Braking distance calculation method, device, vehicle and medium

Abstract

The present invention provides a method, device, automobile and medium for calculating braking distance, including: obtaining the current driving behavior data of the target user in the adaptive cruise mode; inputting the current driving behavior data into a pre-trained rule model to obtain the braking distance output by the rule model based on the current driving behavior data; wherein the rule model is trained based on the historical braking behavior data of the target user. The present invention can determine the braking distance suitable for the driver according to the driver's driving habits, and avoid the driver's active braking to inhibit the function of ACC.

Description

Technical Field

[0001] The present invention relates to the field of automobile intelligent technology, and in particular to a braking distance calculation method, device, automobile and medium. Background Art

[0002] With the rapid development of Advanced Driving Assistance System (ADAS) technology, its market penetration rate is increasing. In some specific scenarios, the Adaptive Cruise Control (ACC) function can be turned on to relieve the driver's fatigue. The following distance and cruising speed set by different drivers according to their driving proficiency are inconsistent, and the braking distances corresponding to different following distances and speeds are also inconsistent. At the same time, the driver's ideal braking distance and the expected braking distance of ACC may also be inconsistent, which leads to some drivers' uncertainty about the state of ACC or braking distance. In some cases, they will actively brake to inhibit the function of ACC. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a braking distance calculation method, device, automobile and medium, which can determine the braking distance suitable for the driver according to the driver's driving habits, and avoid the driver's active braking to suppress the ACC function.

[0004] In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for calculating a braking distance, comprising: obtaining current driving behavior data of a target user in an adaptive cruise mode; inputting the current driving behavior data into a pre-trained rule model to obtain a braking distance output by the rule model based on the current driving behavior data; wherein the rule model is trained based on the historical braking behavior data of the target user.

[0006] In one embodiment, the current driving behavior data carries a user identifier, and the rule model includes at least one braking behavior rule; the rule model outputs a braking distance based on the current driving behavior data, including: the rule model searches for a target braking behavior rule that matches the user identifier; and outputs a braking distance based on the target braking behavior rule.

[0007] In one implementation, the aforementioned method further includes: prompting the target user based on the braking distance.

[0008] In one embodiment, the training process of the rule model includes: obtaining historical braking behavior data of the target user when actively braking in adaptive cruise mode; wherein the historical braking behavior data includes historical driving behavior data and historical braking distances corresponding to the historical driving behavior data; performing data cleaning on the historical braking behavior data; dividing the cleaned historical braking behavior data into a training set; and iteratively training the machine learning model based on the training set to generate a rule model.

[0009] In one embodiment, the aforementioned method also includes: dividing the historical braking behavior data after cleaning into a test set; wherein the test set is different from the training set; based on the test set, using a preset evaluation algorithm, evaluating the rule model to obtain an evaluation result; if the evaluation result does not meet the preset conditions, iteratively training the machine learning model based on the training set.

[0010] In one embodiment, a machine learning model is iteratively trained based on a training set to generate a rule model, including: determining a braking behavior rule corresponding to a target user based on the training set; wherein the braking behavior rule represents a corresponding relationship between driving behavior data and braking distance; and optimizing the braking behavior rule using a preset rule learning algorithm to generate a rule model.

[0011] In one embodiment, the aforementioned method further includes: obtaining current braking behavior data of the target user actively braking in the adaptive cruise mode; and updating the braking behavior rules corresponding to the target user based on the current braking behavior data.

[0012] In a second aspect, an embodiment of the present invention provides a braking distance calculation device, comprising: a data acquisition module, used to obtain the current driving behavior data of a target user in an adaptive cruise mode; a braking distance determination module, used to input the current driving behavior data into a pre-trained rule model to obtain a braking distance output by the rule model based on the current driving behavior data; wherein the rule model is trained based on the historical braking behavior data of the target user.

[0013] In a third aspect, an embodiment of the present invention provides a car, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of any one of the methods provided in the first aspect above.

[0014] In a fourth aspect, an embodiment of the present invention 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 any one of the methods provided in the first aspect are executed.

[0015] The embodiments of the present invention bring the following beneficial effects:

[0016] The above-mentioned braking distance calculation method, device, automobile and medium provided by the embodiment of the present invention first obtain the current driving behavior data of the target user in the adaptive cruise mode; then input the current driving behavior data into a pre-trained rule model (trained based on the historical braking behavior data of the target user) to obtain the braking distance output by the rule model based on the current driving behavior data. The above-mentioned method can analyze the historical behavior data of the driver taking active braking when the ACC function is turned on, and train a rule model based on the analyzed data results. Based on the rule model, the braking distance that meets the driver's driving habits (i.e., the ideal braking distance) can be obtained, so that autonomous braking can be performed at a braking distance that is comfortable for the driver, thereby improving safety and driver comfort; at the same time, it can avoid the driver's active braking to suppress the ACC function.

[0017] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flowchart of a method for calculating braking distance provided by an embodiment of the present invention;

[0021] Figure 2 A flowchart of a behavior analysis method based on machine learning provided by an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of the structure of a behavior analysis system based on machine learning provided by an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of the structure of a braking distance calculation device provided by an embodiment of the present invention;

[0024] Figure 5 A schematic structural diagram of a car provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] At present, the following distances and cruising speeds set by different drivers according to their driving proficiency are inconsistent, and the braking distances corresponding to different following distances and speeds are also inconsistent. At the same time, the driver's ideal braking distance and the ACC's expected braking distance may also be inconsistent, causing some drivers to become uncertain about the ACC status or braking distance, and in some cases actively brake to inhibit the ACC function.

[0027] Based on this, the embodiments of the present invention provide a braking distance calculation method, device, automobile and medium, which can determine a braking distance suitable for the driver according to the driver's driving habits, and avoid the driver's active braking to suppress the ACC function.

[0028] To facilitate understanding of this embodiment, a method for calculating a braking distance disclosed in an embodiment of the present invention is first introduced in detail. The method can be executed by a controller of a vehicle, see Figure 1 The flowchart of a method for calculating braking distance shown in FIG. 1 illustrates that the method mainly includes the following steps S101 to S102:

[0029] Step S101: Acquire current driving behavior data of a target user in an adaptive cruise mode.

[0030] In one embodiment, the target user is the driver, and the current driving behavior data is the driver's behavior data when the ACC function is turned on, including: time information, weather information, relative speed and relative distance to the target object (such as vehicles, pedestrians, obstacles, etc.), vehicle deceleration, road curvature and other information.

[0031] Step S102: input the current driving behavior data into a pre-trained rule model to obtain a braking distance output by the rule model based on the current driving behavior data; wherein the rule model is trained based on the historical braking behavior data of the target user.

[0032] In one embodiment, the rule model can be obtained by analyzing the historical behavior data of the driver taking active braking when the ACC function is turned on, and training the machine learning model based on the analyzed data results. When the ACC cruise control or following mode is turned on, the rule model can output the corresponding braking distance according to different driving behavior data, so as to meet the driver's ideal braking distance.

[0033] The above-mentioned braking distance calculation method provided by the embodiment of the present invention can analyze the historical behavior data of the driver's active braking when the ACC function is turned on, and obtain a rule model based on the analysis data results. Based on the rule model, the braking distance that meets the driver's driving habits (i.e., the ideal braking distance) can be obtained, so that autonomous braking can be performed at a braking distance that is comfortable for the driver, thereby improving safety and driver comfort; at the same time, it can avoid the driver's active braking to suppress the ACC function.

[0034] Considering that different drivers have different driving habits, their ideal braking distances will also be different. Therefore, the braking behavior rules corresponding to each driver are also different. The rule model in the embodiment of the present invention may include braking behavior rules obtained by analyzing the historical behavior data of different drivers taking active braking when the ACC function is turned on. In order to distinguish them, the braking behavior rules and the current driving behavior data can be marked by the driver's user ID, so that the braking behavior rules corresponding to the target user can be determined based on the user ID. Based on this, in the embodiment of the present invention, when the rule model outputs the braking distance based on the current driving behavior data, it can adopt the following methods, including but not limited to: first, find the target braking behavior rule that matches the user ID; then output the braking distance based on the target braking behavior rule.

[0035] Furthermore, in order to enhance the driver's experience, enable the driver to determine the state of ACC and the current braking distance, and avoid the inhibition of ACC due to the driver's active intervention in braking, the embodiment of the present invention can also prompt the target user based on the braking distance. Specifically, the current braking distance, the start time of autonomous braking, and the working state of ACC can be fed back to the driver in advance when braking is required through text display on the central control screen or instrument, or through voice broadcast, so that the driver can understand the working state of ACC and the start time of autonomous braking. The start time of autonomous braking can be determined based on the distance difference between the current position of the vehicle and the braking distance, as well as the current vehicle speed.

[0036] The present invention also provides a method for training a rule model, which mainly includes the following steps 1 to 5:

[0037] Step 1: Obtain historical braking behavior data of the target user when actively braking in an adaptive cruise mode; wherein the historical braking behavior data includes historical driving behavior data and historical braking distances corresponding to the historical driving behavior data.

[0038] In one embodiment, to facilitate data collection, when the ACC of the vehicle is normally turned on, the time information, weather information, relative speed and relative distance to the target object (such as vehicles, pedestrians, obstacles, etc.), vehicle deceleration, road curvature and other information when the driver actively brakes in different time periods, different scenes, different weather, and different road conditions can be collected, as well as the braking distance when the driver actively brakes.

[0039] Step 2: Clean the historical braking behavior data.

[0040] In order to facilitate model training and improve the accuracy of the rule model, the acquired historical braking behavior data can be processed in advance in this embodiment. Specifically, the acquired historical braking behavior data can be formatted first, such as converting the braking behavior data into a chart format, so as to facilitate subsequent data cleaning and model training; then the formatted data can be cleaned by using the python pandas data analysis library through two-dimensional or three-dimensional display, and the data can be cleaned according to the ISO15622-2018 ACC performance requirements to remove outlier data, such as data when the driver misoperates.

[0041] Step 3: Divide the cleaned historical braking behavior data into a training set.

[0042] Specifically, the cleaned historical braking behavior data may be divided into a training set, a test set, and a validation set according to a certain ratio, such as a ratio of 8:1:1.

[0043] Step 4: Iteratively train the machine learning model based on the training set to generate a rule model.

[0044] Since the behavior data of the user when turning on ACC is known, the rule model can be trained using supervised learning of machine learning. In specific applications, the rule model can be generated using the following methods, including but not limited to:

[0045] Firstly, based on the training set, the braking behavior rules corresponding to the target user are determined; wherein the braking behavior rules represent the corresponding relationship between the driving behavior data and the braking distance.

[0046] In one embodiment, a rule model that can cover as much data as possible can be generated based on first-order rule learning using the data in the training set. Specifically, the cleaned data can be used to generate different braking behavior rules according to the rule information, and then generate corresponding label information (that is, the braking distances corresponding to different braking behavior rules) to facilitate rule model training. For example, a braking behavior rule can be expressed as r1: f(a)∧f(b)∧f(c)f(d)…∧f(n)→Result, where a, b, c, d, and n represent rule conditions, which can specifically represent weather, speed, distance, time and other information, f(a), f(b), f(c), and f(n) represent judgments on rule conditions, and Result represents a classification result after all conditions have been processed. This result can represent the braking distance by default. When the rule conditions are different, the braking distances obtained are also different.

[0047] Then, the preset rule learning algorithm is used to optimize the braking behavior rules and generate a rule model.

[0048] In order to prevent the overfitting of the rules, the embodiments of the present invention may use a preset rule learning algorithm, such as a pre-pruned CN2 algorithm, to optimize the braking behavior rules, and select whether to prune by evaluating the performance of the rule model, thereby obtaining an optimized rule model. In this embodiment, the judgment may be made by calculating the likelihood ratio statistic (LRS), and the larger the value of the LRS, the better the effect of the rule model, and vice versa, the worse the effect of the rule model.

[0049] Specifically, you can use m + With m - represents the number of positive and negative samples in the training set, Indicates the number of positive and negative samples covered by the rule model. The calculation method of LRS is as follows:

[0050]

[0051] Step 5: Based on the test set, use the preset evaluation algorithm to evaluate the rule model and obtain the evaluation result; if the evaluation result does not meet the preset conditions, iteratively train the machine learning model based on the training set.

[0052] Specifically, in this embodiment, the F1 score indicator can be used to test whether the rule model meets the expected requirements. If the F1 score reaches the threshold (that is, it meets the preset conditions), it indicates that the rule model meets the expected requirements; otherwise, the rule model continues to be trained. The F1 score takes into account both the precision rate P and the recall rate R, and the calculation formula is as follows:

[0053]

[0054] Furthermore, considering that the driver's driving habits may also change, in order to ensure that the braking distance output by the rule model can make the driver feel comfortable and safe, in the embodiment of the present invention, the braking behavior rules can also be updated according to the changes in the driver's braking behavior data when the ACC active braking is turned on. Specifically, firstly, the current braking behavior data of the target user's active braking in the adaptive cruise mode is obtained; then, based on the current braking behavior data, the braking behavior rules corresponding to the target user are updated.

[0055] The above method provided by the embodiment of the present invention learns the driver's ACC active braking behavior through a machine learning method to obtain the braking distance corresponding to each driver, thereby improving the interaction and experience between the driver and the assisted driving.

[0056] The embodiment of the present invention also provides a behavior analysis method based on machine learning, that is, a method for updating a rule model, see Figure 2 As shown, the method mainly includes the following steps S201 to S205:

[0057] Step S201: Obtain user behavior data to be analyzed.

[0058] Specifically, the time information, weather information, relative speed and relative distance to the target object, vehicle deceleration, road curvature and other information when the user turns on the ACC function for autonomous braking are obtained, as well as the braking distance when the driver actively brakes.

[0059] Step S202: Input the user behavior data into the machine learning model for detection.

[0060] In specific applications, the user behavior data can be formatted and cleaned through a machine learning model (rule model), and details can be found in the aforementioned embodiments.

[0061] Step S203: Outputting user behavior data that complies with preset rules.

[0062] Specifically, the user behavior data is analyzed through a machine learning model, and data that conforms to the user's braking behavior rules is output.

[0063] Step S204: Generate a tag corresponding to the user based on the user's behavior data, that is, generate a braking distance corresponding to the user based on the user's behavior data.

[0064] Step S205: updating the labeled user behavior data into the machine learning model, that is, updating the machine learning model with the user's new behavior data and braking distance.

[0065] The behavior analysis method based on machine learning provided in the embodiment of the present invention analyzes the driver's active braking behavior data when the ACC function is turned on, updates the new braking behavior rules to the machine learning model according to the analyzed data results, and feeds back the braking countdown and the operating status of ACC to the driver in advance when braking is required, thereby improving safety and driver comfort, and at the same time avoiding the driver's active braking to suppress the ACC function.

[0066] The present invention also provides a behavior analysis system based on machine learning. Figure 3 As shown, it includes: an input module, an analysis module, an update module and an application module.

[0067] The input module is used to input the user's driving behavior data when active braking is turned on with ACC.

[0068] The analysis module is used to analyze the driving behavior data of users who turn on ACC active braking according to the basic control strategy, minimum requirements for diagnosis and fault response, and performance test requirements of the ISO15622-2018 ACC system, and determine whether the current behavior data is reasonable. If it is unreasonable, it is filtered. If it is reasonable, the data is labeled and counted according to the user's ID, that is, the user identification of the driving behavior data and the corresponding braking distance are determined.

[0069] The update module is used to update the labeled driving behavior data into the machine learning model and update the output rules of the machine learning model (i.e., braking behavior rules).

[0070] The application module is used to apply the model of the update rule to the actual scenario, and output the braking distance corresponding to the user's driving behavior data in the ACC-on scenario according to the user's corresponding current driving behavior data.

[0071] The system provided by the embodiment of the present invention analyzes the driver's active braking behavior data when the ACC function is turned on, updates the new braking behavior rules to the machine learning model according to the analysis data results, and provides the driver with advance feedback of the braking countdown and the operating status of ACC when braking is required, thereby improving safety and driver comfort, and at the same time avoiding the driver's active braking to suppress the ACC function.

[0072] For the calculation method of the braking distance provided in the above embodiment, the embodiment of the present invention further provides a calculation device for the braking distance, see Figure 4 A schematic diagram of a braking distance calculation device is shown, and the device may include the following parts:

[0073] The data acquisition module 401 is used to acquire the current driving behavior data of the target user in the adaptive cruise mode.

[0074] The braking distance determination module 402 is used to input the current driving behavior data into a pre-trained rule model to obtain a braking distance output by the rule model based on the current driving behavior data; wherein the rule model is trained based on the historical braking behavior data of the target user.

[0075] The above-mentioned braking distance calculation device provided by the embodiment of the present invention can analyze the historical behavior data of the driver's active braking when the ACC function is turned on, and train a rule model based on the analyzed data results. Based on the rule model, the braking distance that meets the driver's driving habits (i.e., the ideal braking distance) can be obtained, so that autonomous braking can be performed at a braking distance that is comfortable for the driver, thereby improving safety and driver comfort; at the same time, it can avoid the driver's active braking to suppress the ACC function.

[0076] In one embodiment, the current driving behavior data carries a user identifier, and the rule model includes at least one braking behavior rule; the aforementioned braking distance determination module 402 is also used to: the rule model searches for a target braking behavior rule that matches the user identifier; and outputs a braking distance based on the target braking behavior rule.

[0077] In one embodiment, the aforementioned device further includes a push module, which is used to prompt the target user based on the braking distance.

[0078] In one embodiment, the aforementioned device also includes a model training module for obtaining historical braking behavior data of the target user when actively braking in adaptive cruise mode; wherein the historical braking behavior data includes historical driving behavior data and historical braking distances corresponding to the historical driving behavior data; performing data cleaning on the historical braking behavior data; dividing the cleaned historical braking behavior data into a training set; and iteratively training the machine learning model based on the training set to generate a rule model.

[0079] In one embodiment, the aforementioned model training module is also used to divide the historical braking behavior data after cleaning into a test set; wherein the test set is different from the training set; based on the test set, a preset evaluation algorithm is used to evaluate the rule model to obtain an evaluation result; if the evaluation result does not meet the preset conditions, the machine learning model is iteratively trained based on the training set.

[0080] In one embodiment, the aforementioned model training module is also used to determine the braking behavior rules corresponding to the target user based on the training set; wherein the braking behavior rules represent the corresponding relationship between the driving behavior data and the braking distance; and a preset rule learning algorithm is used to optimize the braking behavior rules to generate a rule model.

[0081] In one embodiment, the aforementioned model training module is also used to obtain current braking behavior data of the target user who actively brakes in the adaptive cruise mode; based on the current braking behavior data, the braking behavior rules corresponding to the target user are updated.

[0082] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0083] An embodiment of the present invention further provides a car. Specifically, the car includes a processor and a storage device. The storage device stores a computer program, and when the computer program is run by the processor, it executes any method of the above implementation methods.

[0084] Figure 5 A schematic diagram of the structure of a car provided in an embodiment of the present invention, the car 100 includes: a processor 50, a memory 51, a bus 52 and a communication interface 53, the processor 50, the communication interface 53 and the memory 51 are connected via the bus 52; the processor 50 is used to execute an executable module stored in the memory 51, such as a computer program.

[0085] The memory 51 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 53 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0086] The bus 52 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0087] Among them, the memory 51 is used to store programs, and the processor 50 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 50 or implemented by the processor 50.

[0088] The processor 50 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 50. The above processor 50 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor to be executed, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and completes the steps of the above method in combination with its hardware.

[0089] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.

[0090] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0091] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for calculating braking distance, characterized in that: include: Obtain the target user's current driving behavior data in adaptive cruise mode; Inputting the current driving behavior data into a pre-trained rule model to obtain a braking distance output by the rule model based on the current driving behavior data; wherein the rule model is trained based on the historical braking behavior data of the target user; The method further includes: prompting the target user based on the braking distance; The training process of the rule model includes: obtaining historical braking behavior data of the target user when actively braking in an adaptive cruise mode; wherein the historical braking behavior data includes historical driving behavior data and historical braking distances corresponding to the historical driving behavior data; performing data cleaning on the historical braking behavior data; dividing the cleaned historical braking behavior data into a training set; iteratively training the machine learning model based on the training set to generate a rule model; The method further includes: acquiring current braking behavior data of the target user actively braking in the adaptive cruise mode; and updating the braking behavior rules corresponding to the target user based on the current braking behavior data.

2. The method according to claim 1, characterized in that The current driving behavior data carries a user identifier, and the rule model includes at least one braking behavior rule; The rule model outputs a braking distance based on the current driving behavior data, including: The rule model searches for a target braking behavior rule that matches the user identifier; Based on the target braking behavior rule, a braking distance is output.

3. The method according to claim 1, characterized in that The method further comprises: Dividing the cleaned historical braking behavior data into a test set; wherein the test set is different from the training set; Based on the test set, a preset evaluation algorithm is used to evaluate the rule model to obtain an evaluation result; If the evaluation result does not meet the preset conditions, the machine learning model is iteratively trained based on the training set.

4. The method according to claim 1, characterized in that: Iteratively training the machine learning model based on the training set to generate a rule model includes: Based on the training set, determining a braking behavior rule corresponding to the target user; wherein the braking behavior rule represents a corresponding relationship between driving behavior data and braking distance; The braking behavior rules are optimized using a preset rule learning algorithm to generate a rule model.

5. A braking distance calculation device, characterized in that: include: A data acquisition module is used to acquire the current driving behavior data of the target user in the adaptive cruise mode; A braking distance determination module, used for inputting the current driving behavior data into a pre-trained rule model to obtain a braking distance output by the rule model based on the current driving behavior data; wherein the rule model is trained based on the historical braking behavior data of the target user; Also included is a push module, for prompting the target user based on the braking distance; It also includes a model training module for obtaining historical braking behavior data of the target user when actively braking in the adaptive cruise mode; wherein the historical braking behavior data includes historical driving behavior data and historical braking distances corresponding to the historical driving behavior data; performing data cleaning on the historical braking behavior data; dividing the cleaned historical braking behavior data into a training set; iteratively training the machine learning model based on the training set to generate a rule model; The model training module is also used to obtain current braking behavior data of the target user when actively braking in the adaptive cruise mode; based on the current braking behavior data, the braking behavior rules corresponding to the target user are updated.

6. A car, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the steps of the method according to any one of claims 1 to 4.

7. 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 4 are executed.

Images