Vehicle owner platform role permission configuration method and system

Abstract

The invention relates to a vehicle owner platform role permission configuration method and system. The method comprises the steps of obtaining user data of a target vehicle owner user on a vehicle owner platform, performing feature analysis on the user data, and generating a behavior feature data set of the target vehicle owner user on the vehicle owner platform; based on a role mining algorithm, decomposing the behavior feature data set into a user role matrix and a role permission matrix, based on a clustering analysis algorithm, determining an association degree between the user role matrix and the role permission matrix, and based on the association degree, determining a target user role of the target vehicle owner user in the vehicle owner platform; and in each function module of the vehicle owner platform, determining a target function module corresponding to the target user role, and obtaining a target permission corresponding to the target vehicle owner user based on configuration information of the target function module. By adopting the method, the user role of the vehicle owner user can be efficiently and accurately identified, so that the corresponding authority is effectively configured for the vehicle owner user on the vehicle owner platform.

Description

Technical Field

[0001] The present application relates to the technical field of user permission allocation, and particularly to a method and system for configuring role permissions on a vehicle owner platform. Background Art

[0002] In the technical field of user permission allocation, it involves identifying the user roles of vehicle owner users in a vehicle owner platform, and then configuring corresponding permissions for the vehicle owner users on the vehicle owner platform according to the identified user roles.

[0003] In related permission configuration methods, user role recognition and permission allocation are achieved through a role division method based on fixed rules. However, this method has the disadvantages of insufficient flexibility, poor adaptability, and low role matching accuracy, resulting in inaccurate user role division and problems such as redundancy or lack of permission configuration. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, system, computer device, and computer-readable storage medium for configuring role permissions on a vehicle owner platform to efficiently and accurately identify the user roles of vehicle owner users, and thus effectively configure corresponding permissions for the vehicle owner users on the vehicle owner platform.

[0005] In a first aspect, the present application provides a method for configuring role permissions on a vehicle owner platform, including: Obtain the user data of a target vehicle owner user on the vehicle owner platform, perform feature analysis on the user data to generate a behavior feature data set of the target vehicle owner user on the vehicle owner platform, where the user data includes the registration information, historical operation records, and device interaction data of the target vehicle owner user on the vehicle owner platform; Based on a preset role mining algorithm, decompose the behavior feature data set into a user role matrix and a role permission matrix, determine the degree of association between the user role matrix and the role permission matrix based on a preset clustering analysis algorithm, and determine the target user role of the target vehicle owner user on the vehicle owner platform based on the degree of association; In each function module of the vehicle owner platform, determine the target function module corresponding to the target user role, and obtain the target permissions corresponding to the target vehicle owner user based on the configuration information of the target function module, where the target permissions represent the operation permissions configured for the target vehicle owner user on the vehicle owner platform.

[0006] In a second aspect, the present application further provides a system for configuring role permissions on a vehicle owner platform, including: An acquisition module, configured to acquire user data of a target vehicle owner user on a vehicle owner platform, perform feature parsing on the user data, and generate a behavior feature data set of the target vehicle owner user on the vehicle owner platform, where the user data includes registration information, historical operation records, and device interaction data of the target vehicle owner user on the vehicle owner platform; A role recognition module, configured to decompose the behavior feature data set into a user role matrix and a role permission matrix based on a preset role mining algorithm, determine the association degree between the user role matrix and the role permission matrix based on a preset clustering analysis algorithm, and determine the target user role of the target vehicle owner user on the vehicle owner platform based on the association degree; A permission configuration module, configured to determine a target function module corresponding to the target user role in each function module of the vehicle owner platform, and obtain the target permission corresponding to the target vehicle owner user based on the configuration information of the target function module, where the target permission represents the operation permission configured for the target vehicle owner user on the vehicle owner platform.

[0007] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the above steps are implemented.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above steps are implemented.

[0009] For the above vehicle owner platform role permission configuration method, system, computer device, and computer-readable storage medium, first, perform feature parsing on the user data of the target vehicle owner user to generate a behavior feature data set, so as to ensure that subsequent role mining is based on complete and accurate user behavior features, and improve the reliability of role classification; furthermore, decompose the behavior feature data set into a user role matrix and a role permission matrix according to the role mining algorithm, and use the clustering analysis algorithm to determine their association degree, so as to accurately identify the target user role of the target vehicle owner user, optimize the role division process, and improve the role matching degree; furthermore, determine the target function module corresponding to the target user role in each function module of the vehicle owner platform, and efficiently and accurately obtain the operation permission configured for the target vehicle owner user on the vehicle owner platform based on the configuration information of the target function module; based on this, the accuracy of role division is improved, so that the rationality of permission configuration is improved based on the accurate role division process, and further the intelligence and security of the permission management of the vehicle owner platform are realized. Description of the Drawings

[0010] To more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required for the description of the embodiments or the related art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0011] Figure 1 It is a schematic flowchart of the method for configuring role permissions of the vehicle owner platform in an embodiment; Figure 2 It is a structural block diagram of the system for configuring role permissions of the vehicle owner platform in an embodiment. Specific Embodiments

[0012] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the following further details the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0013] In one embodiment, as Figure 1 shown, a method for configuring role permissions of a vehicle owner platform is provided. In this embodiment, it is exemplified that the method is applied to a server. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is realized through the interaction between the terminal and the server. In this embodiment, the method includes the following steps S101 to S103.

[0014] Step S101: Obtain the user data of the target vehicle owner user on the vehicle owner platform, perform feature analysis on the user data, and generate a behavioral feature data set of the target vehicle owner user on the vehicle owner platform. The user data includes the registration information, historical operation records, and device interaction data of the target vehicle owner user on the vehicle owner platform.

[0015] Among them, the target vehicle owner user refers to a specific user who needs to configure operation permissions on the vehicle owner platform; the vehicle owner platform refers to an online system or application that provides vehicle owner-related services for users. For example, a platform that supports vehicle owners to perform functions such as account management, vehicle control, and order processing.

[0016] Among them, the user data refers to various information records of the target vehicle owner user on the vehicle owner platform; the behavioral feature data set refers to a structured data set extracted from the user data that can characterize the user's behavioral features.

[0017] Exemplarily, first, access the database or other data storage systems of the vehicle owner platform, and extract the user data of the target vehicle owner user from them. These user data include registration information, historical operation records, and device interaction data. Among them, the registration information includes the basic identity information of the target vehicle owner user, such as the platform account, authentication status, vehicle brand, and vehicle model, etc. The historical operation records include various operation logs of the target vehicle owner user on the vehicle owner platform, such as the accessed pages, executed instructions, etc. The device interaction data includes the situation of the target vehicle owner user interacting with the platform through different terminals, such as access frequency, logged-in devices, used device functions, etc. Furthermore, after obtaining the user data of the target vehicle owner user, it is necessary to perform feature parsing on the user data. This process involves cleaning, normalizing, and format converting the original data to ensure the integrity and consistency of the data; subsequently, analyze these data to extract the feature values that can characterize the user behavior characteristics, and integrate these feature values into the behavior feature dataset of the target vehicle owner user on the vehicle owner platform. This behavior feature dataset contains a series of behavior patterns of the target vehicle owner user on the vehicle owner platform.

[0018] Step S102, based on a preset role mining algorithm, decompose the behavior feature dataset into a user role matrix and a role permission matrix, determine the degree of association between the user role matrix and the role permission matrix based on a preset clustering analysis algorithm, and determine the target user role of the target vehicle owner user in the vehicle owner platform based on the degree of association.

[0019] Among them, the role mining algorithm represents a method for analyzing and decomposing the behavior feature dataset of users to extract user role information; the clustering analysis algorithm represents a method for grouping the data in the dataset according to their similarity.

[0020] Among them, the user role matrix represents a data structure that stores the correspondence between user behavior characteristics and role categories in matrix form, and is used to describe the matching degree between the target vehicle owner user and different user roles; the role permission matrix represents a data structure that stores the correspondence between role categories and operation permissions in matrix form, and is used to describe the matching degree between the target vehicle owner user in different user roles and the corresponding operation permissions.

[0021] Among them, the target user role represents the role category of the finally determined target vehicle owner user, and is used to clarify the user role that should be assigned to the target vehicle owner user in the vehicle owner platform.

[0022] Exemplarily, in the role mining algorithm, the matrix decomposition method is adopted to decompose the behavior feature dataset into a user role matrix and a role permission matrix, where: the user role matrix is used to represent the matching degree between the target car owner user and different user roles, that is, each row of the matrix corresponds to a behavior feature of the target car owner user, each column corresponds to a user role, and the value in the matrix represents the matching degree between the target car owner user and the corresponding user role in the corresponding behavior feature; the role permission matrix is used to represent the matching degree between the target car owner user and the corresponding operation permissions in different user roles, that is, each row of the matrix corresponds to a user role, each column corresponds to a permission, and the value in the matrix represents the matching degree between the target car owner user and the corresponding operation permission in the corresponding user role.

[0023] Exemplarily, in the clustering analysis algorithm, based on similarity calculation methods such as cosine similarity, the similarity degree between the vectors in the user role matrix and the vectors in the role permission matrix is analyzed, so as to determine the target user role of the target car owner user in the car owner platform according to the vector correlation degree between the user role matrix and the role permission matrix. That is, relying solely on the user role matrix to determine the target user role may lead to problems such as inaccurate role division, unreasonable permission configuration, and role redundancy. By analyzing the correlation degree between the user role matrix and the role permission matrix, the role division can be optimized, the classification accuracy can be improved, the permission rationality can be ensured, and redundant roles can be reduced.

[0024] Step S103, in each functional module of the car owner platform, determine the target functional module corresponding to the target user role, and obtain the target permission corresponding to the target car owner user based on the configuration information of the target functional module. The target permission represents the operation permissions configured for the target car owner user in the car owner platform.

[0025] Among them, the functional module represents each independent functional unit in the car owner platform, which is used to provide specific services or operations for the car owner user. For example, the "remote unlocking" module is used to control the opening and closing of the vehicle door, the "navigation service" module is used to provide maps and route planning, and the "account management" module is used to modify personal information and payment management, etc.

[0026] Among them, the target functional module represents the set of functional modules that the target user role can access and use in the car owner platform; the configuration information of the target functional module represents the permission settings, access rules, and operation restrictions of the target functional module, which are used to define the available operations and their usage scopes of different user roles in a specific functional module. For example, the configuration information of the "remote unlocking" module may include "whether additional security verification is required", "the maximum number of unlocking operations that can be performed per day", "whether it is limited to use within a specific time period", etc.

[0027] Exemplarily, different functional modules are set in the car owner platform, and each functional module has different configuration information, wherein the configuration information of the functional module is used to define the available operations and the usage scope of different user roles in the functional module, that is, to implement the operation permissions of the corresponding functional role of the functional module; further, based on the mapping relationship between each user role and each functional module predetermined in the car owner platform, in each functional module of the car owner platform, the target functional module applicable to the target user role is determined, and further, the available operations and the usage scope applicable to the target user role are determined in the configuration information of the target functional module, so as to obtain the target permissions of the target car owner user in the car owner platform.

[0028] In the above-mentioned car owner platform role permission configuration method, first, the user data of the target car owner user is feature parsed to generate a behavior feature data set, thereby ensuring that subsequent role mining is based on complete and accurate user behavior features, thereby improving the reliability of role classification; secondly, the behavior feature data set is decomposed into a user role matrix and a role permission matrix according to the role mining algorithm, and a cluster analysis algorithm is used to determine the degree of association, thereby accurately identifying the target user role of the target car owner user, optimizing the role division process and improving the role matching degree; thirdly, the target function module corresponding to the target user role is determined in each function module of the car owner platform, and the operation permission configured by the target car owner user in the car owner platform is efficiently and accurately obtained based on the configuration information of the target function module; based on this, the accuracy of role division is improved, thereby improving the rationality of permission configuration based on the accurate role division process, and then realizing the intelligence and security of the car owner platform permission management.

[0029] In an exemplary embodiment, feature analysis is performed on user data to generate a behavioral feature data set of the target car owner user on the car owner platform, including steps S201 to S204.

[0030] Step S201, feature analysis is performed on the registration information to obtain user identity features corresponding to the target vehicle owner user, where the user identity features include the identity authentication status, account type, and vehicle association information of the target vehicle owner user on the vehicle owner platform.

[0031] Among them, the user identity feature refers to the identity-related feature data extracted from the registration information of the target car owner user, which is used to describe the identity attributes of the target car owner user in the car owner platform, including identity authentication status, account type and vehicle association information.

[0032] Among them, the identity authentication status indicates the identity verification situation of the target vehicle owner user on the vehicle owner platform, such as whether the target vehicle owner user has passed real-name authentication, whether a third-party authentication method is bound, etc.; the account type indicates the account category of the target vehicle owner user in the vehicle owner platform, such as ordinary user, enterprise user, etc.; the vehicle association information indicates the vehicle-related data bound by the target vehicle owner user on the vehicle owner platform, such as whether the target vehicle owner user has bound one or more vehicles, and the brand, model, purchase time, etc. of the vehicle.

[0033] Step S202: Perform feature analysis on the historical operation records to obtain the user operation features corresponding to the target vehicle owner user. The user operation features include various operation types corresponding to the target vehicle owner user and the operation frequency and operation time period corresponding to each operation type.

[0034] Among them, the user operation features represent the feature data related to the platform operation behavior extracted from the historical operation records of the target vehicle owner user, and are used to describe the operation behavior of the target vehicle owner user on the vehicle owner platform. It includes various operation types and the operation frequency and operation time period corresponding to each operation type.

[0035] Among them, the operation type represents the category corresponding to the operation behavior performed by the target vehicle owner user on the vehicle owner platform, such as remote unlocking, vehicle status query, order management, account setting, etc.; the operation frequency and operation time period corresponding to the operation type represent the frequency of the target vehicle owner user performing the operation behavior within the corresponding time period. For example, a certain user uses the remote unlocking function 5 times a day, mainly concentrated from 8 pm to 10 pm.

[0036] Step S203: Perform feature analysis on the device interaction data to obtain the device usage features corresponding to the target vehicle owner user. The device usage features include the function usage preferences of the target vehicle owner user in the corresponding device environment.

[0037] Among them, the device usage features represent the device usage behaviors in different device environments extracted from the device interaction data of the target vehicle owner user, and are used to analyze the main operation devices of the target vehicle owner user and the corresponding operation habits. It includes the function usage preferences in the corresponding device environment.

[0038] Among them, the function usage preferences in the corresponding device environment represent the types of functions preferred by the target vehicle owner user on different devices. For example, a certain user uses the navigation function more frequently on the in-vehicle device and mainly uses the remote control function on the mobile device.

[0039] Step S204: Combine the user identity features, user operation features, and device usage features to generate the behavior feature dataset of the target vehicle owner user on the vehicle owner platform.

[0040] Exemplarily, standardize various types of features obtained from the above parsing to ensure that different types of data have a consistent format and numerical range; furthermore, fuse and match user identity features and user operation features. For example, combine the identity authentication status and operation type to analyze whether the authentication status affects the user's platform operation behavior; furthermore, add device usage features to the fusion calculation process to further analyze whether the usage preferences of the target car owner user on different devices affect their overall operation habits; finally, all features are integrated to form a complete behavioral feature dataset, which comprehensively and relevantly reflects the data features related to the target car owner user, such as user identity features, user operation features, and device usage features.

[0041] In this embodiment, on the one hand, based on the feature parsing of the registration information, extract the user identity features to ensure that subsequent role recognition can be accurately matched based on identity factors; on the other hand, based on the feature parsing of the historical operation records, extract the user operation features to ensure that subsequent role recognition can be accurately matched based on operation behavior factors; on the other hand, based on the feature parsing of the device interaction data, extract the device usage features to ensure that subsequent role recognition can be accurately matched based on device interaction factors; based on this, fuse the user identity features, user operation features, and device usage features to generate a complete behavioral feature dataset, thereby achieving accurate user modeling in multiple dimensions to optimize the processing basis for role recognition.

[0042] In an exemplary embodiment, based on a preset role mining algorithm, decompose the behavioral feature dataset into a user role matrix and a role permission matrix, including steps S301 to S303.

[0043] Step S301, based on a preset permission behavior data structure in the car owner platform, convert the behavioral feature dataset into a behavioral feature dataset represented by a permission behavior feature matrix according to the permission behavior data structure.

[0044] Among them, the permission behavior data structure represents a data model used to define and organize user permission behaviors in the car owner platform, that is, used to unify permission classification and data format, so that the permission behaviors of different car owner users can be stored and analyzed in a structured manner; permission behavior represents the actual usage of different permission categories by car owner users on the car owner platform. For example, when a car owner user performs a "remote unlocking" operation, it involves the usage frequency or activity level of related permission behaviors such as "remote control permission", while when a car owner user performs an "order payment" operation, it involves the usage frequency or activity level of related permission behaviors such as "payment management permission".

[0045] Among them, the permission behavior feature matrix represents the matrix representation after converting the behavior feature dataset of the target vehicle owner user according to the permission behavior data structure, and is used to standardize the permission behavior of the target vehicle owner user. For example, the rows of the matrix represent various features of the target vehicle owner user (such as user identity features, user operation features, and device usage features, etc.), the columns represent each permission, and the values in the matrix represent the usage frequency or activity level of the corresponding features of the target vehicle owner user on the corresponding permissions, etc.

[0046] Exemplarily, based on the preset permission behavior data structure in the vehicle owner platform, the behavior feature dataset of the target vehicle owner user needs to be converted into a permission behavior feature matrix to ensure that various features of the target vehicle owner user can be standardized and represented according to the dimension of permission behavior. Among them: First, extract user identity features, user operation features, and device usage features from the user behavior feature dataset, and then fill various features into the matrix according to the mapping rules of the permission behavior data structure. For example, if a certain target vehicle owner user has a high operation frequency on the remote unlocking permission, then the value of this target vehicle owner user in the "remote control permission" column is larger; if the account type of the target vehicle owner user is an enterprise user, then its value in the "enterprise management permission" column may be higher than that of ordinary users. Based on this, a standardized representation based on the permission behavior feature matrix is obtained from the original behavior feature dataset, so that various features of the target vehicle owner user can be analyzed under a unified data framework for different permissions.

[0047] Step S302, based on the role mining algorithm, decompose the behavior feature dataset represented by the permission behavior feature matrix to obtain an initial user role matrix and an initial role permission matrix.

[0048] Among them, the initial user role matrix represents the user role matrix to be optimized; the initial role permission matrix represents the role permission matrix to be optimized.

[0049] Exemplarily, in the role mining algorithm, different user roles are automatically identified from a large amount of permission behavior data in the permission behavior feature matrix, and the permission range corresponding to each user role is determined, that is, the matrix decomposition method is used to decompose the permission behavior feature matrix to extract the relationship between the vehicle owner user and the user role and the relationship between the user role and the permission, so as to disassemble the permission behavior feature matrix into two low-dimensional matrices. Among them, one matrix is used to represent the initial matching degree between the target vehicle owner user and different user roles, that is, the initial user role matrix, and the other matrix is used to represent the initial matching degree between the target vehicle owner user on different user roles and the corresponding permissions, that is, the initial role permission matrix.

[0050] Step S303: Based on the preset role hierarchy relationship, optimize the user role assignment status in the initial user role matrix to obtain an optimized user role matrix. Based on the preset role inheritance relationship, optimize the role permission assignment status in the initial role permission matrix to obtain an optimized role permission matrix.

[0051] Among them, the role hierarchy relationship represents the hierarchical structure and attribution relationship between preset user roles; the role inheritance relationship represents the inheritance rules of permissions between preset user roles.

[0052] Among them, the user role assignment status in the initial user role matrix represents the initial matching situation between the car owner user and the user roles in the initial user role matrix; the role permission assignment status in the initial role permission matrix represents the initial matching situation between the user roles and permissions in the initial role permission matrix.

[0053] Exemplarily, in the process of optimizing the user role matrix, according to the preset role hierarchy relationship, adjust the initial user role matrix, and finally obtain an optimized user role matrix, that is, the role hierarchy relationship is used to define the attribution relationship and hierarchical relationship between different user roles. For example, some user roles are sub-roles of a certain senior user role, or there is a certain functional overlap between some user roles. Then, during optimization, based on the user role assignment status in the initial user role matrix, it is necessary to check whether there is a target car owner user who simultaneously matches multiple user roles with similar levels, and merge them according to the role hierarchy relationship to reduce redundant role assignments.

[0054] Furthermore, in the process of optimizing the initial role permission matrix, according to the preset role inheritance relationship, adjust the initial role permission matrix, and finally obtain an optimized role permission matrix, that is, the role inheritance relationship is used to define the inheritance rules of permissions between different user roles. For example, some senior roles should inherit the permissions of all their sub-roles, and some specific user roles may need to add or delete some permissions additionally. Then, during optimization, based on the role permission assignment status in the initial role permission matrix, it is necessary to ensure that the permissions of senior roles include the permissions of their sub-roles, and at the same time correct some abnormal permission assignments to avoid the situation of permission redundancy or permission missing.

[0055] In this embodiment, first, the behavioral feature dataset is converted into a behavioral feature dataset represented by a permission behavior feature matrix according to the permission behavior data structure, so as to realize the standardized expression and quantitative analysis of the behavioral feature dataset in the dimension of permission behavior; furthermore, based on the role mining algorithm, the behavioral feature dataset represented by the permission behavior feature matrix is decomposed to obtain an initial user role matrix and an initial role permission matrix, so as to preliminarily extract the matching relationship between the target car owner user and the user role and the matching degree between the user role and the permission through matrix decomposition, making the processing basis of role division more multi-dimensional; furthermore, according to the role hierarchy relationship, the user role allocation status is optimized to obtain an optimized user role matrix, and according to the role inheritance relationship, the role permission allocation status is optimized to obtain an optimized role permission matrix, so as to ensure that the processing basis of role division conforms to the role hierarchy relationship and the role inheritance relationship, and improve the accuracy and effectiveness of the role division process.

[0056] In an exemplary embodiment, based on the role mining algorithm, the behavioral feature dataset represented by the permission behavior feature matrix is decomposed to obtain an initial user role matrix and an initial role permission matrix, including steps S401 to S403.

[0057] Step S401, based on the permission usage behavior features in the permission behavior feature matrix, generate a usage behavior pattern matrix corresponding to the permission behavior feature matrix, and based on the permission control behavior features in the usage behavior pattern matrix, generate a control behavior pattern matrix corresponding to the permission behavior feature matrix.

[0058] Among them, the permission usage behavior features represent the features related to the usage situation such as the access frequency, usage time period, and behavior intensity of the target car owner user to different permission categories on the car owner platform.

[0059] Among them, the usage behavior pattern matrix represents a matrix representation constructed based on the permission usage behavior features. For example, the rows of the matrix represent various features of the target car owner user, the columns represent each permission, and the values in the matrix represent the features related to the usage situation such as the access frequency, usage time period, and behavior intensity of the corresponding features of the target car owner user on the corresponding permission.

[0060] Among them, the permission control behavior features represent the features related to the control functions triggered after the target car owner user uses different permission categories on the car owner platform. For example, after the target car owner user performs an operation on the "remote start permission", the car owner platform triggers two-factor authentication or limits the time interval of remote start, then these control functions of the car owner platform constitute the permission control behavior features of the target car owner user on this permission.

[0061] Among them, the control behavior pattern matrix represents a matrix representation constructed based on permission control behavior characteristics. For example, the rows of this matrix represent various characteristics of the target car owner user, the columns represent each permission, and the values in the matrix represent the characteristics related to the control functions triggered after the corresponding characteristics of the target car owner user use the corresponding permissions.

[0062] Step S402: Combine the feature distributions of the usage behavior pattern matrix and the control behavior pattern matrix, integrate the usage behavior pattern matrix and the control behavior pattern matrix, and obtain an optimized behavior feature dataset represented by the permission behavior feature matrix.

[0063] Exemplarily, analyze the feature distributions of the usage behavior pattern matrix and the control behavior pattern matrix to identify the correlation between the features. For example, in certain permission categories, analyze whether there is a direct association between the user's usage frequency and the control intensity. If the target car owner user has a very high usage frequency in the "remote start permission" category and its control intensity is also high (such as frequently triggering identity verification or device binding restrictions), it indicates that there is a strong association between the permission usage behavior characteristics and the permission control behavior characteristics of this permission category.

[0064] Furthermore, according to the correlation between the features of the usage behavior pattern matrix and the control behavior pattern matrix, determine the weight distribution of the permission usage behavior characteristics and the permission control behavior characteristics under each permission category, and realize the integration of the usage behavior pattern matrix and the control behavior pattern matrix based on the determined weight distribution to ensure that the combined data can accurately reflect the overall permission behavior of the target car owner user in different permission categories; among them, for certain permission categories, if the correlation between the permission usage behavior characteristics and the permission control behavior characteristics is strong, equal weights can be given to both; if the influence of the permission control behavior characteristics on the permission usage behavior characteristics in certain permission categories is large, the weight of the permission usage behavior characteristics can be appropriately increased. For example, in the "order management permission" category, if the payment behavior is restricted by dual identity verification or transaction limits, the weight of the permission control behavior characteristics should be appropriately increased to more accurately describe the actual permission usage situation of the user.

[0065] Step S403: Based on the role mining algorithm, perform matrix iterative decomposition processing on the optimized behavior feature dataset until the error is less than the preset threshold, and then obtain the initial user role matrix and the initial role permission matrix.

[0066] Exemplarily, in the role mining algorithm, matrix iterative decomposition processing is performed on the optimized behavioral feature dataset to gradually optimize the relationship between the vehicle owner user and the user role, as well as the relationship between the user role and the permissions, so as to disassemble the behavioral feature dataset into an initial user role matrix and an initial role permission matrix. That is, an iterative optimization method is adopted. In each iterative calculation process, the deviation between the current matrix decomposition result and the original data is calculated, and the weight distribution in the matrix is adjusted based on this deviation, so that the final two matrices can more accurately reflect the relationship between the vehicle owner user and the user role, as well as the relationship between the user role and the permissions. When the error is less than the preset threshold, the matrix decomposition is completed, and the final initial user role matrix and initial role permission matrix are obtained.

[0067] In this embodiment, first, a usage behavior pattern matrix is generated based on the permission usage behavior features in the permission behavior feature matrix, and a control behavior pattern matrix is generated based on the permission control behavior features in the behavior pattern matrix, so as to perform fine-grained disassembly on the permission usage behavior and permission control behavior of the target vehicle owner user. Furthermore, by combining the feature distributions of the usage behavior pattern matrix and the control behavior pattern matrix and integrating them, an optimized behavioral feature dataset is obtained, thereby integrating the permission usage behavior features and permission control behavior features of the target vehicle owner user to make the data structure more complete. Furthermore, based on the role mining algorithm, matrix iterative decomposition processing is performed on the optimized behavioral feature dataset to generate an initial user role matrix and an initial role permission matrix, so as to improve the reliability and accuracy of the processing basis for role division through the optimized matrix decomposition process.

[0068] In an exemplary embodiment, by combining the feature distributions of the usage behavior pattern matrix and the control behavior pattern matrix, the usage behavior pattern matrix and the control behavior pattern matrix are integrated to obtain an optimized behavioral feature dataset represented by the permission behavior feature matrix, including steps S501 to S503.

[0069] Step S501: Perform feature distribution trend analysis processing on the usage behavior pattern matrix and the control behavior pattern matrix to obtain the usage behavior feature distribution trend corresponding to the usage behavior pattern matrix and the control behavior feature distribution trend corresponding to the control behavior pattern matrix.

[0070] Among them, the usage behavior feature distribution trend represents the variation law of the target vehicle owner user's usage behavior of each permission category in the time dimension. For example, the target vehicle owner user uses the "remote start permission" permission category less during the day on weekdays, but has a higher usage frequency at night and on weekends. This change in usage behavior over time is the usage behavior feature distribution trend.

[0071] Among them, the usage behavior feature distribution trend represents the change rule of the control functions triggered by the target car owner user after using each permission category in the time dimension. For example, when the target car owner user uses the "remote start permission" permission category at night, the car owner platform triggers dual-factor authentication and device binding restrictions, while only basic verification is required during the day. The change of this control mechanism over time is the control behavior feature distribution trend.

[0072] Exemplarily, on the one hand, perform a time series analysis on the permission usage behavior features in the usage behavior pattern matrix to obtain the usage behavior feature distribution trend corresponding to the usage behavior pattern matrix. For example, extract the access records of the target car owner user on different permission categories from the usage behavior pattern matrix and organize them according to the time dimension to observe the permission access frequency, usage period, and behavior intensity of the target car owner user in different time periods, so as to obtain the usage behavior feature distribution trend; on the other hand, perform a time series analysis on the permission control behavior features in the control behavior pattern matrix to obtain the control behavior feature distribution trend corresponding to the control behavior pattern matrix. For example, extract the control mechanisms triggered by the target car owner user after using the permissions from the control behavior pattern matrix and analyze the changes of these control mechanisms in different time periods to obtain the control behavior feature distribution trend.

[0073] Step S502: Determine the trend weight values corresponding to the usage behavior pattern matrix and the control behavior pattern matrix respectively based on the contribution degrees of the usage behavior feature distribution trend and the control behavior feature distribution trend to the permission behavior feature matrix in the time dimension.

[0074] Among them, the contribution degree represents the influence ratio of the usage behavior feature distribution trend and the control behavior feature distribution trend on the permission behavior feature matrix, and is used to measure the relative importance of the permission usage behavior features and the permission control behavior features to the overall permission behavior in different permission categories and different time periods.

[0075] Among them, the trend weight value represents a weighting coefficient calculated based on the contribution degrees of the usage behavior feature distribution trend and the control behavior feature distribution trend in the time dimension, and is used to reasonably adjust the influence degrees of the usage behavior pattern matrix and the control behavior pattern matrix during data integration.

[0076] Exemplarily, the distribution trend of usage behavior characteristics and the distribution trend of control behavior characteristics are respectively mapped to the time dimension to calculate their impacts on the overall permission behavior in different time periods. For example, if the distribution trend of usage behavior characteristics (such as operation frequency) of a certain permission category significantly increases in a specific time period (such as at night), and at the same time, the distribution trend of control behavior characteristics (such as authentication, time limit) of this permission category also significantly strengthens during this period, it can be considered that the distribution trend of usage behavior characteristics and the distribution trend of control behavior characteristics have equal contribution degrees to the overall permission behavior of this permission category in this time period. Therefore, equal trend weight values need to be assigned to the usage behavior pattern matrix and the control behavior pattern matrix for this permission category.

[0077] For another example, for some permission categories, if the change in the distribution trend of usage behavior characteristics is large, while the change in the distribution trend of control behavior characteristics is small, a higher trend weight value needs to be assigned to the usage behavior pattern matrix for this permission category; for another example, if the change in the distribution trend of control behavior characteristics is more obvious, for example, a certain permission category is subject to strict access restrictions in some time periods and completely open in other time periods, a higher trend weight value needs to be assigned to the control behavior pattern matrix for this permission category.

[0078] Step S503, based on the trend weight values corresponding to the usage behavior pattern matrix and the control behavior pattern matrix respectively, integrate the usage behavior pattern matrix and the control behavior pattern matrix to obtain an optimized behavior feature dataset represented by the permission behavior feature matrix.

[0079] Exemplarily, based on the trend weight values corresponding to the usage behavior pattern matrix and the control behavior pattern matrix respectively, the values of the two matrices are weighted and adjusted to ensure that the contribution degrees of different feature categories in the data integration process can reasonably reflect the actual permission behavior status of the target car owner user. For example, in the "remote control permission" category, if the usage frequency of the target car owner user significantly increases at night, and at the same time, the control intensity of this permission (such as dual authentication and time limit) also strengthens at night, then during the integration process, it is necessary to appropriately increase the weights of this permission category in the usage behavior pattern matrix and the control behavior pattern matrix to accurately reflect the actual permission usage and control situation; furthermore, the two matrices after weighted adjustment are fused to construct a more comprehensive behavior feature dataset that can cover both the permission usage status and the permission control status of the target car owner user.

[0080] In this embodiment, first, by analyzing the characteristic distribution trends of the usage behavior pattern matrix and the control behavior pattern matrix, the usage behavior characteristic distribution trend and the control behavior characteristic distribution trend are obtained, so as to accurately extract the time variation law of the permission usage status and the control mechanism, and improve the timeliness of the data. Furthermore, according to the usage behavior characteristic distribution trend and the control behavior characteristic distribution trend, calculate their contribution degrees to the permission behavior characteristic matrix in different time periods to determine the trend weight values of the usage behavior pattern matrix and the control behavior pattern matrix, so as to dynamically adjust the influence of the permission usage behavior characteristics and the permission control behavior characteristics in the data integration process. Furthermore, according to the trend weight values of the usage behavior pattern matrix and the control behavior pattern matrix, integrate the two to generate an optimized behavior characteristic data set, so as to ensure that the final data can not only accurately depict the permission usage habits of the target car owner user, but also reflect the actual impact of the system permission control.

[0081] In an exemplary embodiment, based on a preset clustering analysis algorithm, determine the association degree between the user role matrix and the role permission matrix, and based on the association degree, determine the target user role of the target car owner user in the car owner platform, including steps S601 to S603.

[0082] Step S601: Determine each user role vector in the user role matrix and each role permission vector in the role permission matrix, and determine the association degree between each user role vector and each role permission vector based on the clustering analysis algorithm.

[0083] Among them, the user role vector represents the vector extracted from the user role matrix, which is used to describe the matching degree of the target car owner user in different user roles in vector form; the role permission vector represents the vector extracted from the role permission matrix, which is used to describe the matching degree between the target car owner user in different user roles and the corresponding operation permissions in vector form.

[0084] Step S602: Based on the association degree between each user role vector and each role permission vector, generate an association degree matrix, which is used to characterize the association degree of each vector between the user role matrix and the role permission matrix.

[0085] Among them, in the association degree matrix, the rows of the matrix represent user role vectors, the columns represent role permission vectors, and the values in the matrix represent the matching degree between a certain user role vector and a certain role permission vector.

[0086] Exemplarily, based on the similarity calculation method, among each user role vector and each role permission vector, each user role vector and each role permission vector can be paired one by one to calculate the similarity score of each paired combination, and then the similarity scores of each paired combination can be integrated in the form of a matrix, thereby constructing an association degree matrix.

[0087] Step S603: Combine the association degree matrix with the preset role determination rules to screen the user roles corresponding to each user role vector in the user role matrix, and obtain the target user role of the target car owner user in the car owner platform.

[0088] Among them, the role determination rule represents a rule set for screening the final user role, that is, making a role matching decision based on the numerical distribution of the association degree matrix.

[0089] Exemplarily, first, combine the numerical distribution in the association degree matrix, and according to the role determination rules, screen the user roles corresponding to each user role vector in the user role matrix to further screen the optimal user role. For example, the role determination rule usually includes multiple determination criteria, such as whether the matching degree between the user role vector and the role permission vector exceeds a certain threshold, whether the target car owner user already has the permissions of some matching user roles, whether some advanced roles require additional conditions to be met, etc. Through these rules, the data in the association degree matrix can be screened, so that the target car owner user finally only matches the most suitable user role, that is, the target user role of the target car owner user in the car owner platform. Furthermore, during the screening process, it is also necessary to filter some user roles with low matching degrees to prevent the target car owner user from being misclassified into user roles that do not conform to the actual operation habits.

[0090] In this embodiment, first, determine each user role vector in the user role matrix and each role permission vector in the role permission matrix, generate an association degree matrix based on the association degree between each user role vector and each role permission vector, thereby establishing a quantitative mapping between the user role and the role permission, making the calculation of role matching more intuitive and improving the accuracy of role classification; furthermore, combine the association degree matrix with the role determination rules to screen each user role and determine the final user role of the target car owner user to ensure that the user role assignment conforms to the platform management strategy and avoid the situation of incorrect role matching.

[0091] In an exemplary embodiment, combining the association degree matrix with the preset role determination rules to screen the user roles corresponding to each user role vector in the user role matrix, and obtaining the target user role of the target car owner user in the car owner platform includes steps S701 to S703.

[0092] Step S701: Obtain multiple correlation threshold intervals in the role determination rule. Combine the correlation degree matrix with the multiple correlation threshold intervals, and perform zonal screening to obtain user role sets where the correlation degrees are respectively in each correlation threshold interval.

[0093] Among them, the correlation threshold interval represents multiple ranges of correlation degree values set according to the role determination rule. For example, a high correlation threshold interval (such as the correlation degree is within 0.8 to 1.0, and does not include 0.8), a medium correlation threshold interval (such as the correlation degree is within 0.5 to 0.8, and does not include 0.5), and a low correlation threshold interval (such as the correlation degree is within 0.3 to 0.5) are set to divide user roles with different correlation degrees in different correlation threshold intervals, and filter out user roles with lower correlation degrees (such as the correlation degree is less than 0.3).

[0094] Among them, the user role set represents a set of user roles whose correlation degrees are in the same correlation threshold interval, screened based on the correlation threshold interval.

[0095] Exemplarily, in the role determination rule, three correlation threshold intervals such as a high correlation threshold interval, a medium correlation threshold interval, and a low correlation threshold interval can be set. Based on the correlation degree between each user role vector and each role permission vector in the correlation degree matrix, each user role is divided into the correlation threshold interval to which the corresponding correlation degree belongs, so as to obtain user role sets in each correlation threshold interval. Furthermore, if in the same user role, the correlation degrees between its user role vector and multiple role permission vectors are respectively in different correlation threshold intervals, then this user role can be divided into the corresponding correlation threshold intervals to which the respective correlation degrees belong.

[0096] Step S702: Combine the role coverage degree of each user role set and the adaptation degree between different user roles in each user role set, screen each user role set, and assign corresponding role weight values to each user role in the screened target user role set.

[0097] Among them, the role coverage degree represents the completeness of the function modules and permission scopes covered by a certain user role set, and is used to evaluate whether this user role set can meet the main permission requirements of the target car owner user. For example, if the user roles in a certain user role set cover remote control, order management, and account management permissions, then its role coverage degree is relatively high, while the role coverage degree of a user role set that only covers remote control permissions is relatively low.

[0098] Among them, the degree of adaptation between different user roles in each user role set represents the compatibility of each user role in terms of permission configuration within the same user role set, and is used to ensure that the finally assigned user roles can be reasonably combined without causing permission conflicts or redundancies. For example, for two user roles in a certain user role set, one focuses on remote control and the other focuses on order management, and their permissions are complementary, then the degree of adaptation is relatively high; if the permissions of the two roles overlap highly, then the degree of adaptation is relatively low.

[0099] Among them, the role weight value represents the weight value calculated for each user role in the target user role set according to the role coverage degree and the degree of adaptation with other user roles, and is used to measure the importance and priority of different user roles.

[0100] Exemplarily, first, in the user role sets in each relevance threshold interval, analyze the user role categories covered by each user role set, and determine the role coverage degree of each user role set based on the covered user role categories. For example, some user role sets may only cover some function modules, while other user role sets may cover multiple key function modules. Furthermore, analyze the degree of adaptation between different user roles within each user role set, and judge whether different user roles in the same user role set can be reasonably combined. Furthermore, based on the degree of adaptation between different user roles within each user role set, screen out the target user role set from each user role set, that is, different user roles in the target user role set can be reasonably combined, and the role coverage degree of the target user role set is as large as possible. Furthermore, in the target user role set, combine the role coverage degree of each user role and the degree of adaptation with other user roles to determine the role weight value of each user role. For example, a user role with comprehensive coverage permissions and good adaptation degree is given a higher role weight value, while a user role with low adaptation degree and single coverage permissions is given a lower role weight value.

[0101] Step S703: Based on the role weight values respectively corresponding to each user role in the target user role set, use the user roles whose role weight values meet the preset threshold conditions as the target user roles of the target vehicle owners in the vehicle owner platform.

[0102] Among them, the preset threshold condition represents the lower limit threshold corresponding to the role weight value used to screen the final target user role, that is, it is used to ensure that the final target user role meets the minimum requirements in terms of role coverage degree and adaptation degree.

[0103] Exemplarily, each user role in the target user role set is sorted according to the corresponding role weight value, and the user role whose role weight value meets the preset threshold condition is used as the target user role of the target vehicle owner user in the vehicle owner platform, thereby completing the final role assignment of the target vehicle owner user. This target user role will be used as the official role identity of the target vehicle owner user on the vehicle owner platform.

[0104] In this embodiment, first, in combination with the association degree matrix and multiple association threshold intervals, user role sets with association degrees in each association threshold interval are screened out respectively, improving the accuracy of role screening and avoiding interference from low-matching roles in the final role determination. Furthermore, in combination with the role coverage degree of each user role set and the adaptation degree between different user roles in each user role set, a target user role set is screened out and corresponding role weight values are assigned to each user role in it, thereby ensuring the rationality of the permission coverage range and the role adaptation degree of the role weight values assigned to each user role in the selected target role set. Furthermore, the target user role that meets the preset threshold condition is screened out according to the role weight value, thereby improving the objectivity of role selection and ensuring that the finally determined target user role not only conforms to the business rules but also can dynamically adapt to the actual usage situation of the target vehicle owner user.

[0105] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential either, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0106] Based on the same inventive concept, the embodiments of the present application also provide a vehicle owner platform role permission configuration system for implementing the vehicle owner platform role permission configuration method involved above. The implementation solutions for solving problems provided by this system are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the vehicle owner platform role permission configuration system provided below can refer to the limitations on the vehicle owner platform role permission configuration method in the above text, and will not be repeated here.

[0107] In an exemplary embodiment, as Figure 2As shown, a vehicle owner platform role permission configuration system is provided, including: an acquisition module 201, a role recognition module 202, and a permission configuration module 203, where: The acquisition module 201 is used to acquire the user data of the target vehicle owner user on the vehicle owner platform, perform feature analysis on the user data, and generate a behavior feature data set of the target vehicle owner user on the vehicle owner platform. The user data includes the registration information, historical operation records, and device interaction data of the target vehicle owner user on the vehicle owner platform. The role recognition module 202 is used to decompose the behavior feature data set into a user role matrix and a role permission matrix based on a preset role mining algorithm, determine the degree of association between the user role matrix and the role permission matrix based on a preset clustering analysis algorithm, and determine the target user role of the target vehicle owner user on the vehicle owner platform based on the degree of association. The permission configuration module 203 is used to determine the target function module corresponding to the target user role in each function module of the vehicle owner platform, and obtain the target permission corresponding to the target vehicle owner user based on the configuration information of the target function module. The target permission represents the operation permission configured for the target vehicle owner user on the vehicle owner platform.

[0108] In an exemplary embodiment, the acquisition module 201 is further used to: perform feature analysis on the registration information to obtain the user identity features corresponding to the target vehicle owner user, where the user identity features include the identity authentication status, account type, and vehicle association information of the target vehicle owner user on the vehicle owner platform; perform feature analysis on the historical operation records to obtain the user operation features corresponding to the target vehicle owner user, where the user operation features include each operation type corresponding to the target vehicle owner user and the operation frequency and operation period corresponding to each operation type; perform feature analysis on the device interaction data to obtain the device usage features corresponding to the target vehicle owner user, where the device usage features include the function usage preferences of the target vehicle owner user in the corresponding device environment; combine the user identity features, user operation features, and device usage features to generate a behavior feature data set of the target vehicle owner user on the vehicle owner platform.

[0109] In an exemplary embodiment, the role recognition module 202 is further used to: convert the behavior feature data set into a behavior feature data set represented by a permission behavior feature matrix according to the permission behavior data structure preset in the vehicle owner platform; perform decomposition processing on the behavior feature data set represented by the permission behavior feature matrix based on the role mining algorithm to obtain an initial user role matrix and an initial role permission matrix; optimize the user role assignment status in the initial user role matrix based on the preset role hierarchy relationship to obtain an optimized user role matrix, and optimize the role permission assignment status in the initial role permission matrix based on the preset role inheritance relationship to obtain an optimized role permission matrix.

[0110] In an exemplary embodiment, the role recognition module 202 is further configured to: generate a usage behavior pattern matrix corresponding to the permission behavior feature matrix based on the permission usage behavior features in the permission behavior feature matrix, and generate a control behavior pattern matrix corresponding to the permission behavior feature matrix based on the permission control behavior features in the usage behavior pattern matrix; combine the feature distributions of the usage behavior pattern matrix and the control behavior pattern matrix, integrate the usage behavior pattern matrix and the control behavior pattern matrix, and obtain an optimized behavior feature data set represented by the permission behavior feature matrix; perform matrix iterative decomposition processing on the optimized behavior feature data set based on the role mining algorithm until the error is less than a preset threshold, and then obtain an initial user role matrix and an initial role permission matrix.

[0111] In an exemplary embodiment, the role recognition module 202 is further configured to: perform feature distribution trend analysis processing on the usage behavior pattern matrix and the control behavior pattern matrix to obtain a usage behavior feature distribution trend corresponding to the usage behavior pattern matrix and a control behavior feature distribution trend corresponding to the control behavior pattern matrix; determine the trend weight values corresponding to the usage behavior pattern matrix and the control behavior pattern matrix respectively based on the contribution degrees of the usage behavior feature distribution trend and the control behavior feature distribution trend to the permission behavior feature matrix in the time dimension; integrate the usage behavior pattern matrix and the control behavior pattern matrix based on the trend weight values corresponding to the usage behavior pattern matrix and the control behavior pattern matrix respectively, and obtain an optimized behavior feature data set represented by the permission behavior feature matrix.

[0112] In an exemplary embodiment, the role recognition module 202 is further configured to: determine each user role vector in the user role matrix and each role permission vector in the role permission matrix, and determine the association degree between each user role vector and each role permission vector based on the clustering analysis algorithm; generate an association degree matrix based on the association degree between each user role vector and each role permission vector, where the association degree matrix is used to represent the association degree of each vector between the user role matrix and the role permission matrix; combine the association degree matrix with a preset role determination rule to screen the user roles corresponding to each user role vector in the user role matrix, and obtain the target user role of the target car owner in the car owner platform.

[0113] In an exemplary embodiment, the role recognition module 202 is further configured to: obtain multiple relevance threshold intervals in the role determination rule, combine the association degree matrix with the multiple relevance threshold intervals, and partition and screen to obtain user role sets with association degrees respectively in each relevance threshold interval; combine the role coverage degrees of each user role set and the adaptation degrees between different user roles in each user role set, screen each user role set, and assign corresponding role weight values to each user role in the screened target user role set; based on the role weight values respectively corresponding to each user role in the target user role set, use the user role whose role weight value meets the preset threshold condition as the target user role of the target car owner in the car owner platform.

[0114] Each module in the above car owner platform role permission configuration system can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor in the computer device in hardware form or be independent of it, or can be stored in the memory in the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0115] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in any of the above embodiments are implemented.

[0116] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in any of the above embodiments are implemented.

[0117] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0118] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0119] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for configuring the role authority of a vehicle owner platform, characterized in that: The method comprises: Obtain user data of the target car owner user on the car owner platform, perform feature analysis on the user data, and generate a behavioral feature data set of the target car owner user on the car owner platform, wherein the user data includes registration information, historical operation records, and device interaction data of the target car owner user on the car owner platform; Based on a preset role mining algorithm, the behavior feature data set is decomposed into a user role matrix and a role authority matrix, the correlation degree between the user role matrix and the role authority matrix is ​​determined based on a preset cluster analysis algorithm, and the target user role of the target car owner user in the car owner platform is determined based on the correlation degree; In each functional module of the car owner platform, the target functional module corresponding to the target user role is determined, and the target authority corresponding to the target car owner user is obtained based on the configuration information of the target functional module. The target authority represents the operation authority configured for the target car owner user in the car owner platform.

2. The method according to claim 1, characterized in that The feature analysis of the user data to generate a behavior feature data set of the target car owner user on the car owner platform includes: Performing feature analysis on the registration information to obtain user identity features corresponding to the target vehicle owner user, wherein the user identity features include the identity authentication status, account type, and vehicle association information of the target vehicle owner user on the vehicle owner platform; Performing feature analysis on the historical operation records to obtain user operation features corresponding to the target vehicle owner user, wherein the user operation features include various operation types corresponding to the target vehicle owner user and operation frequencies and operation time periods corresponding to various operation types; Performing feature analysis on the device interaction data to obtain device usage features corresponding to the target vehicle owner user, wherein the device usage features include the function usage preferences of the target vehicle owner user in a corresponding device environment; In combination with the user identity features, the user operation features and the device usage features, a behavioral feature data set of the target car owner user on the car owner platform is generated.

3. The method according to claim 1, characterized in that The method of decomposing the behavior feature data set into a user role matrix and a role authority matrix based on a preset role mining algorithm includes: Based on a preset authority behavior data structure in the vehicle owner platform, converting the behavior feature data set into a behavior feature data set represented by an authority behavior feature matrix according to the authority behavior data structure; Based on the role mining algorithm, the behavior feature data set represented by the authority behavior feature matrix is ​​decomposed to obtain an initial user role matrix and an initial role authority matrix; Based on the preset role hierarchy relationship, the user role allocation state in the initial user role matrix is ​​optimized to obtain an optimized user role matrix; based on the preset role inheritance relationship, the role authority allocation state in the initial role authority matrix is ​​optimized to obtain an optimized role authority matrix.

4. The method according to claim 3, characterized in that Based on the role mining algorithm, the behavior feature data set represented by the authority behavior feature matrix is ​​decomposed to obtain an initial user role matrix and an initial role authority matrix, including: Based on the permission usage behavior characteristics in the permission behavior characteristic matrix, generating a usage behavior pattern matrix corresponding to the permission behavior characteristic matrix, and based on the permission control behavior characteristics in the usage behavior pattern matrix, generating a control behavior pattern matrix corresponding to the permission behavior characteristic matrix; Combining the characteristic distribution of the use behavior pattern matrix and the control behavior pattern matrix, integrating the use behavior pattern matrix and the control behavior pattern matrix to obtain an optimized behavior characteristic data set represented by the authority behavior characteristic matrix; Based on the role mining algorithm, the optimized behavior feature data set is subjected to matrix iterative decomposition processing until the error is less than a preset threshold, thereby obtaining the initial user role matrix and the initial role authority matrix.

5. The method according to claim 4, characterized in that The combining the characteristic distribution of the usage behavior pattern matrix and the control behavior pattern matrix, integrating the usage behavior pattern matrix and the control behavior pattern matrix, and obtaining an optimized behavior characteristic data set represented by the authority behavior characteristic matrix, includes: Performing feature distribution trend analysis on the usage behavior pattern matrix and the control behavior pattern matrix to obtain a usage behavior feature distribution trend corresponding to the usage behavior pattern matrix and a control behavior feature distribution trend corresponding to the control behavior pattern matrix; Determining trend weight values ​​corresponding to the usage behavior pattern matrix and the control behavior pattern matrix respectively based on the contribution of the usage behavior feature distribution trend and the control behavior feature distribution trend to the authority behavior feature matrix in the time dimension; Based on the trend weight values ​​respectively corresponding to the usage behavior pattern matrix and the control behavior pattern matrix, the usage behavior pattern matrix and the control behavior pattern matrix are integrated to obtain an optimized behavior feature data set represented by the authority behavior feature matrix.

6. The method according to claim 1, characterized in that The determining the correlation degree between the user role matrix and the role authority matrix based on a preset cluster analysis algorithm, and determining the target user role of the target car owner user in the car owner platform based on the correlation degree, includes: Determine each user role vector in the user role matrix and each role permission vector in the role permission matrix, and determine the degree of association between each user role vector and each role permission vector based on the cluster analysis algorithm; Based on the degree of association between each user role vector and each role authority vector, a correlation degree matrix is ​​generated, wherein the correlation degree matrix is ​​used to characterize the degree of association between each vector between the user role matrix and the role authority matrix; By combining the association degree matrix with a preset role determination rule, the user roles corresponding to the user role vectors in the user role matrix are screened to obtain the target user role of the target car owner user in the car owner platform.

7. The method according to claim 6, characterized in that The step of combining the association degree matrix with a preset role determination rule to screen the user roles corresponding to the user role vectors in the user role matrix to obtain the target user role of the target car owner user in the car owner platform includes: Acquire multiple relevance threshold intervals in the role determination rule, combine the relevance degree matrix with the multiple relevance threshold intervals, and perform partition screening to obtain a set of user roles whose relevance degrees are respectively in each relevance threshold interval; Based on the role coverage of each user role set and the adaptability between different user roles in each user role set, each user role set is screened and a corresponding role weight value is assigned to each user role in the screened target user role set; Based on the role weight values ​​respectively corresponding to the respective user roles in the target user role set, the user role whose role weight value meets the preset threshold condition is used as the target user role of the target car owner user in the car owner platform.

8. A vehicle owner platform role authority configuration system, characterized in that: The system comprises: An acquisition module is used to acquire user data of a target car owner user on a car owner platform, perform feature analysis on the user data, and generate a behavioral feature data set of the target car owner user on the car owner platform, wherein the user data includes registration information, historical operation records, and device interaction data of the target car owner user on the car owner platform; A role identification module, used to decompose the behavior feature data set into a user role matrix and a role authority matrix based on a preset role mining algorithm, determine the degree of association between the user role matrix and the role authority matrix based on a preset cluster analysis algorithm, and determine the target user role of the target car owner user in the car owner platform based on the degree of association; The permission configuration module is used to determine the target function module corresponding to the target user role in each function module of the car owner platform, and obtain the target permission corresponding to the target car owner user based on the configuration information of the target function module. The target permission represents the operation permission configured for the target car owner user in the car owner platform.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images