾驶员的行为信息，例如，疲劳驾驶信息、打手机信息、双眼不目视前方信息、是否说话信息、双手是否脱离方向盘信息、是否争吵信息等。In this embodiment, the driver's speeding information can be acquired from a GPS device, and the steps of acquiring the driver's behavior information can be as follows: the driver's behavior information is acquired by an intelligent video analysis device set in the vehicle, for example, an intelligent video analysis device ADAS (Advanced Driving Assistant System) devices and/or DSM (Driver Monitoring System) devices may be included. The image information in the cab is collected, and then the image information is processed by the
所述车辆状态信息还可以包括驾驶员所在车辆与前车的距离信息。车辆状态信息可以由车辆上设置的摄像装置采集车辆外的图像信息，然后由处理器130对该图像信息进行处理，从而获得车辆状态信息。摄像装置可以是智能视频分析设备上的摄像装置。The vehicle state information may also include distance information between the driver's vehicle and the preceding vehicle. The vehicle state information may be acquired by a camera device provided on the vehicle to collect image information outside the vehicle, and then processed by the
本实施例中，驾驶员基础信息、安全驾驶记录数据和驾驶违章及事故数据均包括多种信息，既有静态信息(在采集前一段时间已经产生且不变的指标对应的信息，例如基础信息)又有动态信息(与驾驶员驾驶的实时驾驶过程相关的数据，例如，安全驾驶记录数据和驾驶违章及事故数据中的部分数据)，使得用于评估驾驶员驾驶安全性，也就是驾驶安全等级的数据更加完整。In this embodiment, the driver's basic information, safe driving record data, and driving violation and accident data all include a variety of information, including static information (information corresponding to indicators that have been generated and remain unchanged for a period of time before the collection, such as basic information ) and dynamic information (data related to the real-time driving process of the driver, such as safe driving record data and some data in the driving violation and accident data), so that it can be used to evaluate the driver's driving safety, that is, driving safety. Level data is more complete.
可选地，本实施例中，所述获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据的具体步骤包括以下步骤：从第三方平台获取心理疾病测评量表、心理测评报告、历史患病信息和体检信息；从智能穿戴设备获取所述待评估驾驶员的实时生理信息；从GPS装置(Global Positioning System，全球定位系统)中获取所述待评估驾驶员的超速信息；从所述CAN(Controller Area Network，控制器局域网络)总线装置获取所述待评估驾驶员的驾驶信息；从包括ADAS(Advanced Driving Assistant System，高级驾驶辅助系统)装置和/或DSM(驾驶员监控系统)装置的智能视频分析设备获取待评估驾驶员的行为信息；从Adas(Advanced Driving Assistant System，高级驾驶辅助系统)获取车辆状态信息。Optionally, in this embodiment, the specific steps for obtaining the basic information of the driver to be evaluated, the safe driving record data, and the data on driving violations and accidents include the following steps: obtaining a mental illness assessment scale, a psychological assessment from a third-party platform Report, historical disease information and physical examination information; obtain the real-time physiological information of the driver to be evaluated from the smart wearable device; obtain the speeding information of the driver to be evaluated from a GPS device (Global Positioning System, global positioning system); The driving information of the driver to be evaluated is obtained from the CAN (Controller Area Network) bus device; the driving information of the driver to be evaluated is obtained from the device including ADAS (Advanced Driving Assistant System, advanced driving assistance system) device and/or DSM (driver monitoring system) The intelligent video analysis device of the system) device obtains the behavior information of the driver to be evaluated; obtains the vehicle status information from Adas (Advanced Driving Assistant System, advanced driving assistance system).
本实施例中，通过GPS装置、CAN总线装置、DSM装置、Adas装置来获取驾驶员的相关的数据，能够充分利用现有的架构，及时获得待评估驾驶员的部分相关信息。In this embodiment, the GPS device, the CAN bus device, the DSM device, and the Adas device are used to obtain the relevant data of the driver, which can make full use of the existing architecture and obtain part of the relevant information of the driver to be evaluated in time.
步骤S120，向预先训练好的驾驶安全评估模型输入数据。Step S120, input data to the pre-trained driving safety assessment model.
具体地，将所述基础信息、所述安全驾驶记录数据和所述驾驶违章及事故数据，或者将所述基础信息和所述安全驾驶记录数据输入预先训练好的驾驶安全评估模型，以由驾驶安全评估模型对所述待评估驾驶员进行画像。Specifically, the basic information, the safe driving record data and the driving violation and accident data, or the basic information and the safe driving record data are input into a pre-trained driving safety evaluation model, so that the driving The safety assessment model draws a portrait of the driver to be assessed.
步骤S130，根据所述待评估驾驶员的画像获得所述待评估驾驶员的驾驶安全等级。Step S130, obtaining the driving safety level of the driver to be evaluated according to the portrait of the driver to be evaluated.
步骤S140，根据所述驾驶安全等级进行报警。Step S140, alarm according to the driving safety level.
其中，驾驶安全等级表征驾驶员驾驶的安全程度，驾驶安全等级越高，说明驾驶员驾驶安全性越高。Among them, the driving safety level represents the driving safety level of the driver, and the higher the driving safety level, the higher the driving safety of the driver.
本实施例中，可以设置一个安全等级阈值，当驾驶安全等级低于安全等级阈值时，则进行报警。本实施例中，所述驾驶安全等级可以是发生事故的概率，当发生事故的概率越高时，说明驾驶安全等级越低。In this embodiment, a safety level threshold may be set, and when the driving safety level is lower than the safety level threshold, an alarm will be issued. In this embodiment, the driving safety level may be the probability of an accident. When the probability of an accident is higher, it means that the driving safety level is lower.
本实施例中，将驾驶员的基础信息、所述安全驾驶记录数据和所述驾驶违章及事故数据，或者将所述基础信息和所述安全驾驶记录数据输入预先训练好的驾驶安全评估模型，从而能够准确地评估出驾驶员的驾驶安全等级，并定位出潜在的可能发生事故的驾驶员，从而便于针对性地对驾驶员进行管理，进而减少事故的发生。In this embodiment, the basic information of the driver, the safe driving record data and the driving violation and accident data, or the basic information and the safe driving record data are input into a pre-trained driving safety assessment model, Therefore, the driving safety level of the driver can be accurately evaluated, and the potential driver who may have an accident can be located, so as to facilitate the targeted management of the driver, thereby reducing the occurrence of accidents.
请参见图3，可选地，在所述获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据的步骤前，还可以根据已知的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据进行大数据分析训练，以得到驾驶安全评估模型。在进行大数据分析训练时，需要先将已知的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据输入大数据平台，然后由大数据平台通过分类聚类或相关性分析，从而形成驾驶员的违章和事故画像，此画像包含危险驾驶相关的强关联属性，例如，严重超速、脾气暴躁、高血压等，当驾驶员超速严重或者具有暴躁症或者具有高血压时，那么说明该驾驶员很容易出现危险驾驶，也就是说，该驾驶员的驾驶安全等级会相对没有这些属性的驾驶员低。Please refer to FIG. 3 , optionally, before the step of acquiring the basic information of the driver to be evaluated, the safe driving record data and the driving violation and accident data, the basic information of the driver, the safe driving record can also be obtained according to the known basic information of the driver, the safe driving record Data and driving violation and accident data are used for big data analysis training to obtain a driving safety assessment model. When conducting big data analysis and training, it is necessary to first input the known basic information of drivers, safe driving record data, and driving violation and accident data into the big data platform, and then the big data platform conducts classification and clustering or correlation analysis, thereby A profile of the driver's violations and accidents is formed. This profile contains strongly correlated attributes related to dangerous driving, such as severe speeding, grumpy, high blood pressure, etc. When the driver is speeding seriously or has irritability or high blood pressure, it indicates that the A driver is prone to dangerous driving, that is, the driver's driving safety rating will be lower than a driver who does not have these attributes.
具体可以，对初始训练模型进行训练的方法可以是分类聚类或相关性分析法。通过分类聚类或相关性分析获得这些多源数据与危险驾驶行为的统计学意义相关性程度(正相关及负相关)，从而获得驾驶安全等级。分类聚类或相关性分析法可以是决策树、基于规则的分类算法、支持向量机和朴素贝叶斯分类法或者神经网络算法、Aprori算法、FP-growth算法或者K-means算法(k-means clustering algorithm，k均值聚类算法)等中的至少一种算法，其中，神经网络算法可以是C神经网络算法。可以理解的是，本领域技术人员可以根据需要，从各种分类聚类或相关性分析算法中进行选择，以获得更为准确的驾驶安全评估模型。Specifically, the method for training the initial training model may be a classification clustering method or a correlation analysis method. The degree of statistical significance (positive and negative correlation) between these multi-source data and dangerous driving behaviors is obtained through classification clustering or correlation analysis, so as to obtain the driving safety level. The classification clustering or correlation analysis method can be decision tree, rule-based classification algorithm, support vector machine and naive Bayesian classification or neural network algorithm, Aprori algorithm, FP-growth algorithm or K-means algorithm (k-means algorithm). At least one of clustering algorithm, k-means clustering algorithm), etc., wherein the neural network algorithm may be a C neural network algorithm. It can be understood that, those skilled in the art can select from various classification and clustering or correlation analysis algorithms as required to obtain a more accurate driving safety evaluation model.
为帮助理解，以下以神经网络为例来讲解训练驾驶安全评估模型的方法，所述方法还包括步骤S210-步骤S220。To help understanding, the following takes a neural network as an example to explain the method for training a driving safety assessment model, and the method further includes steps S210-S220.
步骤S210，获取包括多个训练样本的训练样本集，所述训练样本包括驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据和用于表征驾驶的安全程度的标签。Step S210, acquiring a training sample set including a plurality of training samples, the training samples including the basic information of the driver, safe driving record data, driving violation and accident data, and labels used to characterize the safety degree of driving.
步骤S220，根据所述训练样本集进行模型训练，获得驾驶安全评估模型。Step S220: Perform model training according to the training sample set to obtain a driving safety assessment model.
具体地，将所述训练样本集输入预先配置好的初始训练模型进行模型训练，获得驾驶安全评估模型。Specifically, the training sample set is input into a preconfigured initial training model for model training to obtain a driving safety evaluation model.
本方案中，先采用多个训练样本训练出驾驶安全评估模型，这样，当需要对驾驶员进行驾驶安全评估时，只需要将待评估驾驶员的基础信息、所述安全驾驶记录数据和所述驾驶违章及事故数据，或者将所述基础信息和所述安全驾驶记录数据输入驾驶安全评估模型，由驾驶安全评估模型对需要评估的驾驶员进行画像从而能够快速地评估出驾驶员的驾驶安全等级。In this solution, a driving safety evaluation model is first trained by using multiple training samples. In this way, when driving safety evaluation of the driver is required, only the basic information of the driver to be evaluated, the safe driving record data and the Driving violation and accident data, or input the basic information and the safe driving record data into the driving safety evaluation model, and the driving safety evaluation model will draw a portrait of the driver to be evaluated, so that the driver's driving safety level can be quickly evaluated .
需要说明的是，本实施例中，训练样本均是来自交通行业，本实施例中，所述驾驶违章及事故数据可以包括较长一段时间内驾驶员不安全驾驶的信息(如企业内部所记录的违规或者事故信息，交警所记录的违章或者交通事故信息等)这些静态数据。训练样本的采集对象可以是整个交通行业的各种驾驶员，也可以是交通行业中的细分行业的驾驶员。交通行业可以包括，但不限于，公交车行业、两客一危行业、货运行业、轨道驾驶行业等细分行业。也就是说，所述驾驶安全评估模型可以是根据某一细分行业的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据训练得来。It should be noted that, in this embodiment, the training samples are all from the transportation industry. In this embodiment, the driving violation and accident data may include information about unsafe driving by the driver for a long period of time (such as the internal records of the enterprise). information on violations or accidents, information on violations or traffic accidents recorded by the traffic police, etc.) these static data. The collection objects of training samples can be various drivers in the entire transportation industry, or can be drivers in sub-sectors in the transportation industry. The transportation industry can include, but is not limited to, the bus industry, the two-passenger and one-hazard industry, the freight industry, the rail driving industry and other sub-industries. That is to say, the driving safety evaluation model may be trained according to the basic information of drivers in a certain sub-sector, safe driving record data, and driving violation and accident data.
例如，驾驶安全评估模型可以是根据公交车行业的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据训练得来，也可以是根据货运行业驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据训练得来，也可以是根据客运行业的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据训练得来，还可以是根据轨道驾驶行业的驾驶员，如地铁、动车的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据训练得来。For example, the driving safety evaluation model can be trained based on the basic information of drivers in the bus industry, safe driving record data, and driving violation and accident data, or it can be based on the basic information of drivers in the freight industry, safe driving record data and Driving violation and accident data training, it can also be based on the basic information of drivers in the passenger transportation industry, safe driving record data and driving violation and accident data, or it can be based on drivers in the rail driving industry, such as subway, The basic information of the driver of the motor car, the safe driving record data and the driving violation and accident data are trained.
当训练样本来自于某一特定行业的驾驶员时，那么获得的驾驶安全评估模型便可以用于评估这一特定行业驾驶员的驾驶安全等级。也就是说，此时，输入驾驶安全评估模型的基础信息、安全驾驶记录数据和驾驶违章及事故数据来自于与训练样本对应的行业的一个驾驶员。例如，当训练样本采自公交车行业的驾驶员，那么待评估驾驶员也属于公交车行业的驾驶员；当训练样本采自两客一危行业的驾驶员，那么待评估驾驶员也属于两客一危行业的驾驶员；当训练样本采自货运行业的驾驶员，那么待评估驾驶员也属于货运行业的驾驶员；当训练样本采自轨道驾驶行业的驾驶员，那么待评估驾驶员也属于轨道驾驶行业的驾驶员。本实施例中，针对特定的细分行业的驾驶员单独训练一个驾驶安全评估模型，从而可以进一步提高对待评估驾驶员的驾驶安全等级的评估准确性，从而更加准确地定位潜在容易出事故的驾驶员。When the training samples come from drivers in a specific industry, the obtained driving safety evaluation model can be used to evaluate the driving safety level of drivers in this specific industry. That is to say, at this time, the basic information, safe driving record data, and driving violation and accident data input to the driving safety evaluation model come from a driver in the industry corresponding to the training sample. For example, when the training samples are collected from drivers in the bus industry, the drivers to be evaluated also belong to the bus industry; when the training samples are collected from drivers in the two-passenger and one-hazard industry, then the drivers to be evaluated also belong to the two industries. Drivers in the passenger-hazard industry; when the training samples are collected from drivers in the freight industry, the drivers to be evaluated are also drivers in the freight industry; when the training samples are collected from drivers in the rail driving industry, the drivers to be evaluated are also Drivers belonging to the rail driving industry. In this embodiment, a driving safety evaluation model is separately trained for drivers in a specific sub-sector, so that the evaluation accuracy of the driving safety level of the driver to be evaluated can be further improved, thereby more accurately locating potentially accident-prone drivers member.
这样在判断待评估驾驶员的驾驶安全等级时，同时输入待评估驾驶员的不安全驾驶的信息(如企业内部所记录的违规或者事故信息，交警所记录的违章或者交通事故信息等)等静态数据，从而能够更加准确地获取待评估驾驶员的驾驶安全性，进一步减少驾驶安全事故。In this way, when judging the driving safety level of the driver to be evaluated, the unsafe driving information of the driver to be evaluated (such as the violation or accident information recorded within the enterprise, the violation or traffic accident information recorded by the traffic police, etc.) Data, so that the driving safety of the driver to be evaluated can be obtained more accurately, and driving safety accidents can be further reduced.
可选地，本实施例中，所述训练样本的还可以包括驾驶员需要改进的驾驶行为、需要调节的生理指标和需要调节的心理指标。Optionally, in this embodiment, the training samples may further include the driving behavior that the driver needs to improve, the physiological index that needs to be adjusted, and the psychological index that needs to be adjusted.
此外，本实施例中，在训练驾驶安全评估模型时，训练样本中，还可以包括驾驶员的驾驶违章及事故数据，所述驾驶违章及事故数据包括交通部门记录的该驾驶员的违规信息和事故信息，也可以包括驾驶员所在单位所记录的该驾驶员的违规信息和事故信息。In addition, in this embodiment, when training the driving safety evaluation model, the training samples may also include the driver's driving violation and accident data, and the driving violation and accident data include the driver's violation information recorded by the traffic department and The accident information may also include the driver's violation information and accident information recorded by the driver's unit.
本实施例中，在训练样本的标签中设置驾驶员需要改进的驾驶行为、需要调节的生理指标和需要调节的心理指标，这样，可以使得驾驶安全评估模型可以根据待评估驾驶员的心理数据、生理数据和驾驶技能数据获得该待评估驾驶员需要改进的驾驶行为、需要调节的生理指标和需要调节的心理指标，具有方便直观的特点。In this embodiment, the driving behavior that the driver needs to improve, the physiological index that needs to be adjusted, and the psychological index that needs to be adjusted are set in the label of the training sample, so that the driving safety evaluation model can be based on the psychological data of the driver to be evaluated, The physiological data and the driving skill data are used to obtain the driving behavior that needs to be improved, the physiological index that needs to be adjusted, and the psychological index that needs to be adjusted, which is convenient and intuitive.
可选地，本实施例中，所述方法还包括，获取所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据；根据所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据更新所述训练样本集；根据更新后的训练样本集调整所述驾驶安全评估模型。Optionally, in this embodiment, the method further includes: acquiring new basic information of the driver corresponding to the training sample, new safe driving record data, new driving violation and accident data or new driver's basic information. information, safe driving record data, and driving violation and accident data; new basic information, new safe driving record data, new driving violation and accident data, or new driver basic information, corresponding to the training sample. The training sample set is updated with safe driving record data and driving violation and accident data; the driving safety evaluation model is adjusted according to the updated training sample set.
本实施例中，可以根据更新后的训练样本集调整驾驶安全评估模型，这样，就可以使驾驶安全评估模型的准确度进一步提高。In this embodiment, the driving safety evaluation model can be adjusted according to the updated training sample set, so that the accuracy of the driving safety evaluation model can be further improved.
请参见图4，本申请提供的驾驶安全评估装置110包括获取模块111、输入模块112和评估模块113。所述驾驶安全评估装置110包括一个可以软件或固件的形式存储于所述存储器120中或固化在所述驾驶安全评估设备100的操作系统(operating system，OS)中的软件功能模块。Referring to FIG. 4 , the driving
其中，获取模块111，用于获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据，所述基础信息包括心理数据、生理数据和驾驶技能数据，所述心理数据是表征驾驶员心理状态的信息，所述生理数据是表征驾驶员的生理健康状态的信息，所述驾驶技能数据包括所述驾驶员获取驾照的时间、驾龄、是否定期审核驾照、学历、年龄；所述安全驾驶记录数据是用于表征所述驾驶员是否安全驾驶的信息，所述驾驶违章及事故数据是用于表征所述驾驶员发生的安全事故的信息。Wherein, the
本实施例中的获取模块111用于执行步骤S110，关于所述获取模块111的具体描述可参照对所述步骤S110的描述。The obtaining
输入模块112，用于将所述基础信息、所述安全驾驶记录数据和所述驾驶违章及事故数据，或者将所述基础信息和所述安全驾驶记录数据输入预先训练好的驾驶安全评估模型，以对所述待评估驾驶员进行画像。The
本实施例中的输入模块112用于执行步骤S120，关于所述输入模块112的具体描述可参照对所述步骤S120的描述。The
评估模块113，用于根据所述待评估驾驶员的画像获得所述待评估驾驶员的驾驶安全等级。The
本实施例中的评估模块113用于执行步骤S130，关于所述评估模块113的具体描述可参照对所述步骤S130的描述。The
报警模块114，用于根据所述驾驶安全等级进行报警。The
可选地，所述装置还包括训练模块115，在获取待评估驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据的步骤前，所述训练模块115具体用于：获取包括多个训练样本的训练样本集，所述训练样本包括驾驶员的基础信息、安全驾驶记录数据、驾驶违章及事故数据和用于表征驾驶的安全程度的标签；将所述训练样本集输入预先训练好的初始训练模型进行模型训练；获得驾驶安全评估模型。Optionally, the device further includes a
可选地，所述装置还包括，调整模块116，具体用于：Optionally, the apparatus further includes an
获取所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据；Obtain the new basic information, new safe driving record data and new driving violation and accident data or new driver's basic information, safe driving record data and driving violation and accident data corresponding to the training sample;
根据所述训练样本对应驾驶员的新的基础信息、新的安全驾驶记录数据和新的驾驶违章及事故数据或新的驾驶员的基础信息、安全驾驶记录数据和驾驶违章及事故数据更新所述训练样本集；According to the corresponding driver's new basic information, new safe driving record data and new driving violation and accident data or new driver's basic information, safe driving record data and driving violation and accident data, update the training sample training sample set;
根据更新后的训练样本集调整所述驾驶安全评估模型。The driving safety evaluation model is adjusted according to the updated training sample set.
以上所述，仅为本申请的各种实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应所述以权利要求的保护范围为准。The above are only various embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, All should be covered within the scope of protection of this application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910923281.0ACN110648075A (en) | 2019-09-27 | 2019-09-27 | Driving safety assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910923281.0ACN110648075A (en) | 2019-09-27 | 2019-09-27 | Driving safety assessment method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110648075Atrue CN110648075A (en) | 2020-01-03 |
Family
ID=68992819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910923281.0APendingCN110648075A (en) | 2019-09-27 | 2019-09-27 | Driving safety assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110648075A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523766A (en)* | 2020-03-27 | 2020-08-11 | 中国平安财产保险股份有限公司 | Driving risk assessment method and device, electronic equipment and readable storage medium |
| CN111914687A (en)* | 2020-07-15 | 2020-11-10 | 深圳民太安智能科技有限公司 | Method for actively identifying accident based on Internet of vehicles |
| CN112348095A (en)* | 2020-11-10 | 2021-02-09 | 易显智能科技有限责任公司 | Method and related device for evaluating safe driving consciousness of driver |
| CN112396913A (en)* | 2020-10-12 | 2021-02-23 | 易显智能科技有限责任公司 | Method and related device for recording and authenticating training duration of motor vehicle driver |
| CN112541676A (en)* | 2020-12-10 | 2021-03-23 | 广州市建筑集团混凝土有限公司 | Driving scheduling method and system in mixing plant, computer equipment and storage medium thereof |
| CN112766658A (en)* | 2020-12-31 | 2021-05-07 | 车主邦（北京）科技有限公司 | Driver information processing method and device |
| CN112890572A (en)* | 2021-02-07 | 2021-06-04 | 广州一盒科技有限公司 | Intelligent control system and method for cooking food materials |
| CN113288148A (en)* | 2021-06-02 | 2021-08-24 | 华南师范大学 | Driving psychological quality classification method |
| CN114154592A (en)* | 2021-12-17 | 2022-03-08 | 江西洪都航空工业集团有限责任公司 | Flight training quality and efficiency evaluation method fusing physiological data and flight parameter data |
| CN114189829A (en)* | 2021-11-02 | 2022-03-15 | 南京中创智元科技有限公司 | Intelligent traffic data processing method based on 5G wireless communication |
| CN114841589A (en)* | 2022-05-17 | 2022-08-02 | 国网浙江省电力有限公司舟山供电公司 | Generation method of safety hazard information code for illegal portraits and safety portraits of electric power members |
| CN114889620A (en)* | 2022-05-25 | 2022-08-12 | 重庆长安汽车股份有限公司 | A big data-based driving behavior safety assessment method |
| CN115104114A (en)* | 2022-05-16 | 2022-09-23 | 广东逸动科技有限公司 | Evaluation method, evaluation device, electronic device, and computer-readable storage medium |
| CN115171457A (en)* | 2022-07-04 | 2022-10-11 | 上海明略信息技术有限公司 | Interactive training and evaluation system for aircraft ground signal command situation |
| CN116485285A (en)* | 2023-06-21 | 2023-07-25 | 太极计算机股份有限公司 | Safe driving evaluation method, device, electronic equipment and storage medium |
| CN116680547A (en)* | 2023-08-03 | 2023-09-01 | 南京智慧交通信息股份有限公司 | Public transport driving safety big data management method and system thereof |
| US11798321B2 (en) | 2020-08-28 | 2023-10-24 | ANI Technologies Private Limited | Driver score determination for vehicle drivers |
| CN117251697A (en)* | 2023-11-17 | 2023-12-19 | 深圳市光速时代科技有限公司 | Comprehensive evaluation management system for safety data of intelligent wearable equipment |
| CN118025193A (en)* | 2024-01-17 | 2024-05-14 | 广州市启宏普浩企业管理服务有限公司 | Driver risk evaluation management method and system |
| CN118364245A (en)* | 2024-06-17 | 2024-07-19 | 广汽埃安新能源汽车股份有限公司 | A driving behavior evaluation method, device, electronic device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509418A (en)* | 2011-10-11 | 2012-06-20 | 东华大学 | Fatigue driving estimation and early-warning method and device of multi-sensor information fusion |
| CN108647708A (en)* | 2018-04-28 | 2018-10-12 | 清华-伯克利深圳学院筹备办公室 | Driver evaluation's method, apparatus, equipment and storage medium |
| CN108860157A (en)* | 2018-07-16 | 2018-11-23 | 深圳市元征科技股份有限公司 | A kind of methods of risk assessment violating the regulations, system, equipment and storage medium |
| CN110120153A (en)* | 2019-05-24 | 2019-08-13 | 广州公交集团第三公共汽车有限公司 | A kind of public transport drives accident risk assessment system and its method |
- 2019
- 2019-09-27CNCN201910923281.0Apatent/CN110648075A/enactivePending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509418A (en)* | 2011-10-11 | 2012-06-20 | 东华大学 | Fatigue driving estimation and early-warning method and device of multi-sensor information fusion |
| CN108647708A (en)* | 2018-04-28 | 2018-10-12 | 清华-伯克利深圳学院筹备办公室 | Driver evaluation's method, apparatus, equipment and storage medium |
| CN108860157A (en)* | 2018-07-16 | 2018-11-23 | 深圳市元征科技股份有限公司 | A kind of methods of risk assessment violating the regulations, system, equipment and storage medium |
| CN110120153A (en)* | 2019-05-24 | 2019-08-13 | 广州公交集团第三公共汽车有限公司 | A kind of public transport drives accident risk assessment system and its method |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523766A (en)* | 2020-03-27 | 2020-08-11 | 中国平安财产保险股份有限公司 | Driving risk assessment method and device, electronic equipment and readable storage medium |
| CN111523766B (en)* | 2020-03-27 | 2020-11-13 | 中国平安财产保险股份有限公司 | Driving risk assessment method and device, electronic equipment and readable storage medium |
| CN111914687A (en)* | 2020-07-15 | 2020-11-10 | 深圳民太安智能科技有限公司 | Method for actively identifying accident based on Internet of vehicles |
| CN111914687B (en)* | 2020-07-15 | 2023-11-17 | 深圳民太安智能科技有限公司 | Method for actively identifying accidents based on Internet of vehicles |
| US11798321B2 (en) | 2020-08-28 | 2023-10-24 | ANI Technologies Private Limited | Driver score determination for vehicle drivers |
| CN112396913A (en)* | 2020-10-12 | 2021-02-23 | 易显智能科技有限责任公司 | Method and related device for recording and authenticating training duration of motor vehicle driver |
| CN112348095A (en)* | 2020-11-10 | 2021-02-09 | 易显智能科技有限责任公司 | Method and related device for evaluating safe driving consciousness of driver |
| CN112541676A (en)* | 2020-12-10 | 2021-03-23 | 广州市建筑集团混凝土有限公司 | Driving scheduling method and system in mixing plant, computer equipment and storage medium thereof |
| CN112766658A (en)* | 2020-12-31 | 2021-05-07 | 车主邦（北京）科技有限公司 | Driver information processing method and device |
| CN112766658B (en)* | 2020-12-31 | 2024-06-07 | 能链物流科技有限公司 | Driver information processing method and device |
| CN112890572A (en)* | 2021-02-07 | 2021-06-04 | 广州一盒科技有限公司 | Intelligent control system and method for cooking food materials |
| CN113288148A (en)* | 2021-06-02 | 2021-08-24 | 华南师范大学 | Driving psychological quality classification method |
| CN113288148B (en)* | 2021-06-02 | 2023-03-07 | 华南师范大学 | Driving psychological quality classification method |
| CN114189829A (en)* | 2021-11-02 | 2022-03-15 | 南京中创智元科技有限公司 | Intelligent traffic data processing method based on 5G wireless communication |
| CN114154592A (en)* | 2021-12-17 | 2022-03-08 | 江西洪都航空工业集团有限责任公司 | Flight training quality and efficiency evaluation method fusing physiological data and flight parameter data |
| CN115104114A (en)* | 2022-05-16 | 2022-09-23 | 广东逸动科技有限公司 | Evaluation method, evaluation device, electronic device, and computer-readable storage medium |
| CN114841589A (en)* | 2022-05-17 | 2022-08-02 | 国网浙江省电力有限公司舟山供电公司 | Generation method of safety hazard information code for illegal portraits and safety portraits of electric power members |
| CN114841589B (en)* | 2022-05-17 | 2022-12-06 | 国网浙江省电力有限公司舟山供电公司 | Potential safety hazard information code generation method for electric power member violation portrait and safety portrait |
| CN114889620A (en)* | 2022-05-25 | 2022-08-12 | 重庆长安汽车股份有限公司 | A big data-based driving behavior safety assessment method |
| CN115171457A (en)* | 2022-07-04 | 2022-10-11 | 上海明略信息技术有限公司 | Interactive training and evaluation system for aircraft ground signal command situation |
| CN116485285A (en)* | 2023-06-21 | 2023-07-25 | 太极计算机股份有限公司 | Safe driving evaluation method, device, electronic equipment and storage medium |
| CN116680547B (en)* | 2023-08-03 | 2023-10-10 | 南京智慧交通信息股份有限公司 | Public transport driving safety big data management method and system thereof |
| CN116680547A (en)* | 2023-08-03 | 2023-09-01 | 南京智慧交通信息股份有限公司 | Public transport driving safety big data management method and system thereof |
| CN117251697A (en)* | 2023-11-17 | 2023-12-19 | 深圳市光速时代科技有限公司 | Comprehensive evaluation management system for safety data of intelligent wearable equipment |
| CN117251697B (en)* | 2023-11-17 | 2024-02-23 | 深圳市光速时代科技有限公司 | Comprehensive evaluation management system for safety data of intelligent wearable equipment |
| CN118025193A (en)* | 2024-01-17 | 2024-05-14 | 广州市启宏普浩企业管理服务有限公司 | Driver risk evaluation management method and system |
| CN118364245A (en)* | 2024-06-17 | 2024-07-19 | 广汽埃安新能源汽车股份有限公司 | A driving behavior evaluation method, device, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110648075A (en) | Driving safety assessment method and device | |
| Markkula et al. | A farewell to brake reaction times? Kinematics-dependent brake response in naturalistic rear-end emergencies | |
| Feng et al. | Can vehicle longitudinal jerk be used to identify aggressive drivers? An examination using naturalistic driving data | |
| Furlan et al. | Advanced vehicle technologies and road safety: A scoping review of the evidence | |
| CN111231969A (en) | A kind of vehicle driving state detection method | |
| JP6449401B1 (en) | Call / inspection support device, call / inspection support system, and call / inspection support program | |
| Macalisang et al. | Drive-awake: A yolov3 machine vision inference approach of eyes closure for drowsy driving detection | |
| Li et al. | Understanding factors associated with misclassification of fatigue-related accidents in police record | |
| CN108312964A (en) | A kind of fatigue driving state identification early warning system and method | |
| CN110901385A (en) | Active speed limiting method based on fatigue state of driver | |
| Kutila et al. | Driver cognitive distraction detection: Feature estimation and implementation | |
| CN111341106B (en) | Traffic early warning method, device and equipment | |
| WO2024015018A1 (en) | Cognitive workload recognition from temporal series information | |
| Li et al. | Vehicle real-time collision risk prediction: A multi-modal learning approach for diverse urban road scenarios based on a large-scale near-crash event dataset | |
| Qin et al. | Prediction of driving stress on high-altitude expressway using driving environment features: A naturalistic driving study in Tibet | |
| WO2019136201A1 (en) | Vehicular artificial intelligence triage of collisions | |
| Alabi et al. | Design and implementation of an alcohol detection driver system | |
| Karkouch et al. | Cads: A connected assistant for driving safe | |
| Ren et al. | Exploring factors affecting the injury severity of highway-rail grade crossing crashes during the COVID-19 pandemic | |
| CN116834748A (en) | Operation assisting method, operation assisting system and server | |
| Pavlova et al. | Automated system for determining speed of cars ahead | |
| Shvets et al. | A Driver Fatigue Recognition System, Based on an Artificial Neural Network | |
| Poliak et al. | Analysis and research plan of commercial truck drivers’ potentially dangerous driving behaviors caused by the changes of Regulation (EC) No. 561/2006 | |
| Vimal et al. | Automated Injury Detection and Alert Systems in Public Transportation Integrating IoT with Convolutional Neural Networks | |
| CN118247773B (en) | Risk driver identification method and system based on different SP driver behaviors |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20200103 |