CN117828303A - Driving behavior analysis method, device and equipment - Google Patents

Abstract

The present invention provides a driving behavior analysis method, device and equipment, which relates to the technical field of vehicle data analysis. The method includes: obtaining multiple driving behavior parameters and usage ratio distribution information of multiple driving behavior parameters in a vehicle improvement task; obtaining a first high-perceived demand customer score corresponding to the driving behavior parameter according to the driving behavior parameter and an objective evaluation model, and the objective evaluation model is used to output a high-perceived demand customer score according to the input driving behavior parameter; determining an adjustment parameter range corresponding to the driving behavior parameter according to the driving behavior parameter and the corresponding usage ratio distribution information; obtaining a second high-perceived demand customer score according to the adjustment parameter range and the objective evaluation model; analyzing the vehicle improvement task based on the first high-perceived demand customer score and the second high-perceived demand customer score, and determining the driving behavior analysis result of the vehicle improvement task. The solution of the present invention analyzes driving behavior based on customer perceived demand.

Description

Driving behavior analysis method, device and equipment

Technical Field

The present invention relates to the technical field of vehicle data analysis, and in particular to a driving behavior analysis method, device and equipment.

Background technique

In recent years, the scale of the new energy vehicle market has expanded rapidly, and the definition of "good cars" in the eyes of consumers has also been changing. Only by mastering the "user-centric" market and analyzing user behavior and understanding user needs can we lead and occupy the market. In order to understand consumer needs more accurately, automobile manufacturers first need to understand users' driving behavior, and then clarify users' high perception indicators, guide the engineering side to develop automobile products that meet user needs, and ensure that the products are competitive in the market.

However, the current vehicle performance development index system has the problem that the core development index cannot effectively express user needs, and there is a barrier between user language and R&D language. Therefore, it is urgent to break through the barriers, analyze user driving behavior, set goals for user high-perceived demand indicators, guide engineering design and development, and ensure that the final product meets the product strength definition.

Summary of the invention

The technical solution of the present invention aims to provide a driving behavior analysis method, device and equipment to solve the problem in the prior art that vehicle improvement tasks cannot analyze driving behavior based on user high perception needs as a breakthrough.

In order to achieve the above object, the present invention is achieved as follows:

In a first aspect, an embodiment of the present invention provides a driving behavior analysis method, comprising:

Acquire multiple driving behavior parameters in a vehicle improvement task and usage ratio distribution information of the multiple driving behavior parameters;

According to each of the driving behavior parameters and the objective evaluation model, a first high perceived demand customer score corresponding to each of the driving behavior parameters is obtained, wherein the objective evaluation model is used to output a high perceived demand customer score according to the input driving behavior parameter;

Determining an adjustment parameter range corresponding to each driving behavior parameter according to each driving behavior parameter and corresponding usage ratio distribution information;

Obtaining a second highest perceived demand customer score based on the adjustment parameter range and the objective evaluation model;

The vehicle improvement task is analyzed based on the first high perceived need customer score and the second high perceived need customer score to determine a driving behavior analysis result of the vehicle improvement task.

Optionally, the driving behavior analysis method, wherein, according to each driving behavior parameter and corresponding usage proportion distribution information, determining the adjustment parameter range corresponding to each driving behavior parameter comprises:

Compare the proportion distribution data corresponding to each of the driving behavior parameters with the standard proportion distribution data to determine a change value;

Normalizing the change value to obtain a normalized change value threshold;

Determining an adjustment parameter range corresponding to each of the driving behavior parameters according to a change interval of the normalized change value threshold;

Among them, the usage proportion distribution information includes the proportion distribution data and the standard proportion distribution data, the proportion distribution data is related to the user attributes and the driving scene index data, and the standard proportion distribution data is irrelevant to the user attributes and the driving scene index data.

Optionally, the driving behavior analysis method, wherein the vehicle improvement task is analyzed based on the first high perceived need customer score and the second high perceived need customer score to determine a driving behavior analysis result of the vehicle improvement task, comprises:

Determining a scoring range according to the first high perceived need customer score and the second high perceived need customer score;

The scoring range is compared with the improvement target in the vehicle improvement task to determine the driving behavior analysis result of the vehicle improvement task.

Optionally, the driving behavior analysis method further comprises:

Determining whether there is a correlation between the second high perceived demand customer score and the driving behavior parameter;

If there is no correlation between the second high perceived need customer score and the driving behavior parameter, the driving behavior parameter is adjusted, and the second high perceived need customer score is re-obtained based on the adjusted driving behavior parameter.

Optionally, in the driving behavior analysis method, determining a score range according to the first high perceived demand customer score and the second high perceived demand customer score comprises one of the following:

Determining the score range according to an interval formed by the first high perceived need customer score and the second high perceived need customer score;

The score range is determined according to an interval formed by a cluster center of the second high perceived need customer scores and the first high perceived need customer scores.

Optionally, the driving behavior analysis method further comprises:

Acquire driving behavior parameters of a simulated driver when driving a vehicle in accordance with driving scenario index data, wherein the driving scenario index data is clue data related to the driving scenario;

constructing a correlation matrix between the high perceived demand customer scores and the driving behavior parameters;

The correlation matrix is analyzed to obtain the objective evaluation model.

Optionally, the driving behavior analysis method, wherein:

The driving scenario index data is related to user attributes of a target driver in the vehicle improvement task;

The user attributes of the simulated driver match the user attributes of the target driver.

Optionally, the driving behavior analysis method, wherein constructing a correlation matrix between high perceived demand customer scores and the driving behavior parameters, comprises:

Determining, based on the driving behavior parameters corresponding to the high perceived demand indicators, the high perceived demand customer scores corresponding to the driving behavior parameters;

A correlation matrix between the high perceived demand customer scores and corresponding driving behavior parameters is constructed.

Optionally, the driving behavior analysis method, wherein analyzing the correlation matrix to obtain the objective evaluation model, includes:

constructing a basic model between the driving behavior parameters and the high perceived demand customer scores;

Based on the correlation matrix, the basic model is processed using the least squares method to obtain the objective evaluation model.

In a second aspect, an embodiment of the present invention further provides a driving behavior analysis device, comprising:

A first acquisition module is used to acquire a plurality of driving behavior parameters in a vehicle improvement task and usage ratio distribution information of the plurality of driving behavior parameters;

A first obtaining module, configured to obtain a first high perceived demand customer score corresponding to each driving behavior parameter according to each driving behavior parameter and an objective evaluation model, wherein the objective evaluation model is configured to output a high perceived demand customer score according to an input driving behavior parameter;

A first determination module, configured to determine an adjustment parameter range corresponding to each driving behavior parameter according to each driving behavior parameter and corresponding usage ratio distribution information;

A second obtaining module, configured to obtain a score of a customer with the second highest perceived demand according to the adjustment parameter range and the objective evaluation model;

The second determination module is used to analyze the vehicle improvement task based on the first high perceived need customer score and the second high perceived need customer score to determine a driving behavior analysis result of the vehicle improvement task.

In a third aspect, an embodiment of the present invention further provides a driving behavior analysis device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor; when the processor executes the program or instruction, the driving behavior analysis method as described in any one of the above items is implemented.

In a fourth aspect, an embodiment of the present invention further provides a readable storage medium, on which a program is stored, and when the program is executed by a processor, the driving behavior analysis method as described in any one of the above items is implemented.

The above technical solution of the present invention has at least the following beneficial effects:

By adopting the driving behavior analysis method described in the embodiment of the present invention, a plurality of driving behavior parameters in a vehicle improvement task and the usage ratio distribution information of the plurality of driving behavior parameters are obtained; a first high-perceived demand customer score corresponding to each driving behavior parameter is obtained according to each driving behavior parameter and an objective evaluation model, and the objective evaluation model is used to output a high-perceived demand customer score according to the input driving behavior parameter; an adjustment parameter range corresponding to each driving behavior parameter is determined according to each driving behavior parameter and the corresponding usage ratio distribution information; a second high-perceived demand customer score is obtained according to the adjustment parameter range and the objective evaluation model; the vehicle improvement task is analyzed based on the first high-perceived demand customer score and the second high-perceived demand customer score to determine the driving behavior analysis result of the vehicle improvement task, so that the high-perceived demand of the customer is taken as a breakthrough point, the driving behavior parameters in the vehicle improvement task are analyzed, the design and development of the vehicle improvement project are guided, and the final product is ensured to meet the user needs.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a flow chart of a driving behavior analysis method according to an embodiment of the present invention;

FIG2 is a schematic diagram of the classification of high-perception demand indicators according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of the structure of a driving behavior analysis device according to an embodiment of the present invention.

Detailed ways

In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

The technical solution of the present invention aims to solve the problem in the prior art that vehicle improvement tasks cannot analyze driving behavior by taking users' high-perception needs as a breakthrough, and provides a driving behavior analysis method, device and equipment.

An embodiment of the present invention, as shown in FIG1 , provides a driving behavior analysis method, including:

Step 101: Acquire multiple driving behavior parameters in a vehicle improvement task and usage ratio distribution information of the multiple driving behavior parameters.

The driving behavior parameter is the driver's use behavior data of the vehicle during driving, for example: "0km/h to 50km/h, normal temperature, 40% pedal opening, half load"; "20km/h to 50km/h, normal temperature, 30% pedal opening, half load".

The usage ratio distribution information of the driving behavior parameter is used to indicate the usage ratio of the driving behavior parameter. For example, if the usage ratio distribution information of the driving behavior parameter is 50%, it means that 50% of the person-times involve the driving behavior parameter.

Optionally, user attributes of target drivers in the vehicle improvement task and driving behavior parameters of driving scenario index data are obtained from a VoC (Voice of Customer) big data platform as a supplement to the usage distribution information of the driving behavior parameters.

Step 102, obtaining a first high perceived need customer score corresponding to each driving behavior parameter according to each driving behavior parameter and an objective evaluation model, wherein the objective evaluation model is used to output a high perceived need customer score according to the input driving behavior parameter.

By using the driving behavior analysis method described in the embodiment of the present invention, each driving behavior parameter is sequentially input into the objective evaluation model to obtain the corresponding first high perceived demand customer score.

It can be understood that the high perceived need customer score is the customer's score on driving behavior based on the high perceived need indicators of vehicle driving performance.

As shown in Figure 2, high-perception demand indicators include: dynamic indicators, steering indicators, braking indicators and NVH (Noise, Vibration, Harshness) indicators; further, dynamic indicators are divided into starting dynamic indicators, urban performance indicators, highway performance indicators, etc.

Step 103: Determine an adjustment parameter range corresponding to each driving behavior parameter according to each driving behavior parameter and the corresponding usage ratio distribution information.

In one implementation mode, optionally, step 103 includes:

Compare the proportion distribution data corresponding to each of the driving behavior parameters with the standard proportion distribution data to determine a change value;

Normalizing the change value to obtain a normalized change value threshold;

Determining an adjustment parameter range corresponding to each of the driving behavior parameters according to a change interval of the normalized change value threshold;

Among them, the usage proportion distribution information includes the proportion distribution data and the standard proportion distribution data, the proportion distribution data is related to the user attributes and the driving scene index data, and the standard proportion distribution data is irrelevant to the user attributes and the driving scene index data.

Next, step 103 is described in detail:

Obtaining the proportion value pr _t corresponding to the t-th driving behavior parameter v _t in the proportion distribution data;

Obtaining a standard proportion value bpr _t corresponding to the driving behavior parameter v _t in the standard proportion distribution data;

According to the proportion value pr _t and the standard proportion value bpr _t , calculate the change value (pr _t -bpr _t )/bpr _t ;

The change value is normalized using the following formula to obtain the normalized change threshold Tr _t ;

Tr _t =(pr ^t −bpr ^t )/bpr ^t /∑ _t (pr _t −bpr _t )/bpr _t

Determine the adjustment parameter range corresponding to the t-th driving behavior parameter v _t as Ar = [ArL, ArH], where:

ArL＝MIN(v _t ,v _t ×(1+Tr _t ))

ArH＝MAX(v _t ,v _t ×(1+Tr _t ))

In one implementation mode, optionally, step 103 includes:

Based on the typical interval that each driving behavior parameter falls into, an adjustment parameter range corresponding to each driving behavior parameter is determined.

It should be noted that when the driving behavior parameter falls into a high-frequency interval, the adjustment parameter range is smaller (for example, 1% to 2% above and below the benchmark value), and when the driving behavior parameter falls into a low-frequency interval, the adjustment parameter range is larger (for example, 10% above and below the benchmark value). Otherwise, no adjustment is made; here the benchmark value is the driving behavior parameter itself.

It is understandable that the change in the parameter adjustment range is also related to the engineering cost required for parameter adjustment. It can be set that when the driving behavior parameter falls into the high-frequency range, the parameter adjustment range is large; when the driving behavior parameter falls into the medium-frequency range, the parameter adjustment range is in the middle; when the driving behavior parameter falls into the low-frequency range, the parameter adjustment range is small.

Step 104: Obtain the score of the customer with the second highest perceived demand according to the adjustment parameter range and the objective evaluation model.

Optionally, the driving behavior parameter is divided into fine granularities within the adjustment parameter range to obtain a plurality of divided driving behavior parameters;

The divided multiple driving behavior parameters are respectively input into the objective evaluation model to obtain the second highest perceived demand customer score.

Step 105 : analyzing the vehicle improvement task based on the first high perceived need customer score and the second high perceived need customer score to determine a driving behavior analysis result of the vehicle improvement task.

In one implementation mode, optionally, step 105 includes:

Determining a scoring range according to the first high perceived need customer score and the second high perceived need customer score;

The scoring range is compared with the improvement target in the vehicle improvement task to determine the driving behavior analysis result of the vehicle improvement task.

Optionally, if the scoring range meets the improvement target in the vehicle improvement task, the driving behavior analysis result of the vehicle improvement task is determined to be "meeting the improvement target, stop vehicle improvement";

If the scoring range does not meet the improvement target in the vehicle improvement task, the driving behavior analysis result of the vehicle improvement task is determined to be "does not meet the improvement target, and the driving behavior parameters need to be improved."

It should be noted that if it is determined that the scoring range corresponding to a single driving behavior parameter does not meet the improvement target, the driving behavior parameter can be improved individually; if it is determined that the scoring ranges corresponding to multiple driving behavior parameters do not meet the improvement target, the multiple driving behavior parameters can be improved jointly.

It should also be noted that when the score range covers a higher score, the driving behavior analysis result is "in line with the improvement target"; when the score range as a whole exceeds the improvement target, the driving behavior analysis result is "in line with the improvement target, stop vehicle improvements."

The driving behavior analysis method described in the embodiment of the present invention obtains a scoring range based on the first high perceived demand customer score and the second high perceived demand customer score, starts with objective driving behavior parameters to provide a basis for objective analysis, and determines the driving behavior analysis result based on the scoring range, so that subsequent improvement directions can be carried out in multiple directions and can be tried, thereby improving the feasibility of analysis guidance.

In one embodiment, optionally, the method further comprises:

Determining whether there is a correlation between the second high perceived demand customer score and the driving behavior parameter;

If there is no correlation between the second high perceived need customer score and the driving behavior parameter, the driving behavior parameter is adjusted, and the second high perceived need customer score is re-obtained based on the adjusted driving behavior parameter.

Optionally, based on the Pearson correlation coefficient, it is determined whether there is a correlation between the second highest perceived demand customer score and the driving behavior parameter.

The Pearson correlation coefficient is expressed as follows:

Wherein, CORREL((x _k ),Ay _j ) represents the Pearson correlation coefficient; AY=(Ay _j ) represents the second highest perceived demand customer score, Ay _j is the jth second highest perceived demand customer score; x _k is the kth driving behavior parameter.

Optionally, the Pearson correlation coefficient is compared with a correlation threshold to determine whether there is a correlation between the second high perceived demand customer score and the driving behavior parameter.

The correlation threshold is a preset value and is set as needed, for example, it may be 75%.

The driving behavior analysis method described in the embodiment of the present invention is executed based on the second highest perceived need customer score if there is a correlation between the second highest perceived need customer score and the driving behavior parameters; if there is no correlation between the second highest perceived need customer score and the driving behavior parameters, it is necessary to adjust the driving behavior parameters, and determine a new second highest perceived need customer score based on the adjusted driving behavior parameters, and repeat the correlation judgment step until there is a correlation between the second highest perceived need customer score and the driving behavior parameters.

In one implementation manner, optionally, determining a score range according to the first high perceived need customer score and the second high perceived need customer score includes one of the following:

Determining the score range according to an interval formed by the first high perceived need customer score and the second high perceived need customer score;

The score range is determined according to an interval formed by a cluster center of the second high perceived need customer scores and the first high perceived need customer scores.

Optionally, the cluster center of the second high perceived need customer scores is the cluster center of the largest cluster of the second high perceived need customer scores.

The driving behavior analysis method described in the embodiment of the present invention uses the interval formed by the first high perceived need customer score and the second high perceived need customer score as the score range; or, clusters the second high perceived need customer score to obtain a cluster center, and uses the interval formed by the cluster center and the first high perceived need customer score as the score range.

In addition, the driving behavior analysis method of the embodiment of the present invention further includes determining the scoring range according to the following steps:

Obtaining a third customer score with the highest perceived need, whose distance from the first customer score with the highest perceived need is less than a preset distance;

Obtaining an average of the first high perceived need customer score and the third high perceived need customer score;

The score range is determined according to an interval formed by the average value and the score of the first high perceived demand customer.

In one embodiment, optionally, the method further comprises:

Acquire driving behavior parameters of a simulated driver when driving a vehicle in accordance with driving scenario index data, wherein the driving scenario index data is clue data related to the driving scenario;

constructing a correlation matrix between the high perceived demand customer scores and the driving behavior parameters;

The correlation matrix is analyzed to obtain the objective evaluation model.

Optionally, the driving scenario index data is related to user attributes of a target driver in the vehicle improvement task; wherein, there may be multiple target drivers; and the user attributes include: gender, age and job.

It should be noted that the vehicle improvement task described in the embodiment of the present invention is aimed at a typical user, wherein the target driver is a typical user.

Optionally, the driving scene index data is clue data related to the driving scene.

The definition of scenes in the prior art is relatively rough, for example: urban conditions, starting conditions, but in fact, these scenes can only represent the situation of a driving segment and cannot fully describe the typical user's car experience. Compared with the prior art, the driving behavior parameters described in the embodiment of the present invention can describe the driving scene from an all-round definition, discover driving scene index data through typical users, and then simulate the driving behavior parameters by simulating drivers, and combine big data to discover the accurate all-round usage scenarios of typical users, so that more targeted vehicle improvements that meet user expectations can be made; that is, multiple driving behavior parameters are used to finely characterize the user's driving scene.

Optionally, the driving scenario index data includes: travel behavior data and driving habit data; wherein the travel behavior data includes: driving mileage data, driving time data, vehicle usage frequency data and travel route data.

Exemplarily, 50 days of vehicle usage data of a target driver is obtained, including three typical states: weekdays, weekends, and holidays, and travel behavior data of the target driver is counted, including: driving mileage data, driving time data, vehicle usage frequency data, and travel route data.

Optionally, the user attributes of the simulated driver are consistent with the user attributes of the target driver.

The driving behavior analysis method described in the embodiment of the present invention is adopted. First, the user attributes of the target driver are obtained, and the driving scene index data is obtained from the big data platform based on the user attributes of the target driver. Then, a simulated driver is selected, and the user attributes of the simulated driver are the same as the user attributes of the target driver, so that the simulated driver drives the vehicle in accordance with the driving scene index data, and the driving behavior parameters are collected during the vehicle driving process.

Optionally, the time-varying driving behavior parameters are collected through T-BOX (Telematics BOX, vehicle-mounted telematics processing system), wherein the time-varying driving behavior parameters include: acceleration in the X/Y/Z directions, vehicle speed, braking, steering, and smoothness.

Optionally, the driving behavior parameters of the driving feeling type are collected through the user terminal, wherein the driving behavior parameters of the driving feeling type include: good points and bad points.

Exemplarily, obtaining driving behavior parameters of a simulated driver when driving a vehicle in accordance with driving scenario index data includes:

Referring to the user attributes of the target driver in the vehicle improvement task, a simulated driver is selected, and the driving behavior parameters of the simulated driver during the vehicle driving process are collected and recorded. For example: the user attributes meet the following conditions: 80% of the males, 82% of the people aged 35 to 45, and the driving scenario index data includes 75% of commuting to and from get off work under congested conditions, and 10% of travel on holidays for more than 5 hours.

By applying the cdf function in MATLAB to perform frequency statistics and skewed distribution analysis on the driving behavior parameters, the usage ratio distribution information of the driving behavior parameters can be obtained; here, the icdf function can be applied to inversely obtain the driving behavior parameters corresponding to the usage ratio distribution information.

The usage ratio distribution information of driving behavior parameters is analyzed based on the 3σ principle of normal distribution; here, the usage ratio distribution can be divided into several typical intervals (for example, 0% to 30%, 30% to 50%, 50% to 70%, 70% to 90%, 90% to 100%). The adjustment parameter range can be determined based on the interval in which the driving behavior parameter falls. When the interval in which the driving behavior parameter falls is a high-frequency interval (for example, 70% to 90%, 90% to 100%), the adjustment parameter range is small; when the interval in which the driving behavior parameter falls is a low-frequency interval (for example, 0% to 30%, 30% to 50%), the adjustment parameter range is large; other medium-frequency intervals may not be adjusted.

In one implementation mode, optionally, a correlation matrix between high perceived demand customer scores and the driving behavior parameters is constructed, including:

Determining, based on the driving behavior parameters corresponding to the high perceived demand indicators, the high perceived demand customer scores corresponding to the driving behavior parameters;

A correlation matrix between the high perceived demand customer scores and corresponding driving behavior parameters is constructed.

Optionally, the driving behavior parameters corresponding to the high perceived demand indicators are determined through the VoC big data platform, and the high perceived demand customer scores corresponding to the driving behavior parameters are determined.

Optionally, driving behavior parameters corresponding to different high perception demand indicators are different or the same.

Optionally, constructing a correlation matrix between the high perceived demand customer scores and corresponding driving behavior parameters includes:

Constructing a first correlation matrix between the high perceived demand customer scores and corresponding driving behavior parameters;

Acquire directional sample data from the VoC big data platform, and supplement the first correlation matrix based on the directional sample data to obtain the correlation matrix; wherein the directional sample data are driving behavior parameters of a target vehicle and a competitor vehicle of the target vehicle; and the target vehicle is the vehicle targeted by the vehicle improvement task.

Optionally, the first correlation matrix is constructed using a QFD tool, and the first correlation matrix is supplemented by the QFD tool to obtain the correlation matrix.

The driving behavior analysis method described in the embodiment of the present invention describes the all-round usage scenarios of typical users (target drivers) based on multiple driving behavior parameters, and scientifically constructs a correlation matrix between high-perceived demand customer scores and driving behavior parameters, thereby obtaining an objective evaluation model, which becomes the basis for objective analysis, and determines the quantitative adjustment direction through the usage distribution ratio information corresponding to the driving behavior parameters, thereby providing quantitative and qualitative improvement direction support for subsequent typical users' vehicle improvement tasks.

In one implementation manner, optionally, analyzing the correlation matrix to obtain the objective evaluation model includes:

constructing a basic model between the driving behavior parameters and the high perceived demand customer scores;

Based on the correlation matrix, the basic model is processed using the least squares method to obtain the objective evaluation model.

The embodiment of the present invention constructs the following basic model:

Y＝β ₀ +β ₁ x ₁ +β ₂ x ₂ +…++β _k x _k +…+β _k1 x _k1 +ε

Wherein, Y=(y _i ); i∈1～I; k∈1～k1; y _i is the score of the i-th high perceived demand customer; x _k is the k-th driving behavior parameter; β ₀ , β ₁ , ...β _k1 are k1+1 regression parameters; ε is the estimation error.

Based on the correlation matrix, the least squares method is used to solve the multivariate parameter _βk and the estimation error ε in the above basic model. The loss function is set to the square of the estimation error ε. The loss function is iterated as the objective function to obtain a linear regression model, which is used as an objective evaluation model.

The objective evaluation model is as follows:

Y＝βX+ε

Where Y is the score of customers with high perceived demand; β is the regression parameter; X is the driving behavior parameter; and ε is the estimation error.

The embodiment of the present invention, as shown in FIG3 , further provides a driving behavior analysis device, characterized in that it includes:

A first acquisition module 301 is used to acquire a plurality of driving behavior parameters in a vehicle improvement task and usage ratio distribution information of the plurality of driving behavior parameters;

A first obtaining module 302 is used to obtain a first high perceived demand customer score corresponding to each driving behavior parameter according to each driving behavior parameter and an objective evaluation model, wherein the objective evaluation model is used to output a high perceived demand customer score according to the input driving behavior parameter;

A first determination module 303, configured to determine an adjustment parameter range corresponding to each driving behavior parameter according to each driving behavior parameter and corresponding usage ratio distribution information;

A second obtaining module 304 is used to obtain a score of the customer with the second highest perceived demand according to the adjustment parameter range and the objective evaluation model;

The second determination module 305 is used to analyze the vehicle improvement task based on the first high perceived need customer score and the second high perceived need customer score to determine a driving behavior analysis result of the vehicle improvement task.

Optionally, in the driving behavior analysis device, the first determination module 303 is specifically configured to:

Compare the proportion distribution data corresponding to each of the driving behavior parameters with the standard proportion distribution data to determine a change value;

Normalizing the change value to obtain a normalized change value threshold;

Determining an adjustment parameter range corresponding to each of the driving behavior parameters according to a change interval of the normalized change value threshold;

Among them, the usage proportion distribution information includes the proportion distribution data and the standard proportion distribution data, the proportion distribution data is related to the user attributes and the driving scene index data, and the standard proportion distribution data is irrelevant to the user attributes and the driving scene index data.

Optionally, in the driving behavior analysis device, the second determination module 305 includes:

A first determining unit, configured to determine a score range according to the first high perceived need customer score and the second high perceived need customer score;

The second determination unit is used to compare the scoring range with the improvement target in the vehicle improvement task to determine the driving behavior analysis result of the vehicle improvement task.

Optionally, the driving behavior analysis device further comprises:

A judgment module, used for judging whether there is a correlation between the second high perceived demand customer score and the driving behavior parameter;

An adjustment module is used for adjusting the driving behavior parameter if there is no correlation between the second high perceived need customer score and the driving behavior parameter, and re-obtaining the second high perceived need customer score based on the adjusted driving behavior parameter.

Optionally, in the driving behavior analysis device, the first determination unit is specifically used for one of the following:

Determining the score range according to an interval formed by the first high perceived need customer score and the second high perceived need customer score;

The score range is determined according to an interval formed by a cluster center of the second high perceived need customer scores and the first high perceived need customer scores.

Optionally, the driving behavior analysis device further comprises:

A second acquisition module is used to acquire driving behavior parameters of a simulated driver when driving a vehicle in accordance with driving scenario index data, wherein the driving scenario index data is clue data related to the driving scenario;

A construction module, used to construct a correlation matrix between the high perceived demand customer scores and the driving behavior parameters;

The analysis module is used to analyze the correlation matrix to obtain the objective evaluation model.

Optionally, the driving behavior analysis device, wherein:

The driving scenario index data is related to user attributes of a target driver in the vehicle improvement task;

The user attributes of the simulated driver match the user attributes of the target driver.

Optionally, in the driving behavior analysis device, the building module is specifically used for:

Determining, based on the driving behavior parameters corresponding to the high perceived demand indicators, the high perceived demand customer scores corresponding to the driving behavior parameters;

A correlation matrix between the high perceived demand customer scores and corresponding driving behavior parameters is constructed.

Optionally, in the driving behavior analysis device, the analysis module is specifically used to:

constructing a basic model between the driving behavior parameters and the high perceived demand customer scores;

Based on the correlation matrix, the basic model is processed using the least squares method to obtain the objective evaluation model.

An embodiment of the present invention also provides a driving behavior analysis device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor; when the processor executes the program or instruction, the driving behavior analysis method as described in any one of the above items is implemented.

In addition, a specific embodiment of the present invention further provides a readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the driving behavior analysis method as described in any one of the above is implemented.

Specifically, the readable storage medium is applied to the above-mentioned driving behavior analysis device. When applied to the driving behavior analysis device, the execution steps in the corresponding driving behavior analysis method are described in detail above and will not be repeated here.

The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims (12)

1. A driving behavior analysis method, characterized by comprising:

acquiring a plurality of driving behavior parameters and usage proportion distribution information of a plurality of the driving behavior parameters in a vehicle improvement task;

obtaining a first high-perception-demand customer score corresponding to each driving behavior parameter according to each driving behavior parameter and an objective evaluation model, wherein the objective evaluation model is used for outputting the high-perception-demand customer score according to the inputted driving behavior parameters;

determining an adjustment parameter range corresponding to each driving behavior parameter according to each driving behavior parameter and corresponding usage proportion distribution information;

obtaining a second high-perception-demand customer score according to the adjustment parameter range and the objective evaluation model;

and analyzing the vehicle improvement task based on the first high-perception-demand customer score and the second high-perception-demand customer score, and determining a driving behavior analysis result of the vehicle improvement task.

2. The driving behavior analysis method according to claim 1, wherein determining a corresponding adjustment parameter range for each of the driving behavior parameters based on each of the driving behavior parameters and the corresponding usage-duty distribution information includes:

comparing the corresponding duty ratio distribution data of each driving behavior parameter with the standard duty ratio distribution data to determine a change value;

normalizing the change value to obtain a normalized change value threshold;

according to the change interval of the normalized change value threshold, determining an adjustment parameter range corresponding to each driving behavior parameter;

the usage duty distribution information comprises duty distribution data and standard duty distribution data, the duty distribution data is related to user attributes and driving scene index data, and the standard duty distribution data is unrelated to the user attributes and the driving scene index data.

3. The driving behavior analysis method according to claim 1, wherein analyzing the vehicle improvement task based on the first high perceived-demand customer score and the second high perceived-demand customer score, determining a driving behavior analysis result of the vehicle improvement task, comprises:

determining a scoring range according to the first high perceived-demand customer score and the second high perceived-demand customer score;

and comparing the scoring range with the improvement targets in the vehicle improvement task to determine a driving behavior analysis result of the vehicle improvement task.

4. A driving behavior analysis method according to claim 3, characterized in that the method further comprises:

judging whether the second high-perception-requirement customer score and the driving behavior parameter have correlation or not;

and if the second high-perception-demand customer score and the driving behavior parameter do not have correlation, adjusting the driving behavior parameter, and acquiring the second high-perception-demand customer score again based on the adjusted driving behavior parameter.

5. A driving behavior analysis method according to claim 3, wherein determining a scoring range from the first high perceived demand customer score and the second high perceived demand customer score comprises one of:

determining the scoring range according to a section formed by the first high-perception-demand customer score and the second high-perception-demand customer score;

and determining the scoring range according to the interval formed by the clustering center of the second high-perception-demand customer score and the first high-perception-demand customer score.

6. The driving behavior analysis method according to claim 1, characterized in that the method further comprises:

acquiring driving behavior parameters of a simulated driver when driving a vehicle under the condition of conforming to driving scene index data, wherein the driving scene index data is clue data related to a driving scene;

constructing a correlation matrix between the high perceived-demand customer scores and the driving behavior parameters;

and analyzing the correlation matrix to obtain the objective evaluation model.

7. The driving behavior analysis method according to claim 6, wherein,

the driving scenario index data is related to user attributes of a target driver in the vehicle improvement task;

the user attributes of the simulated driver conform to the user attributes of the target driver.

8. The driving behavior analysis method according to claim 6, wherein constructing a correlation matrix between a high perceived demand customer score and the driving behavior parameter comprises:

determining a high perceived-demand customer score corresponding to a driving behavior parameter based on the driving behavior parameter corresponding to the high perceived-demand index;

and constructing a correlation matrix between the high-perception-demand customer scores and the corresponding driving behavior parameters.

9. The driving behavior analysis method according to claim 6, wherein analyzing the correlation matrix to obtain the objective evaluation model includes:

constructing a basic model between the driving behavior parameters and the high-perception-demand customer scores;

and processing the basic model by adopting a least square method based on the correlation matrix to obtain the objective evaluation model.

10. A driving behavior analysis device, characterized by comprising:

the first acquisition module is used for acquiring a plurality of driving behavior parameters and usage proportion distribution information of a plurality of the driving behavior parameters in the vehicle improvement task;

the first obtaining module is used for obtaining a first high-perception-demand customer score corresponding to each driving behavior parameter according to each driving behavior parameter and an objective evaluation model, and the objective evaluation model is used for outputting the high-perception-demand customer score according to the input driving behavior parameters;

the first determining module is used for determining an adjusting parameter range corresponding to each driving behavior parameter according to each driving behavior parameter and the corresponding usage proportion distribution information;

the second obtaining module is used for obtaining a second high-perception-demand customer score according to the adjustment parameter range and the objective evaluation model;

and the second determining module is used for analyzing the vehicle improvement task based on the first high-perception-demand customer score and the second high-perception-demand customer score and determining a driving behavior analysis result of the vehicle improvement task.

11. A driving behavior analysis device comprising a processor, a memory and a program or instructions stored on the memory and executable on the processor; a driving behavior analysis method according to any one of claims 1 to 9, characterized in that the processor implements the driving behavior analysis method when executing the program or instructions.

12. A readable storage medium, characterized in that the readable storage medium has stored thereon a program which, when executed by a processor, implements the driving behavior analysis method according to any one of claims 1 to 9.