Vehicle risk prompting method and system based on big data

Abstract

The invention relates to the technical field of big data, and particularly discloses a vehicle risk prompting method and system based on big data. The road surface friction coefficient is obtained according to the road surface roughness value and the road surface gradient, then the braking error influence index is obtained, and the effective braking distance is obtained according to the initial speed of the vehicle, the road surface friction coefficient and the preset gravitational acceleration. And then the braking force is obtained according to the initial speed of the vehicle, the quality of the vehicle, the braking error influence index and the effective braking distance, and the vehicle risk is prompted according to the braking force, so that the vehicle risk is prompted through a visual indicating lamp, and different colors and signals correspond to different braking force conditions. Therefore, the driver can quickly know the risk state, the driver can timely adjust the operation, and the accident risk is reduced. And meanwhile, a driver can be intuitively informed of the required braking force to meet the current braking distance through the steps, so that the braking risk of the vehicle can be avoided.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a vehicle risk warning method and system based on big data. Background Art

[0002] As the number of cars increases, the driving risks of vehicles will also increase. Vehicle risk warning refers to the use of technical means, such as sensors or historical data extracted from big data, to identify and evaluate various potential dangers that may be encountered during vehicle driving, and to promptly issue warnings or suggestions to drivers. Its purpose is to help drivers understand and respond to safety hazards in driving in advance, thereby reducing the occurrence of traffic accidents and improving road safety. Existing vehicle risk warnings can usually only judge the distance between vehicles based on sensors, and then judge the risk based on the distance between vehicles. When the vehicle prompts the driver, it can only remind the driver of the risk, but cannot intuitively tell the driver how much braking force is needed to meet the current braking distance. Therefore, a vehicle risk warning method and system based on big data is needed to solve the above problems. Summary of the invention

[0003] The purpose of the present invention is to provide a vehicle risk warning method and system based on big data to solve the technical problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: A vehicle risk warning method based on big data, comprising: Acquiring vehicle driving information, wherein the vehicle driving information includes road surface information and vehicle braking information; Acquiring the mass of the vehicle and the initial speed of the vehicle according to the vehicle braking information; Acquire a road surface roughness value and a road surface inclination according to the road surface information, and acquire a road surface friction coefficient according to the road surface roughness value and the road surface inclination; Acquire vehicle maintenance information based on big data, acquire multiple brake pad surface wear values ​​according to the vehicle maintenance information, and acquire a brake error influence index according to the multiple brake pad surface wear values ​​and a preset replacement cycle; Obtaining an effective braking distance according to the initial speed of the vehicle, the road friction coefficient and a preset gravity acceleration; Obtaining the braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance; The vehicle risk is prompted according to the braking force.

[0005] Preferably, the step of obtaining the road surface friction coefficient according to the road surface roughness value and the road surface inclination includes: Obtain image information according to the road surface information, and perform grayscale processing on the image information to obtain road surface grayscale image information; Perform grid segmentation on the road surface grayscale image information in standard pixel units to obtain a plurality of pixel grids; Obtain the corresponding RGB pixel values according to the pixel grids, where the RGB pixel values include R pixel values, G pixel values, and B pixel values; Obtain the pixel grid grayscale values according to the R pixel values, the G pixel values, and the B pixel values, where the calculation formula is: ; Wherein, represents the pixel grid grayscale value, R represents the R pixel value, G represents the G pixel value, and B represents the B pixel value; Repeat the steps of obtaining the corresponding RGB pixel values according to the pixel grids, where the RGB pixel values include R pixel values, G pixel values, and B pixel values to obtaining the pixel grid grayscale values according to the R pixel values, the G pixel values, and the B pixel values to traverse all pixel grids and obtain a plurality of pixel grid grayscale values; Compare the plurality of pixel grid grayscale values with a preset grayscale value - roughness value table to obtain a plurality of first road surface roughness values, and perform mean calculation on the plurality of first road surface roughness values to obtain an average road surface roughness value, and use the average road surface roughness value as the road surface roughness value; Obtain the road surface inclination angle according to the road surface inclination; Calculate the road surface friction coefficient according to the road surface roughness value and the road surface inclination angle, where the calculation formula is: ; Wherein, represents the road surface friction coefficient, represents the road surface roughness value, represents the road surface inclination angle.

[0006] Preferably, the step of obtaining the braking error influence index according to the surface wear values of a plurality of brake pads and a preset replacement period includes: Obtain the starting use time and replacement time of the brake pads according to the preset replacement period; Calculate the average surface wear degree value of the brake pads according to the surface wear values of the plurality of brake pads, the starting use time, and the replacement time, where the calculation formula is: ; Wherein, represents the average surface wear degree value of the brake pads, Indicates the starting usage time, Indicates the replacement time, Indicates the surface wear value of the brake pad, and n indicates the number of surface wear values of the brake pad, where i = 1, 2, 3... n; Calculate the standard surface wear value of the brake pad based on multiple surface wear values of the brake pad and the average surface wear degree value of the brake pad, where the calculation formula is: ; Wherein, Indicates the standard surface wear value of the brake pad, Indicates the o-th surface wear value of the brake pad, Indicates the number of surface wear values of the brake pad, o indicates the serial number of the surface wear value of the brake pad, where o = 1, 2, 3... k, Indicates the average surface wear degree of the brake pad; Calculate the surface wear influence coefficient of the brake pad based on the standard surface wear value of the brake pad and the average surface wear degree value of the brake pad, where the calculation formula is: ; Wherein, Indicates the surface wear influence coefficient of the brake pad, Indicates the average surface wear degree value of the brake pad, Indicates the standard surface wear value of the brake pad; Take the surface wear influence coefficient of the brake pad as the braking error influence index.

[0007] Preferably, the step of obtaining the effective braking distance according to the initial speed of the vehicle, the road surface friction coefficient and the preset gravitational acceleration includes: Obtain the effective braking distance according to the initial speed of the vehicle, the road surface friction coefficient and the preset gravitational acceleration, where the calculation formula is: ; Wherein, Indicates the effective braking distance, Indicates the road surface friction coefficient, Indicates the initial speed of the vehicle, Indicates the preset gravitational acceleration.

[0008] Preferably, the step of obtaining the braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance includes: Obtain historical braking force and the force of the historical driver stepping on the pedal based on big data, and calculate the braking efficiency between the historical braking force and the force of the historical driver stepping on the pedal; Obtain the braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking efficiency, the braking error influence index, and the effective braking distance, where the calculation formula is: ; Wherein, represents the braking force, represents the mass of the vehicle, represents the initial speed of the vehicle, represents the braking efficiency, represents the braking error influence index.

[0009] Preferably, the step of prompting vehicle risks according to the braking force includes: Judge whether the braking force meets the preset threshold range; When the braking force does not meet the preset threshold range and is less than the minimum value of the preset threshold range, it is determined that the driver steps on the brake pedal with a small force and a first reminder signal is generated, and a corresponding preset yellow indicator light is turned on according to the first reminder signal for risk prompting; When the braking force meets the preset threshold range, it is determined that the driver steps on the brake pedal with a normal force and a second reminder signal is generated, and a corresponding preset green indicator light is turned on according to the second reminder signal for safety prompting; When the braking force does not meet the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the driver steps on the brake pedal with a large force and a third reminder signal is generated, and a corresponding preset red indicator light is turned on according to the third reminder signal for risk prompting.

[0010] This application also provides a vehicle risk prompting system based on big data, including: A first acquisition module for acquiring vehicle driving information, where the vehicle driving information includes road surface information and vehicle braking information; A second acquisition module for acquiring the mass and initial speed of the vehicle according to the vehicle braking information; A third acquisition module for acquiring the road surface roughness value and road surface inclination according to the road surface information, and acquiring the road surface friction coefficient according to the road surface roughness value and the road surface inclination; A fourth acquisition module for acquiring vehicle maintenance information based on big data, acquiring multiple brake pad surface wear values according to the vehicle maintenance information, and acquiring the braking error influence index according to the multiple brake pad surface wear values and the preset replacement cycle; A fifth acquisition module for acquiring the effective braking distance according to the initial speed of the vehicle, the road surface friction coefficient, and the preset gravitational acceleration; A sixth acquisition module, configured to acquire a braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index, and the effective braking distance; A first prompt module, configured to prompt vehicle risks according to the braking force.

[0011] Preferably, the third acquisition module includes: A first acquisition unit, configured to acquire image information according to the road surface information, perform grayscale processing on the image information, and obtain road surface grayscale image information; A first segmentation unit, configured to perform grid segmentation on the road surface grayscale image information in standard pixel units to obtain a plurality of pixel grids; A second acquisition unit, configured to acquire corresponding RGB pixel values according to the pixel grids, where the RGB pixel values include R pixel values, G pixel values, and B pixel values; A first calculation unit, configured to obtain a pixel grid grayscale value according to the R pixel value, the G pixel value, and the B pixel value, where the calculation formula is: ; Wherein, represents the pixel grid grayscale value, R represents the R pixel value, G represents the G pixel value, and B represents the B pixel value; A third acquisition unit, configured to repeat the steps of acquiring corresponding RGB pixel values according to the pixel grids, where the RGB pixel values include R pixel values, G pixel values, and B pixel values to obtaining a pixel grid grayscale value according to the R pixel value, the G pixel value, and the B pixel value to traverse all pixel grids and obtain a plurality of pixel grid grayscale values; A first comparison unit, configured to compare a plurality of the pixel grid grayscale values with a preset grayscale-roughness value table to obtain a plurality of first road surface roughness values, perform mean calculation on the plurality of first road surface roughness values to obtain an average road surface roughness value, and use the average road surface roughness value as the road surface roughness value; A fourth acquisition unit, configured to acquire a road surface tilt angle according to the road surface inclination; A second calculation unit, configured to calculate a road surface friction coefficient according to the road surface roughness value and the road surface tilt angle, where the calculation formula is: ; Wherein, represents the road surface friction coefficient, represents the road surface roughness value, represents the road surface tilt angle.

[0012] The present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0013] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0014] The beneficial effects of the present application are as follows: By obtaining the road surface information and vehicle braking information in the vehicle driving information, as well as the vehicle maintenance information based on big data, the present invention comprehensively considers various factors affecting vehicle braking, such as road surface roughness value, inclination, brake pad wear condition, etc., and can evaluate vehicle risks more comprehensively and accurately. Then, the road surface roughness value and road surface inclination are obtained according to the road surface information, and the road surface friction coefficient is obtained according to the road surface roughness value and the road surface inclination. Then, the vehicle maintenance information is obtained based on big data, multiple brake pad surface wear values are obtained according to the vehicle maintenance information, and the braking error influence index is obtained according to the multiple brake pad surface wear values and the preset replacement cycle. Then, the effective braking distance is obtained according to the initial speed of the vehicle, the road surface friction coefficient and the preset gravitational acceleration. Then, the braking force of the vehicle is obtained according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance. Finally, the vehicle risk is prompted according to the braking force. In this way, through intuitive indicator light prompts (yellow, green, red), different colors and signals correspond to different braking force conditions of the vehicle, enabling the driver to quickly understand the risk status, which helps them adjust operations in a timely manner and reduce the accident risk. At the same time, through the above steps, it can intuitively tell the driver how much braking force needs to be applied to meet the current braking distance, thereby avoiding the occurrence of vehicle braking risks. Brief Description of the Drawings

[0015] Figure 1 It is a schematic flowchart of the method according to an embodiment of the present application.

[0016] Figure 2 It is a schematic structural diagram of the system according to an embodiment of the present application.

[0017] Figure 3 It is a schematic internal structure diagram of the computer device according to an embodiment of the present application.

[0018] The realization, functional features and advantages of the purpose of the present application will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0020] As shown Figures 1-3 in the figure, the present application provides a vehicle risk prompting method based on big data, including: S1. Obtain vehicle driving information, where the vehicle driving information includes road surface information and vehicle braking information; S2. Obtain the mass and initial speed of the vehicle according to the vehicle braking information; S3. Obtain the road surface roughness value and road surface inclination according to the road surface information, and obtain the road surface friction coefficient according to the road surface roughness value and the road surface inclination; S4. Obtain vehicle maintenance information based on big data, obtain multiple brake pad surface wear values according to the vehicle maintenance information, and obtain a braking error influence index according to the multiple brake pad surface wear values and a preset replacement cycle; S5. Obtain the effective braking distance according to the initial speed of the vehicle, the road surface friction coefficient and a preset gravitational acceleration; S6. Obtain the braking force of the vehicle according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance; S7. Prompt vehicle risks according to the braking force.

[0021] As described in the above steps S1 - S7, existing vehicle risk warnings usually can only judge the vehicle distance based on sensors, and then judge the risk through the vehicle distance. When the vehicle warns the driver, it can only remind that there is a risk, and cannot directly tell the driver how much braking force is needed to meet the current braking distance. At the same time, if the driver suddenly steps on the brake pedal, there will also be a certain risk of rollover (suddenly stepping on the brake will cause the vehicle to decelerate sharply. During the emergency braking process, the front part of the vehicle sinks due to deceleration, and the rear part will rise relatively. This transfer of the front and rear center of gravity may cause the vehicle to lose balance. Especially when driving at high speed, the front wheels receive a large braking force, which will increase the risk of rollover. Especially in the case of poor road conditions or high vehicle speed, this risk will be more obvious). Therefore, the present invention first obtains vehicle driving information, wherein the vehicle driving information includes road surface information and vehicle braking information, so as to comprehensively collect key information during vehicle driving and provide basic data for accurately evaluating vehicle risks in the follow-up. Road surface information can reflect the impact of road conditions on vehicle driving, and vehicle braking information is directly related to the deceleration performance and safety control of the vehicle. Then, according to the vehicle braking information, the mass and initial speed of the vehicle are obtained. Among them, the vehicle mass and initial speed are important basic data for calculating vehicle braking related parameters. Mass affects the inertia of the vehicle, and the initial speed determines the motion state of the vehicle before braking. These data are crucial for calculating braking distance, braking force, etc. in the follow-up and are necessary conditions for accurately evaluating vehicle braking. Since road surface conditions are an important factor in vehicle driving safety, different road surface roughness and inclination angles will change the braking performance of the vehicle. Therefore, the road surface roughness value and road surface inclination can be obtained according to the road surface information, and the road surface friction coefficient can be obtained according to the road surface roughness value and the road surface inclination. The road surface roughness value and inclination can reflect the actual condition of the road surface. The roughness value affects the friction between the tire and the road surface, and the inclination will affect the gravity component of the vehicle, thereby affecting the braking effect of the vehicle. By calculating the road surface friction coefficient, the influence degree of road surface conditions on vehicle braking can be quantified, providing key parameters for accurately calculating braking distance, etc. Since the brake pads will gradually wear during vehicle use, this is one of the important factors affecting the braking effect. Considering the wear condition of the brake pads can more truly reflect the current braking ability of the vehicle, avoid inaccurate risk warnings caused by ignoring this factor, and thus better ensure driving safety. Therefore, based on big data, vehicle maintenance information is obtained, multiple brake pad surface wear values are obtained according to the vehicle maintenance information, and a braking error influence index is obtained according to the multiple brake pad surface wear values and a preset replacement cycle. In this way, the wear condition of the brake pads is directly related to the braking performance of the vehicle. Obtaining maintenance information through big data and calculating wear values and braking error influence indexes can take into account the changes in braking performance caused by vehicle use.Severely worn brake pads can lead to an increase in braking distance. The braking error impact index can quantify this impact, making risk warnings more comprehensive and accurate. Among them, obtaining vehicle maintenance information based on big data is to screen valid data through the clustering model in the big data model. The screening process uses the existing vehicle information as the centroid and other data to be screened as samples, making the samples approach the centroid. In this way, multiple surface wear values of the brake pads can be quickly screened. Then, based on the initial speed of the vehicle, the road surface friction coefficient, and the preset gravitational acceleration, the effective braking distance is obtained. Thus, the theoretical braking distance under the current road surface conditions and vehicle initial speed is calculated according to physical principles, which is a key indicator for evaluating whether the vehicle can stop within a safe distance. The driver can understand how long the vehicle needs to completely stop under the current conditions through this indicator, and thus make reasonable driving decisions in advance. Then, based on the initial speed of the vehicle, the mass of the vehicle, the braking error impact index, and the effective braking distance, the braking force is obtained, and the braking force required to achieve the safe braking distance is calculated, providing specific operation references for the driver. The driver can adjust the braking force according to this prompt, enabling the vehicle to brake more effectively under different road conditions and vehicle states, reducing the risk of accidents caused by improper braking. Finally, the vehicle risk is prompted according to the braking force. In this way, through the prompt of the braking force, the driver can quickly understand the risk status of the current braking operation, and at the same time, the driver can also know whether their braking operation meets the safety requirements without complex calculations, which helps to adjust the operation in time and reduce the accident risk.

[0022] In one embodiment, step S3 of obtaining the road surface friction coefficient according to the road surface roughness value and the road surface inclination includes: S301. Obtain image information according to the road surface information, and perform grayscale processing on the image information to obtain road surface grayscale image information; S302. Perform grid division on the road surface grayscale image information in standard pixel units to obtain a plurality of pixel grids; S303. Obtain the corresponding RGB pixel values according to the pixel grids, where the RGB pixel values include R pixel values, G pixel values, and B pixel values; S304. Obtain the pixel grid grayscale value according to the R pixel value, the G pixel value, and the B pixel value, where the calculation formula is: ; Among them, represents the pixel grid grayscale value, R represents the R pixel value, G represents the G pixel value, and B represents the B pixel value; S305. Repeat the step of obtaining the corresponding RGB pixel values according to the pixel grid, where the RGB pixel values include the R pixel value, the G pixel value, and the B pixel value, to the step of obtaining the pixel grid gray value according to the R pixel value, the G pixel value, and the B pixel value, so as to traverse all pixel grids and obtain a plurality of pixel grid gray values; S306. Compare the plurality of pixel grid gray values with a preset gray value - roughness value table to obtain a plurality of first road roughness values, and perform an average calculation on the plurality of first road roughness values to obtain an average road roughness value, and use the average road roughness value as the road roughness value; S307. Obtain the road inclination angle according to the road inclination; S308. Calculate the road friction coefficient according to the road roughness value and the road inclination angle, where the calculation formula is: ; where represents the road friction coefficient, represents the road roughness value, represents the road inclination angle.

[0023] As described in the above steps S301 - S308, the present invention obtains image information based on the road surface information, performs grayscale processing on the image information to obtain road surface grayscale image information. After obtaining the road surface information, the image data is often complex and contains a large amount of redundant information. Grayscale processing can simplify the data structure without losing key information (road surface texture and brightness features), making subsequent image - based analysis more efficient. Moreover, grayscale images are easier to operate and calculate in many image - processing algorithms, can provide a more suitable data format for subsequent steps. At the same time, extracting image information from the road surface information, converting the color image to a grayscale image, reduces the amount of image data while highlighting the texture and brightness information of the image, facilitating subsequent processing. Grayscale images only contain brightness information, which can simplify the calculation process, and the brightness information is related to features such as the roughness of the road surface, providing basic data for accurately analyzing the road surface condition. Then, the road surface grayscale image information is segmented into a grid of standard pixel units to obtain a plurality of pixel grids. In this way, the image is divided into multiple small pixel grids, which is convenient for local analysis of the image. Each pixel grid can be regarded as a small area of the road surface. By analyzing these small areas, the overall characteristics of the road surface, such as the change in roughness in different areas, can be understood more carefully. Then, the corresponding RGB pixel values are obtained according to the pixel grids. Among them, the RGB pixel values include R pixel values, G pixel values, and B pixel values. Obtaining the RGB pixel values of each pixel grid, these values reflect the brightness information of this area in the red, green, and blue color channels. Although the image has been grayscale, the original RGB values may still be useful in some calculations and feature extractions. For example, they may play a role in some auxiliary judgments of road surface conditions based on color features or in comparison with other image data. Since in image processing, converting RGB values to grayscale values is a common operation, but different conversion methods will affect the accuracy of the grayscale values. Using a weighted - average formula based on the visual characteristics of the human eye can obtain a grayscale image closer to the actual perception of the human eye, which is very important for road surface condition assessment based on visual information and can improve the accuracy and reliability of subsequent analysis. Therefore, the pixel grid grayscale value is obtained according to the R pixel value, the G pixel value, and the B pixel value, and the RGB pixel values are converted to grayscale values using a specific weighted calculation formula. This formula determines the weights according to the sensitivity of the human eye to different colors and can more accurately reflect the brightness perceived by the human eye.The grayscale values obtained in this way are more in line with the actual visual perception and are more accurate and reliable when analyzing features such as road surface roughness based on the grayscale values subsequently. Then, repeat the steps of obtaining the corresponding RGB pixel values according to the pixel grid, where the RGB pixel values include the R pixel value, the G pixel value, and the B pixel value to obtaining the grayscale value of the pixel grid according to the R pixel value, the G pixel value, and the B pixel value, so as to traverse all pixel grids and obtain multiple grayscale values of the pixel grids. In order to accurately evaluate the overall roughness of the road surface, it is necessary to analyze each part of the road surface image. Traversing all pixel grids is a necessary means to obtain complete road surface information. Only in this way can a comprehensive and accurate grayscale value distribution be obtained, and then based on these data, the road surface roughness value can be accurately calculated, avoiding misjudgment of the road surface condition due to local analysis. At the same time, by traversing all pixel grids, the grayscale values of each small area of the entire road surface image are obtained, so as to comprehensively master the distribution of the road surface image in terms of brightness. These sets of grayscale values constitute the grayscale feature map of the road surface image, which can reflect information such as the roughness difference at different positions of the road surface, providing sufficient data samples for accurately calculating the road surface roughness value. Then, compare multiple grayscale values of the pixel grids with a preset grayscale value - roughness value table to obtain multiple first road surface roughness values, and perform an average calculation on the multiple first road surface roughness values to obtain the average road surface roughness value. Take the average road surface roughness value as the road surface roughness value. In this way, by comparing with the preset grayscale value - roughness value table, the grayscale value of the pixel grid is converted into the corresponding road surface roughness value, realizing the quantitative conversion from image data to the actual roughness of the road surface. Taking the average of multiple first road surface roughness values can reduce the roughness value deviation caused by local abnormal grayscale values (such as image noise, local special textures, etc.), making the finally obtained road surface roughness value better represent the average roughness of the entire road surface and improving the stability and reliability of the data. Then, obtain the road surface inclination angle according to the road surface inclination, and convert the road surface inclination into the road surface inclination angle, which is a parameter that is more convenient to use in physical calculations. The road surface inclination angle needs to be considered when calculating the road surface friction coefficient because the inclination angle affects the components of the vehicle gravity in the directions parallel and perpendicular to the road surface, thereby affecting the braking effect of the vehicle. Accurately obtaining the road surface inclination angle can calculate the road surface friction coefficient more precisely, so as to more accurately evaluate the braking risk of the vehicle on the inclined road surface. Finally, calculate the road surface friction coefficient according to the road surface roughness value and the road surface inclination angle. In this way, using the road surface roughness value and the inclination angle, the road surface friction coefficient is calculated through a specific formula. This coefficient comprehensively considers the influence of the roughness and inclination of the road surface on the friction force between the vehicle tire and the road surface and is a key index for measuring the road surface braking condition. An accurate road surface friction coefficient can provide an important basis for subsequent calculations of braking distance, braking force, etc., making the risk assessment more accurate and scientific.

[0024] In one embodiment, step S4 of obtaining the braking error influence index according to the surface wear values of multiple brake pads and a preset replacement cycle includes: S401. Obtain the starting usage time and replacement time of the brake pads according to the preset replacement cycle; S402. Calculate the average surface wear degree value of the brake pads according to the surface wear values of multiple brake pads, the starting usage time, and the replacement time. The calculation formula is: ; Wherein, represents the average surface wear degree value of the brake pads, represents the starting usage time, represents the replacement time, represents the surface wear value of the brake pads, n represents the number of surface wear values of the brake pads, where i = 1, 2, 3... n; S403. Calculate the standard surface wear value of the brake pads according to the surface wear values of multiple brake pads and the average surface wear degree value of the brake pads. The calculation formula is: ; Wherein, represents the standard surface wear value of the brake pads, represents the surface wear value of the o-th brake pad, represents the number of surface wear values of the brake pads, o represents the serial number of the surface wear value of the brake pads, where o = 1, 2, 3... k, represents the average surface wear degree of the brake pads; S404. Calculate the surface wear influence coefficient of the brake pads according to the standard surface wear value of the brake pads and the average surface wear degree value of the brake pads. The calculation formula is: ; Wherein, represents the surface wear influence coefficient of the brake pads, represents the average surface wear degree value of the brake pads, represents the standard surface wear value of the brake pads; S405. Use the surface wear influence coefficient of the brake pads as the braking error influence index.

[0025] As described in the above steps S401-S405, the present invention first obtains the starting time of use and the replacement time of the brake pad according to the preset replacement cycle, so as to clarify the use time range of the brake pad, which is the time dimension basis for evaluating the wear of the brake pad. The starting time of use and the replacement time determine the time period of the brake pad in the entire use cycle, provide a time reference system for the subsequent calculation of the wear degree, and help to accurately analyze the wear condition of the brake pad at different use stages. Then, the average wear degree value of the brake pad surface is calculated based on the multiple wear values ​​of the brake pad surface, the starting time of use and the replacement time, and the wear value and the use time of the brake pad in the entire use cycle are comprehensively considered to calculate the average wear degree value. This value can reflect the average wear rate of the brake pad over a period of time, so that we can have a macroscopic understanding of the overall wear of the brake pad, rather than just being limited to the wear state at a specific moment. At the same time, through the average wear degree value, it can be compared with the standard wear conditions of other vehicles or brake pads of the same type to determine whether the current wear of the brake pad is normal, whether there is abnormal wear (such as wear too fast or too slow), and provide an important quantitative indicator for further evaluating the change in braking performance. Then, the standard brake pad surface wear value is calculated based on the multiple brake pad surface wear values ​​and the average wear degree value of the brake pad surface. In this way, the calculation of the standard brake pad surface wear value can measure the discrete degree of each brake pad surface wear value relative to the average wear degree value. A small discrete degree indicates that the wear of each brake pad is relatively uniform, otherwise it indicates uneven wear, and there may be abnormal wear of individual brake pads. Next, the brake pad surface wear influence coefficient is calculated based on the standard brake pad surface wear value and the average wear degree value of the brake pad surface. In this way, the brake pad surface wear influence coefficient reflects the proportional relationship between the average wear degree value and the standard wear value, and it can quantify the degree of influence of brake pad wear on braking performance. The larger the wear impact coefficient, the greater the potential impact of wear on braking performance, and vice versa. At the same time, this coefficient directly links the wear of the brake pads with the impact on braking performance, providing a key intermediate parameter for the subsequent calculation of the brake error impact index, allowing the system to more accurately evaluate the changes in braking performance caused by brake pad wear, and then consider this factor in the risk warning. Finally, the brake pad surface wear impact coefficient is used as the brake error impact index. In this way, the brake error impact index comprehensively considers the wear of the brake pads and uses it as the final indicator to measure the changes in braking performance caused by brake pad wear. This index can directly reflect the possible degree of deviation between the actual braking performance of the vehicle and the ideal braking performance under the current brake pad wear state.

[0026] In one embodiment, the step S5 of obtaining the effective braking distance according to the initial speed of the vehicle, the road friction coefficient and the preset gravity acceleration includes: S501. Obtain the effective braking distance based on the initial speed of the vehicle, the road surface friction coefficient, and the preset gravitational acceleration. The calculation formula is as follows: ; Wherein, represents the effective braking distance, represents the road surface friction coefficient, represents the initial speed of the vehicle, represents the preset gravitational acceleration.

[0027] As described in the above step S501, the present invention obtains the effective braking distance based on the initial speed of the vehicle, the road surface friction coefficient, and the preset gravitational acceleration. In this way, during the vehicle driving process, accurately mastering the braking distance is an important prerequisite for ensuring safety. Calculating the braking distance according to the classical physical kinematics formula is a scientific and widely recognized method, which can accurately reflect the relationship between the vehicle motion state, road surface conditions, and braking effect. Incorporating the initial speed, road surface friction coefficient, and gravitational acceleration into the calculation takes into account the main factors affecting braking, provides a reliable braking distance reference value based on physical principles for the driver, enables them to make reasonable driving decisions according to this value in actual driving, and meets the actual needs of vehicle safe driving and risk assessment.

[0028] In one embodiment, step S6 of obtaining the braking force based on the initial speed of the vehicle, the mass of the vehicle, the braking error influence index, and the effective braking distance includes: S601. Obtain the historical braking force and the force of the historical driver stepping on the pedal based on big data, and calculate the braking efficiency according to the historical braking force and the force of the historical driver stepping on the pedal; S602. Obtain the braking force based on the initial speed of the vehicle, the mass of the vehicle, the braking efficiency, the braking error influence index, and the effective braking distance. The calculation formula is as follows: ; Wherein, represents the braking force, represents the mass of the vehicle, represents the initial speed of the vehicle, represents the braking efficiency, represents the braking error influence index.

[0029] As described in the above steps S601 - S602, since the braking effect of a vehicle depends not only on the braking system hardware of the vehicle itself but also is closely related to the driver's operation. To more comprehensively and accurately evaluate the braking ability of a vehicle during actual driving, the driver operation factor needs to be considered. Therefore, the present invention first obtains historical braking force and the force with which the driver stepped on the pedal based on big data, and calculates the braking efficiency according to the historical braking force and the force with which the driver stepped on the pedal. In this way, by mining the historical data of the vehicle through big data to obtain the historical braking force and the information on the force with which the driver stepped on the pedal, the braking performance of the vehicle under different past driving conditions can be reflected. Calculating the braking efficiency can quantify the relationship between the force with which the driver steps on the pedal and the actual generated braking force, that is, evaluate the effectiveness of the driver's operation in the vehicle braking system. At the same time, the braking efficiency is an important indicator for measuring the performance of the vehicle braking system and the degree of cooperation between the driver's operation. Understanding the braking efficiency helps to more accurately predict the braking effect of the vehicle in the current situation because it takes into account the comprehensive influence of the characteristics of the vehicle's own braking system and the driver's operation habits on braking. Since during the vehicle braking process, multiple factors interact to jointly determine the required braking force. The initial speed and mass determine the kinetic energy of the vehicle, the braking efficiency reflects the actual effectiveness of the vehicle braking system, the braking error impact index takes into account the influence of brake pad wear on braking, and the safe braking distance is the ultimate target requirement. Therefore, the braking force of the brake is obtained according to the initial speed of the vehicle, the mass of the vehicle, the braking efficiency, the braking error impact index, and the effective braking distance. In this way, various factors such as the initial motion state of the vehicle (initial speed and mass), the performance of the braking system (braking efficiency), the brake pad wear condition (braking error impact index), and the required safe braking distance are comprehensively considered, and the braking force of the brake required to achieve safe braking is accurately calculated. This force value provides a clear operation reference for the driver, informing them of how much braking force should be applied under the current vehicle state and road conditions to ensure that the vehicle stops within a safe distance. At the same time, calculating the braking force of the brake organically combines various factors affecting vehicle braking, elevating the risk prompt from a simple risk notification to the level of providing specific operation guidance for the driver, which helps to improve the driver's operation accuracy, reduce the accident risk caused by improper braking, and ensure driving safety.

[0030] In one embodiment, step S7 of prompting vehicle risks according to the braking force of the brake includes: S701. Determine whether the braking force of the brake meets the preset threshold interval range; When the braking force of the brake does not meet the preset threshold interval range and is less than the minimum value of the preset threshold interval range, it is determined that the force with which the driver steps on the brake pedal is small, and a first reminder signal is generated, and a corresponding preset yellow indicator light is turned on according to the first reminder signal for risk prompting; When the braking force meets the preset threshold range, it is determined that the force of the driver stepping on the brake pedal is normal and a second reminder signal is generated, and a corresponding preset green indicator light is turned on according to the second reminder signal for safety reminder; When the braking force does not meet the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the force of the driver stepping on the brake pedal is relatively large and a third reminder signal is generated, and a corresponding preset red indicator light is turned on according to the third reminder signal for risk reminder.

[0031] As described in the above step S701, since excessive braking force during driving is an extremely dangerous situation that requires the driver to react immediately. Red indicator lights are widely used to indicate emergency dangerous situations due to their strong visual warning effect, which conforms to the human instinctive reaction mechanism to danger signals. In this way, the system can convey the most urgent risk information to the driver in the shortest time, prompting them to take emergency measures to correct wrong operations and prevent serious accidents. This is one of the key measures to ensure driving safety and also the core function manifestation of the risk warning system when facing emergency dangerous situations. The present invention determines whether the braking force meets the preset threshold range. By comparing the calculated braking force with the preset threshold range, the rationality of the current braking operation can be quickly evaluated. The preset threshold range is determined according to the vehicle's performance, safety standards, as well as a large amount of actual driving data and experience, representing the normal and safe braking force range. When the braking force does not meet the preset threshold range and is less than the minimum value of the preset threshold range, it is determined that the driver steps on the brake pedal with a small force and a first reminder signal is generated, and the corresponding preset yellow indicator light is turned on according to the first reminder signal for risk warning. In this way, when the braking force is too small, the vehicle may not be able to stop within the expected safe distance, and there is a risk of collision such as rear-end collision. Generating the first reminder signal and turning on the yellow indicator light can timely attract the driver's attention, informing them that the current braking force is insufficient. At the same time, the yellow indicator light, as a warning signal, reminds the driver to increase the braking force, but it does not indicate an emergency danger like the red indicator light, giving the driver an appropriate warning level, allowing them to adjust the operation relatively calmly while paying attention to the risk and avoiding panicking due to a sudden emergency reminder, which helps to guide the driver to correctly respond to the risk on the premise of ensuring safety. When the braking force meets the preset threshold range, it is determined that the driver steps on the brake pedal with a normal force and a second reminder signal is generated, and the corresponding preset green indicator light is turned on according to the second reminder signal for safety warning. In this way, when the braking force is within the normal range, it indicates that the driver's braking operation meets the safety requirements and the vehicle can stop within the expected safe distance.Generate a second reminder signal and turn on the green indicator light to give positive feedback to the driver, letting them know that the current braking operation is correct, enhancing the driver's confidence in their own operation, and at the same time strengthening the correct operation behavior pattern. At the same time, as a safety reminder, the green indicator light helps the driver maintain a good state of mind during driving, reducing the anxiety caused by uncertainty about the braking operation, enabling them to focus more on other driving tasks, and further improving driving safety and comfort. When the braking force does not meet the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the driver steps on the brake pedal with a large force and a third reminder signal is generated, and the corresponding preset red indicator light is turned on according to the third reminder signal for risk warning. In this way, too large a braking force may lead to dangerous situations such as vehicle out of control, rollover or passenger discomfort, especially when driving at high speed or on poor road conditions, the risk is higher. Generate a third reminder signal and turn on the red indicator light to warn the driver in the strongest way that there is a serious risk in the current braking operation and immediate adjustment is needed. At the same time, as an emergency danger signal, the red indicator light can quickly attract the driver's attention, making them aware of the severity of the problem, and prompting them to release the brake pedal as soon as possible or appropriately reduce the braking force to avoid dangerous situations and maximize the safety of the vehicle and personnel. Furthermore, through the above steps, the driver can be intuitively told how much braking force is needed to meet the current braking distance, thus avoiding braking risks for the vehicle.

[0032] The present application also provides a vehicle risk reminder system based on big data, including: A first acquisition module for acquiring vehicle driving information, where the vehicle driving information includes road surface information and vehicle braking information; A second acquisition module for acquiring the mass and initial speed of the vehicle according to the vehicle braking information; A third acquisition module for acquiring the road surface roughness value and road surface inclination according to the road surface information, and acquiring the road surface friction coefficient according to the road surface roughness value and the road surface inclination; A fourth acquisition module for acquiring vehicle maintenance information based on big data, acquiring multiple brake pad surface wear values according to the vehicle maintenance information, and acquiring a braking error influence index according to the multiple brake pad surface wear values and a preset replacement cycle; A fifth acquisition module for acquiring the effective braking distance according to the initial speed of the vehicle, the road surface friction coefficient and a preset gravitational acceleration; A sixth acquisition module for acquiring the braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance; A first reminder module for reminding of vehicle risks according to the braking force.

[0033] In one embodiment, the third acquisition module includes: A first acquisition unit, configured to acquire image information according to the road surface information, perform gray-scale processing on the image information, and obtain road surface gray-scale image information; A first segmentation unit, configured to perform grid segmentation on the road surface gray-scale image information in standard pixel units to obtain a plurality of pixel grids; A second acquisition unit, configured to acquire corresponding RGB pixel values according to the pixel grids, where the RGB pixel values include R pixel values, G pixel values, and B pixel values; A first calculation unit, configured to obtain pixel grid gray-scale values according to the R pixel values, the G pixel values, and the B pixel values, where the calculation formula is: ; where, represents the pixel grid gray-scale value, R represents the R pixel value, G represents the G pixel value, and B represents the B pixel value; A third acquisition unit, configured to repeat the steps of acquiring corresponding RGB pixel values according to the pixel grids, where the RGB pixel values include R pixel values, G pixel values, and B pixel values to obtaining pixel grid gray-scale values according to the R pixel values, the G pixel values, and the B pixel values, so as to traverse all pixel grids and obtain a plurality of pixel grid gray-scale values; A first comparison unit, configured to compare a plurality of the pixel grid gray-scale values with a preset gray-scale value - roughness value table to obtain a plurality of first road surface roughness values, perform mean calculation on the plurality of first road surface roughness values to obtain an average road surface roughness value, and use the average road surface roughness value as the road surface roughness value; A fourth acquisition unit, configured to acquire a road surface tilt angle according to the road surface inclination; A second calculation unit, configured to calculate a road surface friction coefficient according to the road surface roughness value and the road surface tilt angle, where the calculation formula is: ; where, represents the road surface friction coefficient, represents the road surface roughness value, represents the road surface tilt angle.

[0034] This application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above method for vehicle risk prompt based on big data are implemented.

[0035] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for vehicle risk prompt based on big data are implemented.

[0036] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in the present application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0037] It should be noted that in this article, the terms "including", "comprising", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, device, article, or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, device, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, device, article, or method including that element.

[0038] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A vehicle risk warning method based on big data, characterized in that: include: Acquiring vehicle driving information, wherein the vehicle driving information includes road surface information and vehicle braking information; Acquiring the mass of the vehicle and the initial speed of the vehicle according to the vehicle braking information; Acquire a road surface roughness value and a road surface inclination according to the road surface information, and acquire a road surface friction coefficient according to the road surface roughness value and the road surface inclination; Acquire vehicle maintenance information based on big data, acquire multiple brake pad surface wear values ​​according to the vehicle maintenance information, and acquire a brake error influence index according to the multiple brake pad surface wear values ​​and a preset replacement cycle; Obtaining an effective braking distance according to the initial speed of the vehicle, the road friction coefficient and a preset gravity acceleration; Obtaining the braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance; The vehicle risk is prompted according to the braking force.

2. The vehicle risk warning method based on big data according to claim 1 is characterized in that: The step of obtaining the road surface friction coefficient according to the road surface roughness value and the road surface inclination comprises: Acquiring image information according to the road surface information, and performing grayscale processing on the image information to obtain road surface grayscale image information; Performing standard pixel unit grid segmentation on the road surface grayscale image information to obtain multiple pixel grids; Obtaining corresponding RGB pixel values ​​according to the pixel grid, and obtaining pixel grid grayscale values ​​according to the RGB pixel values; Repeat the steps of obtaining the corresponding RGB pixel value according to the pixel grid, and obtaining the pixel grid grayscale value according to the RGB pixel value, so as to traverse all pixel grids and obtain multiple pixel grid grayscale values; Comparing the plurality of pixel grid grayscale values ​​with a preset grayscale value-roughness value table to obtain a plurality of first road surface roughness values, and calculating the average of the plurality of first road surface roughness values ​​to obtain an average road surface roughness value as the road surface roughness value; Acquiring a road surface inclination angle according to the road surface inclination; The road surface friction coefficient is calculated according to the road surface roughness value and the road surface inclination angle.

3. The vehicle risk warning method based on big data according to claim 1 is characterized in that: The step of obtaining the brake error influence index according to the plurality of brake pad surface wear values ​​and the preset replacement cycle comprises: Obtain the starting time of use and the replacement time of the brake pad according to the preset replacement cycle; Calculate the average wear degree value of the brake pad surface according to the plurality of brake pad surface wear values, the start time of use and the replacement time; Calculating a standard brake pad surface wear value based on the plurality of brake pad surface wear values ​​and the brake pad surface average wear degree value; Calculate the brake pad surface wear influence coefficient according to the standard brake pad surface wear value and the brake pad surface average wear degree value; The brake pad surface wear influence coefficient is used as the braking error influence index.

4. The vehicle risk warning method based on big data according to claim 1 is characterized in that: The step of obtaining the effective braking distance according to the initial speed of the vehicle, the road friction coefficient and the preset gravity acceleration comprises: The effective braking distance is obtained according to the initial speed of the vehicle, the road friction coefficient and the preset gravity acceleration, wherein the calculation formula is: ； in, Indicates the effective braking distance, is the road friction coefficient, represents the initial speed of the vehicle, Indicates the preset gravity acceleration.

5. The vehicle risk warning method based on big data according to claim 1 is characterized in that: The step of obtaining the braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance comprises: Acquire historical braking force and historical driver pedaling force based on big data, and calculate braking efficiency according to the historical braking force and historical driver pedaling force; The braking force is obtained according to the initial speed of the vehicle, the mass of the vehicle, the braking efficiency, the braking error influence index and the effective braking distance.

6. The vehicle risk warning method based on big data according to claim 1 is characterized in that: The step of prompting the vehicle risk according to the braking force includes: Determining whether the braking force meets a preset threshold range; When the braking force does not meet the preset threshold value range and is less than the minimum value of the preset threshold value range, it is determined that the driver's foot is too weak on the brake pedal and a first reminder signal is generated, and the corresponding preset yellow indicator light is turned on according to the first reminder signal to give a risk warning; When the braking force meets the preset threshold range, it is determined that the force of the driver's foot on the brake pedal is normal and a second reminder signal is generated, and the corresponding preset green indicator light is turned on according to the second reminder signal for safety reminder; When the braking force does not meet the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the driver's foot is pressing the brake pedal with great force and a third reminder signal is generated, and the corresponding preset red indicator light is turned on according to the third reminder signal to provide a risk warning.

7. A vehicle risk warning system based on big data, characterized in that: include: A first acquisition module is used to acquire vehicle driving information, wherein the vehicle driving information includes road surface information and vehicle braking information; A second acquisition module, used for acquiring the mass of the vehicle and the initial speed of the vehicle according to the vehicle braking information; A third acquisition module, used to acquire a road surface roughness value and a road surface inclination according to the road surface information, and acquire a road surface friction coefficient according to the road surface roughness value and the road surface inclination; a fourth acquisition module, configured to acquire vehicle maintenance information based on big data, acquire a plurality of brake pad surface wear values ​​according to the vehicle maintenance information, and acquire a brake error influence index according to the plurality of brake pad surface wear values ​​and a preset replacement cycle; A fifth acquisition module, configured to acquire an effective braking distance according to an initial speed of the vehicle, a friction coefficient of the road surface and a preset gravity acceleration; a sixth acquisition module, configured to acquire the braking force according to the initial speed of the vehicle, the mass of the vehicle, the braking error influence index and the effective braking distance; The first prompt module is used to prompt the vehicle risk according to the braking force.

8. The vehicle risk warning system based on big data according to claim 7 is characterized in that: The third acquisition module includes: A first acquisition unit, configured to acquire image information according to the road surface information, and perform grayscale processing on the image information to obtain road surface grayscale image information; The first segmentation unit is used to perform standard pixel unit grid segmentation on the road surface grayscale image information to obtain a plurality of pixel grids; A second acquisition unit, configured to acquire corresponding RGB pixel values ​​according to the pixel grid, and acquire a pixel grid grayscale value according to the RGB pixel values; A third acquisition unit, configured to repeat the steps of acquiring the corresponding RGB pixel value according to the pixel grid, and acquiring the pixel grid grayscale value according to the RGB pixel value, so as to traverse all pixel grids and obtain a plurality of pixel grid grayscale values; A first comparison unit is used to compare the grayscale values ​​of the plurality of pixel grids with a preset grayscale value-roughness value table to obtain a plurality of first road surface roughness values, and average the plurality of first road surface roughness values ​​to obtain an average road surface roughness value, and use the average road surface roughness value as the road surface roughness value; A fourth acquisition unit, configured to acquire a road surface inclination angle according to the road surface inclination; The second calculation unit is used to calculate the road surface friction coefficient according to the road surface roughness value and the road surface inclination angle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images