A method for configuring on-the-go services for autonomous passenger vehicles based on user profiles

Abstract

This invention discloses a method for configuring in-transit services for autonomous passenger vehicles based on user profiles, relating to the field of autonomous driving technology. The invention constructs an initial set of influencing factors through literature retrieval and questionnaire surveys, and then uses a multiple linear regression model to screen for significant influencing factors. It integrates significant factors with driving factor data collected from driving simulators, and uses clustering algorithms to determine the number of classification levels and threshold standards for each factor. Based on user basic information, travel habits, and preference data, it uses latent profile analysis to characterize passenger user profiles, achieving scientific classification of user groups. Finally, based on the classification results and threshold standards, it automatically configures personalized in-transit service plans for different users. This invention solves the problems of strong subjectivity and low adaptability in traditional methods by quantitatively screening influencing factors, dynamically clustering thresholds, and accurately profiling users, significantly improving the efficiency of matching services with needs and passenger satisfaction.

Description

Technical Field

[0001] This invention belongs to the field of autonomous driving technology, and more specifically, relates to a method for configuring on-the-go services for autonomous passenger vehicles based on user profiles. Background Technology

[0002] With the rapid development of autonomous driving technology, the demand for in-transit services for passenger vehicles is becoming increasingly diversified and personalized. During the use of autonomous passenger vehicles, users' needs for in-transit services are influenced by a variety of factors, including but not limited to environmental factors, driving factors, service factors, and travel plan factors. The diversity of these factors leads to variations in user needs.

[0003] Traditional service plans often adopt a uniform and fixed model. While this model is simple to design and implement, it cannot effectively meet the personalized needs of different user groups, resulting in many shortcomings in the user experience. Furthermore, with the development of big data and artificial intelligence technologies, user profiling technology has gradually matured. By collecting and analyzing users' personal information, travel habits, and preference settings, detailed and accurate user profiles can be constructed, providing strong data support for the configuration of personalized service plans.

[0004] However, there is currently a lack of effective methods to fully leverage user profiling technology to configure personalized on-the-go service solutions for autonomous passenger vehicles. Therefore, developing a user-profiling-based on-the-go service configuration method for autonomous passenger vehicles has become an urgent need for industry development. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] To address the problems in related technologies, this invention provides a method for configuring on-the-go services for autonomous passenger vehicles based on user profiles. This invention constructs user profiles, analyzes user characteristics and needs, and configures personalized on-the-go service solutions for autonomous passenger vehicles, thereby improving the user's riding experience and satisfaction.

[0007] (II) Technical Solution

[0008] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0009] This invention discloses a method for configuring on-the-go services for autonomous passenger vehicles based on user profiles, comprising the following steps:

[0010] S1. Construct an initial set of influencing factors; design a questionnaire based on the initial set of influencing factors; conduct a questionnaire survey using the questionnaire to obtain valid questionnaires;

[0011] S2. Construct a multiple linear regression model; combine the valid questionnaires with the multiple linear regression model to screen each influencing factor in the initial set of influencing factors, and obtain a set of significant influencing factors.

[0012] S3. Collect the preference results of the set of significant influencing factors to obtain the final preference result data; based on the final preference result data and combined with the clustering algorithm, obtain the classification threshold standard set of the influencing factor levels of the autonomous passenger vehicle on-the-go service scheme.

[0013] S4. Based on the set of classification threshold standards, characterize the user profile of autonomous passenger vehicle passengers in the valid questionnaires; based on the user profile of autonomous passenger vehicle passengers, configure the on-the-go service plan.

[0014] Preferably, step S1 includes the following steps:

[0015] S11. Through literature retrieval and comprehensive analysis of previous studies, the influencing factors of passenger vehicle on-the-go service schemes were confirmed. Preliminary screening of influencing factors for autonomous passenger vehicle on-the-go service schemes was conducted, and an initial set of influencing factors a = {a1, a2, ..., a...} was constructed. i ,...a n}, where a i Let represent the i-th influencing factor of the on-the-go service plan for autonomous passenger vehicles, and n represent the total number of influencing factors. Influencing factors include environmental factors, such as in-vehicle temperature, humidity, odor, and noise; driving factors, such as changes in three-axis acceleration, speed, and driving stability; service factors, such as passenger space size and entertainment system; and travel plan factors, such as travel time and travel cost.

[0016] S12. Based on the initial set of influencing factors, design a questionnaire for passengers of autonomous passenger vehicles. The questionnaire includes basic information (age, gender, occupation, income), travel habits (travel frequency, common time periods, destination type), user preferences for each influencing factor (e.g., what is your favorite in-car temperature), the overall satisfaction rating of the virtual on-the-go service plan formed by the combination of each influencing factor (e.g., how satisfied are you with the above on-the-go service plan in scenarios such as a temperature of 26 degrees Celsius and humidity of 40%? 1 is very dissatisfied, 10 is very satisfied), and the changes in preferences for each influencing factor under different scenarios (peak / off-peak hours, different seasons, weekends / weekdays, multi-person travel (with elderly people, children)) (e.g., how do you prefer the in-car temperature to change during peak hours? 1 is a significant decrease, 5 is a significant increase).

[0017] S13. Collect a certain number of questionnaire results by conducting online questionnaire surveys and offline questionnaire surveys among passengers of autonomous passenger vehicles. Eligible questionnaires with missing data and those with the same answer option are removed to obtain valid questionnaires.

[0018] The above steps, through literature retrieval and multi-dimensional questionnaire design, systematically constructed an initial set of influencing factors for on-the-go service solutions for autonomous passenger vehicles. Based on a questionnaire survey combining online and offline methods, user preferences and scenario-based demand data were efficiently obtained, ensuring the scientific rigor and comprehensiveness of the influencing factors and avoiding subjective omissions. The structured questionnaire accurately captured users' dynamic needs for service solutions, providing data support for personalized services. The elimination of invalid questionnaires ensured the reliability of the analysis results, laying a high-quality data foundation for subsequent modeling and user profiling.

[0019] Preferably, step S2 includes the following steps:

[0020] S21. Construct a multiple linear regression model;

[0021] S22. Using a multiple linear regression model, each influencing factor in the initial set of influencing factors is screened to obtain a set of significant influencing factors.

[0022] The above steps construct a multiple linear regression model to correlate initial influencing factors with user satisfaction scores, quantitatively analyze the impact of each factor on the service plan, provide accurate input for subsequent level classification and user profiling, and ultimately enhance the scientific nature and operability of the service plan.

[0023] Preferably, step S21 includes the following steps:

[0024] S211. Setting the significance level to α, each influencing factor in the initial set of influencing factors is used as the independent variable, and the passenger satisfaction ratings in the valid questionnaires are used as the dependent variable. A multiple linear regression model is constructed, parameters are estimated, and the regression coefficients and error terms of each independent variable are obtained, as shown in the following formula.

[0025] Y = β0 + β1X1 + β2X2 + ... + β n X n +ε;

[0026] Where Y represents the satisfaction rating; β0 represents the intercept term; β1, β2, ... β n For a1, a2...a n The regression coefficients represent the degree of influence of each independent variable on the dependent variable; ε represents the error term.

[0027] The above steps, by setting a significance level, using the initial influencing factors as independent variables and passenger satisfaction scores as dependent variables, construct a multiple linear regression model and estimate the parameters, thereby obtaining the regression coefficients and error terms of each independent variable; this effectively identifies and quantifies the key factors affecting passenger satisfaction.

[0028] Preferably, step S22 includes the following steps:

[0029] S221. For each independent variable, perform a t-test using SPSS software to obtain the set of P-values ​​for the independent variable P = {P1, P2, ..., P...}. i ,...P n}, where P i Let p represent the p-value of the i-th independent variable;

[0030] S222. For independent variables whose P-values ​​are below the significance level α, remove the independent variable from the multiple linear regression model, refit the multiple linear regression model, calculate the new regression coefficients and error terms, and recalculate the P-value for each independent variable.

[0031] S223. Repeat S221 and S222. Stop iterating when the p-values ​​of all independent variables are less than the significance level α, and obtain the set of significant influencing factors b = {b1, b2, ..., b...} i ,...b m}, where b i This indicates the i-th factor whose P-value is less than the significance level α, and m represents the total number of factors whose P-value is less than the significance level α.

[0032] Otherwise, continue to remove independent variables and fit a multiple linear regression model, calculate the regression coefficients, error terms and p-values ​​of independent variables until the p-values ​​of all independent variables are less than the significance level α.

[0033] The above steps involve dynamically eliminating non-significant factors based on significance tests and iteratively optimizing the model; using data-driven screening of key influencing factors to avoid redundant variable interference and improve model explanatory power and prediction accuracy; significance tests ensure that the screening results are objective and reliable, providing statistical basis for service plan configuration; the determination of the set of significant influencing factors focuses on the real needs of users, reduces the computational resource consumption of invalid parameter analysis, provides accurate input for subsequent level classification and user profiling, and ultimately enhances the scientificity and operability of the service plan.

[0034] Preferably, step S3 includes the following steps:

[0035] S31. Collect the set of significant influencing factors, the preference results of the influencing factors obtained through valid questionnaires, and the preference results of driving factors not obtained through valid questionnaires, to obtain the final preference results;

[0036] S32. Using the final preference result data and combining it with clustering algorithms, obtain the classification threshold standard set for the level of influencing factors of on-the-go service schemes for autonomous passenger vehicles.

[0037] The above steps obtain the final preference results by collecting the preference results of the significant influence set; formulate a set of threshold standards for classifying the influencing factors of autonomous passenger vehicle on-the-go service solutions; refine the key factors affecting autonomous passenger vehicle on-the-go service and provide clear standards for their importance classification; this helps service providers to more accurately understand and meet passenger needs, optimize service solutions, and improve passenger satisfaction and riding experience.

[0038] Preferably, step S31 includes the following steps:

[0039] S311. Sorting through the valid questionnaires, users' preference data for the influencing factors in the significant influencing factor set is obtained to get the questionnaire preference data; using a driving simulator, users' satisfaction rating data under various driving factors are collected to obtain driving factor preference data; driving factors include three-axis acceleration change, speed, and driving stability;

[0040] S312. The questionnaire preference results are fused with the driving factor preference results to obtain the final preference result data;

[0041] The above steps integrate preference data from user surveys with driving factor scoring data collected from driving simulators to form a final preference result that covers both subjective and objective needs. By combining subjective user preferences with objective driving scenario data, the comprehensiveness and accuracy of influencing factor analysis are improved. Through multi-source data complementarity (static preferences from questionnaires + dynamic simulator scoring), the adaptability and scenario coverage of service solution configuration are enhanced. This provides a high-reliability data foundation for subsequent cluster analysis, ensuring that the classification threshold can truly reflect the synergistic influence of user needs and driving scenarios, thereby supporting the design of highly personalized service solutions.

[0042] Preferably, step S32 includes the following steps:

[0043] S321. Use a clustering algorithm to perform cluster analysis on the final preference result data to obtain the optimal cluster set d = {d1, d2, ..., dn}. i ,...d m}; where d i This represents the optimal number of clusters for the influencing factors of the i-th autonomous passenger vehicle on-the-go service plan; the optimal number of clusters represents the number of riding preferences corresponding to each influencing factor in the set of significant influencing factors; for example, if the optimal number of clusters for in-vehicle temperature preference data is 5, then the in-vehicle temperature is divided into 5 levels, namely level 1, level 2, level 3, level 4, and level 5.

[0044] S322. Each cluster in the optimal clustering set represents a group of samples with similar riding preferences. The distance from each sample in each cluster to its cluster center is calculated to obtain the classification threshold standard set e = {e1, e2, ..., e...}. i ,...e m}; where e i This represents the threshold values ​​corresponding to various riding preferences for each influencing factor; for example, the threshold values ​​for the five levels of in-vehicle temperature are Level 1 (21-23.5 degrees Celsius), Level 2 (23.5-25 degrees Celsius), Level 3 (25 degrees Celsius), Level 4 (25-27 degrees Celsius), and Level 5 (27-28 degrees Celsius).

[0045] The above steps analyze the final preference results data using clustering algorithms to determine the optimal number of categories for each factor and set level thresholds based on the distance distribution between samples and cluster centers. This quantifies abstract user preferences into concrete and operable classification standards, resolving the issue of service parameter ambiguity. By dynamically dividing thresholds through data-driven approaches, subjective pre-set biases are avoided, adapting to the diverse needs of different user groups. This provides standardized input for subsequent user profiling and personalized service configuration, ensuring that service solutions accurately match users' true preferences in different scenarios, significantly improving the service response efficiency and passenger experience of autonomous passenger vehicles.

[0046] Preferably, step S4 includes the following steps:

[0047] S41. Based on the classification threshold standard set, characterize the user profile of passengers in autonomous passenger vehicles in the valid questionnaires to obtain the optimal number of classifications;

[0048] S42. Analyze the user group characteristics and corresponding on-the-way service plan results for each category under the optimal number of categories, and store the user group characteristics and on-the-way service plan for each category; after users in this category place an order for autonomous passenger vehicles, configure the on-the-way service plan based on historical data.

[0049] The above steps involve using a set of classification threshold standards to create user profiles of autonomous passenger vehicle passengers in valid questionnaires, determining the optimal number of categories; analyzing the characteristics of each user group and its corresponding in-transit service plans, and storing this information; when a user in the corresponding category places an order, the system can configure a suitable in-transit service plan for them based on historical data; thus achieving accurate classification and personalized service configuration for autonomous passenger vehicle passengers.

[0050] Preferably, step S41 includes the following steps:

[0051] S411. Sorting through the basic information and travel habit data in the aforementioned valid questionnaires, and combining them with the classification threshold standard set, the questionnaire data is transformed into structured feature vector data; for example, User 1: {Age: 30; Gender: Male; Occupation: Private enterprise executive; Income: High; Travel frequency: High; Frequently used time period: Peak period; Destination type: Office building; Preferred in-vehicle temperature: Low; Preferred in-vehicle humidity: High};

[0052] S412. In Mplus software, latent profile analysis is used to classify user profiles from the structured feature vector data.

[0053] The number of categories was set to k=1, and the value of k was gradually increased. By observing AIC, BIC, ABIC, entropy, likelihood ratio test index LMR, and Bootstrap-based likelihood ratio test index BLRT, the optimal number of categories was obtained. Among them, AIC, BIC, and ABIC are information evaluation indicators, and the smaller the value of the three indicators, the better the model fit. The entropy value represents the classification accuracy. The closer it is to 1, the more accurate the classification. When it is less than 0.6, it means that more than 20% of the individuals are misclassified. When it is greater than 0.8, it means that the classification accuracy exceeds 90%. When the p-value of LMR and BLRT test values ​​reaches the significance level (P<0.05), it means that the model with k categories is better than the model with k-1 categories.

[0054] The above steps transform multidimensional user data into structured feature vectors and dynamically optimize the user classification model based on latent profile analysis to achieve accurate segmentation of passenger groups. Standardized data transformation (such as mapping preferences to classification thresholds) eliminates data dimensional differences, improving the compatibility and efficiency of profile analysis. Combined with statistical indicators such as AIC, BIC, and entropy, the optimal number of classifications is scientifically determined, avoiding subjective biases from manually preset classifications. High-precision classification identifies the core characteristics of different user groups (such as "high-income business users prefer quiet environments"), providing quantifiable configuration basis for personalized service solutions. This significantly enhances the adaptability and user satisfaction of autonomous passenger vehicle services while reducing service trial-and-error costs.

[0055] (III) Beneficial Effects

[0056] The present invention has the following beneficial effects:

[0057] This invention constructs a more comprehensive, scientific, and accurate set of influencing factors and their classification threshold standards for on-the-go service solutions for autonomous passenger vehicles through preliminary screening via literature retrieval, quantitative significance testing of influencing factors, and grade classification.

[0058] By collecting massive amounts of multidimensional data and conducting latent profile analysis, we scientifically classify users of autonomous passenger vehicles. By analyzing the characteristics and riding preferences of each user category, we construct comprehensive and accurate user profiles, providing theoretical support for personalized on-the-go service solutions for autonomous passenger vehicles. This enables precise matching of services and demands, improving the efficiency of service delivery.

[0059] This invention, through a configuration method based on user profiles, can provide passengers of autonomous passenger vehicles with highly personalized on-the-go service solutions, significantly improving passenger experience and satisfaction, and meeting the needs of modern consumers for personalized services.

[0060] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0061] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, the drawings can be obtained from these drawings without creative effort.

[0062] Figure 1 This is a flowchart illustrating a method for configuring on-the-go services for autonomous passenger vehicles based on user profiles, according to the present invention.

[0063] Figure 2 This is a flowchart illustrating the process of determining a set of significant influencing factors in an autonomous passenger vehicle on-the-go service configuration method based on user profiles, according to the present invention.

[0064] Figure 3 This is a schematic diagram illustrating the process of obtaining user profile classification in the method for configuring on-the-go services for autonomous passenger vehicles based on user profiles according to the present invention. Detailed Implementation

[0065] The technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, and not all embodiments. Based on the embodiments of the invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the invention.

[0066] In the description of this invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc., which indicate orientation or positional relationship, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the invention.

[0067] Example 1:

[0068] Please see Figure 1 , Figure 2 , Figure 3 This invention discloses a method for configuring on-the-go services for autonomous passenger vehicles based on user profiles, comprising the following steps:

[0069] S1. Construct an initial set of influencing factors; design a questionnaire based on the initial set of influencing factors; conduct a questionnaire survey using the questionnaire to obtain valid questionnaires;

[0070] S1 includes the following steps:

[0071] S11. Through literature retrieval and comprehensive analysis of previous studies, the influencing factors of passenger vehicle on-the-go service schemes were confirmed. Preliminary screening of influencing factors for autonomous passenger vehicle on-the-go service schemes was conducted, and an initial set of influencing factors a = {a1, a2, ..., a...} was constructed. i ,...a n}, where a i Let represent the i-th influencing factor of the on-the-go service plan for autonomous passenger vehicles, and n represent the total number of influencing factors. Influencing factors include environmental factors, such as in-vehicle temperature, humidity, odor, and noise; driving factors, such as changes in three-axis acceleration, speed, and driving stability; service factors, such as passenger space size and entertainment system; and travel plan factors, such as travel time and travel cost.

[0072] S12. Based on the initial set of influencing factors, design a questionnaire for passengers of autonomous passenger vehicles. The questionnaire includes basic information (age, gender, occupation, income), travel habits (travel frequency, common time periods, destination type), user preferences for each influencing factor (e.g., your preferred in-car temperature), overall satisfaction rating of the virtual on-the-go service plan formed by the combination of influencing factors (e.g., how satisfied are you with the above on-the-go service plan in scenarios such as a temperature of 26 degrees Celsius and humidity of 40%? 1 indicates very dissatisfied, 10 indicates very satisfied), and changes in preferences for each influencing factor under different scenarios (peak / off-peak hours, different seasons, weekends / weekdays, multi-person travel (with elderly people, children)) (e.g., how much do you prefer the in-car temperature to change during peak hours? 1 indicates a significant decrease, 5 indicates a significant increase).

[0073] S13. Collect a certain number of questionnaire results by conducting online questionnaire surveys and offline questionnaire surveys among passengers of autonomous passenger vehicles. Eligible questionnaires with missing data and those with the same answer option are removed to obtain valid questionnaires.

[0074] S2. Construct a multiple linear regression model; combine the valid questionnaires with the multiple linear regression model to screen each influencing factor in the initial set of influencing factors, and obtain a set of significant influencing factors.

[0075] S2 includes the following steps:

[0076] S21. Construct a multiple linear regression model;

[0077] S21 includes the following steps:

[0078] S211. Setting the significance level to α, each influencing factor in the initial set of influencing factors is used as the independent variable, and the passenger satisfaction ratings in the valid questionnaires are used as the dependent variable. A multiple linear regression model is constructed, parameters are estimated, and the regression coefficients and error terms of each independent variable are obtained, as shown in the following formula.

[0079] Y = β0 + β1X1 + β2X2 + ... + β n X n +ε;

[0080] Where Y represents the satisfaction rating; β0 represents the intercept term; β1, β2, ... β n For a1, a2...a n The regression coefficients represent the degree of influence of each independent variable on the dependent variable; ε represents the error term.

[0081] S22. Using a multiple linear regression model, each influencing factor in the initial set of influencing factors is screened to obtain a set of significant influencing factors.

[0082] S22 includes the following steps:

[0083] S221. For each independent variable, perform a t-test using SPSS software to obtain the set of P-values ​​for the independent variable P = {P1, P2, ..., P...}. i ,...P n}, where P i Let p represent the p-value of the i-th independent variable;

[0084] S222. For independent variables whose P-values ​​are below the significance level α, remove the independent variable from the multiple linear regression model, refit the multiple linear regression model, calculate the new regression coefficients and error terms, and recalculate the P-value for each independent variable.

[0085] S223. Repeat S221 and S222. Stop iterating when the p-values ​​of all independent variables are less than the significance level α, and obtain the set of significant influencing factors b = {b1, b2, ..., b...} i ,...b m}, where bi This indicates the i-th factor whose P-value is less than the significance level α, and m represents the total number of factors whose P-value is less than the significance level α.

[0086] Otherwise, continue to remove independent variables and fit a multiple linear regression model, calculate the regression coefficients, error terms and p-values ​​of independent variables until the p-values ​​of all independent variables are less than the significance level α.

[0087] S3. Collect the preference results of the set of significant influencing factors to obtain the final preference result data; based on the final preference result data and combined with the clustering algorithm, obtain the classification threshold standard set of the influencing factor levels of the autonomous passenger vehicle on-the-go service scheme.

[0088] S3 includes the following steps:

[0089] S31. Collect the set of significant influencing factors, the preference results of the influencing factors obtained through valid questionnaires, and the preference results of driving factors not obtained through valid questionnaires, to obtain the final preference results;

[0090] S31 includes the following steps:

[0091] S311. Sorting through the valid questionnaires, users' preference data for the influencing factors in the significant influencing factor set is obtained to get the questionnaire preference data; using a driving simulator, users' satisfaction rating data under various driving factors are collected to obtain driving factor preference data; driving factors include three-axis acceleration change, speed, and driving stability;

[0092] S312. The questionnaire preference results are fused with the driving factor preference results to obtain the final preference result data;

[0093] S32. Using the final preference result data and combining it with clustering algorithms, obtain the classification threshold standard set for the level of influencing factors of on-the-go service schemes for autonomous passenger vehicles.

[0094] S32 includes the following steps:

[0095] S321. Use a clustering algorithm to perform cluster analysis on the final preference result data to obtain the optimal cluster set d = {d1, d2, ..., dn}. i ,...d m}; where d i This represents the optimal number of clusters for the influencing factors of the i-th autonomous passenger vehicle on-the-go service plan; the optimal number of clusters represents the number of riding preferences corresponding to each influencing factor in the set of significant influencing factors; for example, if the optimal number of clusters for in-vehicle temperature preference data is 5, then the in-vehicle temperature is divided into 5 levels, namely level 1, level 2, level 3, level 4, and level 5.

[0096] S322. Each cluster in the optimal clustering set represents a group of samples with similar riding preferences. The distance from each sample in each cluster to its cluster center is calculated to obtain the classification threshold standard set e = {e1, e2, ..., e...}. i ,...e m}; where e i This represents the threshold values ​​corresponding to various riding preferences for each influencing factor; for example, the threshold values ​​for the five levels of in-vehicle temperature are Level 1 (21-23.5 degrees Celsius), Level 2 (23.5-25 degrees Celsius), Level 3 (25 degrees Celsius), Level 4 (25-27 degrees Celsius), and Level 5 (27-28 degrees Celsius).

[0097] S4. Based on the set of classification threshold standards, characterize the user profile of passengers in autonomous driving passenger vehicles in the valid questionnaires; configure the on-the-go service plan based on the user profile of passengers in autonomous driving passenger vehicles.

[0098] S4 includes the following steps:

[0099] S41. Based on the classification threshold standard set, characterize the user profile of passengers in autonomous passenger vehicles in the valid questionnaires to obtain the optimal number of classifications;

[0100] S41 includes the following steps:

[0101] S411. Sorting through the basic information and travel habit data in the aforementioned valid questionnaires, and combining them with the classification threshold standard set, the questionnaire data is transformed into structured feature vector data; for example, User 1: {Age: 30; Gender: Male; Occupation: Private enterprise executive; Income: High; Travel frequency: High; Frequently used time period: Peak period; Destination type: Office building; Preferred in-vehicle temperature: Low; Preferred in-vehicle humidity: High};

[0102] S412. In Mplus software, latent profile analysis is used to classify user profiles from the structured feature vector data.

[0103] Set the number of categories k=1, and gradually increase the value of k. By observing AIC, BIC, ABIC, entropy, likelihood ratio test index LMR and Bootstrap-based likelihood ratio test index BLRT, the optimal number of categories is obtained.

[0104] S42. Analyze the user group characteristics and corresponding on-the-way service solutions for each category under the optimal number of categories, and store the user group characteristics and on-the-way service solutions for each category; after users in this category place an order for autonomous passenger vehicles, configure the on-the-way service solutions based on historical data.

[0105] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0106] The preferred embodiments of the invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method for configuring on-the-go services for autonomous passenger vehicles based on user profiles, characterized in that, Includes the following steps: S1. Construct an initial set of influencing factors; design a questionnaire based on the initial set of influencing factors; conduct a questionnaire survey using the questionnaire to obtain valid questionnaires; S2. Construct a multiple linear regression model; combine the valid questionnaires with the multiple linear regression model to screen each influencing factor in the initial set of influencing factors, and obtain a set of significant influencing factors. S2 includes the following steps: S21. Set the significance level to α, take each influencing factor in the initial influencing factor set as the independent variable, and take the passenger satisfaction score in the valid questionnaire as the dependent variable to construct a multiple linear regression model. S22. For each independent variable, perform a t-test to obtain the set of P-values ​​for the independent variables, where Pi represents the P-value of the i-th independent variable. S23. For independent variables whose P-values ​​are below the significance level α, remove the independent variable from the multiple linear regression model, refit the multiple linear regression model, calculate the new regression coefficients and error terms, and recalculate the P-value for each independent variable. S24. Repeat S22 and S23. Stop iterating when the p-values ​​of all independent variables are less than the significance level α, and obtain the set of significant influencing factors. S3. Collect the preference results of the set of significant influencing factors to obtain the final preference result data; based on the final preference result data and combined with the clustering algorithm, obtain the classification threshold standard set of the influencing factor levels of the autonomous passenger vehicle on-the-go service scheme. S3 includes the following steps: The questionnaire preference data is obtained by analyzing the user preference data for the significant influencing factors in the valid questionnaires; the driving factor preference data is obtained by collecting user satisfaction rating data under various driving factors through a driving simulator; the driving factors include three-axis acceleration change, speed, and driving stability; the questionnaire preference data and the driving factor preference data are then fused to obtain the final preference data. Clustering algorithms are used to perform cluster analysis on the final preference result data to obtain the optimal cluster set. Each cluster in the optimal cluster set represents a group of samples with similar travel preference characteristics. The distance from the sample in each cluster to its cluster center is calculated to obtain the classification threshold standard set. The threshold for each influencing factor in the classification threshold standard set corresponds to various travel preferences. S4. Based on the set of classification threshold standards, characterize the user profile of passengers in autonomous driving passenger vehicles in the valid questionnaires; configure the on-the-go service plan based on the user profile of passengers in autonomous driving passenger vehicles. The S4 includes: based on the classification threshold standard set, characterizing the user profile of passengers in autonomous passenger vehicles in the valid questionnaires to obtain the optimal number of classifications; Includes the following steps: By sorting out the basic information and travel habit data from the aforementioned valid questionnaires and combining them with the set of classification threshold standards, the questionnaire data is transformed into structured feature vector data. In Mplus software, latent profile analysis is used to classify user profiles from structured feature vector data; Set the number of categories k =1, and gradually increase k The optimal number of classifications is obtained by observing the values ​​of AIC, BIC, ABIC, entropy, likelihood ratio test index LMR, and Bootstrap-based likelihood ratio test index BLRT.

2. The method for configuring on-the-go services for autonomous passenger vehicles based on user profiles according to claim 1, characterized in that, S1 includes the following steps: S11. Through literature retrieval and comprehensive analysis of previous studies, the influencing factors of passenger vehicle on-the-go service schemes were identified, and an initial set of influencing factors for autonomous passenger vehicle on-the-go service schemes was constructed. ,in, a i The first step in the autonomous passenger vehicle on-the-go service plan i One influencing factor, n This indicates the total number of influencing factors; S12. Based on the influencing factors in the initial influencing factor set, design a questionnaire for passengers of autonomous passenger vehicles that includes basic information, travel habits, user preferences for each influencing factor, comprehensive satisfaction score of the virtual on-the-go service solution formed by the combination of each influencing factor, and changes in preferences for each influencing factor in different scenarios. S13. Collect a certain number of questionnaire results by conducting online questionnaire surveys and offline questionnaire surveys among passengers of autonomous driving passenger vehicles. Eligible questionnaires with missing data and those with the same answer option are removed to obtain valid questionnaires.

3. The method for configuring on-the-go services for autonomous passenger vehicles based on user profiles according to claim 1, characterized in that, S2 further includes the following steps: S211, Set the significance level as α Using each influencing factor in the initial set of influencing factors as the independent variable and the passenger satisfaction ratings from the valid questionnaires as the dependent variable, a multiple linear regression model is constructed. Parameter estimation is performed to obtain the regression coefficients and error terms for each independent variable, as shown in the following formula. ； in, Y Indicates satisfaction rating; β 0 indicates the intercept term; β 1. β 2, ... β n for a 1. a 2 . ... a n The regression coefficients represent the degree of influence of each independent variable on the dependent variable; ε This indicates the error term.

4. The method for configuring on-the-go services for autonomous passenger vehicles based on user profiles according to claim 1, characterized in that, S4 further includes the following steps: Analyze the user group characteristics and corresponding on-the-go service solutions for each category under the optimal number of categories, and store the user group characteristics and on-the-go service solutions for each category; after users in this category place an order for autonomous passenger vehicles, configure the on-the-go service solutions based on historical data.

Images