WO2020147391A1 - 驾驶水平评估方法、装置、计算机设备和存储介质 - Google Patents
驾驶水平评估方法、装置、计算机设备和存储介质 Download PDFInfo
- Publication number
- WO2020147391A1 WO2020147391A1 PCT/CN2019/116981 CN2019116981W WO2020147391A1 WO 2020147391 A1 WO2020147391 A1 WO 2020147391A1 CN 2019116981 W CN2019116981 W CN 2019116981W WO 2020147391 A1 WO2020147391 A1 WO 2020147391A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- driving
- target user
- value
- target
- occurrences
- 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.)
- Ceased
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
Definitions
- This application relates to a driving level evaluation method, device, computer equipment and storage medium.
- a driving level evaluation method for example, a driving level evaluation method, device, computer equipment, and storage medium are provided.
- a driving level assessment method which includes:
- the driving trajectory data analyze the current number of occurrences of various types of target driving behaviors of the target user in each road segment, and obtain the average number of occurrences of various types of target driving behaviors in each road segment;
- the driving score value of the target user is determined according to each driving score sub-value and the length value of each road section, and the driving level of the target user is evaluated according to the driving score value.
- a driving level assessment device which includes:
- the link length obtaining module is used to obtain the driving trajectory data of the target user, and determine each driving section of the target user and the length value of each driving section according to the driving trajectory data;
- the frequency acquisition module is used to analyze the current number of occurrences of various types of target driving behaviors of the target user in each vehicle segment according to the driving trajectory data, and obtain the average number of occurrences of various types of target driving behaviors in each vehicle segment;
- the score acquisition module is used to determine the driving score sub-values of the target user for each driving section according to the current occurrence times and the average occurrence times, and to determine the driving score value of the target user according to the driving score sub-values and the length of each road section;
- the level evaluation module is used to evaluate the driving level of the target user according to the driving score value.
- a computer device includes a memory and one or more processors.
- the memory stores computer-readable instructions.
- the one or more processors are executed The following steps:
- the driving trajectory data analyze the current number of occurrences of various types of target driving behaviors of the target user in each road segment, and obtain the average number of occurrences of various types of target driving behaviors in each road segment;
- the driving score value of the target user is determined according to each driving score sub-value and the length value of each road section, and the driving level of the target user is evaluated according to the driving score value.
- One or more non-volatile computer-readable storage media storing computer-readable instructions.
- the computer-readable instructions When executed by one or more processors, the one or more processors perform the following steps:
- the driving trajectory data analyze the current number of occurrences of various types of target driving behaviors of the target user in each road segment, and obtain the average number of occurrences of various types of target driving behaviors in each road segment;
- the driving score value of the target user is determined according to each driving score sub-value and the length value of each road section, and the driving level of the target user is evaluated according to the driving score value.
- Fig. 1 is an application scenario diagram of a driving level evaluation method according to one or more embodiments.
- Fig. 2 is a schematic flowchart of a driving level assessment method according to one or more embodiments.
- Fig. 3 is a schematic flowchart of a step of determining a driving score sub-value according to one or more embodiments.
- Fig. 4 is a schematic flow chart of the steps of obtaining vehicle trajectory data according to one or more embodiments.
- Fig. 5 is a block diagram of a driving level evaluation device according to one or more embodiments.
- Figure 6 is a block diagram of a computer device in accordance with one or more embodiments.
- the driving level evaluation method provided in this application can be applied to the application environment as shown in FIG. 1.
- the terminal 102 and the server 104 communicate through the network.
- the terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and may also be a vehicle-mounted terminal.
- the server 104 may be implemented as an independent server or a server cluster composed of multiple servers.
- the terminal 102 collects the driving trajectory data of the target user, and sends the collected driving trajectory data to the server 104.
- the server 104 After the server 104 obtains the target user's driving trajectory data, it determines the target user's driving sections and the length value of each driving section according to the driving trajectory data, and analyzes the target user's various types of target driving in each driving section according to the driving trajectory data The current number of occurrences of the behavior, and obtain the average number of occurrences of each type of target driving behavior in each road segment, and determine the driving score sub-values of each road segment of the target user according to the current number of occurrences and the average number of occurrences. The driving score sub-value and the length of each road section determine the driving score value of the target user, and the driving level of the target user is evaluated according to the driving score value. In this way, the accuracy of the obtained driving credit score can be improved.
- a driving level evaluation method is provided.
- the method is applied to the server in FIG. 1 as an example for description, including the following steps:
- Step S202 Obtain the driving trajectory data of the target user, and determine each driving section of the target user and the length value of each driving section according to the driving trajectory data;
- the driving trajectory data may be a collection of GPS points (Global Positioning System, global positioning system).
- the GPS point collection includes GPS point data at multiple times, and the GPS point data may include precision values and latitude values.
- the driving trajectory data may also be other data that characterizes the location of the vehicle currently driven by the user at each moment.
- the server obtains the target user's driving trajectory data collected by the terminal. After obtaining the driving trajectory data, it can determine the target user's driving paths and the driving distances of each driving path according to the driving path data and current road traffic network information.
- the length of the link mainly includes attributes that represent the basic characteristics of the traffic network, such as road sections, section lengths, section speed limits, and road grades.
- Step S204 Analyze the current number of occurrences of each type of target driving behavior of the target user in each vehicle section according to the driving trajectory data, and obtain the average number of appearances of each type of target driving behavior in each vehicle section;
- the target driving behavior may be a bad driving behavior, which may specifically include abrupt braking, abrupt deceleration, abrupt acceleration, and abrupt turn.
- the current number of appearances is for the target user. It is the number of times the target user’s various types of target driving behaviors occur in each road segment.
- the average number of appearances is for each user, which is the number of times each user is in the corresponding vehicle.
- Step S206 Determine the driving score sub-value of each driving section of the target user according to each current number of occurrences and each average number of occurrences;
- Step S208 Determine the driving score value of the target user according to each driving score sub-value and each link length value, and evaluate the driving level of the target user according to the driving score value.
- the driving score value may be equal to the weighted sum value obtained by weighted summation of the driving score sub-values of each driving section of the target user.
- Each weight value in the weighted summation is the difference between the length value of each road section and the length value of each road section. The ratio of the total value.
- the driving trajectory data of the target user is obtained, and each driving section of the target user and the length value of the road section of each driving section are determined according to the driving trajectory data.
- the current number of occurrences of the target driving behavior of the target type and obtain the average number of occurrences of each type of target driving behavior in each road segment, and determine the driving score of each road segment of the target user according to the current number of occurrences and the average number of occurrences Value
- the driving score value of the target user is determined according to each driving score sub-value and each road segment length value
- the driving level of the target user is evaluated according to the driving score value.
- various factors such as the difference in the types of bad driving behaviors, the length values of different driving sections, and the average level of users of different driving sections are combined to improve the accuracy of the driving level evaluation result.
- the driving level evaluated by the embodiment of the present invention can be applied to many aspects. For example, driving assistance, vehicle recommendation, and insurance premium determination. The following examples are applied to three aspects: assisted driving, vehicle recommendation, and premium determination. However, it should be noted that the application of driving level is not limited to this, and the implementation of driving assistance, vehicle recommendation, and premium determination are not limited to the following methods.
- the driving level can be used as the execution condition of driving assistance.
- a driving assistance method includes: determining the driving level of a vehicle driver (target user), judging whether the driving level meets a preset driving assistance execution condition, and if so, executing driving assistance.
- the driving assistance strategy may also be determined according to the driving level.
- a driving assistance method includes: determining the driving level of the vehicle driver according to the driving level of the vehicle driver, and determining a match with the driving level according to the driving level Driving assistance strategies. In this way, the pertinence of driving assistance can be improved, for example, different driving assistance strategies can be provided to vehicle drivers of different driving levels.
- the driving level can be used as the recommendation condition of the vehicle recommendation.
- a vehicle recommendation method includes: obtaining a vehicle recommendation request of a terminal, the vehicle recommendation request carrying current location information of the terminal; and determining a target vehicle according to the current location information, and the target vehicle is the target vehicle.
- a vehicle within a preset range of the terminal acquiring the driving level parameter of the vehicle driver of the target vehicle; determining the vehicle to be recommended in the target vehicle according to the driving level parameter, and recommending the vehicle to be recommended to the terminal, Among them, the driving level parameter of the vehicle driver is determined by the driving level of the vehicle driver.
- This scheme combines driving level parameters and distance parameters for vehicle recommendation, which can make drivers with high driving skills have a greater chance of recommendation, which can help improve traffic safety.
- linking vehicle recommendation with the driving behavior of the driver can enable drivers (for example, taxi drivers) to experience the increase in recommendation rate brought about by the improvement of driving level, thereby helping the driver improve driving behavior and improve the overall quality of driving. Further improve traffic safety.
- the discount rate may be determined according to the driving level.
- a vehicle insurance premium discount parameter method includes: determining the driving level of a vehicle driver (target user), determining the driving level of the vehicle driver according to the driving level, and determining the vehicle according to the driving level
- Driver’s auto insurance premium discount parameter For example, users with higher driving skills can give a higher premium discount parameter.
- the driver’s auto insurance premium discount parameters are linked to the driver’s driving behavior (driving level), so that the driver can experience the reduction in insurance premiums brought about by safe driving, thereby helping the driver improve driving behavior and improve the overall driving quality of the car owner , Improve traffic safety.
- the foregoing determination of the driving score sub-value of each driving section of the target user according to the current number of occurrences and the average number of occurrences can be selected according to needs. Two specific implementation manners are given below, but the manner of obtaining the sub-value of the driving score is not limited to this.
- F is represents the driving score sub-value of the ith driving section of the target user
- F f is the basic score value, which is a preset constant.
- the current number of occurrences of the j-th type N ij represents the target user of the i-th sections of the carriageway
- N aij represents the average number of occurrences of the j-th type of i-th sections of the carriageway
- f 1ij represents a first type of fastening the j-th
- m represents the total number of types
- i 1, 2, 3,..., n
- n represents the total number of traffic sections.
- F is represents the driving score sub-value of the ith driving section of the target user
- F f is the basic score value, which is a preset constant.
- k ij is a coefficient and N aij N ij determined to be the ratio of N ij with N aij
- N ij denotes the j-th type currently present i-th sections of the carriageway target user Number of times
- Naij represents the average number of appearances of the j-th type of the i-th traffic section
- f 2ij represents the second deduction parameter of the j-th type
- j 1, 2, 3,...,m
- the foregoing determination of the driving score sub-values of each driving section of the target user according to the current occurrence times and the average occurrence times may include:
- Step S302 Determine each first scoring parameter value according to the current number of occurrences and the preset behavior type coefficient factor, and each first scoring parameter value is the scoring parameter value of the target user in each driving section;
- Step S304 Determine each second scoring parameter value according to the average number of appearances and the preset behavior type coefficient factor, and each second scoring parameter value is the average scoring parameter value in each road segment;
- P ai represents the second scoring parameter value of the i-th driving section.
- Step S306 Determine the driving score sub-value of each driving section of the target user according to each first scoring parameter value and each second scoring parameter value;
- the coefficient determined by P ai can be the ratio of P i to P ai , and f represents the third deduction parameter.
- a behavior type coefficient factor is set for each target driving behavior, and the influence of the behavior type coefficient factor is taken into account when calculating the driving score value, which can further improve the accuracy of the driving level evaluation result.
- determining the driving score value of the target user based on each driving score sub-value and each link length value may include: summing the length values of each link to obtain the total link length value; according to the length of each link The value and the total link length value determine the weight value of each driving score sub-value; according to each weight value, each driving score sub-value is weighted and summed to obtain the driving score value of the target user.
- F represents the driving score value of the target user
- Bi represents the link length value of the i-th driving link.
- the driving score value of the target user is obtained based on the weighted summation method, and the weight value of the weighted summation is determined according to the length value of each link and the total length of the link. In this way, it is possible to prevent the user from driving with a longer distance. The lower the level of the question, the accuracy of the driving level assessment can be improved.
- the foregoing analysis of the current number of occurrences of various types of target driving behaviors of the target user in each road segment based on the driving trajectory data may include: determining the target user in each road segment based on the driving trajectory data The speed value, speed direction, acceleration value and acceleration direction at the time; according to the speed value, speed direction, acceleration value and acceleration direction at each time in the driving section, as well as the preset various types of judgment thresholds, analyze the target user in each driving The current number of occurrences of various target driving behaviors in the road segment.
- the acceleration value is greater than the first preset judgment threshold and the speed value decreases, if the speed value does not decrease to zero within the preset time period, it is determined that a sudden deceleration has occurred; when the acceleration value is greater than the first preset judgment threshold and When the speed value decreases, if the speed value decreases to zero within the preset time, it is judged that a sudden brake has occurred; when the acceleration value is greater than the first preset judgment threshold and the speed value increases, it is judged that a sudden acceleration has occurred; If the angle change value of the speed direction within the time period is greater than the second preset judgment threshold, or the angle change value of the acceleration direction within the set time period is greater than the second preset judgment threshold, it is judged that a sharp turn has occurred; the target is counted in this way The current number of occurrences of various types of target driving behaviors of the user in each road segment.
- the target driving behavior may also include speeding. Specifically, the speed limit information in each road segment can be acquired, and the number of occurrences of speeding of the target user in each road segment can be determined according to the speed limit information and the speed value at each time in each road segment.
- the target driving behavior may also include making a call while driving. Specifically, the call record information of the target user can be obtained, and the target user is determined to be in each driving section based on the call record information and the driving time period corresponding to the driving trajectory data. Information about the number of calls made while driving and the duration of calls while driving.
- the traditional way of judging bad driving behavior is often based on a single threshold. For example, when the acceleration value determined according to the driving trajectory data is greater than a preset threshold, it is judged as abrupt deceleration or abrupt acceleration, but even if the same is abrupt deceleration or rapid acceleration, deceleration Or the degree of acceleration is different, the risk factor is also different. For example, for the same sudden braking, the acceleration value is greater than 10 m/s, and the acceleration value is greater than 20 m/s, the degree of damage that may be caused is different. Therefore, the sudden braking with the acceleration value greater than 10 m/s is the same as the acceleration value greater than The sudden braking of 20 meters per second is regarded as the same sudden braking, which is less reasonable.
- the driving level assessment method of the present invention may further include: classifying the driving behavior of each type of target according to the classification threshold of each type; and counting the targets of each type and each level according to the result of the classification. The number of occurrences of driving behavior; the current number of occurrences of each type of target driving behavior of the target user is corrected according to the number of occurrences of each type of target driving behavior of each level.
- the aforementioned first preset judgment threshold and the second preset judgment threshold may respectively include multiple different thresholds, and each type of target driving behavior is classified according to these thresholds, and statistics of each type of each type are calculated according to the results of the classification.
- the number of occurrences of target driving behavior for the level The number of levels divided by different types of target driving behaviors can be different.
- q jo represents the number of times adjustment factor of the o-th level of the jth type, and the times adjustment factor can be set according to actual needs. The higher the risk factor, the greater the frequency adjustment factor.
- each type of target driving behavior is subdivided, and the current number of occurrences is corrected based on the result of the grade division, which can facilitate the further improvement of the accuracy of the evaluation result.
- the above-mentioned obtaining the driving trajectory data of the target user may include:
- Step S402 Obtain original driving trajectory data, and obtain driver's facial images in each driving section in the original driving trajectory data;
- the terminal can collect the facial image of the driver in each road section, and send the collected facial image of the driver to the server,
- Step S404 Filter the original driving trajectory data according to the facial image of the driver in each trip and the facial image of the target user to obtain the driving trajectory data of the target user.
- the original driving trajectory data matching the facial image of the driver in each trip and the facial image of the target user is filtered out, and the original driving trajectory data is filtered out as the driving trajectory data of the target user.
- the subsequent driving trajectory data used to evaluate the driving level of the target user are all driving trajectory data of the target user, which is convenient for further improving the accuracy of the evaluation result of the driving level of the target user.
- the above-mentioned evaluating the driving level of the target user based on the driving score value may include: evaluating the driving level of the target user according to the driving score value of the target user and the preset correspondence relationship between the driving score value and the driving level. Driving level.
- the corresponding relationship between the driving score value and the driving level can be found in Table 1, and the sizes of F1, F2, F3 and F4 can be set according to needs.
- the corresponding relationship between the driving score value and the driving level is not limited to the method provided in Table 1.
- FIGS. 2 to 4 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least part of the steps in FIGS. 2 to 4 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. These sub-steps or The execution order of the stages is not necessarily carried out sequentially, but may be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.
- a driving level evaluation device which includes: a link length acquisition module 502, a frequency acquisition module 504, a score acquisition module 506, and a level evaluation module 508, wherein:
- the link length obtaining module 502 is used to obtain the driving trajectory data of the target user, and determine each driving section of the target user and the length value of each driving section according to the driving trajectory data;
- the frequency acquisition module 504 is configured to analyze the current number of occurrences of various types of target driving behaviors of the target user in each vehicle section according to the driving trajectory data, and obtain the average number of appearances of various types of target driving behaviors in each vehicle section;
- the score obtaining module 506 is configured to determine the driving score sub-value of each driving section of the target user according to the current occurrence times and the average occurrence times, and determine the driving score value of the target user according to each driving score sub-value and the length value of each road section;
- the level evaluation module 508 is used to evaluate the driving level of the target user according to the driving score value.
- the score obtaining module 506 may determine each first scoring parameter value according to the current number of occurrences and preset behavior type coefficient factors, and each first scoring parameter value is the target user's value in each driving section. The value of the scoring parameter is determined according to the average number of occurrences and the preset behavior type coefficient factor. Each second scoring parameter value is the average scoring parameter value in each traffic section, according to the first scoring parameter The value and each second score parameter value determine the driving score sub-values of each driving section of the target user.
- the score obtaining module 506 may sum the length values of each road section to obtain the total road section length value, and determine the weight value of each driving score sub-value according to the length value of each road section and the total road section length value. The value performs a weighted summation of each driving score sub-value to obtain the driving score value of the target user.
- the frequency acquisition module 504 can determine the speed value, speed direction, acceleration value, and acceleration direction of the target user at each time in each driving section according to the driving trajectory data, and according to the speed value at each time in the driving section , Speed direction, acceleration value and acceleration direction, as well as preset various types of judgment thresholds, analyze the current number of occurrences of various types of target driving behaviors of target users in each driving section.
- the frequency acquisition module 504 can also be used to classify the target driving behaviors of each type according to the classification thresholds of each type, and count the occurrence of the target driving behaviors of each type and each level according to the classification results. The number of times is to modify the current number of occurrences of each type of target driving behavior of the target user according to the number of occurrences of each type of target driving behavior of each level.
- the link length obtaining module 502 can obtain the original driving trajectory data, and obtain the driver's facial image in each driving section in the original driving trajectory data, according to the driver's facial image in each trip and the target user
- the original driving trajectory data is filtered through the facial image of, and the driving trajectory data of the target user is obtained.
- the level evaluation module 508 may evaluate the driving level of the target user based on the driving score value of the target user and the corresponding relationship between the preset driving score value and the driving level level.
- Each module in the above-mentioned driving level assessment device can be implemented in whole or in part by software, hardware and a combination thereof.
- the above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.
- a computer device is provided.
- the computer device may be a server, and its internal structure diagram may be as shown in FIG. 6.
- the computer equipment includes a processor, a memory, and a network interface connected through a system bus.
- the processor of the computer device is used to provide computing and control capabilities.
- the memory of the computer device includes a non-volatile computer-readable storage medium and internal memory.
- the non-volatile computer-readable storage medium stores an operating system, computer-readable instructions, and a database.
- the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile computer-readable storage medium.
- the network interface of the computer device is used to communicate with external terminals through a network connection.
- the computer-readable instructions are executed by the processor to realize a driving level assessment method.
- FIG. 6 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
- the specific computer device may Including more or less parts than shown in the figure, or combining some parts, or having a different part arrangement.
- a computer device includes a memory and one or more processors.
- the memory stores computer-readable instructions.
- the one or more processors execute the following steps:
- the driving trajectory data analyze the current number of occurrences of various types of target driving behaviors of the target user in each road segment, and obtain the average number of occurrences of various types of target driving behaviors in each road segment;
- the driving score value of the target user is determined according to each driving score sub-value and the length value of each road section, and the driving level of the target user is evaluated according to the driving score value.
- One or more non-volatile computer-readable storage media storing computer-readable instructions.
- the computer-readable instructions When executed by one or more processors, the one or more processors perform the following steps:
- the driving trajectory data analyze the current number of occurrences of various types of target driving behaviors of the target user in each road segment, and obtain the average number of occurrences of various types of target driving behaviors in each road segment;
- the driving score value of the target user is determined according to each driving score sub-value and the length value of each road section, and the driving level of the target user is evaluated according to the driving score value.
- Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
- Volatile memory may include random access memory (RAM) or external cache memory.
- RAM random access memory
- DRAM dynamic RAM
- SDRAM synchronous DRAM
- DDRSDRAM double data rate SDRAM
- ESDRAM enhanced SDRAM
- SLDRAM synchronous chain (Synchlink) DRAM
- RDRAM direct RAM
- DRAM direct memory bus dynamic RAM
- RDRAM memory bus dynamic RAM
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
一种驾驶水平评估方法，包括：获取目标用户的行车轨迹数据，根据所述行车轨迹数据确定所述目标用户的各行车路段以及各所述行车路段的路段长度值；根据所述行车轨迹数据分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数，并获取在各所述行车路段内的各类型的目标开车行为的平均出现次数；根据各所述当前出现次数和各所述平均出现次数确定所述目标用户的各所述行车路段的驾驶分数子值；根据各所述驾驶分数子值以及各所述路段长度值确定所述目标用户的驾驶分数值，根据所述驾驶分数值评估目标用户的驾驶水平。
Description
本申请要求于2019年01月16日提交中国专利局，申请号为2019100402835，申请名称为“驾驶水平评估方法、装置、计算机设备和存储介质”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。
本申请涉及一种驾驶水平评估方法、装置、计算机设备和存储介质。
随着人们生活质量的不断提升，汽车已变成人们主要的代步工具，这就造成汽车的数量不断增加，汽车的增加的同时也使得汽车驾驶人员的人数也不断增多。在驾驶汽车时，每个人往往都会有一些不规范或不良的驾驶习惯，这些不规范的操作在没有人提醒时自己不易察觉，但却会提高发生危险的可能，为此，评估用户的驾驶水平非常有必要。发明人意识到，传统的用户驾驶水平评估方式是基于检测到的不良驾驶行为采用分数扣取的方式进行评估，这种方式得到的驾驶水平评估结果往往准确性较低。
发明内容
根据本申请公开的各种实施例，提供一种驾驶水平评估方法、装置、计算机设备和存储介质。
一种驾驶水平评估方法，该方法包括：
获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值；及
根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，根据驾驶分数值评估目标用户的驾驶水平。
一种驾驶水平评估装置，该装置包括：
路段长度获取模块，用于获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
次数获取模块，用于根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
分数获取模块，用于根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值，根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值；及
水平评估模块，用于根据驾驶分数值评估目标用户的驾驶水平。
一种计算机设备，包括存储器和一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述一个或多个处理器执行以下步骤：
获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值；及
根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，根据驾驶分数值评估目标用户的驾驶水平。
一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，计 算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行以下步骤：
获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值；及
根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，根据驾驶分数值评估目标用户的驾驶水平。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，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它的附图。
图1为根据一个或多个实施例中驾驶水平评估方法的应用场景图。
图2为根据一个或多个实施例中驾驶水平评估方法的流程示意图。
图3为根据一个或多个实施例中驾驶分数子值确定步骤的流程示意图。
图4为根据一个或多个实施例中行车轨迹数据获取步骤的流程示意图。
图5为根据一个或多个实施例中驾驶水平评估装置的框图。
图6为根据一个或多个实施例中计算机设备的框图。
为了使本申请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，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供的驾驶水平评估方法，可以应用于如图1所示的应用环境中。其中，终端102与服务器104通过网络进行通信。终端102可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备，也可以是车载终端。服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。终端102对目标用户的行车轨迹数据进行采集，并将所采集的行车轨迹数据发送给服务器104。服务器104获取到目标用户的行车轨迹数据后，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值，根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数，根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值，根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，根据驾驶分数值评估目标用户的驾驶水平。如此，可以提升所获取到的驾驶信用分数的准确性。
在其中一个实施例，如图2所示，提供了一种驾驶水平评估方法，以该方法应用于图1中的服务器为例进行说明，包括以下步骤：
步骤S202：获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
这里，行车轨迹数据可以是GPS点(Global Positioning System，全球定位系统)集合，GPS点集合中包括多个时刻的GPS点数据，GPS点数据可以包括精度值和纬度值。行车轨迹数据也可以是其他表征当前用户所驾驶的车辆各个时刻所在位置的数据。
具体地，服务器获取终端所采集的目标用户的行车轨迹数据，在获取到该行车轨迹数据后，可以根据该行车轨迹数据以及当前的道路交通网络信息确定目标用户的各行车路段以及各行车路段的路段长度值。其中，道路交通 网络信息主要包括道路路段、路段长度、路段限速和道路等级等表示交通网络基本特征的属性。
步骤S204：根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
这里，目标开车行可以是不良开车行为，具体可以包括急刹车、急减速、急加速和急转弯等等。
这里，当前出现次数是针对目标用户而言的，是目标用户在各行车路段内各类型的目标开车行为的出现次数，平均出现次数是针对各个用户而言的，是各个用户在相应的各行车路段内各类型的目标开车行为的出现次数的平均值。
步骤S206：根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值；
具体地，可以根据第i个行车路段各类型的目标开车行为的当前出现次数和第i个行车路段各类型的目标开车行为的平均出现次数确定目标用户的第i个行车路段的驾驶分数子值，其中，i＝1,2,3,...,n，n表示行车路段的总个数。
步骤S208：根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，根据驾驶分数值评估目标用户的驾驶水平。
其中，驾驶分数值可以等于对目标用户的各行车路段的驾驶分数子值进行加权求和得到的加权求和值，加权求和中的各权值分别为各路段长度值与各路段长度值的总和值的比值。
上述驾驶水平评估方法中，是获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值，根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数，根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值，根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值， 根据驾驶分数值评估目标用户的驾驶水平。本实施例中，综合了不良开车行为的类型的区别，不同行车路段的路段长度值，以及不同行车路段的用户平均水平等各方面的因素，可以提升驾驶水平评估结果的准确性。
本发明实施例评估出的驾驶水平可以应用到诸多方面。例如，驾驶辅助、车辆推荐以及保费确定等方面。以下以分别应用到辅助驾驶、车辆推荐以及保费确定三方面为例进行举例说明。但需要说明的是，驾驶水平的应用不限于此，且驾驶辅助、车辆推荐以及保费确定的实现方式也不限于以下方式。
对于驾驶水平应用到驾驶辅助中，可以将驾驶水平作为驾驶辅助的执行条件。例如，提供一种驾驶辅助方法，该方法包括：确定车辆驾驶员(目标用户)的驾驶水平，判断该驾驶水平是否满足预设的驾驶辅助的执行条件，若是，执行驾驶辅助。也可以是根据驾驶水平确定驾驶辅助策略，具体地，一种驾驶辅助方法，包括：根据车辆驾驶员的驾驶水平确定车辆驾驶员的驾驶水平等级，根据该驾驶水平等级确定与该驾驶水平等级匹配的驾驶辅助策略。如此，可以提高驾驶辅助的针对性，如可以对不同驾驶水平的车辆驾驶人员提供不同的驾驶辅助策略。
对于驾驶水平应用到车辆推荐中，可以将驾驶水平作为车辆推荐的推荐条件。具体地，提供一种车辆推荐方法，该方法包括：获取终端的车辆推荐请求，该车辆推荐请求携带有所述终端的当前位置信息；根据所述当前位置信息确定目标车辆，该目标车辆为所述终端的预设范围内的车辆；获取该目标车辆的车辆驾驶员的驾驶水平参数；根据该驾驶水平参数确定所述目标车辆中的待推荐车辆，向所述终端推荐所述待推荐车辆，其中，车辆驾驶员驾驶水平参数由车辆驾驶员的驾驶水平确定。该方案中结合驾驶水平参数和距离参数进行车辆推荐，可以使得驾驶水平高的驾驶员有更大的推荐几率，可以利于提升交通安全。同时，将车辆推荐与驾驶员的驾驶行为挂钩，能够使驾驶员(例如，出租车司机)体验到驾驶水平提升带来的推荐率的提升，从而帮助驾驶员改善驾驶行为，提升驾车综合素质，进一步提升交通安全。
对于驾驶水平应用到保费确定中，可以是根据驾驶水平确定折扣比例。 具体地，提供一种车险保费折扣参数方法，该方法包括：确定车辆驾驶员(目标用户)的驾驶水平，根据该驾驶水平确定该车辆驾驶员的驾驶水平等级，根据该驾驶水平等级确定该车辆驾驶员的车险保费折扣参数。例如，对于驾驶水平越高的用户可以给一个越高的保费折扣参数。如此，将驾驶员的车险保费折扣参数和驾驶员的驾驶行为(驾驶水平)挂钩，使得驾驶员能够体验到安全驾驶带来的保费的下降，从而帮助驾驶员改善驾驶行为，提升车主驾车综合素质，提升交通安全。
上述的根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值，可以根据需要选择实现方式。以下给出两种具体的实现方式，但驾驶分数子值的获取方式不限于此。
方式一，根据
其中，F
is表示目标用户的第i个行车路段的驾驶分数子值，F
f为基础分数值，为一个预设常数。N
ij表示目标用户的第i个行车路段的第j个类型的当前出现次数，N
aij表示第i个行车路段的第j个类型的平均出现次数，f
1ij表示第j个类型的第一扣分参数，j＝1,2,3,...,m，m表示总类型数，i＝1,2,3,...,n，n表示行车路段的总个数。
方式二。根据
其中，F
is表示目标用户的第i个行车路段的驾驶分数子值，F
f为基础分数值，为一个预设常数。k
ij表示第一调整系数，k
ij是根据N
ij与N
aij确定的系数，可以是N
ij与N
aij的比值，N
ij表示目标用户的第i个行车路段的第j个类型的当前出现次数，N
aij表示第i个行车路段的第j个类型的平均出现次数，f
2ij表示第j个类型的第二扣分参数，j＝1,2,3,...,m，m表示总类型数，i＝1,2,3,...,n，n表示行车路段的总个数。
在其中一个实施例中，如图3所示，上述的根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值，可以包括：
步骤S302：根据各当前出现次数以及预设的行为类型系数因子确定各第一评分参数值，各各第一评分参数值分别为目标用户在各行车路段内的评分参数值；
具体地，可以根据
确定各第一评分参数值，其中，l
j表示第j 个类型的行为类型系数因子，不同的类型的目标驾驶行为的行为类型系数因子可以是不同的，P
i表示目标用户的第i个行车路段的第一评分参数值。
步骤S304：根据根据各平均出现次数以及预设的行为类型系数因子确定各第二评分参数值，各第二评分参数值分别为各行车路段内的平均评分参数值；
具体地，可以根据
确定各第二评分参数值，P
ai表示第i个行车路段的第二评分参数值。
步骤S306：根据各第一评分参数值和各第二评分参数值确定目标用户的各行车路段的驾驶分数子值；
具体地，可以根据F
is＝F
f-k’
i·f·P
i确定目标用户的各行车路段的驾驶分数子值，其中，k’
i表示第二调整系数，k
ij是根据P
i与P
ai确定的系数，可以是P
i与P
ai的比值，f表示第三扣分参数。
本实施例中，对各个目标开车行为分别设置了行为类型系数因子，在计算驾驶分数值考虑了该行为类型系数因子的影响，可便于进一步提升驾驶水平评估结果的准确性。
在其中一个实施例中，上述的根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，可以包括：对各路段长度值进行求和，得到总路段长度值；根据各路段长度值和总路段长度值确定各驾驶分数子值的权重值；根据各权重值对各驾驶分数子值进行加权求和，得到目标用户的驾驶分数值。
具体地，可以根据
其中，F表示目标用户的驾驶分数值，B
i表示第i个行车路段的路段长度值。
本实施例中，基于加权求和的方式得到目标用户的驾驶分数值，且加权求和的权重值根据各路段长度值和总路段长度值确定，如此，可以避免出现用户的行驶距离越长驾驶水平越低的问题，可以提升驾驶水平评估的准确性。
在其中一个实施例中，上述的根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，可以包括：根据行车轨迹数据确定目标用户在各行车路段内的各个时刻的速度值、速度方向、加速度 值和加速度方向；根据行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向，以及预设的各类型的评判阈值，分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数。
具体地，当加速度值大于第一预设评判阈值且速度值减小时，若速度值在预设时长内未减小到零，判定出现一次急减速；当加速度值大于第一预设评判阈值且速度值减小时，若速度值在预设时长内减小到零，判定出现一次为急刹车；当加速度值大于第一预设评判阈值且速度值增加时，判定出现一次急加速；若在设定时长内速度方向的角度改变值大于第二预设评判阈值，或者在设定时长内加速度方向的角度改变值大于第二预设评判阈值，判定为出现一次急转弯；根据这种方式统计目标用户在各行车路段内的各类型的目标开车行为的当前出现次数。
此外，目标开车行为还可以包括超速行驶。具体地，可以获取各行车路段内的限速信息，根据该限速信息以及各行车路段内的各个时刻的速度值确定目标用户在各行车路段内的超速行驶的出现次数。目标开车行为还可以包括开车中打电话，具体地，可以获取目标用户的通话记录信息，根据该通话记录信息以及行车轨迹数据的各个行车路段对应的行车时段，确定目标用户在在各行车路段内的开车中打电话次数以及开车中打电话时长信息。
传统判断不良开车行为的方式往往是基于单一阈值的，例如，在根据行车轨迹数据确定的加速度值大于预设阈值时，判定为急减速或者急加速，但即便同为急减速或者急加速，减速或者加速的程度不同，危险系数也是不同的。例如，同为急刹车，加速度值大于10米/秒，和加速度值大于20米/秒，可能造成的危害程度是不同，因此，将加速度值大于10米/秒的急刹车，和加速度值大于20米/秒的急刹车均作为一次相同的急刹车，合理性较低。
在其中一个实施例中，本发明的驾驶水平评估方法，还可以包括：根据各类型的等级划分阈值分别对各类型的目标开车行为进行等级划分；根据等级划分结果统计各类型的各等级的目标开车行为的出现次数；根据该各类型的各等级的目标开车行为的出现次数修正目标用户的各类型的目标开车行为 的当前出现次数。
例如，上述的第一预设评判阈值和第二预设评判阈值可以分别包括多个不同的阈值，根据这些阈值分别对各类型的目标开车行为进行等级划分，根据等级划分结果统计各类型的各等级的目标开车行为的出现次数。不同类型的目标开车行为所划分出的等级的个数可以是不同的。
具体地，可以根据
表示目标用户的第i个行车路段的第j个类型的第o个等级的出现次数，q
jo表示第j个类型的第o个等级的次数调整因子，次数调整因子可以根据实际需要设定，危险系数越大的等级的次数调整因子越大。
本实施例的方案中，对各类型的目标开车行为进行细分，并基于等级划分结果对当前出现次数进行修正，可便于进一步提升评估结果的准确性。
在其中一个实施例中，如图4所示，上述的获取目标用户的行车轨迹数据，可以包括：
步骤S402：获取原始行车轨迹数据，并获原始行车轨迹数据中各行车路段中的驾驶人脸部图像；
其中，终端可以对各行车路段中的驾驶人脸部图像进行采集，将采集的驾驶人脸部图像发送给服务器，
步骤S404：根据各行程中的驾驶人脸部图像以及目标用户的脸部图像对原始行车轨迹数据进行筛选，得到目标用户的行车轨迹数据。
具体地，筛选出各行程中的驾驶人脸部图像与目标用户的脸部图像匹配的原始行车轨迹数据，将筛选出原始行车轨迹数据作为目标用户的行车轨迹数据。
采用本实施例的方案，使得后续用于评估目标用户的驾驶水平的行车轨迹数据均是目标用户的行车轨迹数据，便于进一步提升目标用户的驾驶水平的评估结果的准确性。
在其中一个实施例中，上述的根据驾驶分数值评估目标用户的驾驶水平，可以包括：根据目标用户的驾驶分数值，以及预设的驾驶分数值与驾驶水平 等级的对应关系，评估目标用户的驾驶水平等级。
其中，驾驶分数值与驾驶水平等级的对应关系可以参见表1，F1、F2、F3和F4的大小可以根据需要设定。驾驶分数值与驾驶水平等级的对应关系也不限于表1中提供的方式。
表1
| 驾驶分数值 | 驾驶水平等级 |
| F≤F1 | 第I等级 |
| F1<F≤F2 | 第II等级 |
| F2<F≤F3 | 第III等级 |
| F3<F≤F4 | 第Ⅳ等级 |
| F4<F | 第Ⅴ等级 |
应该理解的是，虽然图2至图4的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2至图4中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
在其中一个实施例，如图5所示，提供了一种驾驶水平评估装置，包括：路段长度获取模块502、次数获取模块504、分数获取模块506和水平评估模块508，其中：
路段长度获取模块502，用于获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
次数获取模块504，用于根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
分数获取模块506，用于根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值，根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值；
水平评估模块508，用于根据驾驶分数值评估目标用户的驾驶水平。
在其中一个实施例中，分数获取模块506可以根据各当前出现次数以及预设的行为类型系数因子确定各第一评分参数值，各各第一评分参数值分别为目标用户在各行车路段内的评分参数值，根据根据各平均出现次数以及预设的行为类型系数因子确定各第二评分参数值，各第二评分参数值分别为各行车路段内的平均评分参数值，根据各第一评分参数值和各第二评分参数值确定目标用户的各行车路段的驾驶分数子值。
在其中一个实施例中，分数获取模块506可以对各路段长度值进行求和，得到总路段长度值，根据各路段长度值和总路段长度值确定各驾驶分数子值的权重值，根据各权重值对各驾驶分数子值进行加权求和，得到目标用户的驾驶分数值。
在其中一个实施例中，次数获取模块504可以根据行车轨迹数据确定目标用户在各行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向，根据行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向，以及预设的各类型的评判阈值，分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数。
在其中一个实施例中，次数获取模块504还可以用于根据各类型的等级划分阈值分别对各类型的目标开车行为进行等级划分，根据等级划分结果统计各类型的各等级的目标开车行为的出现次数，根据该各类型的各等级的目标开车行为的出现次数修正目标用户的各类型的目标开车行为的当前出现次数。
在其中一个实施例中，路段长度获取模块502可以获取原始行车轨迹数据，并获原始行车轨迹数据中各行车路段中的驾驶人脸部图像，根据各行程中的驾驶人脸部图像以及目标用户的脸部图像对原始行车轨迹数据进行筛 选，得到目标用户的行车轨迹数据。
在其中一个实施例中，水平评估模块508可以根据目标用户的驾驶分数值，以及预设的驾驶分数值与驾驶水平等级的对应关系，评估目标用户的驾驶水平等级。
关于驾驶水平评估装置的具体限定可以参见上文中对于驾驶水平评估方法的限定，在此不再赘述。上述驾驶水平评估装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在其中一个实施例，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图6所示。该计算机设备包括通过系统总线连接的处理器、存储器和网络接口。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性计算机可读存储介质、内存储器。该非易失性计算机可读存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为非易失性计算机可读存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种驾驶水平评估方法。
本领域技术人员可以理解，图6中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
一种计算机设备，包括存储器和一个或多个处理器，存储器中储存有计算机可读指令，计算机可读指令被处理器执行时，使得一个或多个处理器执行以下步骤：
获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值；及
根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，根据驾驶分数值评估目标用户的驾驶水平。
一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行以下步骤：
获取目标用户的行车轨迹数据，根据行车轨迹数据确定目标用户的各行车路段以及各行车路段的路段长度值；
根据行车轨迹数据分析目标用户在各行车路段内的各类型的目标开车行为的当前出现次数，并获取在各行车路段内的各类型的目标开车行为的平均出现次数；
根据各当前出现次数和各平均出现次数确定目标用户的各行车路段的驾驶分数子值；及
根据各驾驶分数子值以及各路段长度值确定目标用户的驾驶分数值，根据驾驶分数值评估目标用户的驾驶水平。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性计算机可读取存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外 部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。
Claims (20)
- 一种驾驶水平评估方法，包括：获取目标用户的行车轨迹数据，根据所述行车轨迹数据确定所述目标用户的各行车路段以及各所述行车路段的路段长度值；根据所述行车轨迹数据分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数，并获取在各所述行车路段内的各类型的目标开车行为的平均出现次数；根据各所述当前出现次数和各所述平均出现次数确定所述目标用户的各所述行车路段的驾驶分数子值；及根据各所述驾驶分数子值以及各所述路段长度值确定所述目标用户的驾驶分数值，根据所述驾驶分数值评估目标用户的驾驶水平。
- 根据权利要求1所述的驾驶水平评估方法，其特征在于，所述根据各所述当前出现次数和各所述平均出现次数确定所述目标用户的各所述行车路段的驾驶分数子值，包括：根据各所述当前出现次数以及预设的行为类型系数因子确定各第一评分参数值，各所述各第一评分参数值分别为所述目标用户在各所述行车路段内的评分参数值；根据根据各所述平均出现次数以及预设的行为类型系数因子确定各第二评分参数值，各所述第二评分参数值分别为各所述行车路段内的平均评分参数值；及根据各所述第一评分参数值和各所述第二评分参数值确定所述目标用户的各所述行车路段的驾驶分数子值。
- 根据权利要求1或2所述的驾驶水平评估方法，其特征在于，所述根据各所述驾驶分数子值以及各所述路段长度值确定所述目标用户的驾驶分数值，包括：对各所述路段长度值进行求和，得到总路段长度值；根据各所述路段长度值和所述总路段长度值确定各所述驾驶分数子值的 权重值；及根据各所述权重值对各所述驾驶分数子值进行加权求和，得到所述目标用户的驾驶分数值。
- 根据权利要求3所述的驾驶水平评估方法，其特征在于，所述根据所述行车轨迹数据分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数，包括：根据所述行车轨迹数据确定所述目标用户在各所述行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向；及根据所述行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向，以及预设的各所述类型的评判阈值，分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数。
- 根据权利要求3所述的驾驶水平评估方法，其特征在于，所述方法还包括：根据各所述类型的等级划分阈值分别对各所述类型的目标开车行为进行等级划分；根据等级划分结果统计各类型的各等级的目标开车行为的出现次数；及根据该各类型的各等级的目标开车行为的出现次数修正目标用户的各类型的目标开车行为的当前出现次数。
- 根据权利要求3所述的驾驶水平评估方法，其特征在于，所述获取目标用户的行车轨迹数据，包括：获取原始行车轨迹数据，并获原始行车轨迹数据中各行车路段中的驾驶人脸部图像；及根据各行程中的驾驶人脸部图像以及所述目标用户的脸部图像对所述原始行车轨迹数据进行筛选，得到所述目标用户的行车轨迹数据。
- 根据权利要求1或2所述的驾驶水平评估方法，其特征在于，所述根据所述驾驶分数值评估目标用户的驾驶水平，包括：根据所述目标用户的驾驶分数值，以及预设的驾驶分数值与驾驶水平等 级的对应关系，评估所述目标用户的驾驶水平等级。
- 一种驾驶水平评估装置，包括：路段长度获取模块，用于获取目标用户的行车轨迹数据，根据所述行车轨迹数据确定所述目标用户的各行车路段以及各所述行车路段的路段长度值；次数获取模块，用于根据所述行车轨迹数据分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数，并获取在各所述行车路段内的各类型的目标开车行为的平均出现次数；分数获取模块，用于根据各所述当前出现次数和各所述平均出现次数确定所述目标用户的各所述行车路段的驾驶分数子值，根据各所述驾驶分数子值以及各所述路段长度值确定所述目标用户的驾驶分数值；及水平评估模块，用于根据所述驾驶分数值评估目标用户的驾驶水平。
- 一种计算机设备，包括存储器及一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：获取目标用户的行车轨迹数据，根据所述行车轨迹数据确定所述目标用户的各行车路段以及各所述行车路段的路段长度值；根据所述行车轨迹数据分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数，并获取在各所述行车路段内的各类型的目标开车行为的平均出现次数；根据各所述当前出现次数和各所述平均出现次数确定所述目标用户的各所述行车路段的驾驶分数子值；及根据各所述驾驶分数子值以及各所述路段长度值确定所述目标用户的驾驶分数值，根据所述驾驶分数值评估目标用户的驾驶水平。
- 根据权利要求9所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：根据各所述当前出现次数以及预设的行为类型系数因子确定各第一评分 参数值，各所述各第一评分参数值分别为所述目标用户在各所述行车路段内的评分参数值；根据根据各所述平均出现次数以及预设的行为类型系数因子确定各第二评分参数值，各所述第二评分参数值分别为各所述行车路段内的平均评分参数值；及根据各所述第一评分参数值和各所述第二评分参数值确定所述目标用户的各所述行车路段的驾驶分数子值。
- 根据权利要求9或10所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：对各所述路段长度值进行求和，得到总路段长度值；根据各所述路段长度值和所述总路段长度值确定各所述驾驶分数子值的权重值；及根据各所述权重值对各所述驾驶分数子值进行加权求和，得到所述目标用户的驾驶分数值。
- 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：根据所述行车轨迹数据确定所述目标用户在各所述行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向；及根据所述行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向，以及预设的各所述类型的评判阈值，分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数。
- 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：根据各所述类型的等级划分阈值分别对各所述类型的目标开车行为进行等级划分；根据等级划分结果统计各类型的各等级的目标开车行为的出现次数；及根据该各类型的各等级的目标开车行为的出现次数修正目标用户的各类 型的目标开车行为的当前出现次数。
- 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：获取原始行车轨迹数据，并获原始行车轨迹数据中各行车路段中的驾驶人脸部图像；及根据各行程中的驾驶人脸部图像以及所述目标用户的脸部图像对所述原始行车轨迹数据进行筛选，得到所述目标用户的行车轨迹数据。
- 一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：获取目标用户的行车轨迹数据，根据所述行车轨迹数据确定所述目标用户的各行车路段以及各所述行车路段的路段长度值；根据所述行车轨迹数据分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数，并获取在各所述行车路段内的各类型的目标开车行为的平均出现次数；根据各所述当前出现次数和各所述平均出现次数确定所述目标用户的各所述行车路段的驾驶分数子值；及根据各所述驾驶分数子值以及各所述路段长度值确定所述目标用户的驾驶分数值，根据所述驾驶分数值评估目标用户的驾驶水平。
- 根据权利要求15所述的存储介质，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：根据各所述当前出现次数以及预设的行为类型系数因子确定各第一评分参数值，各所述各第一评分参数值分别为所述目标用户在各所述行车路段内的评分参数值；根据根据各所述平均出现次数以及预设的行为类型系数因子确定各第二评分参数值，各所述第二评分参数值分别为各所述行车路段内的平均评分参数值；及根据各所述第一评分参数值和各所述第二评分参数值确定所述目标用户的各所述行车路段的驾驶分数子值。
- 根据权利要求15或16所述的存储介质，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：对各所述路段长度值进行求和，得到总路段长度值；根据各所述路段长度值和所述总路段长度值确定各所述驾驶分数子值的权重值；及根据各所述权重值对各所述驾驶分数子值进行加权求和，得到所述目标用户的驾驶分数值。
- 根据权利要求17所述的存储介质，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：根据所述行车轨迹数据确定所述目标用户在各所述行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向；及根据所述行车路段内的各个时刻的速度值、速度方向、加速度值和加速度方向，以及预设的各所述类型的评判阈值，分析所述目标用户在各所述行车路段内的各类型的目标开车行为的当前出现次数。
- 根据权利要求17所述的存储介质，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：根据各所述类型的等级划分阈值分别对各所述类型的目标开车行为进行等级划分；根据等级划分结果统计各类型的各等级的目标开车行为的出现次数；及根据该各类型的各等级的目标开车行为的出现次数修正目标用户的各类型的目标开车行为的当前出现次数。
- 根据权利要求17所述的存储介质，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：获取原始行车轨迹数据，并获原始行车轨迹数据中各行车路段中的驾驶人脸部图像；及根据各行程中的驾驶人脸部图像以及所述目标用户的脸部图像对所述原始行车轨迹数据进行筛选，得到所述目标用户的行车轨迹数据。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910040283.5 | 2019-01-16 | ||
| CN201910040283.5A CN109800984B (zh) | 2019-01-16 | 2019-01-16 | 驾驶水平评估方法、装置、计算机设备和存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020147391A1 true WO2020147391A1 (zh) | 2020-07-23 |
Family
ID=66559488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/116981 Ceased WO2020147391A1 (zh) | 2019-01-16 | 2019-11-11 | 驾驶水平评估方法、装置、计算机设备和存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109800984B (zh) |
| WO (1) | WO2020147391A1 (zh) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112185106A (zh) * | 2020-08-25 | 2021-01-05 | 北京北大千方科技有限公司 | 一种不合理限速标志筛查方法、装置、存储介质及终端 |
| CN116674487A (zh) * | 2023-06-21 | 2023-09-01 | 广州小鹏自动驾驶科技有限公司 | 自动驾驶功能的设置方法、装置、设备、介质和产品 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800984B (zh) * | 2019-01-16 | 2024-03-01 | 平安科技（深圳）有限公司 | 驾驶水平评估方法、装置、计算机设备和存储介质 |
| CN111159251A (zh) * | 2019-12-19 | 2020-05-15 | 青岛聚好联科技有限公司 | 一种异常数据的确定方法及装置 |
| CN113859246B (zh) * | 2020-06-30 | 2023-09-08 | 广州汽车集团股份有限公司 | 一种车辆控制方法和装置 |
| CN112183984A (zh) * | 2020-09-21 | 2021-01-05 | 长城汽车股份有限公司 | 驾驶行为处理方法、装置、存储介质和电子设备 |
| CN116542830B (zh) * | 2023-07-06 | 2024-03-15 | 广州市德赛西威智慧交通技术有限公司 | 基于多元参数的智能评判方法及装置 |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040030458A1 (en) * | 2000-01-14 | 2004-02-12 | Volker Entenmann | Method and device for evaluating a driving style |
| CN106710144A (zh) * | 2016-12-21 | 2017-05-24 | 东软集团股份有限公司 | 一种驾驶行程评价方法及装置 |
| CN106780042A (zh) * | 2016-09-05 | 2017-05-31 | 中国人民财产保险股份有限公司 | 基于智能移动设备的驾驶行为数据采集以及评判方法 |
| CN107066787A (zh) * | 2016-11-25 | 2017-08-18 | 东软集团股份有限公司 | 车辆行程的评分方法及装置 |
| CN107161153A (zh) * | 2017-06-16 | 2017-09-15 | 北京车薄荷科技有限公司 | 一种驾驶行为评分方法及装置 |
| CN107292663A (zh) * | 2017-06-08 | 2017-10-24 | 北京深瞐科技有限公司 | 车险定价方法及装置 |
| CN107918826A (zh) * | 2017-11-13 | 2018-04-17 | 北京航空航天大学 | 一种驾驶环境感知的司机评价与调度方法 |
| CN107945311A (zh) * | 2017-11-29 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | 一种危险驾驶行为的预警方法、装置、存储介质及服务器 |
| CN109102194A (zh) * | 2018-08-20 | 2018-12-28 | 合肥优控科技有限公司 | 一种基于全球定位系统与惯性传感器的驾驶行为评分方法 |
| CN109800984A (zh) * | 2019-01-16 | 2019-05-24 | 平安科技（深圳）有限公司 | 驾驶水平评估方法、装置、计算机设备和存储介质 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5386543B2 (ja) * | 2011-05-25 | 2014-01-15 | 株式会社審調社 | 運転評価システム、運転評価用プログラム、及び運転評価方法 |
| WO2016088375A1 (en) * | 2014-12-04 | 2016-06-09 | Ricoh Company, Limited | Driving determination device and detection device |
| JP6341137B2 (ja) * | 2015-04-08 | 2018-06-13 | トヨタ自動車株式会社 | 車両の運転支援制御装置 |
| CN105966404A (zh) * | 2015-11-06 | 2016-09-28 | 乐卡汽车智能科技（北京）有限公司 | 一种驾驶行为评测方法及装置 |
| CN105741556B (zh) * | 2016-04-29 | 2019-03-22 | 盯盯拍（深圳）云技术有限公司 | 路况信息的推送方法以及推送系统 |
| CN106781456A (zh) * | 2016-11-29 | 2017-05-31 | 广东好帮手电子科技股份有限公司 | 一种车辆驾驶安全性的评估数据处理方法及系统 |
| CN108446824A (zh) * | 2018-02-08 | 2018-08-24 | 深圳市赛格导航科技股份有限公司 | 一种驾驶行为的风险评估方法、装置、设备及存储介质 |
| CN109195095A (zh) * | 2018-09-04 | 2019-01-11 | 广东翼卡车联网服务有限公司 | 一种基于车载gps系统的行驶轨迹切分方法及装置 |
-
2019
- 2019-01-16 CN CN201910040283.5A patent/CN109800984B/zh active Active
- 2019-11-11 WO PCT/CN2019/116981 patent/WO2020147391A1/zh not_active Ceased
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040030458A1 (en) * | 2000-01-14 | 2004-02-12 | Volker Entenmann | Method and device for evaluating a driving style |
| CN106780042A (zh) * | 2016-09-05 | 2017-05-31 | 中国人民财产保险股份有限公司 | 基于智能移动设备的驾驶行为数据采集以及评判方法 |
| CN107066787A (zh) * | 2016-11-25 | 2017-08-18 | 东软集团股份有限公司 | 车辆行程的评分方法及装置 |
| CN106710144A (zh) * | 2016-12-21 | 2017-05-24 | 东软集团股份有限公司 | 一种驾驶行程评价方法及装置 |
| CN107292663A (zh) * | 2017-06-08 | 2017-10-24 | 北京深瞐科技有限公司 | 车险定价方法及装置 |
| CN107161153A (zh) * | 2017-06-16 | 2017-09-15 | 北京车薄荷科技有限公司 | 一种驾驶行为评分方法及装置 |
| CN107918826A (zh) * | 2017-11-13 | 2018-04-17 | 北京航空航天大学 | 一种驾驶环境感知的司机评价与调度方法 |
| CN107945311A (zh) * | 2017-11-29 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | 一种危险驾驶行为的预警方法、装置、存储介质及服务器 |
| CN109102194A (zh) * | 2018-08-20 | 2018-12-28 | 合肥优控科技有限公司 | 一种基于全球定位系统与惯性传感器的驾驶行为评分方法 |
| CN109800984A (zh) * | 2019-01-16 | 2019-05-24 | 平安科技（深圳）有限公司 | 驾驶水平评估方法、装置、计算机设备和存储介质 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112185106A (zh) * | 2020-08-25 | 2021-01-05 | 北京北大千方科技有限公司 | 一种不合理限速标志筛查方法、装置、存储介质及终端 |
| CN112185106B (zh) * | 2020-08-25 | 2021-12-21 | 北京北大千方科技有限公司 | 一种不合理限速标志筛查方法、装置、存储介质及终端 |
| CN116674487A (zh) * | 2023-06-21 | 2023-09-01 | 广州小鹏自动驾驶科技有限公司 | 自动驾驶功能的设置方法、装置、设备、介质和产品 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109800984A (zh) | 2019-05-24 |
| CN109800984B (zh) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020147391A1 (zh) | 驾驶水平评估方法、装置、计算机设备和存储介质 | |
| US11842404B2 (en) | Enhancement using analytics based on vehicle kinematic data | |
| CN112700072B (zh) | 交通状况预测方法、电子设备和存储介质 | |
| US10703379B1 (en) | System and methods for determining owner's preferences based on vehicle owner's telematics data | |
| US20140081675A1 (en) | Systems, methods, and apparatus for optimizing claim appraisals | |
| CN111091215B (zh) | 车辆识别方法、装置、计算机设备和存储介质 | |
| JP2021509978A (ja) | 運転行為評価方法、装置及びコンピュータが読み取り可能な記憶媒体 | |
| WO2020108219A1 (zh) | 基于交通安全风险的群体划分与差异性分析方法及系统 | |
| CN112163348A (zh) | 道路异常路面的检测方法、装置、仿真方法、车辆和介质 | |
| CN109767020B (zh) | 车辆推荐方法、装置、计算机设备和存储介质 | |
| CN112241127B (zh) | 自动驾驶安全评分方法、装置、计算机设备和存储介质 | |
| CN114841715A (zh) | 一种商用车违约风险预测方法、装置、计算机设备及介质 | |
| CN112950397B (zh) | 理赔风险预估方法、装置、计算机设备和存储介质 | |
| Ma et al. | Lane change analysis and prediction using mean impact value method and logistic regression model | |
| CN114419894A (zh) | 一种路内停车泊位设置与使用监测的方法与系统 | |
| CN111368621B (zh) | 判断人员关系的方法、装置、设备及存储介质 | |
| US20250131508A1 (en) | Artificial intelligence-based systems and methods for determining insurance premium amount | |
| US12106617B2 (en) | Method and system for auto generating automotive data quality marker | |
| CN111192150A (zh) | 车辆出险代理业务的处理方法、装置、设备及存储介质 | |
| CN111222406A (zh) | 酒后驾驶检测方法、装置、计算机设备和存储介质 | |
| CN112533208B (zh) | 模型训练方法、虚假终端识别方法和装置、电子设备 | |
| CN115204755A (zh) | 服务区入区率测算方法、装置、电子设备及可读存储介质 | |
| Yarlagadda et al. | Exploring the Concept of Driving Volatility at Microscopic Level in the Context of Driving Style Classification | |
| CN117292504B (zh) | 交通安全监控方法、装置、设备及介质 | |
| CN118823698B (zh) | 交通异常检测方法、设备以及存储介质 |
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: 19910024 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: 19910024 Country of ref document: EP Kind code of ref document: A1 |