Structural layout intelligent division method and system based on vehicle-mounted space

Abstract

The invention relates to the technical field of spatial layout, and discloses a structural layout intelligent division method and system based on a vehicle-mounted space, and the method comprises the steps: analyzing the behavior preference characteristics corresponding to a vehicle user, and analyzing the driving behavior characteristics corresponding to the vehicle user; querying a vehicle interaction terminal and vehicle interaction software in the vehicle-mounted space of the target vehicle, evaluating the interaction convenience between the vehicle interaction terminal and the vehicle user, analyzing an information interaction function corresponding to the vehicle interaction software, and calculating an interaction conformance index between the behavior preference characteristics and the information interaction function; carrying out layout planning on the vehicle interaction terminal to obtain a terminal layout blueprint, and carrying out layout planning on the vehicle interaction software to obtain a software layout blueprint; performing parameter setting on the software interface elements to obtain element visual parameters; and carrying out layout optimization processing on the vehicle-mounted space of the target vehicle to obtain an optimization result. The invention mainly aims to solve the problem that the adaptability of the structural layout of the vehicle-mounted space is reduced.

Description

Technical Field

[0001] The invention relates to a method and system for intelligently dividing a structural layout based on a vehicle-mounted space, and belongs to the technical field of space layout. Background Art

[0002] Against the backdrop of the rapid development of the modern automobile industry, consumers have increasing demands for the comfort, functionality and personalization of automobile interior space. As an important component of the entire automobile, the rationality of the structural layout of the in-vehicle space directly affects the driving experience, cargo carrying capacity and the overall performance of the vehicle.

[0003] At present, the structural layout design of vehicle space mostly relies on traditional empirical design methods and relatively fixed ergonomic standards. Designers preliminarily determine the positions and sizes of major components such as seats, center consoles, and storage spaces based on the type and purpose of the vehicle. For example, in car design, the layout of the driver's seat, co-pilot seat, and related control buttons is usually arranged according to the sitting posture and operating range of the standard human body model to ensure that the driver can easily operate the vehicle and obtain a more comfortable driving posture; for SUV models, the storage space of the trunk will be appropriately increased on the basis of considering the driving space to meet consumers' demand for carrying. However, this traditional design method has many limitations. On the one hand, due to the significant differences in physical characteristics, usage habits, and age groups of different users, the traditional fixed layout is difficult to meet the personalized needs of each user, which in turn leads to a decrease in the adaptability of the structural layout of the vehicle space. Summary of the invention

[0004] The present invention provides a method and system for intelligently dividing the structural layout of the vehicle-mounted space, the main purpose of which is to solve the problem of reduced adaptability of the structural layout of the vehicle-mounted space.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for intelligently dividing the structure layout of a vehicle-mounted space, comprising: Acquire a target vehicle to be analyzed and its corresponding vehicle user, collect user behavior data corresponding to the vehicle user, the user behavior data includes daily behavior data and driving behavior data, analyze the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data, and analyze the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data; querying the vehicle interaction terminal and vehicle interaction software in the vehicle-mounted space of the target vehicle, evaluating the convenience of interaction between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, analyzing the information interaction function corresponding to the vehicle interaction software, and calculating the interaction fit index between the behavior preference characteristics and the information interaction function; Based on the interaction convenience, the vehicle interaction terminal is laid out and planned to obtain a terminal layout blueprint, and combined with the interaction fit index, the vehicle interaction software is laid out and planned to obtain a software layout blueprint; Based on a preset visual database, the visual acuity corresponding to the vehicle user is calculated, the software interface elements corresponding to the vehicle interactive software are detected, and based on the visual acuity, parameters of the software interface elements are set to obtain element visual parameters; Combining the element visual parameters, the terminal layout blueprint and the software layout blueprint, the onboard space of the target vehicle is subjected to layout optimization processing to obtain an optimization result.

[0006] Optionally, analyzing the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data includes: Performing data cleaning on the daily behavior data to obtain cleaned behavior data; Extracting behavior tags from the cleaning behavior data, and analyzing behavior function attributes corresponding to the behavior tags; Based on the behavior function attributes, performing data clustering processing on the cleaning behavior data to obtain clustered behavior data; According to the behavior function attributes, mining high-frequency associated behaviors in the clustered behavior data; Based on the high-frequency associated behaviors, behavioral preference features corresponding to the vehicle user are generated.

[0007] Optionally, mining high-frequency associated behaviors in the clustered behavior data according to the behavior function attributes includes: Mining high-frequency behaviors in the clustered behavior data and extracting characteristic functional attributes from the behavioral functional attributes; Quantifying the characteristic functional attributes to obtain functional attribute values; Based on the function attribute value, determining the attribute rank corresponding to the characteristic function attribute, and calculating the attribute rank difference between the attribute ranks; According to the attribute rank difference, the attribute correlation coefficient between the characteristic function attributes is calculated by the following formula:

[0008] Among them, A represents the attribute correlation coefficient between the feature function attributes, It represents the attribute rank difference between the i-th attribute and the i+1-th attribute in the characteristic function attribute, i and i+1 both represent the serial numbers corresponding to the characteristic function attribute, and n represents the number of characteristic function attributes; Determining associated behaviors among the high-frequency behaviors according to the attribute correlation coefficient; The high-frequency behaviors and the associated behaviors are combined to generate high-frequency associated behaviors in the clustered behavior data.

[0009] Optionally, analyzing the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data includes: Performing data preprocessing on the driving behavior data to obtain standard behavior data; Mining the driving behavior information and driving behavior scenarios in the standard behavior data, and extracting behavior feature information in the driving behavior information; Constructing a correlation co-occurrence matrix corresponding to the driving behavior scenario and the behavior feature information; Analyze the association rules corresponding to the association co-occurrence matrix, and calculate the rule confidence corresponding to the association rules; Based on the rule confidence and the association rule, a driving behavior feature corresponding to the vehicle user is determined from the behavior feature information.

[0010] Optionally, the evaluating the convenience of interaction between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics includes: Collecting a user driving image corresponding to the vehicle user, performing subject segmentation processing on the user driving image, and obtaining a user subject driving image; Determining a driving posture corresponding to the vehicle user based on the user subject driving image; Marking a posture feature point corresponding to the driving posture, and calculating an operation interaction distance between the posture feature point and the vehicle interaction terminal according to the driving behavior characteristics; Based on the operation interaction distance, the interaction convenience between the vehicle interaction terminal and the vehicle user is evaluated.

[0011] Optionally, the calculating the interaction fit index between the behavior preference feature and the information interaction function includes: Analyze the preference demand attributes corresponding to the behavior preference characteristics, and extract key demand attributes from the preference demand attributes; Analyzing the functional semantics corresponding to the information interaction function, and determining the functional intent corresponding to the information interaction function based on the functional semantics; Based on the functional intent, analyzing the interactive function perception corresponding to the information interaction function; Calculating the degree of fit between the key demand attributes and the interactive function perception; Based on the degree of fit, an interaction fit index between the behavior preference feature and the information interaction function is calculated.

[0012] Optionally, the calculating the degree of fit between the key requirement attribute and the interactive function perception includes: Vectorizing the key demand attributes and the interactive function perception respectively to obtain a demand attribute vector and a function perception vector; Extracting feature vectors from the demand attribute vector and the function perception vector respectively to obtain an attribute feature vector and a perception feature vector; The vector fit between the attribute feature vector and the perception feature vector is calculated by the following formula:

[0013] Among them, R represents the vector fit between the attribute feature vector and the perception feature vector, represents the ath vector in the attribute feature vector, represents the bth vector in the perceptual feature vector, a and b represent the vector serial numbers corresponding to the attribute feature vector and the perceptual feature vector, respectively, and x and y represent the number of vectors corresponding to the attribute feature vector and the perceptual feature vector, respectively. Represents the modulus length of the ath vector in the attribute feature vector, Represents the modulus of the bth vector in the perceptual feature vector.

[0014] Optionally, combining the interaction fit index to perform layout planning on the vehicle interaction software to obtain a software layout blueprint includes: Scheduling a software interaction log corresponding to the vehicle interaction software, and counting the frequency of interaction operations corresponding to the vehicle interaction software in the software interaction log; Calculating an interaction time interval corresponding to the software interaction log, and calculating a software interaction frequency corresponding to the vehicle interaction software based on the interaction time interval and the interaction operation frequency; In combination with the software interaction frequency and the interaction compatibility index, setting the interaction priority corresponding to the vehicle interaction software; Based on the interaction priority, the vehicle interaction software is layout planned to obtain a software layout blueprint.

[0015] Optionally, the calculating the visual acuity corresponding to the vehicle user based on a preset visual database includes: Extracting visual test data of the vehicle user from the visual database, the visual test data comprising: test feedback data and feedback response data; Calculating the test accuracy rate corresponding to the vehicle user according to the test feedback data; Calculating the test response efficiency corresponding to the vehicle user according to the feedback response data; The visual acuity corresponding to the vehicle user is calculated by combining the test accuracy and the test response efficiency.

[0016] The intelligent division system of the structural layout of the vehicle space is characterized in that the system comprises: A behavior characteristic analysis module is used to obtain a target vehicle to be analyzed and its corresponding vehicle user, collect user behavior data corresponding to the vehicle user, the user behavior data includes daily behavior data and driving behavior data, analyze the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data, and analyze the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data; an interaction fit index calculation module, used to query the vehicle interaction terminal and vehicle interaction software in the vehicle-mounted space of the target vehicle, evaluate the interaction convenience between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, analyze the information interaction function corresponding to the vehicle interaction software, and calculate the interaction fit index between the behavior preference characteristics and the information interaction function; A layout planning module, configured to perform layout planning on the vehicle interaction terminal based on the interaction convenience to obtain a terminal layout blueprint, and perform layout planning on the vehicle interaction software based on the interaction fit index to obtain a software layout blueprint; an element visual parameter setting module, for calculating the visual acuity corresponding to the vehicle user based on a preset visual database, detecting the software interface elements corresponding to the vehicle interactive software, and setting parameters for the software interface elements based on the visual acuity to obtain element visual parameters; The layout optimization module is used to combine the element visual parameters, the terminal layout blueprint and the software layout blueprint to perform layout optimization processing on the vehicle-mounted space of the target vehicle and obtain the optimization result.

[0017] Compared with the problems described in the background technology, the present invention analyzes the behavioral preference characteristics corresponding to the vehicle user based on the daily behavior data, and lays a foundation for the personalized customization of the vehicle space layout and function recommendations by understanding the user's frequency of use and preference for functions, thereby improving the convenience and efficiency of user operations. The present invention evaluates the interaction convenience between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, so as to understand the convenience of the vehicle user in using the vehicle interaction terminal, and thus provides a basis for the subsequent layout planning of the vehicle interaction terminal. The present invention plans the layout of the vehicle interaction terminal based on the interaction convenience, and plans the layout of the vehicle interaction software in combination with the interaction fit index, so as to enable the user to operate the terminal more quickly and accurately during driving, thereby reducing Reduce the amount of eye movement and hand movements, reduce the risk of distraction, and improve driving safety. Combined with the interactive fit index, the vehicle interaction software is laid out and planned to obtain a software layout blueprint, which can improve the fluency and comfort of user-vehicle interaction, optimize the overall driving experience, and enhance user satisfaction and recognition of the vehicle interaction system. The present invention calculates the visual acuity corresponding to the vehicle user based on a preset visual database, and can understand the color sensitivity corresponding to the vehicle user through the visual acuity, thereby improving the accuracy of the subsequent parameter settings of the software interface elements. The present invention optimizes the layout of the vehicle space of the target vehicle by combining the element visual parameters, the terminal layout blueprint and the software layout blueprint, thereby improving the adaptability of the structural layout of the vehicle space of the target vehicle. Therefore, the intelligent division method and system of the structural layout based on the vehicle space proposed in the present invention improves the adaptability of the structural layout of the vehicle space. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a flow chart of a method for intelligently dividing a vehicle-mounted space structure layout according to an embodiment of the present invention; Figure 2 A functional module diagram of the vehicle-based space-based intelligent structural layout partitioning system provided for one embodiment of the present invention.

[0019] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0020] 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.

[0021] An embodiment of the present application provides a method for intelligently dividing the structural layout based on the vehicle-mounted space. The execution subject of the method for intelligently dividing the structural layout based on the vehicle-mounted space includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for intelligently dividing the structural layout based on the vehicle-mounted space can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0022] Example 1 Reference Figure 1 FIG. 1 is a flow chart of a method for intelligently dividing a structure layout based on a vehicle-mounted space provided by an embodiment of the present invention. In this embodiment, the method for intelligently dividing a structure layout based on a vehicle-mounted space includes: S1. Obtain a target vehicle to be analyzed and its corresponding vehicle user, collect user behavior data corresponding to the vehicle user, the user behavior data including daily behavior data and driving behavior data, analyze the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data, and analyze the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data.

[0023] The present invention analyzes the behavioral preference characteristics corresponding to the vehicle user based on the daily behavior data, and lays a foundation for the personalized customization of the vehicle space layout and function recommendations by understanding the user's frequency of use and preference for functions, thereby improving the convenience and efficiency of user operations. It should be explained that the target vehicle is a vehicle that requires structural optimization of the vehicle space, such as a new energy vehicle, and the vehicle user is the user corresponding to the target vehicle. The daily behavior data is data on related activities displayed by the vehicle user in daily life scenarios, and the driving behavior data is data on operations, habits, etc. displayed by the vehicle user in the process of driving the vehicle. The behavioral preference characteristics are the tendency of preference characteristics reflected by the vehicle user based on his daily and driving behavior; further, the user behavior data corresponding to the vehicle user can be collected through a database.

[0024] In detail, the analyzing the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data includes: Performing data cleaning on the daily behavior data to obtain cleaned behavior data; Extracting behavior tags from the cleaning behavior data, and analyzing behavior function attributes corresponding to the behavior tags; Based on the behavior function attributes, performing data clustering processing on the cleaning behavior data to obtain clustered behavior data; According to the behavior function attributes, mining high-frequency associated behaviors in the clustered behavior data; Based on the high-frequency associated behaviors, behavioral preference features corresponding to the vehicle user are generated.

[0025] It should be explained that the cleaning behavior data is the data obtained after removing impurities, correcting errors and regularizing the format of the daily behavior data; the behavior label is a mark assigned to the cleaning behavior data according to certain rules to identify its type or characteristics; the behavior functional attribute is a related property corresponding to the behavior label and reflecting the functional characteristics of the behavior; the clustering behavior data is the data formed after grouping and aggregating the cleaning behavior data according to similarity and other factors; the high-frequency associated behavior is a behavioral manifestation that appears frequently in the clustering behavior data and has a strong correlation with each other.

[0026] Furthermore, the daily behavior data can be cleaned by a box plot method to obtain cleaned behavior data; the behavior labels of the cleaning behavior data can be extracted by a label extraction tool, the label extraction tool is compiled by a script language, and the behavior function attributes corresponding to the behavior labels can be analyzed by a function requirement matrix; according to the degree of similarity corresponding to the behavior function attributes, the cleaning behavior data is clustered using a clustering algorithm to obtain clustered behavior data; the high-frequency associated behavior is used as the behavior preference feature corresponding to the vehicle user.

[0027] Further, as an optional embodiment of the present invention, mining high-frequency associated behaviors in the clustered behavior data according to the behavior function attributes includes: Mining high-frequency behaviors in the clustered behavior data and extracting characteristic functional attributes from the behavioral functional attributes; Quantifying the characteristic functional attributes to obtain functional attribute values; Based on the function attribute value, determining the attribute rank corresponding to the characteristic function attribute, and calculating the attribute rank difference between the attribute ranks; According to the attribute rank difference, the attribute correlation coefficient between the characteristic function attributes is calculated by the following formula:

[0028] Among them, A represents the attribute correlation coefficient between the feature function attributes, It represents the attribute rank difference between the i-th attribute and the i+1-th attribute in the characteristic function attribute, i and i+1 both represent the serial numbers corresponding to the characteristic function attribute, and n represents the number of characteristic function attributes; Determining associated behaviors among the high-frequency behaviors according to the attribute correlation coefficient; The high-frequency behaviors and the associated behaviors are combined to generate high-frequency associated behaviors in the clustered behavior data.

[0029] It should be explained that the high-frequency behavior is the behavior performance that appears frequently in the clustering behavior data, the characteristic functional attribute is the representative related attribute that can reflect the key characteristics extracted from the behavioral functional attributes, the functional attribute value is the actual numerical value presented by the characteristic functional attribute under specific circumstances, the attribute rank is the corresponding serial number after arranging the characteristic functional attributes in a certain order (such as from small to large, etc.), the attribute rank difference is the difference between different attribute ranks, the attribute correlation coefficient is a quantitative indicator used to measure the degree of correlation between the characteristic functional attributes, and the associated behavior is the behavior that exists in the high-frequency behaviors and has a strong correlation with each other.

[0030] Furthermore, by mining the high-frequency behaviors in the clustering behavior data, the characteristic functional attributes in the behavioral functional attributes can be extracted through the principal component analysis method; the characteristic functional attributes can be quantized through an encoding algorithm to obtain functional attribute values, such as a one-hot encoding algorithm; based on the functional attribute values, the attribute rank corresponding to the characteristic functional attribute can be determined through a sorting algorithm; when the attribute correlation coefficient is greater than a preset coefficient, the associated behavior in the high-frequency behavior is determined, and the preset coefficient can be set according to the actual application scenario.

[0031] The present invention analyzes the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data, and can obtain the operating habits of the vehicle user during the driving process, such as the style characteristics of acceleration, deceleration, and steering, as well as the preferences for vehicle control, including driving modes, auxiliary function usage tendencies and other driving-related behavior pattern information, so as to facilitate the subsequent precise customization of personalized driving assistance functions. It should be explained that the driving behavior characteristics are the representation of the behavior pattern that is a combination of a series of unique and regular operating performances, habitual tendencies and vehicle control methods shown by the vehicle user during the driving process, reflecting various information such as his driving style, proficiency and preferences.

[0032] Specifically, analyzing the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data includes: Performing data preprocessing on the driving behavior data to obtain standard behavior data; Mining the driving behavior information and driving behavior scenarios in the standard behavior data, and extracting behavior feature information in the driving behavior information; Constructing a correlation co-occurrence matrix corresponding to the driving behavior scenario and the behavior feature information; Analyze the association rules corresponding to the association co-occurrence matrix, and calculate the rule confidence corresponding to the association rules; Based on the rule confidence and the association rule, a driving behavior feature corresponding to the vehicle user is determined from the behavior feature information.

[0033] It should be explained that the standard behavior data is the data that is regular, standardized and conducive to subsequent analysis after the driving behavior data is pre-processed by removing outliers, filling missing values, unifying data formats, etc.; the driving behavior information and the driving behavior scenario are respectively the relevant content in the standard behavior data that reflects the specific operation of the vehicle user (such as acceleration, braking, steering and other operation details) and the driving environment (including road type, traffic conditions, weather conditions, etc.); the behavior feature information is the driving behavior information that can reflect the user's driving habits and style characteristics (such as whether the acceleration is sudden acceleration or smooth acceleration, whether the braking is pre- The association symbiosis matrix is ​​a matrix corresponding to the driving behavior scenarios and the behavior feature information through a specific construction method (such as using scenarios as rows and feature information as columns to record the frequency of their co-occurrence and other related situations) for presenting the mutual correlation between the two; the association rule is a regular expression of the association symbiosis matrix that can reflect the high probability of certain behavior feature information appearing in a specific driving behavior scenario after mining and analysis; the rule confidence indicates the reliability or probability of the corresponding behavior feature information appearing under the association rule when the corresponding driving behavior scenario is met.

[0034] Furthermore, the driving behavior data can be preprocessed by data cleaning, standardization and outlier processing algorithms to obtain standard behavior data; the driving behavior information and driving behavior scenarios in the standard behavior data can be mined by a decision tree algorithm; the behavior feature information in the driving behavior information can be extracted by a deep learning feature extraction method, such as an autoencoder; the association co-occurrence matrix corresponding to the driving behavior scenario and the behavior feature information can be constructed by a matrix construction algorithm, such as a matrix function; the association rules corresponding to the association co-occurrence matrix can be analyzed by an association rule mining algorithm; the rule confidence corresponding to the association rule can be calculated by a statistical analysis and probability calculation method. Assuming that the association rule is "if it is a city road congestion scenario, then frequent start-stop behavior will occur", the total number of occurrences in the city road congestion scenario (assuming 100 times) and the number of frequent start-stop behaviors in the city road congestion scenario (assuming 80 times) are counted. The rule confidence is the probability of frequent start-stop behaviors occurring in the city road congestion scenario, that is, 80÷100 = 0.8, which means that this rule has an 80% credibility. If the confidence of the association rule "Maintaining high speed for a long time and rarely changing lanes when driving on the highway → stable driving style" is 0.9, when analyzing the behavioral characteristic information of a vehicle user, it is found that most of the cases in the highway driving data meet the antecedent of the rule. Due to the high confidence, it can be determined that the user has the characteristics of a stable driving style, that is, he tends to stay focused and operate smoothly when driving at high speed.

[0035] S2. Query the vehicle interaction terminal and vehicle interaction software in the vehicle-mounted space of the target vehicle, evaluate the convenience of interaction between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, analyze the information interaction function corresponding to the vehicle interaction software, and calculate the interaction fit index between the behavior preference characteristics and the information interaction function.

[0036] The present invention evaluates the convenience of interaction between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, so as to understand the convenience of the vehicle user in using the vehicle interaction terminal, thereby providing a basis for the subsequent layout planning of the vehicle interaction terminal. It should be explained that the vehicle interaction terminal and the vehicle interaction software are respectively the equipment and software program in the on-board space of the target vehicle that realize the interaction function between the vehicle and the user. The interaction convenience indicates the convenience of the vehicle user in using the vehicle interaction terminal. Furthermore, the query of the vehicle interaction terminal and the vehicle interaction software in the on-board space of the target vehicle can be achieved through the vehicle user manual.

[0037] Specifically, the evaluating the interaction convenience between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics includes: Collecting a user driving image corresponding to the vehicle user, performing subject segmentation processing on the user driving image, and obtaining a user subject driving image; Determining a driving posture corresponding to the vehicle user based on the user subject driving image; Marking a posture feature point corresponding to the driving posture, and calculating an operation interaction distance between the posture feature point and the vehicle interaction terminal according to the driving behavior characteristics; Based on the operation interaction distance, the interaction convenience between the vehicle interaction terminal and the vehicle user is evaluated.

[0038] It should be explained that the body feature value is a quantitative value corresponding to the vehicle user that can reflect his body shape characteristics (such as height, body shape, etc.); the user driving image is an image of the vehicle user that is photographed and recorded during the driving process and reflects his overall state; the user main driving image is an image of the user driving image that focuses on the main part of the vehicle user and removes interference factors such as irrelevant background; the driving posture is the body posture state (including sitting posture, limb placement, etc.) presented by the vehicle user when driving; the posture feature point is the specific point corresponding to the driving posture, such as the coordinate position of key parts such as the head, shoulders, hands, etc. in space, which can be used for analysis; the operation interaction distance represents the length distance in space between the posture feature point and the vehicle interaction terminal.

[0039] Furthermore, the body feature value corresponding to the vehicle user can be scheduled through a large database; the user driving image corresponding to the vehicle user can be collected through the in-vehicle camera; the user driving image can be segmented by the threshold segmentation method to obtain the user main driving image; the posture detection of the user main driving image can be performed by a posture estimation algorithm based on deep learning (such as convolutional neural network CNN and its related improved model) to determine the driving posture corresponding to the vehicle user; the posture feature points corresponding to the driving posture can be marked by a feature point labeling algorithm (such as open source algorithms such as OpenPose and its derivative optimization algorithms); according to the driving behavior characteristics, the posture feature point and its corresponding vehicle interaction terminal are determined, and the distance value between the two is calculated to obtain the operation interaction distance. For example, the driving behavior characteristics show that the driver often reaches out to operate the central control screen, and the straight-line distance from the hand (posture feature point) to the central control screen is calculated to be 30 cm, then the operation interaction distance is 30 cm; based on the operation interaction distance, the interaction convenience between the vehicle interaction terminal and the vehicle user is evaluated. If the operation interaction distance is within 20 cm, it is determined to be high in convenience, and 20 - 40 cm is medium, and more than 40 cm is low. For example, if the distance from a user's hand to the central control screen for operation interaction is measured to be 15 cm, then the interactive terminal has high interaction convenience for this user's operation, and the operation is easy and unobstructed.

[0040] By analyzing the information interaction function corresponding to the vehicle interaction software, the present invention can understand the software implementation purpose corresponding to the interaction software, and calculate the interaction fit index between the behavior preference characteristics and the information interaction function, so as to understand the matching degree between the behavior preference characteristics and the information interaction function, thereby laying a foundation for the subsequent layout planning of the vehicle interaction software. It should be explained that the information interaction function is the specific implementation function corresponding to the vehicle interaction software, and the interaction fit index represents the matching degree between the behavior preference characteristics and the information interaction function. Furthermore, the interaction function can be analyzed through the information description corresponding to the vehicle interaction software and the meaning of the software name.

[0041] In detail, the calculation of the interaction fit index between the behavior preference feature and the information interaction function includes: Analyze the preference demand attributes corresponding to the behavior preference characteristics, and extract key demand attributes from the preference demand attributes; Analyzing the functional semantics corresponding to the information interaction function, and determining the functional intent corresponding to the information interaction function based on the functional semantics; Based on the functional intent, analyzing the interactive function perception corresponding to the information interaction function; Calculating the degree of fit between the key demand attributes and the interactive function perception; Based on the degree of fit, an interaction fit index between the behavior preference feature and the information interaction function is calculated.

[0042] It should be explained that the preference demand attributes are the relevant characteristics corresponding to the behavioral preference features that reflect the essence of the user's internal needs, the key demand attributes are the core parts of the preference demand attributes that play a key and decisive role in the overall needs, the functional semantics represent the meaning corresponding to the information interaction function, the functional intention is the goal and purpose that the development and design corresponding to the information interaction function expects to achieve, the interactive function perception is the subjective feelings and experience cognition formed by the user during the use of the information interaction function, and the fit degree represents the quantitative reflection of the matching and conformity between the key demand attributes and the interactive function perception.

[0043] Furthermore, the above-mentioned principal component analysis method can be used to analyze the preference demand attributes corresponding to the behavioral preference characteristics; the key demand attributes in the preference demand attributes can be extracted through the hierarchical analysis method; the functional semantics corresponding to the information interaction function can be analyzed through the semantic analysis method, and the functional intention corresponding to the information interaction function can be determined based on the descriptive information in the functional semantics; based on the functional intention, the analysis of the interactive function perception corresponding to the information interaction function can be achieved through the semantic difference scale method. For example, if most users choose the end close to "easy to understand" on the "easy to understand-difficult to understand" scale, it can be inferred that users have a better cognitive usability perception of the driving mode selection function; the fit degrees corresponding to the behavioral preference characteristics are summed and converted into a percentage to obtain the interactive fit index between the behavioral preference characteristics and the information interaction function.

[0044] Further, as an optional embodiment of the present invention, the calculating the degree of fit between the key requirement attribute and the interactive function perception includes: Vectorizing the key demand attributes and the interactive function perception respectively to obtain a demand attribute vector and a function perception vector; Extracting feature vectors from the demand attribute vector and the function perception vector respectively to obtain an attribute feature vector and a perception feature vector; The vector fit between the attribute feature vector and the perception feature vector is calculated by the following formula:

[0045] Among them, R represents the vector fit between the attribute feature vector and the perception feature vector, represents the ath vector in the attribute feature vector, represents the bth vector in the perceptual feature vector, a and b represent the vector serial numbers corresponding to the attribute feature vector and the perceptual feature vector, respectively, and x and y represent the number of vectors corresponding to the attribute feature vector and the perceptual feature vector, respectively. Represents the modulus length of the ath vector in the attribute feature vector, Represents the modulus of the bth vector in the perceptual feature vector.

[0046] It should be explained that the requirement attribute vector and the function perception vector are respectively the vector expressions corresponding to the key requirement attributes and the interactive function perception, the attribute feature vector and the perception feature vector are respectively the vectors of the key characteristics in the requirement attribute vector and the function perception vector, and further, the vectorization processing of the key requirement attributes and the interactive function perception can be achieved through the word2vec algorithm; the extraction of the feature vectors in the requirement attribute vector and the function perception vector can be achieved through dimensionality reduction methods, such as factor analysis algorithms.

[0047] S3. Based on the interaction convenience, the vehicle interaction terminal is laid out and planned to obtain a terminal layout blueprint. Combined with the interaction fit index, the vehicle interaction software is laid out and planned to obtain a software layout blueprint.

[0048] The present invention performs layout planning of the vehicle interaction terminals based on the interaction convenience, and performs layout planning of the vehicle interaction software in combination with the interaction fit index, so that users can operate the terminals more quickly and accurately during driving, reduce line of sight shifts and hand movement amplitudes, reduce distraction risks, and improve driving safety. The vehicle interaction software is layout planned in combination with the interaction fit index to obtain a software layout blueprint, which can improve the fluency and comfort of user-vehicle interaction, optimize the overall driving experience, and enhance user satisfaction and recognition of the vehicle interaction system. It should be explained that the terminal layout blueprint is a layout of the vehicle interaction terminals with reasonable positions based on the interaction convenience, and the software layout blueprint is a planning arrangement obtained after the vehicle interaction software is laid out in combination with the interaction fit index. Furthermore, the layout planning of the vehicle interaction terminals can be carried out according to the numerical value of the interaction convenience, such as the vehicle interaction terminals with high interaction convenience can be close to the user's driving position. At the same time, without compressing the space inside the car, a small space can be designed somewhere inside the car to place medical equipment such as ECG monitors and delivery kits, so that medical insurance services can be provided in a timely manner in special circumstances, further improving the functionality and practicality of the vehicle.

[0049] In detail, the vehicle interaction software is layout-planned in combination with the interaction fit index to obtain a software layout blueprint, including: Scheduling a software interaction log corresponding to the vehicle interaction software, and counting the frequency of interaction operations corresponding to the vehicle interaction software in the software interaction log; Calculating an interaction time interval corresponding to the software interaction log, and calculating a software interaction frequency corresponding to the vehicle interaction software based on the interaction time interval and the interaction operation frequency; In combination with the software interaction frequency and the interaction compatibility index, setting the interaction priority corresponding to the vehicle interaction software; Based on the interaction priority, the vehicle interaction software is layout planned to obtain a software layout blueprint.

[0050] It should be explained that the software interaction log is a document that records information related to the use process of the vehicle interaction software, the interaction operation frequency is a statistic in the software interaction log that reflects the number of times each function of the vehicle interaction software is used, the interaction time interval is the time span divided in the software interaction log for data analysis, the software interaction frequency indicates how frequently the vehicle interaction software is used within a specific time period, and the interaction priority indicates the order of importance of each function of the vehicle interaction software during layout planning, optimization and other processing.

[0051] Furthermore, the software interaction log corresponding to the vehicle interaction software can be scheduled from the data storage module in the target vehicle; the frequency of interaction operations corresponding to the vehicle interaction software in the software interaction log can be counted by a data statistical analysis tool, and the data statistical analysis tool is compiled by a scripting language, such as JS scripting language; the record timestamp corresponding to the software interaction log is identified, and the interaction time interval is obtained by subtracting the start time from the end time in the record timestamp, and the ratio of the interaction operation frequency to the interaction time interval is calculated to obtain the software interaction frequency corresponding to the vehicle interaction software; the software interaction frequency and the ratio of the interaction operation frequency to the interaction time interval are combined to obtain the software interaction frequency corresponding to the vehicle interaction software. Interaction fit index, setting the interaction priority corresponding to the vehicle interaction software. For example, if the software interaction frequency of the vehicle navigation function is extremely high and the interaction fit index is high, it means that it is very important to the user and the user experience is good, so it can be set to a high interaction priority. The interaction frequency of the vehicle seat heating function is low and the fit index is average, so it can be set to a low interaction priority. Based on the numerical value of the interaction priority, the vehicle interaction software is laid out and planned to obtain a software layout blueprint. If the interaction priority is high, it will be displayed first in the software layout and placed in a conspicuous and convenient position. If the interaction priority is low, it will be placed in a relatively hidden and secondary menu level.

[0052] S4. Based on a preset visual database, the visual acuity corresponding to the vehicle user is calculated, the software interface elements corresponding to the vehicle interaction software are detected, and based on the visual acuity, parameters of the software interface elements are set to obtain element visual parameters.

[0053] The present invention calculates the visual acuity of the vehicle user based on a preset visual database, and can use the visual acuity to understand the color sensitivity of the vehicle user, thereby improving the accuracy of the parameter settings of the subsequent software interface elements. It should be explained that the visual database is a collection of pre-collected and organized information including various vision-related standard data, different visual feature parameters, and visual perception tests, and the visual acuity is a quantitative reflection of the vehicle user's ability to distinguish and perceive visual information.

[0054] In detail, the calculating the visual acuity corresponding to the vehicle user based on a preset visual database includes: Extracting visual test data of the vehicle user from the visual database, the visual test data comprising: test feedback data and feedback response data; Calculating the test accuracy rate corresponding to the vehicle user according to the test feedback data; Calculating the test response efficiency corresponding to the vehicle user according to the feedback response data; The visual acuity corresponding to the vehicle user is calculated by combining the test accuracy and the test response efficiency.

[0055] It should be explained that the visual test data are all the original data generated during the vehicle user's participation in visual acuity related tests. The test feedback data and the feedback response data are respectively specific data manifestations of the vehicle user's judgment results on the test samples and the corresponding reaction time in the visual test data. The test accuracy rate represents the proportion of the vehicle user's ability to correctly judge samples in the visual test, and the test response efficiency represents the vehicle user's ability to respond quickly and accurately to the visual test samples.

[0056] Furthermore, the visual test data of the vehicle user can be extracted from the visual database by an extraction function, where the extraction function is compiled by a programming language; the test accuracy corresponding to the vehicle user is calculated based on the test feedback data. For example, the vehicle user performs 10 visual tests, and the feedback data shows that the number of correct sample identifications is 8 times. Then the test accuracy is obtained by dividing the correct number of times 8 by the total number of tests 10, and the test accuracy is 80%, that is, the test accuracy of the user this time reflects his ability level to correctly identify visual test samples; the test response corresponding to the vehicle user is calculated based on the feedback response data. For example, if the standard response time threshold is set to 5 seconds, and the vehicle user performs 20 For a visual test, if 12 of them have a response time within 5 seconds, then the test response efficiency is 12÷20=60%, which reflects the user's ability to respond quickly to the visual test within the specified time standard; respectively assign weight values ​​corresponding to the test accuracy and the test response efficiency, multiply the test accuracy and the test response efficiency by the corresponding weight values, and calculate the corresponding visual acuity of the vehicle user. The weight values ​​corresponding to the test accuracy and the test response efficiency are 0.6 and 0.4 respectively, and the test accuracy and the test response efficiency are 80% and 70% respectively, then the visual acuity is 0.6×80%+0.4×70%=76%.

[0057] The present invention can obtain the visually presented components of the vehicle interaction software by detecting the software interface elements corresponding to the vehicle interaction software. Based on the visual acuity, the software interface elements are parameterized to make the interface element size, color contrast, text clarity, etc. more suitable for the user's visual perception, thereby improving the user's recognition efficiency, reducing misoperation, and enhancing the interactive experience, so that the user can more easily and accurately obtain information and operate functions when using the vehicle interaction software. It should be explained that the software interface elements are the visually presented components of the vehicle interaction software, and the element visual parameters are the attribute indicators corresponding to the software interface elements. Furthermore, the detection of software interface elements corresponding to the vehicle interaction software can be achieved through image recognition technology, such as OpenCV computer vision library; based on the visual acuity, the software interface elements are parameterized to obtain element visual parameters. If the visual acuity is low, the size of the button elements in the software interface can be increased to make them easier to be found and clicked, and at the same time, the contrast between the button color and the background color can be increased, such as changing the original light blue button to bright blue, and the text color is also adjusted accordingly. The adjustment of these element visual parameters is used to adapt to the user's visual ability and enhance the interactive experience.

[0058] S5. Combining the element visual parameters, the terminal layout blueprint and the software layout blueprint, perform layout optimization processing on the vehicle-mounted space of the target vehicle to obtain an optimization result.

[0059] The present invention optimizes the layout of the onboard space of the target vehicle by combining the element visual parameters, the terminal layout blueprint and the software layout blueprint, thereby improving the adaptability of the structural layout of the onboard space of the target vehicle.

[0060] Compared with the problems described in the background technology, the present invention analyzes the behavioral preference characteristics corresponding to the vehicle user based on the daily behavior data, and lays a foundation for the personalized customization of the vehicle space layout and function recommendations by understanding the user's frequency of use and preference for functions, thereby improving the convenience and efficiency of user operations. The present invention evaluates the interaction convenience between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, so as to understand the convenience of the vehicle user in using the vehicle interaction terminal, and thus provides a basis for the subsequent layout planning of the vehicle interaction terminal. The present invention plans the layout of the vehicle interaction terminal based on the interaction convenience, and plans the layout of the vehicle interaction software in combination with the interaction fit index, so as to enable the user to operate the terminal more quickly and accurately during driving, thereby reducing Reduce the amount of eye movement and hand movements, reduce the risk of distraction, and improve driving safety. Combined with the interaction fit index, the vehicle interaction software is laid out and planned to obtain a software layout blueprint, which can improve the fluency and comfort of user-vehicle interaction, optimize the overall driving experience, and enhance user satisfaction and recognition of the vehicle interaction system. The present invention calculates the visual acuity corresponding to the vehicle user based on a preset visual database, and can understand the color sensitivity corresponding to the vehicle user through the visual acuity, thereby improving the accuracy of the subsequent parameter settings of the software interface elements. The present invention optimizes the layout of the vehicle space of the target vehicle by combining the element visual parameters, the terminal layout blueprint and the software layout blueprint, thereby improving the adaptability of the structural layout of the vehicle space of the target vehicle. Therefore, the intelligent division method of the structural layout based on the vehicle space proposed in the present invention improves the adaptability of the structural layout of the vehicle space.

[0061] Example 2 like Figure 2 The figure shows a functional module diagram of a system for intelligently dividing a structural layout based on a vehicle-mounted space provided by an embodiment of the present invention.

[0062] The intelligent division system 100 of the structural layout based on the vehicle space of the present invention can be installed in an electronic device. According to the functions implemented, the intelligent division system 100 of the structural layout based on the vehicle space can include a behavior feature analysis module 101, an interaction fit index calculation module 102, a layout planning module 103, an element visual parameter setting module 104 and a layout optimization module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0063] In this embodiment, the functions of each module / unit are as follows: The behavior characteristic analysis module 101 is used to obtain a target vehicle to be analyzed and its corresponding vehicle user, collect user behavior data corresponding to the vehicle user, the user behavior data includes daily behavior data and driving behavior data, analyze the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data, and analyze the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data; The interaction fit index calculation module 102 is used to query the vehicle interaction terminal and vehicle interaction software in the vehicle-mounted space of the target vehicle, evaluate the interaction convenience between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, analyze the information interaction function corresponding to the vehicle interaction software, and calculate the interaction fit index between the behavior preference characteristics and the information interaction function; The layout planning module 103 is used to perform layout planning on the vehicle interaction terminal based on the interaction convenience to obtain a terminal layout blueprint, and to perform layout planning on the vehicle interaction software based on the interaction fit index to obtain a software layout blueprint; The element visual parameter setting module 104 is used to calculate the visual acuity corresponding to the vehicle user based on a preset visual database, detect the software interface elements corresponding to the vehicle interactive software, and set parameters for the software interface elements based on the visual acuity to obtain element visual parameters; The layout optimization module 105 is used to combine the element visual parameters, the terminal layout blueprint and the software layout blueprint to perform layout optimization processing on the vehicle-mounted space of the target vehicle to obtain an optimization result.

[0064] In detail, each module described in the vehicle-mounted space-based structure layout intelligent division system 100 described in the embodiment of the present application is used in the same manner as described above. Figure 1 The technical means described in the text is the same as the method for intelligent division of the structural layout of the vehicle-mounted space, and can produce the same technical effects, so I will not go into details here.

[0065] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for intelligently dividing the structural layout of a vehicle-mounted space, characterized in that: The method comprises: Acquire a target vehicle to be analyzed and its corresponding vehicle user, collect user behavior data corresponding to the vehicle user, the user behavior data includes daily behavior data and driving behavior data, analyze the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data, and analyze the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data; querying the vehicle interaction terminal and vehicle interaction software in the vehicle-mounted space of the target vehicle, evaluating the convenience of interaction between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, analyzing the information interaction function corresponding to the vehicle interaction software, and calculating the interaction fit index between the behavior preference characteristics and the information interaction function; Based on the interaction convenience, the vehicle interaction terminal is laid out and planned to obtain a terminal layout blueprint, and combined with the interaction fit index, the vehicle interaction software is laid out and planned to obtain a software layout blueprint; Based on a preset visual database, the visual acuity corresponding to the vehicle user is calculated, the software interface elements corresponding to the vehicle interactive software are detected, and based on the visual acuity, parameters of the software interface elements are set to obtain element visual parameters; Combining the element visual parameters, the terminal layout blueprint and the software layout blueprint, the onboard space of the target vehicle is subjected to layout optimization processing to obtain an optimization result.

2. The method for intelligently dividing the structure layout of the vehicle space according to claim 1, characterized in that: The analyzing the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data includes: Performing data cleaning on the daily behavior data to obtain cleaned behavior data; Extracting behavior tags from the cleaning behavior data, and analyzing behavior function attributes corresponding to the behavior tags; Based on the behavior function attributes, performing data clustering processing on the cleaning behavior data to obtain clustered behavior data; According to the behavior function attributes, mining high-frequency associated behaviors in the clustered behavior data; Based on the high-frequency associated behaviors, behavioral preference features corresponding to the vehicle user are generated.

3. The method for intelligently dividing the structure layout of the vehicle space according to claim 2, characterized in that: The step of mining high-frequency associated behaviors in the clustered behavior data according to the behavior function attributes includes: Mining high-frequency behaviors in the clustered behavior data and extracting characteristic functional attributes from the behavioral functional attributes; Quantifying the characteristic functional attributes to obtain functional attribute values; Based on the function attribute value, determining the attribute rank corresponding to the characteristic function attribute, and calculating the attribute rank difference between the attribute ranks; According to the attribute rank difference, the attribute correlation coefficient between the characteristic function attributes is calculated by the following formula: Among them, A represents the attribute correlation coefficient between the feature function attributes, It represents the attribute rank difference between the i-th attribute and the i+1-th attribute in the characteristic function attribute, i and i+1 both represent the serial numbers corresponding to the characteristic function attribute, and n represents the number of characteristic function attributes; Determining associated behaviors among the high-frequency behaviors according to the attribute correlation coefficient; The high-frequency behaviors and the associated behaviors are combined to generate high-frequency associated behaviors in the clustered behavior data.

4. The method for intelligently dividing the structure layout of the vehicle space according to claim 1, characterized in that: The analyzing the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data includes: Performing data preprocessing on the driving behavior data to obtain standard behavior data; Mining the driving behavior information and driving behavior scenarios in the standard behavior data, and extracting behavior feature information in the driving behavior information; Constructing a correlation co-occurrence matrix corresponding to the driving behavior scenario and the behavior feature information; Analyze the association rules corresponding to the association co-occurrence matrix, and calculate the rule confidence corresponding to the association rules; Based on the rule confidence and the association rule, a driving behavior feature corresponding to the vehicle user is determined from the behavior feature information.

5. The method for intelligently dividing the structure layout of the vehicle space according to claim 1, characterized in that: The step of evaluating the convenience of interaction between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics includes: Collecting a user driving image corresponding to the vehicle user, performing subject segmentation processing on the user driving image, and obtaining a user subject driving image; Determining a driving posture corresponding to the vehicle user based on the user subject driving image; Marking a posture feature point corresponding to the driving posture, and calculating an operation interaction distance between the posture feature point and the vehicle interaction terminal according to the driving behavior characteristics; Based on the operation interaction distance, the interaction convenience between the vehicle interaction terminal and the vehicle user is evaluated.

6. The method for intelligently dividing the structure layout of the vehicle space according to claim 1, characterized in that: The calculating the interaction fit index between the behavior preference feature and the information interaction function includes: Analyze the preference demand attributes corresponding to the behavior preference characteristics, and extract key demand attributes from the preference demand attributes; Analyzing the functional semantics corresponding to the information interaction function, and determining the functional intent corresponding to the information interaction function based on the functional semantics; Based on the functional intent, analyzing the interactive function perception corresponding to the information interaction function; Calculating the degree of fit between the key demand attributes and the interactive function perception; Based on the degree of fit, an interaction fit index between the behavior preference feature and the information interaction function is calculated.

7. The method for intelligently dividing the structure layout of the vehicle space according to claim 1, characterized in that: The calculating the degree of fit between the key requirement attributes and the interactive function perception includes: Vectorizing the key demand attributes and the interactive function perception respectively to obtain a demand attribute vector and a function perception vector; Extracting feature vectors from the demand attribute vector and the function perception vector respectively to obtain an attribute feature vector and a perception feature vector; The vector fit between the attribute feature vector and the perception feature vector is calculated by the following formula: Among them, R represents the vector fit between the attribute feature vector and the perception feature vector, represents the ath vector in the attribute feature vector, represents the bth vector in the perceptual feature vector, a and b represent the vector serial numbers corresponding to the attribute feature vector and the perceptual feature vector, respectively, and x and y represent the number of vectors corresponding to the attribute feature vector and the perceptual feature vector, respectively. Represents the modulus length of the ath vector in the attribute feature vector, Represents the modulus of the bth vector in the perceptual feature vector.

8. The method for intelligently dividing the structure layout of the vehicle space according to claim 1, characterized in that: The step of performing layout planning on the vehicle interaction software in combination with the interaction fit index to obtain a software layout blueprint includes: Scheduling a software interaction log corresponding to the vehicle interaction software, and counting the frequency of interaction operations corresponding to the vehicle interaction software in the software interaction log; Calculating an interaction time interval corresponding to the software interaction log, and calculating a software interaction frequency corresponding to the vehicle interaction software based on the interaction time interval and the interaction operation frequency; In combination with the software interaction frequency and the interaction compatibility index, setting the interaction priority corresponding to the vehicle interaction software; Based on the interaction priority, the vehicle interaction software is layout planned to obtain a software layout blueprint.

9. The method for intelligently dividing the structure layout of the vehicle space according to claim 1, characterized in that: The calculating the visual acuity corresponding to the vehicle user based on a preset visual database includes: Extracting visual test data of the vehicle user from the visual database, the visual test data comprising: test feedback data and feedback response data; Calculating the test accuracy rate corresponding to the vehicle user according to the test feedback data; Calculating the test response efficiency corresponding to the vehicle user according to the feedback response data; The visual acuity corresponding to the vehicle user is calculated by combining the test accuracy and the test response efficiency.

10. The intelligent division system of the structural layout of the vehicle space is characterized by: The system comprises: A behavior characteristic analysis module is used to obtain a target vehicle to be analyzed and its corresponding vehicle user, collect user behavior data corresponding to the vehicle user, the user behavior data includes daily behavior data and driving behavior data, analyze the behavior preference characteristics corresponding to the vehicle user based on the daily behavior data, and analyze the driving behavior characteristics corresponding to the vehicle user based on the driving behavior data; an interaction fit index calculation module, used to query the vehicle interaction terminal and vehicle interaction software in the vehicle-mounted space of the target vehicle, evaluate the interaction convenience between the vehicle interaction terminal and the vehicle user according to the driving behavior characteristics, analyze the information interaction function corresponding to the vehicle interaction software, and calculate the interaction fit index between the behavior preference characteristics and the information interaction function; A layout planning module, configured to perform layout planning on the vehicle interaction terminal based on the interaction convenience to obtain a terminal layout blueprint, and perform layout planning on the vehicle interaction software based on the interaction fit index to obtain a software layout blueprint; an element visual parameter setting module, for calculating the visual acuity corresponding to the vehicle user based on a preset visual database, detecting the software interface elements corresponding to the vehicle interactive software, and setting parameters for the software interface elements based on the visual acuity to obtain element visual parameters; The layout optimization module is used to combine the element visual parameters, the terminal layout blueprint and the software layout blueprint to perform layout optimization processing on the vehicle-mounted space of the target vehicle and obtain the optimization result.

Images