Driving behavior normative evaluation method, device, equipment, medium and vehicle

By linearly normalizing and nonlinearly transforming driving behavior indicators, the standardization of drivers' driving behavior is comprehensively evaluated, solving the problem that existing technologies cannot fully reflect the overall compliance of drivers and reducing the probability of traffic accidents.

CN115762130BActive Publication Date: 2024-11-26BEIJING CHEHEJIA AUTOMOBILE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211235551.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-10-10
Publication Date
2024-11-26
Estimated Expiration
2042-10-10

AI Technical Summary

Technical Problem

Existing technologies cannot comprehensively reflect the overall compliance of drivers' behavior, leading to an increased probability of traffic accidents.

Method used

By performing linear normalization and weighted summation on multiple driving behavior indicators, followed by nonlinear transformation, driving behavior normative data are determined, and the driving behavior normativeness of drivers is comprehensively evaluated.

Benefits of technology

It enables a comprehensive evaluation of driving behavior, which can intuitively reflect the correlation between driving behavior and traffic accidents, thereby reducing the probability of accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115762130B_ABST
    Figure CN115762130B_ABST
Patent Text Reader

Abstract

The disclosed embodiment provides a driving behavior normative evaluation method, device, equipment, medium and vehicle, and the normative data method includes: determining multiple target driving behavior indicators according to target signal data, performing linear normalization processing on each target driving behavior indicator, and determining normalized data corresponding to each target driving behavior indicator; performing weighted summation according to the normalized data corresponding to each target driving behavior indicator and weight, and determining linear indicator data; performing nonlinear transformation on the linear indicator data, and determining nonlinear indicator data; determining driving behavior normative data according to the nonlinear indicator data, and the driving behavior normative data is used to evaluate the normativeness of the target driver's driving behavior. The normative data obtained based on this solution can intuitively warn the driver of the danger of driving behavior, so that the driver can adjust his driving behavior and reduce the probability of traffic accidents.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle data processing, and in particular to a driving behavior normative evaluation method, device, equipment, medium and vehicle. Background Art

[0002] During vehicle driving, whether the driver's driving behavior is compliant and reasonable has an inverse correlation with the probability of road traffic accidents. In order to evaluate the standardization of the driver's driving behavior, the existing technology mostly estimates the driver's driving intensity, road condition prediction ability and driving behavior randomness based on driving speed, rapid acceleration and deceleration data and steering data, and then obtains various corresponding normative evaluation data. However, the evaluation data obtained by the above method is only related to a specific driving behavior, and does not comprehensively reflect the driver's overall behavioral compliance. The data obtained cannot intuitively warn the driver, which may increase the probability of traffic accidents. Summary of the invention

[0003] In order to solve the above technical problems, the embodiments of the present disclosure provide a driving behavior normative evaluation method, device, equipment, medium and vehicle.

[0004] In a first aspect, an embodiment of the present disclosure provides a driving behavior normative evaluation method, comprising:

[0005] Determining a plurality of target driving behavior indicators according to the target signal data, wherein the target signal data is signal data characterizing the driving behavior of the target driver, and the target driving behavior indicator is a driving behavior indicator characterizing the driving behavior characteristics of the target driver;

[0006] Performing linear normalization processing on each target driving behavior indicator to determine normalized data corresponding to each target driving behavior indicator;

[0007] Determine linear index data by performing weighted summation based on normalized data and weights corresponding to each target driving behavior index;

[0008] Perform nonlinear transformation on linear indicator data to determine nonlinear indicator data;

[0009] The driving behavior normative data is determined according to the nonlinear index data, and the driving behavior normative data is used to evaluate the normativeness of the driving behavior of the target driver.

[0010] Optionally, performing a nonlinear transformation on the linear indicator data to determine the nonlinear indicator data includes:

[0011] Determining a transformation index of an exponential function according to the linear index data;

[0012] The transformation index is used as an exponent of an exponential function to perform a nonlinear transformation to determine the nonlinear index data, wherein the base value of the exponential function is greater than one.

[0013] Optionally, before performing weighted summation according to the normalized data and weights corresponding to each target driving behavior indicator to determine the linear indicator data, the method further includes:

[0014] According to the pairwise importance ratios of each target driving behavior indicator, a pairwise comparison matrix is ​​constructed;

[0015] The tomographic analysis method is used to process the pairwise comparison matrix to determine the weights corresponding to each target driving behavior indicator.

[0016] Optionally, before performing weighted summation according to the normalized data corresponding to each target driving behavior indicator and the preset weight to determine the linear indicator data, the method further includes:

[0017] Acquire multiple groups of sample indicators, each group of sample indicators includes a driving behavior indicator characterizing the driving behavior of the sample driver;

[0018] The entropy weight method is used to process the sample indicators of each group and determine the weight corresponding to each target driving behavior indicator.

[0019] Optionally, before performing linear normalization processing on each target driving behavior indicator and determining normalized data corresponding to each target driving behavior indicator, the method further includes:

[0020] Obtain historical behavior indicators corresponding to each target driving behavior indicator;

[0021] Screening is performed according to the historical behavior indicators corresponding to each target driving behavior indicator to determine the corresponding maximum historical behavior indicator and minimum historical behavior indicator, wherein the maximum historical behavior indicator is a larger historical behavior indicator whose confidence meets the preset requirements;

[0022] Perform linear normalization processing on each target driving behavior indicator to determine the normalized data corresponding to each target driving behavior indicator, including:

[0023] Based on the maximum historical behavior indicator and the minimum historical behavior indicator corresponding to each target driving behavior indicator, the target driving behavior indicator is linearly normalized to determine the normalized data corresponding to each target driving behavior indicator.

[0024] Optionally, the target signal data includes first target signal data and second target signal data, the first target signal data is signal data obtained when the target driver manually drives the vehicle, and the second target data is signal data obtained when the target driver turns on the assisted driving function to drive the vehicle;

[0025] Determining a plurality of target driving behavior indicators according to the target signal data includes: determining a plurality of first target driving behavior indicators according to the first signal data, and determining a plurality of second target driving behavior indicators according to the second signal data;

[0026] Determining linear index data by weighted summing the normalized data and weights corresponding to each target driving behavior index, including: determining first linear index data by weighted summing the normalized data and weights corresponding to the first target driving behavior index; and determining second linear index data by weighted summing the normalized data and weights corresponding to the second target driving behavior index;

[0027] Performing a nonlinear transformation on the linear index data to determine the nonlinear index data includes: performing a nonlinear transformation on the first linear index data to determine the first nonlinear index data; and performing a nonlinear transformation on the second linear index data to determine the second nonlinear index data;

[0028] Determining driving behavior normative data according to nonlinear index data includes: fusing first nonlinear index data and second nonlinear index data to determine driving behavior normative data.

[0029] Optionally, before fusing the first nonlinear index data and the second nonlinear index data to determine the driving behavior normative data, the method further includes:

[0030] Determine a first driving distance and a second driving distance, the first driving distance being a distance traveled by manual driving of the vehicle, and the second driving distance being a distance traveled by the vehicle with assisted driving turned on;

[0031] Calculate the distance sum value of the first driving distance and the second driving distance;

[0032] Calculating a manual driving ratio according to the first driving distance and the distance sum value, and calculating an assisted driving ratio according to the second driving distance and the distance sum value;

[0033] The first nonlinear index data and the second nonlinear index data are integrated to determine the driving behavior normative data, including:

[0034] Calculate the manual driving normative data according to the first nonlinear indicator data and the manual driving ratio;

[0035] Calculate the assisted driving normative data based on the second nonlinear indicator data and the assisted driving ratio;

[0036] The sum of the manual driving normative data and the assisted driving normative data is obtained as the driving behavior normative data.

[0037] Optionally, before fusing the first nonlinear index data and the second nonlinear index data to determine the driving behavior normative data, the method further includes:

[0038] Mapping the first nonlinear index data into a percentage system to obtain the mapped first nonlinear index data;

[0039] Mapping the second nonlinear index data into a percentage system to obtain mapped second nonlinear index data;

[0040] The first nonlinear index data and the second nonlinear index data are integrated to determine the driving behavior normative data, including:

[0041] The mapped first nonlinear index data and the mapped second nonlinear index data are fused to determine driving behavior normative data.

[0042] In a second aspect, an embodiment of the present disclosure provides a driving behavior normativeness evaluation device, comprising:

[0043] a target driving behavior index determination unit, configured to determine a plurality of target driving behavior indexes according to target signal data, wherein the target signal data is signal data characterizing the driving behavior of the target driver, and the target driving behavior index is a target driving behavior index characterizing the driving behavior characteristics of the target driver;

[0044] A normalization unit, used to perform linear normalization processing on each target driving behavior indicator to determine normalized data corresponding to each target driving behavior indicator;

[0045] A linear index data acquisition unit, used for performing weighted summation according to normalized data and weights corresponding to each target driving behavior index to determine linear index data;

[0046] A nonlinear transformation unit, used for performing nonlinear transformation on the linear index data to determine the nonlinear index data;

[0047] The normative data determination unit is used to determine driving behavior normative data according to the nonlinear index data, and the driving behavior normative data is used to evaluate the normativeness of the driving behavior of the target driver.

[0048] In a third aspect, an embodiment of the present disclosure provides a computing device, including a processor and a memory, wherein the memory is used to store a computer program;

[0049] When the computer program is loaded by the processor, the processor executes the above-mentioned driving behavior normative evaluation method.

[0050] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program. When the computer program is executed by a processor, the processor implements the aforementioned driving behavior normative evaluation method.

[0051] In a fifth aspect, an embodiment of the present disclosure provides a vehicle, including an on-board control chip, and the on-board control chip is used to execute the above-mentioned driving behavior normative evaluation method.

[0052] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0053] By adopting the scheme provided by the embodiment of the present disclosure, multiple target driving behavior indicators are determined according to the target signal data, and the target driving behavior indicators are normalized and summed to obtain linear indicator data, and then the linear indicator data is nonlinearly changed to obtain nonlinear indicator data, so as to use the nonlinear indicator data to determine the driving behavior normative data. By comprehensively processing multiple driving behavior indicators to obtain linear indicator data and nonlinear indicator data, the compliance of driving behaviors represented by multiple driving behavior indicators is integrated, and then the direct correlation between each driving behavior and the occurrence of road traffic accidents can be intuitively and comprehensively reflected, and then the driver can be intuitively warned of the danger of driving behavior, so that the driver can adjust the driving behavior and reduce the probability of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work, including:

[0056] Figure 1 is a flow chart of a driving behavior normativeness evaluation method provided by an embodiment of the present disclosure;

[0057] Figure 2 is a flow chart of a method for normalizing a target driving behavior index provided by an embodiment of the present disclosure;

[0058] Figure 3 is a schematic diagram of the structure of a driving behavior normativeness evaluation device provided by an embodiment of the present disclosure;

[0059] Figure 4 It is a schematic diagram of the structure of a computing device provided in some embodiments of the present disclosure. DETAILED DESCRIPTION

[0060] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0061] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0062] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0063] The disclosed embodiment provides a method for evaluating the normativeness of driving behavior, which realizes normative data that can more reasonably characterize the normativeness of the driver's driving behavior.

[0064] Figure 1 : is a flow chart of the driving behavior normative evaluation method provided by the embodiment of the present disclosure. Figure 1 As shown, the method provided by the embodiment of the present disclosure includes S110-S150.

[0065] It should be noted that the driving behavior normative evaluation method provided in the embodiment of the present disclosure is executed by a computing device. The aforementioned computing device can be an electronic device such as a vehicle's onboard system, a user's smart phone terminal, or a remote server connected to the vehicle's onboard system that can obtain target signal data. The aforementioned remote server can be a remote server maintained by the host manufacturer, or a factoring company that opens a car insurance business, etc.

[0066] S110: Determine a plurality of target driving behavior indicators according to the target signal data.

[0067] The target signal data is signal data collected by the vehicle sensor or the control system of the vehicle configuration when the target driver is driving the vehicle and is used to characterize the driving behavior of the target driver.

[0068] In actual implementation, the target signal data may be various types of data, such as acceleration sensor data, speed sensor data, camera data, or some auxiliary driving sensor data. In addition, the target signal data or auxiliary operation data fed back by the auxiliary driving system to assist the target driver in driving, correcting erroneous driving behavior, or avoiding accidents.

[0069] The target driving behavior index is a driving behavior index used to characterize the driving behavior characteristics of the target driver. The aforementioned driving behavior index is some indexes used to characterize the degree of standardization and aggressiveness of the driver's driving of the vehicle and the correlation with the occurrence of accidents.

[0070] However, it should be noted that the number of target driving behavior indicators determined according to the target signal data is multiple, specifically two or more.

[0071] S120: Performing linear normalization processing on each target driving behavior indicator to determine normalized data corresponding to each target driving behavior indicator.

[0072] After obtaining each driving behavior indicator, the computing device then normalizes each driving behavior indicator to determine the normalized data corresponding to each driving behavior indicator. The goal of normalizing each target driving behavior indicator is to make it easier to compare each target driving behavior indicator horizontally and to compare the driving behavior characteristics of the target driver with those of other drivers.

[0073] It should be noted that when normalizing each target driving behavior index, it should be ensured that each target driving behavior index represents the standard degree of the target driver's driving of the vehicle in the same order of magnitude change. For example, when each normalized data is a 0-1 point system, 0 can be used to represent that the target driver's driving behavior is strictly standard, and 1 can be used to represent that the target driver's driving behavior is very irregular.

[0074] Figure 2 FIG. 1 is a flow chart of a method for normalizing a target driving behavior index provided by an embodiment of the present disclosure. Figure 2 As shown, the method for normalizing the target driving behavior index includes S121-S123.

[0075] S121: Obtain historical behavior indicators corresponding to each target driving behavior indicator.

[0076] It should be noted that the historical behavior indicators corresponding to each target driving behavior indicator include not only the historical behavior indicators of the target driver, but also the historical behavior indicators of other drivers.

[0077] In a specific implementation, the computing device may send a data query request to the database server to obtain the historical behavior indicators corresponding to each target driving behavior indicator.

[0078] S122: Screening is performed according to the historical behavior indicators corresponding to each target driving behavior indicator to determine the corresponding maximum historical behavior indicator and minimum historical behavior indicator.

[0079] After obtaining the historical behavior indicators corresponding to each target driving behavior indicator, the computing device may filter the historical behavior indicators to determine the maximum historical behavior indicator and the minimum behavior indicator. In a specific embodiment, the computing device may use a data sorting method such as a bubble method to determine the maximum historical behavior indicator and the minimum historical behavior indicator by comparing data.

[0080] In the disclosed embodiment, the maximum historical behavior indicator is a larger historical behavior indicator whose confidence meets the preset requirements. For example, the indicator ranked at the 0.95 ratio position among all historical behavior indicators can be used as the maximum historical behavior indicator, or the larger historical behavior indicator determined by the mean and six times the standard deviation can be used as the maximum historical behavior indicator. By setting the confidence to filter the maximum historical behavior indicator, some historical behavior indicators determined based on abnormal data generated by sensor data errors can be excluded.

[0081] It should be noted that, in actual applications, the aforementioned S121-S122 may not be executed by the computing device, but by other devices, such as the database server mentioned above. That is, the database server only sends the maximum historical behavior indicator and the minimum historical behavior indicator to the computing device, but does not send the historical behavior indicator. In this way, data security can be better guaranteed to avoid sensitive data leakage.

[0082] S123: Based on the maximum historical behavior indicator and the minimum historical behavior indicator corresponding to each target driving behavior indicator, the target driving behavior indicator is normalized to determine normalized data corresponding to each target driving behavior indicator.

[0083] After obtaining the maximum historical behavior index and the minimum historical behavior index, the target driving behavior index can be normalized according to the maximum historical behavior index and the minimum historical behavior index. or Determine the normalized data x′, where x in the above formula is the target driving behavior index, x max is the maximum historical behavior indicator, xmin is the minimum historical behavior index. In specific implementation, which of the above formulas is used by the computing device needs to be determined according to the data meaning of the target driving behavior index and how to define the meaning of the normalized data. For example, if the larger the x, the worse the target driver's driving standardization, and the normalization method uses large data to represent the poor driving standardization of the target driver, then

[0084] S130: Determine linear index data by performing weighted summation based on the normalized data and weights corresponding to each target driving behavior index.

[0085] While obtaining the normalized data corresponding to the target driving behavior index, the computing device may also obtain the weight corresponding to the target driving behavior index.

[0086] In actual applications, the weights corresponding to the various target driving behavior indicators may be manually set weights, or weights calculated using a specific calculation method, which is not limited in the embodiments of the present disclosure.

[0087] In the embodiment of the present disclosure, the computing device may use the formula y=w1x1′+w2x2′+…+w n x n ′Determine the linear indicator data, where w i represents the weight corresponding to the target driving behavior index, x i ′ represents the normalized data corresponding to the target driving behavior index, and n represents the number of target driving behavior indicators.

[0088] As before, because the normalization operation of the target driving behavior index in the previous article is linear normalization, calculating the linear index data based on each normalized data is a linear operation, so that the linear index data can only linearly represent the driving behavior normativeness of the target driving behavior.

[0089] However, the probability of an accident caused by a driving behavior corresponding to the driving behavior normativeness represented by certain target driving behavior indicators is indeed nonlinear, and the stronger the non-normativity corresponding to the target driving behavior indicator, the greater the probability of an accident caused by the corresponding driving behavior. In order to make the data representing the driving behavior normativeness of the target driver determined in the end more intuitively reflect the probability of the accident caused by the driving behavior, the computing device executes the following S150.

[0090] S140: Perform nonlinear transformation on the linear index data to determine the nonlinear index data.

[0091] The computing device may use various possible methods to perform nonlinear changes on the linear index data to determine the nonlinear index data. In a specific implementation, the nonlinear method used by the computing device to perform nonlinear transformation on the linear index data may be determined based on the corresponding relationship between the linear index data and the probability of an accident caused by the target driver's driving behavior. In the following, some solutions that may be used in this embodiment are introduced.

[0092] S150: Determine driving behavior normative data according to the nonlinear indicator data.

[0093] After determining the nonlinear index data, the computing device may determine the driving behavior normativeness data according to the nonlinear index data. The driving behavior normativeness data may be used to evaluate the normativeness of the target driver's driving behavior.

[0094] In some embodiments of the present disclosure, the computing device may directly use the nonlinear index data as the normative data of driving behavior; in other embodiments of the present disclosure, in slightly more complicated situations, the computing device may determine the normative data of driving behavior based on the nonlinear index data according to the specific situation.

[0095] As mentioned above, the driving behavior normativeness evaluation method provided in the embodiment of the present disclosure determines multiple target driving behavior indicators based on target signal data, normalizes the target driving behavior indicators and sums them to obtain linear indicator data, and then performs nonlinear changes on the linear indicator data to obtain nonlinear indicator data, so as to use the nonlinear indicator data to determine the driving behavior normativeness data. By comprehensively processing multiple driving behavior indicators to obtain linear indicator data and nonlinear indicator data, the driving behavior compliance represented by multiple driving behavior indicators is integrated, and then the direct correlation between each driving behavior and the occurrence of road traffic accidents can be intuitively and comprehensively reflected, and then the driver can be intuitively warned of the danger of driving behavior, or it can be used as an intuitive basis for factoring companies to determine the price of vehicle accident insurance.

[0096] The above S140 mentioned that the linear indicator data is nonlinearly transformed to determine the nonlinear indicator data. In some embodiments of the present disclosure, when executing S140, the computing device can determine the transformation index of the exponential function based on the linear indicator data; use the transformation index as the exponent of the exponential function to perform a nonlinear transformation to determine the nonlinear indicator data, wherein the base value of the exponential function is greater than one. According to the mathematical characteristics of the exponential function and the setting of the base value, the aforementioned method can make the nonlinear indicator data determined based on the linear indicator data larger in data sparsity than the linear indicator data, thereby making the final driving behavior normative data more indicative of the probability of an accident.

[0097] As described above, the weight used in S130 can be obtained by using a calculation method. The following describes how to use a calculation method to determine the weight corresponding to the target driving behavior indicator.

[0098] In some embodiments of the present disclosure, the method for determining weights includes S131 - S132 .

[0099] S131: Construct a pairwise comparison matrix according to the pairwise importance ratios of the target driving behavior indicators.

[0100] In the disclosed embodiment, the pairwise importance ratios of the target driving behavior indicators are ratios determined by professional technicians based on experience and the importance of each target driving behavior indicator. After obtaining the pairwise importance ratios, the pairwise importance ratios are placed into a matrix according to a preset matrix size, and a pairwise comparison matrix can be constructed.

[0101] S132: Process the paired comparison matrix using a tomographic analysis method to determine the weight corresponding to each target driving behavior indicator.

[0102] In the disclosed embodiment, the analytic hierarchy process is used to determine the weight corresponding to the target driving behavior indicator. First, a hierarchical structure of the indicator system is constructed. Generally, a structure including three levels is constructed, and the three levels are the target level, the criterion level, and the execution level. Subsequently, the relative weights of each layer are calculated based on the pairwise comparison matrix and the results are checked for consistency. If the consistency check passes, each data item in the determined weight vector can be used as the weight corresponding to the corresponding target driving behavior indicator. If the consistency check does not pass, it is determined that there is a logical conflict in the setting of the pairwise importance ratio. At this time, the computing device can prompt professional and technical personnel to modify the pairwise importance ratio.

[0103] The use of hierarchical analysis method can combine the experience characteristics of professional and technical personnel, and combine qualitative analysis and quantitative analysis methods, so that the setting of weights is more objective and reasonable and meets the expected judgment purpose.

[0104] In some other embodiments of the present disclosure, the method for determining the weight includes S133-S134.

[0105] S133: Acquire multiple groups of sample indicators, each group of sample indicators includes a driving behavior indicator that characterizes the driving behavior of the sample driver.

[0106] S134: Using the entropy weight method to process each group of sample indicators, and determine the weight corresponding to each target driving behavior indicator.

[0107] The entropy weight method is a method that uses information entropy to calculate the entropy weight of each indicator according to the degree of dispersion of each indicator data, and then makes certain corrections to the entropy weight according to each indicator to obtain the weight of each indicator.

[0108] In order to use the entropy weight method to determine the weight corresponding to each target driving behavior indicator, it is necessary to obtain multiple groups of sample indicators in the embodiment of the present disclosure, so as to use the dispersion status of the driving behavior indicators in each group of sample indicators to determine the information entropy contained therein, and then use the information entropy to determine the weight corresponding to each driving behavior indicator.

[0109] Because the entropy weight method is a method for objectively determining weights, the weights corresponding to the target driving behavior indicators obtained by using S133-S134 are more objective. In addition, the aforementioned weights determined by the entropy weight method can also calculate the comprehensive weights corresponding to the target driving behavior indicators, and then the obtained weights can be corrected using the comprehensive weights, so that the final weights have better adaptability.

[0110] As described above, in S110, a plurality of target driving behavior indicators are determined according to the target signal data. The following is an analysis of how to determine the target driving behavior indicators according to the target signal data.

[0111] In some embodiments of the present disclosure, the target signal data includes first target signal data and second target signal data. The first target signal data is signal data obtained when the target driver manually drives the vehicle, and the second target signal data is signal data obtained when the target driver turns on the assisted driving function to drive the vehicle.

[0112] In some embodiments, the first target signal data may include at least two of the following: acceleration data, speed data, turn signal activation data, steering wheel grip, driving time data, driver status image, and the number of times the assisted driving function is activated, etc., collected when the target driver is driving the vehicle. The driver status image is an image captured by a driving status camera, and the assisted driving functions include forward collision warning (FCW) and automatic emergency braking (AEB).

[0113] In a case where the first target signal data includes the aforementioned data, determining the target driving behavior index according to the target signal data may include: determining a plurality of first target driving behavior indexes according to the first signal data.

[0114] The first target driving behavior indicator may include at least two of the proportion of sudden deceleration times, the proportion of sharp turns, the average acceleration within 5 seconds of starting, the proportion of lane changes without turning on the lights, the hands-off driving indicator, the fatigue driving indicator, the high-speed speeding distance ratio, and the number of times the unit assisted driving function is triggered.

[0115] The ratio of rapid deceleration times is the ratio of the number of times when the longitudinal deceleration is greater than the first set value to the total number of times when the speed is greater than the preset speed. In practical applications, the preset speed may be 20 km / h, and the first set value may be 0.3 g (i.e., 0.3 gravitational acceleration).

[0116] The sharp turn times ratio is the ratio of the number of times when the lateral acceleration is greater than the second set value to the total number of times when the speed is greater than the preset speed and the steering wheel angle is greater than the preset angle. The aforementioned preset angle can be 75°, and the aforementioned second set value can be 0.4g.

[0117] The average acceleration within 5 seconds of starting is the average value of the speed within 5 seconds of starting, which can be obtained by integrating and averaging the acceleration data, or calculated by the counting frequency of the wheel end counter.

[0118] The proportion of lane changes without turning on the turn signal is the ratio of the number of times the turn signal is not turned on when changing lanes to the total number of lane changes.

[0119] The hands-off flag is a flag that indicates that the speed is greater than a preset speed and the duration of the steering wheel grip signal being 0 exceeds a preset duration. In the disclosed embodiment, if the speed is greater than the preset speed and the duration of the steering wheel grip signal being 0 exceeds 20 seconds, it is determined that the hands-off flag has occurred. If the hands-off flag has occurred, the hands-off flag is 1; if the hands-off flag has not occurred, the hands-off flag is 0.

[0120] The fatigue driving flag is used to indicate whether the driver is in a fatigue driving state. In some embodiments, if the driving time exceeds a preset time, fatigue driving is determined. In other embodiments, when a driver camera is set, if the driver is determined to be in a fatigue driving state through image analysis, fatigue driving is determined. If fatigue driving is determined, the fatigue driving flag is set to 1; if not in a fatigue driving state, the fatigue driving flag is set to 0.

[0121] The highway speeding distance ratio is used to characterize the distance ratio when driving over a set speed on a highway. The set speed can be determined based on the highway speed limit*1.2.

[0122] The number of times the auxiliary driving function is triggered per unit distance is used to characterize the number of times the forward collision warning or automatic emergency braking is turned on in a unit distance, and the aforementioned unit distance can be 100km. In a specific embodiment, since the forward collision warning is a preceding auxiliary driving function of the automatic emergency braking, multiple forward collision warnings generally occur before the automatic emergency braking is turned on, so in actual application, the following formula can be used to determine the number of times the auxiliary driving function is triggered per unit distance, t = (0.4 × a + 0.6 × b) / d × 100, where t is the number of times the auxiliary driving function is triggered per unit distance, a is the number of forward collision warnings, b is the number of times the automatic emergency braking is turned on, and d is the driving distance.

[0123] In some embodiments, the second target signal data may include acceleration data, steering wheel grip, seat angle, and driver status image collected when the assisted driving function is turned on. The driver status image is an image captured by a driving status camera.

[0124] In the case where the second target signal data includes the aforementioned data, determining the target driving behavior index according to the target signal data may include: determining a plurality of second target driving behavior indexes according to the second signal data. The second target driving behavior index may include at least two of the percentage of rapid acceleration times, the number of hands-off warnings per unit, the percentage of seat reclining time, and the number of fatigue times per unit distance.

[0125] The percentage of rapid acceleration times is used to represent the ratio of the number of times when the longitudinal deceleration is greater than the first set value to the total number of times when the speed is greater than the preset speed. Rapid acceleration occurs when the assisted driving function is turned on because the driver actively steps on the accelerator pedal to control the vehicle's acceleration. If rapid acceleration occurs, it means that the target driver temporarily takes over the vehicle's acceleration control.

[0126] The number of hands-off warnings per unit is the number of hands-off warnings that occur per unit driving distance. In the assisted driving state, the target driver is required to take over the vehicle at any time. If a hands-off warning appears, it means that the target driver has been hands-off for a long time and cannot take over the vehicle at any time.

[0127] The seat down time ratio is used to represent the ratio of the seat down time exceeding the preset time to the driving time. When assisted driving is turned on, the driver may adjust the seat to the maximum flat angle, and then drive as flat as possible. However, lying down while driving reduces the driver's field of vision and the immediacy of control. Therefore, the standardization of the driver's driving behavior can be judged by the seat down time ratio.

[0128] The fatigue times per unit distance is used to represent the unitized value of the fatigue times of the target driver during the assisted driving. The fatigue times can be determined according to the driver status image.

[0129] Corresponding to the aforementioned determination of the first target driving behavior indicator and the second target driving behavior indicator, S120 performs linear normalization processing on each target driving behavior indicator to determine the normalized data corresponding to each target driving behavior indicator, including: performing linear normalization on both the first target driving behavior indicator and the second target driving behavior indicator to determine the corresponding normalized data.

[0130] Correspondingly, S130 performs weighted summation on the normalized data and weights corresponding to each target driving behavior indicator to determine the linear indicator data, including: performing weighted summation on the normalized data and weights corresponding to the first target driving behavior indicator to determine the first linear indicator data; and performing weighted summation on the normalized data and weights corresponding to the second target driving behavior indicator to determine the second linear indicator data.

[0131] After determining the first linear index data and the second linear index data, S140 performs a nonlinear transformation on the linear index data to determine the nonlinear index data, including: performing a nonlinear transformation on the first linear index data to determine the first nonlinear index data; and performing a nonlinear transformation on the second linear index data to determine the second nonlinear index data.

[0132] Furthermore, the nonlinear index data in S150 determines the driving behavior normative data, including S151.

[0133] S151: Fusing the first nonlinear index data and the second nonlinear index data to determine driving behavior normative data.

[0134] In some embodiments of the present disclosure, the first nonlinear index data and the second nonlinear index data may be added together in S151, and the sum of the additions may be used as the driving behavior normative data.

[0135] In actual applications, the driver may decide whether to turn on assisted driving according to actual road conditions, and the proportion of assisted driving use is uncertain. In order to make the driving behavior data obtained by fusion in S150 more consistent with the actual situation, before executing the aforementioned S151, the computing device may also execute S160-S180.

[0136] S160: Determine a first driving distance and a second driving distance, where the first driving distance is a distance traveled by the vehicle manually driven, and the second driving distance is a distance traveled by the vehicle with assisted driving enabled;

[0137] S170: Calculate the sum of the first driving distance and the second driving distance.

[0138] S180: Calculate the manual driving ratio according to the first driving distance and the distance sum value, and calculate the assisted driving ratio according to the second driving distance and the distance sum value.

[0139] The corresponding S151 may include S1511-S1513.

[0140] S1511: Calculating manual driving normative data according to the first nonlinear indicator data and the manual driving ratio;

[0141] S1512: Calculating assisted driving normative data according to the second nonlinear indicator data and the assisted driving ratio;

[0142] S1513: Obtain the sum of the manual driving normative data and the assisted driving normative data as driving behavior normative data.

[0143] After determining the proportion of manual driving and the proportion of assisted driving, the proportion of manual driving is used as the weight of the first non-linear indicator data to calculate the manual driving normative data, and the proportion of assisted driving is used as the weight of the second non-linear indicator data to calculate the assisted driving normative data, and the sum of the manual driving normative data and the assisted driving normative data is used as the driving behavior normative data, so that the driving behavior normative data is more in line with the actual situation.

[0144] Optionally, in some embodiments of the present disclosure, the computing device may further execute S150 before executing the aforementioned 151.

[0145] S150: Mapping the first nonlinear index data to a percentage system to obtain mapped first nonlinear index data; and mapping the second nonlinear index data to a percentage system to obtain mapped second nonlinear index data.

[0146] Correspondingly, the aforementioned S151 specifically fuses the mapped first nonlinear index data and the mapped second nonlinear index data to determine the driving behavior normative data.

[0147] The driving behavior normative data in the foregoing embodiments are comprehensive data that characterize manual driving and when the assisted driving function is turned on. In other embodiments, the driving behavior normative data may also be normative data only under manual driving, or normative data only under the assisted driving function. In a specific implementation, if the driving behavior normative data is normative data under manual driving, the first nonlinear index data can be directly used as the final driving behavior normative data. If the driving behavior normative data is normative data under assisted driving, the second nonlinear index data can be directly used as the final driving behavior normative data.

[0148] In addition to providing the aforementioned driving behavior normative evaluation method, the embodiment of the present disclosure also provides a driving behavior normative evaluation device 300.

[0149] Figure 3Schematic diagram of the structure of the driving behavior normative evaluation device provided by the embodiment of the present disclosure. Figure 3 As shown, the driving behavior normativeness evaluation device 300 includes a target driving behavior index determination unit 301, a normalization unit 302, a linear index data acquisition unit 303, a nonlinear transformation unit 304 and a normative data determination unit 305.

[0150] The target driving behavior index determination unit 301 is used to determine multiple target driving behavior indexes according to target signal data, wherein the target signal data is signal data characterizing the driving behavior of the target driver, and the target driving behavior index is a target driving behavior index characterizing the driving behavior characteristics of the target driver.

[0151] The normalization unit 302 is used to perform linear normalization processing on each target driving behavior indicator to determine normalized data corresponding to each target driving behavior indicator.

[0152] The linear index data acquisition unit 303 is used to perform weighted summation according to the normalized data and weights corresponding to each target driving behavior index to determine the linear index data.

[0153] The non-linear transformation unit 304 is used to perform non-linear transformation on the linear index data to determine the non-linear index data.

[0154] The normative data determining unit 305 is used to determine driving behavior normative data according to the nonlinear index data, and the driving behavior normative data is used to evaluate the normativeness of the target driver's driving behavior.

[0155] In some embodiments of the present disclosure, the nonlinear transformation unit 304 determines a transformation index of an exponential function according to linear index data; uses the transformation index as an exponent of the exponential function for nonlinear transformation to determine the nonlinear index data, wherein the base value of the exponential function is greater than one.

[0156] In some embodiments of the present disclosure, the driving behavior normativeness evaluation device 300 further includes a comparison matrix construction unit and a tomographic analysis weight determination unit. The comparison matrix construction unit constructs a pairwise comparison matrix according to the importance ratios of each target driving behavior indicator; the tomographic analysis weight determination unit processes the pairwise comparison matrix using a tomographic analysis method to determine the weight corresponding to each target driving behavior indicator.

[0157] In some embodiments of the present disclosure, the driving behavior normativeness evaluation device 300 also includes a sample index acquisition unit and an entropy weight determination unit.

[0158] The sample index acquisition unit is used to acquire multiple groups of sample indexes, each group of sample indexes includes a driving behavior index representing the driving behavior of the sample driver;

[0159] The entropy weight determination unit is used to process each group of sample indicators using the entropy weight method to determine the weight corresponding to each target driving behavior indicator.

[0160] In some embodiments of the present disclosure, the driving behavior normativeness evaluation device 300 includes a historical indicator acquisition unit and a historical indicator screening unit. The historical indicator acquisition unit is used to acquire the historical behavior indicators corresponding to each target driving behavior indicator; the historical indicator screening unit is used to screen the historical behavior indicators corresponding to each target driving behavior indicator to determine the corresponding maximum historical behavior indicator and minimum historical behavior indicator, wherein the maximum historical behavior indicator is a larger historical behavior indicator whose confidence meets the preset requirements.

[0161] The normalization unit 302 performs linear normalization processing on the target driving behavior indicators based on the maximum historical behavior indicator and the minimum historical behavior indicator corresponding to each target driving behavior indicator, and determines normalized data corresponding to each target driving behavior indicator.

[0162] In some embodiments of the present disclosure, the target signal data includes first target signal data and second target signal data, the first target signal data is signal data obtained when the target driver manually drives the vehicle, and the second target data is signal data obtained when the target driver turns on the assisted driving function and drives the vehicle.

[0163] The target driving behavior index determination unit 301 determines a plurality of first target driving behavior indexes according to the first signal data, and determines a plurality of second target driving behavior indexes according to the second signal data;

[0164] The linear index data performs weighted summation on the normalized data corresponding to the first target driving behavior index and the weight to determine the first linear index data; and the normalized data corresponding to the second target driving behavior index and the weight to determine the second linear index data;

[0165] The nonlinear transformation unit 304 performs a nonlinear transformation on the first linear index data to determine the first nonlinear index data; and performs a nonlinear transformation on the second linear index data to determine the second nonlinear index data;

[0166] The normative data determining unit 305 fuses the first non-linear index data and the second non-linear index data to determine the driving behavior normative data.

[0167] In some embodiments of the present disclosure, the driving behavior normativeness evaluation device 300 further includes a distance determination unit, a sum value determination unit, and a driving type ratio determination unit. A first driving distance and a second driving distance are determined, the first driving distance is the distance traveled by the vehicle manually driven, and the second driving distance is the distance traveled by the vehicle with assisted driving turned on.

[0168] The sum determination unit is used to calculate a distance sum value of the first driving distance and the second driving distance.

[0169] The driving type ratio determination unit is used to calculate the manual driving ratio according to the first driving distance and the distance sum value, and to calculate the assisted driving ratio according to the second driving distance and the distance sum value.

[0170] The normative data determination includes a manual driving data calculation subunit, an auxiliary driving data calculation subunit and a fusion subunit. The manual driving data calculation subunit is used to calculate the manual driving normative data according to the first nonlinear index data and the manual driving ratio.

[0171] The assisted driving data calculation sub-sheet is used to calculate the assisted driving normative data based on the second non-linear indicator data and the assisted driving ratio.

[0172] The fusion subunit is used to obtain the sum of the manual driving normative data and the assisted driving normative data as the driving behavior normative data.

[0173] In some embodiments of the present disclosure, the driving behavior normativeness evaluation device 300 also includes a percentage mapping unit, which is used to perform percentage mapping on the first nonlinear index data to obtain mapped first nonlinear index data, and to perform percentage mapping on the second nonlinear index data to obtain mapped second nonlinear index data; correspondingly, the fusion subunit fuses the mapped first nonlinear index data and the mapped second nonlinear index data to determine the driving behavior normativeness data.

[0174] Figure 4 is a schematic diagram of the structure of a computing device provided by some embodiments of the present disclosure. Figure 4 , which shows a schematic diagram of the structure of a computing device 400 suitable for implementing the embodiments of the present disclosure. Figure 4 The computing device shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present disclosure.

[0175] like Figure 4 As shown, the computing device 400 may include a processing device 401 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 402 or a program loaded from a storage device 408 to a random access memory RAM 403. Various programs and data required for the operation of the computing device 400 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output I / O interface 405 is also connected to the bus 404.

[0176] Typically, the following devices may be connected to the I / O interface 405: input devices 406 including, for example, a touch screen, a touch pad, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409. The communication devices 409 may allow the computing device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The computing device 400 is shown with various devices, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.

[0177] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0178] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0179] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0180] The computer-readable medium may be included in the computing device, or may exist independently without being incorporated into the computing device.

[0181] The computer-readable medium carries one or more programs. When the one or more programs are executed by the computing device, the computing device: determines multiple target driving behavior indicators based on target signal data, wherein the target signal data is signal data characterizing the driving behavior of the target driver, and the target driving behavior indicator is a driving behavior indicator characterizing the driving behavior characteristics of the target driver; performs linear normalization processing on each target driving behavior indicator to determine the normalized data corresponding to each target driving behavior indicator; performs weighted summation based on the normalized data corresponding to each target driving behavior indicator and the weight to determine the linear indicator data; performs nonlinear transformation on the linear indicator data to determine the nonlinear indicator data; determines the driving behavior normative data based on the nonlinear indicator data, and the driving behavior normative data is used to evaluate the normativeness of the driving behavior of the target driver.

[0182] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0183] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system based on hardware that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0184] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0185] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0186] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection according to one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0187] The embodiments of the present disclosure also provide a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method of any of the above method embodiments can be implemented. The execution method and beneficial effects are similar and will not be repeated here.

[0188] In addition, in a fifth aspect, an embodiment of the present disclosure provides a vehicle, including an on-board control chip and a plurality of interactive display screens, wherein the on-board control chip is used to execute the text input method as described above, and control at least two of the plurality of interactive display screens to independently display a text input interface. The aforementioned on-board control chip may be a central control chip in the vehicle, or an entertainment system control chip independent of the central control chip, or other chips, and the embodiment of the present disclosure does not specifically limit this; preferably, the aforementioned on-board control chip is a control chip specifically used to control the operation of each interactive display screen in the vehicle's intelligent cockpit system.

[0189] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0190] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A driving behavior normative evaluation method, characterized in that: include: Determining a plurality of target driving behavior indicators according to the target signal data, wherein the target signal data is signal data characterizing the driving behavior of the target driver, and the target driving behavior indicators are driving behavior indicators characterizing the driving behavior characteristics of the target driver; Based on the maximum historical behavior indicator and the minimum historical behavior indicator corresponding to each of the target driving behavior indicators, each of the target driving behavior indicators is linearly normalized to determine the normalized data corresponding to each of the target driving behavior indicators; wherein the maximum historical behavior indicator is a historical behavior indicator whose confidence meets the preset requirements; Determine linear index data by performing weighted summation according to normalized data and weights corresponding to each of the target driving behavior indicators; Performing a nonlinear transformation on the linear index data to determine the nonlinear index data; wherein the nonlinear transformation is determined according to a corresponding relationship between the linear index data and the probability of an accident caused by the driving behavior of the target driver; The driving behavior normative data is determined according to the nonlinear index data, and the driving behavior normative data is used to evaluate the normativeness of the driving behavior of the target driver.

2. The method according to claim 1, characterized in that The performing nonlinear transformation on the linear index data to determine the nonlinear index data includes: Determining a transformation index of an exponential function according to the linear index data; The transformation index is used as an exponent of an exponential function to perform a nonlinear transformation to determine the nonlinear index data, wherein the base value of the exponential function is greater than one.

3. The method according to claim 1, characterized in that Before performing weighted summation according to the normalized data and weights corresponding to each of the target driving behavior indicators to determine the linear indicator data, the method further includes: Constructing a pairwise comparison matrix according to the pairwise importance ratios of the target driving behavior indicators; The paired comparison matrix is ​​processed by a tomographic analysis method to determine the weight corresponding to each of the target driving behavior indicators.

4. The method according to claim 1, characterized in that: Before performing weighted summation according to the normalized data and weights corresponding to each target driving behavior index to determine the linear index data, the method further includes: Acquire multiple groups of sample indicators, each group of sample indicators includes a driving behavior indicator characterizing the driving behavior of the sample driver; The entropy weight method is used to process each group of sample indicators to determine the weight corresponding to each target driving behavior indicator.

5. The method according to claim 1, characterized in that Before performing linear normalization processing on each of the target driving behavior indicators to determine normalized data corresponding to each of the target driving behavior indicators, the method further includes: Obtaining historical behavior indicators corresponding to each of the target driving behavior indicators; Screening is performed according to the historical behavior indicators corresponding to each of the target driving behavior indicators to determine the corresponding maximum historical behavior indicator and minimum historical behavior indicator, wherein the maximum historical behavior indicator is a historical behavior indicator whose confidence meets preset requirements.

6. The method according to claim 1, characterized in that The target signal data includes first target signal data and second target signal data, the first target signal data is signal data obtained when the target driver manually drives the vehicle, and the second target signal data is signal data obtained when the target driver turns on the auxiliary driving function to drive the vehicle; Determining a plurality of target driving behavior indicators according to the target signal data includes: determining a plurality of first target driving behavior indicators according to the first signal data, and determining a plurality of second target driving behavior indicators according to the second signal data; The step of performing weighted summation on the normalized data and weights corresponding to each of the target driving behavior indicators to determine the linear indicator data includes: performing weighted summation on the normalized data and weights corresponding to the first target driving behavior indicator to determine the first linear indicator data; and performing weighted summation on the normalized data and weights corresponding to the second target driving behavior indicator to determine the second linear indicator data; The performing a nonlinear transformation on the linear index data to determine the nonlinear index data comprises: performing a nonlinear transformation on the first linear index data to determine the first nonlinear index data; and performing a nonlinear transformation on the second linear index data to determine the second nonlinear index data; Determining the driving behavior normative data according to the nonlinear index data includes: fusing the first nonlinear index data and the second nonlinear index data to determine the driving behavior normative data.

7. The method according to claim 6, characterized in that Before fusing the first nonlinear index data and the second nonlinear index data to determine the driving behavior normative data, the method further includes: Determine a first driving distance and a second driving distance, wherein the first driving distance is a distance traveled by the vehicle manually driven, and the second driving distance is a distance traveled by the vehicle with assisted driving turned on; calculating a distance sum value of the first driving distance and the second driving distance; Calculating a manual driving ratio according to the first driving distance and the distance sum value, and calculating an assisted driving ratio according to the second driving distance and the distance sum value; The fusing of the first nonlinear index data and the second nonlinear index data to determine the driving behavior normative data includes: Calculating manual driving normative data according to the first nonlinear index data and the manual driving ratio; Calculating assisted driving normative data according to the second nonlinear index data and the assisted driving ratio; The sum of the manual driving normative data and the assisted driving normative data is obtained as the driving behavior normative data.

8. The method according to claim 6 or 7, characterized in that: Before fusing the first nonlinear index data and the second nonlinear index data to determine the driving behavior normative data, the method further includes: Mapping the first nonlinear index data into a percentage system to obtain mapped first nonlinear index data; Mapping the second nonlinear index data into a percentage system to obtain mapped second nonlinear index data; The fusing of the first nonlinear index data and the second nonlinear index data to determine the driving behavior normative data includes: The mapped first nonlinear index data and the mapped second nonlinear index data are fused to determine the driving behavior normative data.

9. A driving behavior normative evaluation device, characterized in that: include: a target driving behavior index determination unit, configured to determine a plurality of target driving behavior indexes according to target signal data, wherein the target signal data is signal data characterizing the driving behavior of the target driver, and the target driving behavior index is a target driving behavior index characterizing the driving behavior characteristics of the target driver; A normalization unit, configured to perform linear normalization processing on each of the target driving behavior indicators based on the maximum historical behavior indicator and the minimum historical behavior indicator corresponding to each of the target driving behavior indicators, and determine normalized data corresponding to each of the target driving behavior indicators; wherein the maximum historical behavior indicator is a historical behavior indicator whose confidence meets a preset requirement; A linear index data acquisition unit, used for performing weighted summation according to the normalized data and weights corresponding to each of the target driving behavior indicators to determine the linear index data; A nonlinear transformation unit, used to perform nonlinear transformation on the linear index data to determine the nonlinear index data; wherein the nonlinear transformation is determined according to the corresponding relationship between the linear index data and the probability of an accident caused by the driving behavior of the target driver; The normative data determining unit is used to determine driving behavior normative data according to the nonlinear index data, wherein the driving behavior normative data is used to evaluate the normativeness of the driving behavior of the target driver.

10. A computing device, characterized in that comprising a processor and a memory, the memory being used to store a computer program; When the computer program is loaded by the processor, the processor executes the driving behavior normative evaluation method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the processor implements the driving behavior normative evaluation method as described in any one of claims 1-8.

12. A vehicle, characterized in that: It includes an on-board control chip, which is used to execute the driving behavior normative evaluation method as described in any one of claims 1-8.