Driving behavior data processing method and device, computer equipment and medium

Abstract

The invention relates to the technical field of automotive electronics, and discloses a driving behavior data processing method and device, computer equipment and a medium, and the driving behavior data processing method comprises the steps: firstly obtaining driving behavior feature data of a current driving behavior on a plurality of preset category indexes; secondly, for each preset category index, determining a grade value interval corresponding to each driving behavior grade; correlation calculation is carried out according to the driving behavior characteristic data of each preset category index and the grade value interval corresponding to each driving behavior grade, and an index grade correlation matrix is obtained; then, on the basis of the distribution matrix and the index grade incidence matrix, association degree summarization is carried out on each driving behavior grade, and the comprehensive association degree on each driving behavior grade is obtained; and finally, performing normalization processing on the comprehensive association degree on each driving behavior level, determining safety evaluation data of the current driving behavior, and realizing accurate evaluation of the driving behavior.

Description

Technical Field

[0001] The present application relates to the field of automotive electronic technology, and in particular to a method, device, computer equipment and medium for processing driving behavior data. Background Art

[0002] In recent years, with the increase in the production capacity of passenger cars and commercial vehicles in my country, the number of motor vehicles on the road and drivers has increased dramatically. Statistics show that 90% of road traffic accidents are caused by drivers' wrong decisions or improper operations. Therefore, good driving behavior is crucial and can significantly reduce the risk of collision, rollover and failure. Improving driving safety not only depends on automakers to ensure vehicle quality, but also requires drivers to maintain good driving habits. Therefore, it is particularly necessary to accurately evaluate drivers' driving behavior, which can help them understand their own driving level and provide effective safety reminders.

[0003] In related technologies, after assigning weights to various indicators of driving behavior, the scoring model also needs to grade the triggering events or values ​​of the indicators, and finally obtain the evaluation results through weighting.

[0004] However, the accuracy of driving behavior data processing in related technologies needs to be improved, so there is an urgent need to propose a new driving behavior data processing method. Summary of the invention

[0005] The present application provides a method, apparatus, computer device and medium for processing driving behavior data, which solves the technical problem in the related art that the accuracy of driving behavior data processing needs to be improved, and achieves a technical effect of more accurate and reliable evaluation of driving behavior.

[0006] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0007] In a first aspect, an embodiment of the present application provides a method for processing driving behavior data, the method comprising:

[0008] Acquire driving behavior characteristic data of the current driving behavior on multiple preset category indicators; wherein the importance coefficient corresponding to each preset category indicator constitutes a distribution matrix;

[0009] For each preset category indicator, determining the level value intervals corresponding to the multiple driving behavior levels;

[0010] Performing correlation calculation based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level to obtain an indicator level correlation matrix; wherein the elements of the indicator level correlation matrix are used to characterize the correlation degree between each preset category indicator and each driving behavior level;

[0011] Summarizing the correlation degree at each driving behavior level based on the allocation matrix and the indicator level correlation matrix to obtain a comprehensive correlation degree at each driving behavior level;

[0012] The comprehensive correlation degree at each driving behavior level is normalized to determine the safety assessment data of the current driving behavior.

[0013] In a second aspect, an embodiment of the present application provides a device for processing driving behavior data, the device comprising:

[0014] A feature data acquisition module is used to acquire driving behavior feature data of the current driving behavior on multiple preset category indicators; wherein the importance coefficient corresponding to each preset category indicator constitutes a distribution matrix;

[0015] A level value interval determination module, used to determine the level value intervals corresponding to each of the multiple driving behavior levels for each preset category indicator;

[0016] A correlation matrix calculation module, used to perform correlation calculation based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level, to obtain an indicator level correlation matrix; wherein the elements of the indicator level correlation matrix are used to characterize the degree of correlation between each preset category indicator and each driving behavior level;

[0017] A comprehensive correlation degree acquisition module, used for summarizing the correlation degree at each driving behavior level based on the allocation matrix and the indicator level correlation matrix to obtain the comprehensive correlation degree at each driving behavior level;

[0018] The evaluation data determination module is used to normalize the comprehensive correlation degree at each driving behavior level to determine the safety evaluation data of the current driving behavior.

[0019] In a third aspect, an embodiment of the present application provides a computer device, including:

[0020] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method described in any one of the above embodiments by executing the computer instructions.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute any one of the methods in the above embodiments.

[0022] In this application, firstly, the driving behavior characteristic data of the current driving behavior on multiple preset category indicators are obtained; secondly, for each preset category indicator, the level value intervals corresponding to multiple driving behavior levels are determined; then, the driving behavior characteristic data of each preset category indicator and the level value intervals corresponding to each driving behavior level are correlated and calculated to obtain the indicator level correlation matrix; then, based on the allocation matrix and the indicator level correlation matrix, the correlation degree is summarized on each driving behavior level to obtain the comprehensive correlation degree on each driving behavior level; finally, the comprehensive correlation degree on each driving behavior level is normalized to determine the safety assessment data of the current driving behavior. By accurately processing the driving behavior data, the safety of the driving behavior can be accurately assessed, thereby identifying and improving unsafe driving habits, reducing accidents, and improving traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A flowchart of a driving behavior data processing method provided in an embodiment of this specification;

[0025] Figure 2 A flowchart of a driving behavior data processing method provided in an embodiment of this specification;

[0026] Figure 3 A flowchart of a driving behavior data processing method provided in an embodiment of this specification;

[0027] Figure 4 A flowchart of a driving behavior data processing method provided in an embodiment of this specification;

[0028] Figure 5 A flowchart of a driving behavior data processing method provided in an embodiment of this specification;

[0029] Figure 6 A flowchart of a driving behavior data processing method provided in an embodiment of this specification;

[0030] Figure 7 A schematic diagram of a driving behavior data processing device provided in an embodiment of this specification;

[0031] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0033] It is very necessary to accurately evaluate the driver's driving behavior, which can help the driver understand his or her own driving level and avoid some accidents. However, the accuracy of driving behavior data processing in related technologies needs to be improved.

[0034] Based on this, the present application provides a method for processing driving behavior data, firstly obtaining the driving behavior characteristic data of the current driving behavior on multiple preset category indicators, wherein the importance coefficient corresponding to each preset category indicator constitutes a distribution matrix; secondly, for each preset category indicator, determining the level value interval corresponding to each of the multiple driving behavior levels; then performing association calculation based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level, obtaining an indicator level association matrix, wherein the elements of the indicator level association matrix are used to characterize the degree of association between each preset category indicator and each driving behavior level; then summarizing the degree of association on each driving behavior level based on the allocation matrix and the indicator level association matrix, obtaining the comprehensive degree of association on each driving behavior level; finally, normalizing the comprehensive degree of association on each driving behavior level to determine the safety assessment data of the current driving behavior. This method can accurately process driving behavior data, thereby achieving an accurate assessment of driving behavior. By identifying and improving unsafe driving habits, the accident rate can be effectively reduced and traffic safety can be improved.

[0035] According to an embodiment of the present application, an embodiment of a method for processing driving behavior data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] See also Figure 1 The method for processing driving behavior data provided in the embodiment of the present application includes the following steps:

[0037] S110: Acquire driving behavior characteristic data of the current driving behavior on multiple preset category indicators.

[0038] Among them, the current driving behavior can be the driving behavior in a trip to be evaluated. Evaluating the driving behavior helps the driver to make adjustments and improvements based on feedback and improve driving safety. The preset category indicators can be specific standards for systematically analyzing and evaluating the driver's performance during driving. These indicators cover multiple aspects, such as speed control, safe distance, lane change operation, emergency braking and acceleration behavior, compliance with traffic rules and driving attention. Through the comprehensive evaluation of these indicators, potential safety hazards can be identified. Each preset category indicator has a corresponding importance coefficient. The importance coefficient can be a numerical value that quantifies the relative importance of each preset category indicator in the overall driving behavior evaluation. In order to facilitate the subsequent quantitative calculation of the current driving behavior, the importance coefficient can be formed into a distribution matrix, for example, the importance coefficient can be formed into a row vector according to the order of the preset category indicators. The driving behavior characteristic data can be statistical data on the preset category indicators. By collecting these data to analyze various performances in the driving process, the driver's behavioral characteristics are reflected.

[0039] Specifically, during driving, the terminal (T-BOX) collects driving data in real time at a certain frequency through the CAN bus, and uploads the data to the Internet of Vehicles platform through the wireless network. The Internet of Vehicles platform performs some preprocessing operations on these initial driving data, such as removing invalid fields and abnormal values, supplementing missing values, and smoothing burr data, and then calculates the characteristic values ​​of the preprocessed driving data according to the characteristic value calculation method of each preset category indicator to obtain driving behavior characteristic data. All preset category indicators and the corresponding driving behavior characteristic data constitute the object to be evaluated. For example, when evaluating driving behavior using the matter-element extension method, the matter-element R to be evaluated can be used. q It is expressed as follows

[0040]

[0041] Among them, N q represents the driving behavior to be evaluated, S 1 ,S 2 ,…,S m is the index of each preset category, V 1q ,V 2q ,…,V mq is the driving behavior characteristic data corresponding to each preset category indicator, i∈[1,m], and m is the total number of evaluation indicators.

[0042] S120: For each preset category indicator, determine level value ranges corresponding to a plurality of driving behavior levels.

[0043] Specifically, in order to quantify the driving behavior characteristic data of each driving behavior, it is necessary to determine in advance how many driving behavior levels each preset category indicator is divided into, and the level value interval corresponding to each driving behavior level. For example, a certain amount of data can be randomly selected from the big data collected by the Internet of Vehicles platform as a sample, such as 10,000 data, and then the data of each preset category indicator in the sample data is sorted from low to high, and then the minimum value, first quartile, third quartile and maximum value of each preset category indicator are statistically analyzed based on the box plot, so that four driving behavior levels and the level value interval corresponding to each driving behavior level can be determined.

[0044] For example, when the driving behavior data is processed by the matter-element extension method, the classical domain R of driving behavior level can be used. j To represent each driving behavior level of the preset category indicator and the corresponding level value range, it is expressed as follows

[0045]

[0046] Where j represents the driving behavior of the jth driving behavior level, j∈[1,J], J is the total number of driving behavior levels, V 1j ,V 2j ,…,V mj They represent the value range of the preset category indicators at level j, (x ij ,y ij ), i = 1, 2, ..., m are the upper and lower limits of the value range of the evaluation index at the jth level.

[0047] At the same time, the driving behavior level domain R n To represent the overall driving behavior level of the preset category indicators and the corresponding overall level value range, it is expressed as follows

[0048]

[0049] Where N represents the driving behavior of all evaluation levels, V 1n ,V 2n ,…,V mn is the value range of the preset category index for all evaluation levels n, (x in ,y in ),i=1,2,…,m are the upper and lower limits of the value range of all evaluation levels n.

[0050] S130 , performing correlation calculation based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level to obtain an indicator level correlation matrix.

[0051] Among them, the elements of the indicator level association matrix are used to characterize the degree of association between each preset category indicator and each driving behavior level;

[0052] Specifically, according to the matter-element extension method, let the index level association matrix be represented by K, where each element K ij (v iq ) can be calculated by

[0053]

[0054] Among them, P(V iq ,V ij ) indicates point V iq With a finite interval V ij =[x ij ,y ij ], P(V iq ,V in ) indicates point V iq With a finite interval V in =[x in ,y in ],|V ij | represents a finite interval V ij =[x ij ,y ij ]'s length.

[0055] Exemplarily, the distance calculation formula between a point and a finite interval may be:

[0056]

[0057] Among them, V iq It represents the driving behavior characteristic data of each preset category indicator, which is a point value; x and y represent the finite interval V ij The left and right endpoint values ​​of .

[0058] After calculating the correlation degree between the driving behavior characteristic data of each preset category indicator and each driving behavior level, the indicator level correlation matrix K can be obtained.

[0059] S140 , summarizing the correlation degree at each driving behavior level based on the allocation matrix and the indicator level correlation matrix to obtain a comprehensive correlation degree at each driving behavior level.

[0060] Specifically, assuming there are m preset category indicators, the allocation matrix can be expressed as

[0061] W=[ω 1 ω 2 … ω i … ω m ]

[0062] Among them, ω i is the importance coefficient of the i-th preset category indicator.

[0063] Then, the formula for summarizing the degree of association at each driving behavior level based on the allocation matrix and the indicator level association matrix can be:

[0064]

[0065] Among them, K ij (V iq ) is the correlation coefficient between the i-th preset category index and the j-th driving behavior level, K j (R q ) represents the comprehensive correlation between the current driving behavior and the jth driving behavior level.

[0066] S150: Normalize the comprehensive correlation degree at each driving behavior level to determine safety assessment data of the current driving behavior.

[0067] The matter-element extension model is improved. Specifically, first, the comprehensive correlation degree of each driving behavior level can be normalized. The formula is as follows:

[0068]

[0069] Then, calculate the object element R q The driving behavior level variable characteristic value can be expressed as:

[0070]

[0071] Where j∈[1,J], J is the total number of driving behavior levels, j * R q According to this formula, the improved variable characteristic value of each driving behavior level can be obtained, and the improved maximum comprehensive correlation degree is defined as

[0072] K max =max{j *}

[0073] K max The value is the safety assessment data of the current driving behavior, and also indicates the level of the current driving behavior.

[0074] In the above embodiment, firstly, the driving behavior characteristic data of the current driving behavior on multiple preset category indicators are obtained; secondly, for each preset category indicator, the level value intervals corresponding to each of the multiple driving behavior levels are determined; then, the correlation calculation is performed based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level to obtain the indicator level correlation matrix; then, based on the allocation matrix and the indicator level correlation matrix, the correlation degree is summarized on each driving behavior level to obtain the comprehensive correlation degree on each driving behavior level; finally, the comprehensive correlation degree on each driving behavior level is normalized to determine the safety assessment data of the current driving behavior. By accurately processing the driving behavior data, the safety of the driving behavior can be accurately assessed, thereby identifying and improving unsafe driving habits, reducing accidents, and improving traffic safety.

[0075] In some embodiments, see Figure 2 , the allocation matrix is ​​determined by:

[0076] S210: Determine the empirical coefficient and the statistical coefficient for each preset category indicator.

[0077] Among them, the experience coefficient can be the subjective weight of each preset category indicator, which is used to reflect the relative importance of different preset category indicators to the safety of driving behavior. It is usually based on the knowledge and experience of experts and can be flexibly adjusted.

[0078] The statistical coefficient can be the objective weight of each preset category indicator, which is used to quantify the importance of each preset category indicator in the driving behavior safety assessment. These coefficients are based on actual data analysis and can determine the degree of influence of each indicator on driving behavior safety through statistical methods, correlation analysis, etc. For example, the objective weight of each preset category indicator can be determined based on the CRITIC method, and its main steps are as follows:

[0079] 1) Randomly obtain n pre-processed driving behavior data;

[0080] 2) Perform data standardization. There are m preset category indicators. Each preset category indicator has n data, i = 1, ..., n, j = 1, ..., m.

[0081] The calculation formula for the positive indicator of the preset category indicator is:

[0082]

[0083] The calculation formula for the negative indicator of the preset category indicator is:

[0084]

[0085] Among them, Y ijis the standardized value of each preset category indicator, X ij is the original data value, max(X i )、min(X i ) are the maximum and minimum values ​​of each preset category indicator.

[0086] 3) Pearson correlation coefficient calculation

[0087]

[0088] in, x ij ,y ij The mean of .

[0089] 4) Information value G i calculate

[0090]

[0091] 5) Preset category indicator objective weight β i calculate

[0092]

[0093] The CRITIC method takes into account the degree of differentiation of preset category indicators and the inherent correlation between preset category indicators, and can better reflect the objective weights of preset category indicators.

[0094] S220 , performing coupling processing based on the empirical coefficient and the statistical coefficient on each preset category indicator to obtain the importance coefficient on each preset category indicator.

[0095] Specifically, it is assumed that the empirical coefficients on each preset category indicator constitute a vector ω 1 , the statistical coefficients form a vector ω 2 , we can use game theory to analyze ω 1 and ω 2 The main steps for coupling processing are as follows:

[0096] 1) Construct the objective function and set k 1 , k 2 is the empirical coefficient vector ω 1 and the statistical coefficient vector ω 2 The combination coefficient of. The expression of the combination weight is:

[0097] W=k 1 ω 1 +k 2 ω 2

[0098] Combination coefficient k 1 , k 2Optimize to minimize the deviation between the empirical coefficient and the statistical coefficient, expressed as:

[0099] W * =min{‖k 1 ω 1 -W‖ 2 +‖k 2 ω 2 -W‖ 2}

[0100] 2) Solve the optimal combination coefficient and take the extreme value in the closed interval. The first-order partial derivative must be 0 and a first-order linear equation system must be established:

[0101]

[0102] Calculate the optimal combination coefficient Normalizing the combination coefficients yields:

[0103]

[0104] 3) The importance coefficient of each preset category indicator is obtained as follows:

[0105]

[0106] By optimizing the empirical coefficients and statistical coefficients through game theory, the differences between preset categories can be minimized and the benefits can be maximized, achieving Nash equilibrium and improving the scientific rationality of the importance coefficient to a certain extent.

[0107] S230: constructing a distribution matrix based on the importance coefficient of each preset category indicator.

[0108] Specifically, the importance coefficients of each preset category indicator may be formed into a row vector, namely, an allocation matrix.

[0109] In the above embodiment, the empirical coefficient and the statistical coefficient of each preset category indicator are first determined; secondly, the empirical coefficient and the statistical coefficient of each preset category indicator are coupled to obtain the importance coefficient of each preset category indicator; finally, the allocation matrix is ​​constructed based on the importance coefficient of each preset category indicator. By coupling the empirical coefficient and the statistical coefficient of each preset category indicator, the weight distribution of the empirical coefficient and the statistical coefficient is more reasonable.

[0110] In some embodiments, see Figure 3 , the empirical coefficients for each preset category indicator are determined in the following way:

[0111] S310, sorting each preset category indicator to obtain a sorting result;

[0112] S320, determining the importance scale between two adjacent preset category indicators in the sorting result;

[0113] S330, performing objective weight calculation based on the importance scale to obtain an empirical coefficient.

[0114] The empirical coefficient may be a subjective weight of each preset category indicator. For example, the subjective weight of each preset category indicator may be obtained based on the order relationship method, and the main steps are:

[0115] 1) Determine the order relationship and rank the importance of the preset category indicators through the expert scoring method. The ranking results are:

[0116] λ 1 >λ 2 >···>λ N

[0117] 2) Determine the importance scale, experts determine the index λ of two adjacent preset categories N-1 , N The ratio of the importance scale is r n , the expression is as follows:

[0118]

[0119] Among them, ω n is the weight coefficient of the Nth preset category indicator, n=1,2,…,N.

[0120] 3) Calculate the weight coefficient:

[0121]

[0122] α n-1 =r n α n

[0123] From this we can get the vector ω consisting of empirical coefficients 1 =[α 1 ,α 2 ,…,α N ].

[0124] In the above embodiment, firstly, each preset category indicator is sorted to obtain a sorting result; then, the importance scale between two adjacent preset category indicators in the sorting result is determined; finally, an objective weight calculation is performed based on the importance scale to obtain an empirical coefficient, which provides an important empirical reference for determining the importance coefficient of each preset category indicator.

[0125] In some embodiments, see Figure 4, the multiple driving behavior levels include low-risk level, medium-risk level, sub-high-risk level and high-risk level; for each preset category indicator, determining the level value intervals corresponding to the multiple driving behavior levels, including the following steps:

[0126] S410, obtaining driving behavior sample data, performing box plot analysis on the driving behavior sample data, and obtaining boundary values ​​for each driving behavior level;

[0127] S420: Determine level value intervals corresponding to each of the plurality of driving behavior levels based on the boundary value of each driving behavior level.

[0128] The driving behavior sample data may be a certain amount of data randomly selected from the big data collected from the Internet of Vehicles platform as a sample for a preset category indicator, such as 10,000 pieces of sample data.

[0129] Specifically, the data of each preset category indicator in the sample data are first sorted in order from low to high, and then the minimum value, first quartile, third quartile and maximum value of each preset category indicator are statistically analyzed based on the box plot, wherein the first quartile Q1 is equal to the 25% value of the sample data after being arranged from small to large, the third quartile Q3 is equal to the 75% value of the sample data after being arranged from small to large, the interquartile range IQR = Q3-Q1, that is, IQR is at 50% of the sample data interval, the maximum value Qmax = Q3+1.5IQR, and the minimum value Qmin = Q1-1.5IQR. Thus, the low-risk level value interval of each preset category indicator is [Qmin, Q1], the medium-risk level value interval is [Q1, IQR], the second-highest-risk level value interval is [IQR, Q3], and the high-risk level value interval is [Q3, Qmax].

[0130] It should be noted that the level value intervals corresponding to the above driving behavior levels are obtained through quantitative analysis, that is, based on the analysis of statistical data. In addition, the level value intervals can also be obtained through qualitative analysis, such as determining the fuzzy interval through expert evaluation and dividing it into four intervals: [0, 0.25], [0.25, 0.5], [0.5, 0.75] and [0.75, 1].

[0131] In the above embodiment, firstly, driving behavior sample data is obtained, and a box plot analysis is performed on the driving behavior sample data to obtain the boundary value of each driving behavior level; then, the level value intervals corresponding to the multiple driving behavior levels are determined based on the boundary value of each driving behavior level. By using the driving behavior data in big data for statistical analysis, the evaluation results can be made more objective and generally applicable.

[0132] In some embodiments, see Figure 5, obtaining driving behavior characteristic data of the current driving behavior on multiple preset category indicators, the steps include:

[0133] S510, obtaining initial driving behavior data of the current driving behavior;

[0134] S520, deleting outliers and filling missing values ​​in the initial driving behavior data to obtain processed driving data;

[0135] S530, performing mean filtering on the processed driving data to obtain filtered driving data;

[0136] S540: Calculate characteristic values ​​of the filtered driving data according to each preset category index to obtain driving behavior characteristic data.

[0137] During driving, the terminal (T-BOX) collects dozens of vehicle data including speed in real time at a frequency of 1Hz through the CAN bus, and uploads this data to the Internet of Vehicles platform through the 4G network. Among them, the initial driving behavior data can be the data directly uploaded by the vehicle to the Internet of Vehicles platform. In addition to the data of each preset category indicator, there are some other irrelevant data, which need to be eliminated. In addition, a trip that is too short or the trip time may not generate enough driving behavior feature data, so the characteristics and patterns of driving behavior may not be obvious, making it difficult to accurately evaluate, and are usually not included in the evaluation scope. Outliers can be data that does not conform to objective laws outside the range of each preset category indicator and needs to be eliminated. For example, for driving control data, the speed range is 0km / h~150km / h, and the acceleration range is 2.5m / s 2 ~5m / s 2 , the throttle opening range is 0~100%, the brake pedal opening range is 0~100%, and the number of trigger events has no negative value.

[0138] After the outliers are removed, there will be missing data at the original location. The missing values ​​can be filled by interpolation. For example, the Lagrange interpolation method can be used. The interpolation formula is:

[0139]

[0140] For burr data, filtering method can be used for smoothing. For example, sliding window mean filtering method is used, and the formula is:

[0141]

[0142] Among them, M is the sliding filter window size, x k-i is the original data.

[0143] The characteristic value of each preset category indicator needs to be calculated according to the characteristic value calculation method predetermined for each preset category indicator. For example, the characteristic value of the forward collision warning can be calculated by adding the number of all forward collision warnings in a trip to be evaluated and then dividing it by the trip length or trip duration.

[0144] In the above embodiment, the initial driving behavior data of the current driving behavior is first obtained; then the abnormal values ​​are eliminated and the missing values ​​are filled to obtain the processed driving data; then the processed driving data is subjected to mean filtering to obtain the filtered driving data; finally, the characteristic value of the filtered driving data is calculated according to each preset category index to obtain the driving behavior characteristic data. Through data preprocessing, the accuracy and consistency of the data are ensured, laying a reliable data foundation for the data processing of driving behavior.

[0145] In some embodiments, see Figure 6 , each preset category indicator has a parent indicator; the importance coefficient corresponding to each preset category indicator is determined by the following method:

[0146] S610, determining the first level coefficient on the upper level indicator and the second level coefficient on each preset category indicator;

[0147] S620: Based on the first level coefficient, the second level coefficient of each preset category indicator is corrected to obtain the importance coefficient corresponding to each preset category indicator.

[0148] Table 1 Schematic diagram of the three-level indicator evaluation system for driving behavior safety

[0149]

[0150] For example, please refer to Table 1, where the third-level indicator is a preset category indicator, and the second-level indicator is its parent indicator. The steps for determining the importance coefficient corresponding to each preset category indicator are:

[0151] 1) Determine the first-level coefficient of the secondary index. The empirical coefficient and statistical coefficient of each secondary index can be determined respectively, and then the first-level coefficients of each secondary index can be obtained through coupling processing. For example, the first-level coefficients of A, B, and C are 0.2, 0.3, and 0.5 respectively;

[0152] 2) Determine the second-level coefficient of each preset category indicator. First, the empirical coefficient and statistical coefficient of each third-level indicator relative to each second-level indicator can be determined respectively, and then the second-level coefficients thereof are obtained through coupling processing. For example, the second-level coefficients of A1 and A2 are 0.5 and 0.5 respectively, the second-level coefficients of B1, B2, B3 and B4 are 0.1, 0.2, 0.3 and 0.4 respectively, and the second-level coefficients of C1, C2 and C3 are 0.3, 0.2 and 0.5 respectively;

[0153] 3) Based on the first level coefficient, the second level coefficient of each preset category indicator is corrected by multiplying the first level coefficient and the second level coefficient. For example, according to the data in steps 1) and 2), the importance coefficients of A1 and A2 are 0.1 and 0.1 respectively, and the importance coefficients of B1, B2, B3, and B4 are 0.03, 0.06, and 0.16 respectively.

[0154] 0.09, 0.12, and the importance coefficients of C1, C2, and C3 are 0.15, 0.1, and 0.25, respectively.

[0155] In the above embodiment, the first level coefficient of the upper level indicator and the second level coefficient of each preset category indicator are first determined; and then the second level coefficient of each preset category indicator is level-corrected based on the first level coefficient to obtain the importance coefficient corresponding to each preset category indicator. This method ensures that the importance of each indicator is reasonably evaluated, thereby improving the accuracy and reliability of the evaluation results.

[0156] In some embodiments, please refer to Table 2, the upper-level indicators include ADAS warning, bad driving behavior and DMS alarm;

[0157] ADAS warnings include forward collision warning, lane departure warning, AEBS warning and pedestrian collision warning;

[0158] Bad driving behaviors include speeding percentage, night driving percentage, seat belt, frequent gear changes percentage, accelerator pedal standard deviation, and brake pedal standard deviation;

[0159] DMS alarms include yawning, closing eyes, talking on the phone, smoking, lowering head, looking around, and leaving the post.

[0160] Table 2 Three-level indicator evaluation system for driving behavior safety

[0161]

[0162] Among them, periodic data is collected once a second and uploaded to the Internet of Vehicles platform, and event data is uploaded only when the event is triggered.

[0163] The third-level indicators in the second-level indicator ADAS warning include forward collision warning, lane departure warning, AEBS warning, and pedestrian collision warning. Data is collected once a second. When the trigger conditions are met, T-BOX uploads the data to the Internet of Vehicles platform in the form of a falling edge (1-0) through edge computing. The Internet of Vehicles platform records the number of triggered events.

[0164] The calculation method of the characteristic value of each third-level indicator in the second-level indicator bad driving behavior is as follows:

[0165] 1) The trigger condition for speeding ratio is vehicle speed ≥ 100Km / h. Since the vehicle speed data is collected once per second, the Internet of Vehicles platform can filter out the data set with speed V < 100Km / h in a trip, multiply the number of remaining data by 1 second, and then add them up to get the speeding duration. The formula for calculating speeding ratio is:

[0166]

[0167] Among them, F4 is the speeding ratio, T4 is the speeding duration, T is the driving duration of the trip, and the unit of T4 and T is s.

[0168] 2) The trigger condition for the night driving ratio is that the driving time is after 22:00 and before 6:00 the next day. The calculation formula for the night driving ratio is:

[0169]

[0170] Among them, F5 is the proportion of night driving, T5 is the night driving time, T is the trip driving time, and the unit of T5 and T is s.

[0171] 3) Seat belt: When the vehicle speed is greater than 0, T-BOX continuously collects the seat belt status for 5 seconds, records the seat belt fastened data as 1, and the seat belt unfastened data as 0, and uploads the data.

[0172] 4) The proportion of frequent speed changes is calculated by jerk. When the jerk is greater than 2m / s 3 , it is judged as frequent speed change. Jerk is the first-order derivative of acceleration and the second-order derivative of speed, which can reflect the stability and controllability of vehicle operation. The calculation formula of jerk is:

[0173]

[0174] Among them, a 2 is the acceleration value at the current moment, a 1 is the acceleration value at the previous moment, t 2 is the current moment, t 1 For the previous moment.

[0175] Frequent speed change ratio calculation formula:

[0176]

[0177] Among them, F6 is the proportion of frequent speed changes, N 6 is the number of frequent speed changes, and D is the actual one-way operating mileage.

[0178] 5) Accelerator pedal standard deviation. The platform removes the data with accelerator pedal travel of 0, and then calculates the accelerator pedal travel standard deviation. The calculation formula for the accelerator pedal standard deviation is:

[0179]

[0180] The calculation formula for the average value of the accelerator pedal opening travel is:

[0181]

[0182] Among them, F(l p ) is the standard deviation of the accelerator pedal travel, is the accelerator pedal opening for a single stroke, is the average value of the accelerator pedal opening, and n is the total number of samples.

[0183] 6) Brake pedal standard deviation. The platform removes the data with a brake pedal opening of 0, and then calculates the brake pedal travel standard deviation. The brake pedal standard deviation calculation formula is:

[0184]

[0185] The calculation formula for the average brake pedal opening travel is:

[0186]

[0187] Among them, F(l q ) is the standard deviation of brake pedal travel, is the brake pedal opening for a single stroke, is the average brake pedal opening, and n is the total number of samples.

[0188] The third-level indicators in the second-level indicator DMS alarm can monitor the driver through the new national standard driving recorder. The characteristic value calculation method of each indicator is as follows:

[0189] 1) The trigger condition for yawning is: during vehicle driving, the height-to-width ratio of the driver's mouth is greater than the threshold of 0.75, and the duration exceeds the alarm threshold of 5 seconds.

[0190] 2) The trigger condition for closing eyes is: during the driving process, the driver's eyes are closed for a duration that reaches or exceeds the alarm threshold of 5 seconds.

[0191] 3) The trigger condition for making a phone call is: while the vehicle is driving, the driver puts the phone to his ear and the duration reaches or exceeds the alarm threshold of 5 seconds.

[0192] 4) The trigger condition for smoking is: while the vehicle is driving, the driver makes a smoking action and the duration reaches or exceeds the alarm threshold of 5 seconds.

[0193] 5) The trigger condition for lowering the head is: when the vehicle is driving, without a reverse signal or a turn signal, the driver's head angle exceeds the angle threshold and lasts for more than 5 seconds.

[0194] 6) The trigger condition for looking left and right is: when the vehicle is driving, without a reverse signal or a turn signal, the driver's head turns left and right at an angle exceeding the angle threshold and the duration is greater than the alarm threshold of 5 seconds.

[0195] 7) The triggering conditions for leaving the post are: when the vehicle is in motion, without a reverse signal or a turn signal, the driver leaves the seat or the camera is blocked by a foreign object, and the duration reaches or exceeds the alarm threshold of 5 seconds.

[0196] In the above embodiment, the driving behavior evaluation index includes three dimensions: ADAS warning, bad driving behavior and driver monitoring system (DMS) alarm, and each dimension contains multiple specific evaluation indicators. This systematic evaluation system covers all aspects that affect driving safety, which helps to more accurately evaluate driving behavior and identify potential safety issues.

[0197] See also Figure 7 The embodiment of the present application further provides a driving behavior data processing device 700, and the driving behavior data processing device 700 includes:

[0198] The characteristic data acquisition module 710 is used to obtain the driving behavior characteristic data of the current driving behavior on multiple preset category indicators; wherein the importance coefficient corresponding to each preset category indicator constitutes a distribution matrix;

[0199] A level value interval determination module 720, for determining level value intervals corresponding to each of a plurality of driving behavior levels for each preset category indicator;

[0200] The correlation matrix calculation module 730 is used to perform correlation calculation based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level to obtain an indicator level correlation matrix; wherein the elements of the indicator level correlation matrix are used to characterize the correlation degree between each preset category indicator and each driving behavior level;

[0201] A comprehensive correlation degree acquisition module 740 is used to summarize the correlation degree at each driving behavior level based on the allocation matrix and the indicator level correlation matrix to obtain a comprehensive correlation degree at each driving behavior level;

[0202] The evaluation data determination module 750 is used to normalize the comprehensive correlation degree at each driving behavior level to determine the safety evaluation data of the current driving behavior.

[0203] In some embodiments, the driving behavior data processing device 700 further includes an allocation matrix determination module, which includes an importance coefficient determination module and an allocation matrix construction module:

[0204] The importance coefficient determination module is used to determine the empirical coefficient and statistical coefficient of each preset category indicator, and then perform coupling processing based on the empirical coefficient and statistical coefficient of each preset category indicator to obtain the importance coefficient of each preset category indicator;

[0205] The allocation matrix construction module is used to construct an allocation matrix based on the importance coefficient of each preset category indicator.

[0206] In some embodiments, the driving behavior data processing device 700 further includes an empirical coefficient determination module, which includes a sorting module, an importance scale determination module, and an objective weight calculation module:

[0207] A sorting module is used to sort each preset category indicator to obtain a sorting result;

[0208] An importance scale determination module is used to determine the importance scale between two adjacent preset category indicators in the sorting result;

[0209] The objective weight calculation module is used to perform objective weight calculation based on the importance scale to obtain the empirical coefficient.

[0210] In some embodiments, the driving behavior data processing device 700 further includes a level sample data acquisition module and a value interval determination module:

[0211] A sample data acquisition module is used to acquire driving behavior sample data, perform box plot analysis on the driving behavior sample data, and obtain the boundary value of each driving behavior level;

[0212] The level value interval determination module is used to determine the level value intervals corresponding to multiple driving behavior levels based on the boundary value of each driving behavior level.

[0213] In some implementations, the feature data acquisition module 710 further includes an outlier processing module, a filtering processing module, and a feature value calculation module:

[0214] An outlier processing module is used to delete outliers and fill missing values ​​in the initial driving behavior data to obtain processed driving data;

[0215] A filtering processing module, used for performing mean filtering on the processed driving data to obtain filtered driving data;

[0216] The characteristic value calculation module is used to calculate the characteristic value of the filtered driving data according to each preset category index to obtain driving behavior characteristic data.

[0217] In some embodiments, the driving behavior data processing device 700 also includes an importance coefficient determination module, which is used to determine the first level coefficient on the upper-level indicator and the second level coefficient on each preset category indicator, and to perform level correction on the second level coefficient on each preset category indicator based on the first level coefficient to obtain the importance coefficient corresponding to each preset category indicator.

[0218] In some embodiments, the driving behavior data processing device 700 further includes an upper-level indicator module, which includes an ADAS warning indicator module, a bad driving behavior indicator module, and a DMS alarm indicator module;

[0219] ADAS warning indicator modules include forward collision warning, lane departure warning, AEBS warning and pedestrian collision warning;

[0220] The bad driving behavior indicator module includes speeding percentage, night driving percentage, seat belt, frequent speed change percentage, accelerator pedal standard deviation and brake pedal standard deviation;

[0221] The DMS alarm indicator modules include yawning, closing eyes, making phone calls, smoking, lowering head, looking around, and leaving the post.

[0222] In the above embodiment, the driving behavior evaluation index covers three dimensions: ADAS warning, bad driving behavior and driver monitoring system (DMS) alarm. Each dimension contains multiple evaluation indicators, which comprehensively reflect all aspects that affect driving safety. Through this systematic evaluation system, driving behavior can be evaluated more accurately and safety issues can be identified.

[0223] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0224] The driving behavior data processing device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0225] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0226] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0227] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0228] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0229] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0230] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0231] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0232] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0233] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0234] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0235] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0236] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0237] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0238] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0239] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0240] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0241] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0242] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0243] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for processing driving behavior data, characterized in that: The method comprises: Acquire driving behavior characteristic data of the current driving behavior on multiple preset category indicators; wherein the importance coefficient corresponding to each preset category indicator constitutes a distribution matrix; For each preset category indicator, determining the level value intervals corresponding to the multiple driving behavior levels; Performing correlation calculation based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level to obtain an indicator level correlation matrix; wherein the elements of the indicator level correlation matrix are used to characterize the correlation degree between each preset category indicator and each driving behavior level; Summarizing the correlation degree at each driving behavior level based on the allocation matrix and the indicator level correlation matrix to obtain a comprehensive correlation degree at each driving behavior level; The comprehensive correlation degree at each driving behavior level is normalized to determine the safety assessment data of the current driving behavior.

2. The method according to claim 1, characterized in that The allocation matrix is ​​determined by: Determine the empirical coefficient and the statistical coefficient for each of the preset category indicators; Based on the empirical coefficient and the statistical coefficient of each preset category indicator, coupling processing is performed to obtain the importance coefficient of each preset category indicator; The allocation matrix is ​​constructed based on the importance coefficient of each preset category indicator.

3. The method according to claim 1, characterized in that The empirical coefficients for each of the preset category indicators are determined in the following manner: Sorting each of the preset category indicators to obtain a sorting result; Determining the importance scale between two adjacent preset category indicators in the sorting result; An objective weight calculation is performed based on the importance scale to obtain the empirical coefficient.

4. The method according to claim 1, characterized in that: The multiple driving behavior levels include a low-risk level, a medium-risk level, a second-highest-risk level, and a high-risk level; The step of determining the level value ranges corresponding to the multiple driving behavior levels for each preset category indicator includes: Acquire driving behavior sample data, perform box plot analysis on the driving behavior sample data, and obtain boundary values ​​for each driving behavior level; The level value intervals corresponding to each of the multiple driving behavior levels are determined based on the boundary value of each driving behavior level.

5. The method according to claim 1, characterized in that The step of obtaining driving behavior characteristic data of the current driving behavior on multiple preset category indicators includes: Acquiring initial driving behavior data of the current driving behavior; Deleting outliers and filling missing values ​​on the initial driving behavior data to obtain processed driving data; Performing mean filtering on the processed driving data to obtain filtered driving data; The characteristic value of the filtered driving data is calculated according to each preset category index to obtain the driving behavior characteristic data.

6. The method according to claim 1, characterized in that Each of the preset category indicators has a superior indicator; the importance coefficient corresponding to each of the preset category indicators is determined by the following method: Determine a first level coefficient on the upper level indicator and a second level coefficient on each of the preset category indicators; Based on the first level coefficient, the second level coefficient on each preset category indicator is level-corrected to obtain the importance coefficient corresponding to each preset category indicator.

7. The method according to claim 1, characterized in that Superior indicators include ADAS warnings, bad driving behavior, and DMS alarms; The ADAS warning includes forward collision warning, lane departure warning, AEBS warning and pedestrian collision warning; The bad driving behaviors include speeding percentage, night driving percentage, seat belt usage, frequent gear changes, accelerator pedal standard deviation, and brake pedal standard deviation; The DMS alarms include yawning, closing eyes, talking on the phone, smoking, lowering the head, looking around, and leaving the post.

8. A driving behavior data processing device, characterized in that: The device comprises: A feature data acquisition module is used to acquire driving behavior feature data of the current driving behavior on multiple preset category indicators; wherein the importance coefficient corresponding to each preset category indicator constitutes a distribution matrix; A level value interval determination module, used to determine the level value intervals corresponding to each of the multiple driving behavior levels for each preset category indicator; A correlation matrix calculation module, used to perform correlation calculation based on the driving behavior characteristic data of each preset category indicator and the level value interval corresponding to each driving behavior level, to obtain an indicator level correlation matrix; wherein the elements of the indicator level correlation matrix are used to characterize the degree of correlation between each preset category indicator and each driving behavior level; A comprehensive correlation degree acquisition module, used for summarizing the correlation degree at each driving behavior level based on the allocation matrix and the indicator level correlation matrix to obtain the comprehensive correlation degree at each driving behavior level; The evaluation data determination module is used to normalize the comprehensive correlation degree at each driving behavior level to determine the safety evaluation data of the current driving behavior.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images