Authority management method, computer readable storage medium, electronic device and computer program product

Abstract

The embodiment of the invention provides an authority management method, a storage medium, an electronic device and a computer program product, and the method comprises the steps: obtaining an authority request of an application; whether the permission request conforms to an authorization habit or not is recognized through a machine learning model, and the machine learning model is trained in advance through historical operation data of multiple applications; and processing the permission request according to the identification result. According to the embodiment of the invention, the machine learning model is utilized to intelligently identify the permission request conforming to the user authorization habit and perform corresponding processing, so that the problem that the user experience is influenced by frequent permission requests in the related technology can be solved, and the technical effects of reducing the user perception and improving the user experience are achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing, and specifically, to a permission management method, a computer-readable storage medium, an electronic device, and a computer program product. Background Art

[0002] As smartphones become increasingly versatile, users are faced with frequent permission requests while enjoying their convenience. Traditional permission management methods usually require users to respond to each permission request, which not only affects the user experience but also increases users' concerns about privacy leaks. Existing technologies often lack consideration of user habits when processing permission requests and fail to effectively distinguish the importance of different permission requests, causing users to have to perform cumbersome operations even when faced with low-intensity permission requests. Summary of the invention

[0003] The embodiments of the present application provide a permission management method, a computer-readable storage medium, an electronic device, and a computer program product to at least solve the problem in the related art that frequent permission requests affect user experience.

[0004] According to one embodiment of the present application, a permission management method is provided, including: obtaining a permission request from an application; identifying whether the permission request complies with authorization practices through a machine learning model, wherein the machine learning model is pre-trained using historical operation data of multiple applications; and processing the permission request based on the identification result.

[0005] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0006] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in any one of the above method embodiments when executing the computer program.

[0007] According to another embodiment of the present application, a computer program product is provided, including a computer program, which implements the steps in any of the above method embodiments when executed by a processor.

[0008] Through the above-mentioned embodiments of the present application, a machine learning model is used to intelligently identify permission requests that are consistent with user authorization habits and perform corresponding processing. Therefore, it is possible to solve the problem of frequent permission requests affecting user experience in related technologies, thereby achieving the technical effect of reducing user perception and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a hardware structure block diagram of a mobile terminal of the rights management method of an embodiment of the present application;

[0010] Figure 2 is a flowchart of a rights management method according to an embodiment of the present application;

[0011] Figure 3 It is a flowchart of identifying whether a permission request complies with authorization practices through a machine learning model in one embodiment of the present application;

[0012] Figure 4 It is a schematic diagram of the process of training a machine learning model in one embodiment of the present application;

[0013] Figure 5 is a flowchart of a rights management method in one embodiment of the present application;

[0014] Figure 6 is a flowchart of smart clipboard permission management in one embodiment of the present application;

[0015] Figure 7 This is a flowchart of network rights management in one embodiment of the present application;

[0016] Figure 8 It is a block diagram of a rights management device according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0018] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0019] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is a hardware structure block diagram of the mobile terminal in which the method embodiment of the present application is executed. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0020] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the rights management method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0021] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0022] In this embodiment, a rights management method is provided, which is applied to a terminal. Figure 2 is a flowchart of a rights management method according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0023] Step S202, obtaining the permission request of the application;

[0024] Step S204, identifying whether the permission request complies with the authorization habit through a machine learning model;

[0025] Step S206: Process the permission request according to the recognition result.

[0026] In this embodiment, the machine learning model is pre-trained using historical operation data of multiple applications.

[0027] In some embodiments, the permission request of the application can be dynamic. For example, for the permission request of geographic location information, the terminal can request user authorization only when the application actually needs to use the permission, rather than requesting all permissions at once when the application is installed. This dynamic permission request method can reduce user resistance and improve the pertinence of authorization.

[0028] In the embodiment of the present application, the permission requests that meet the user's authorization habits are intelligently identified through the machine learning model and processed accordingly. Therefore, the problem of frequent permission requests affecting the user experience in the related technology can be solved, and the technical effect of reducing user perception and improving user experience can be achieved. This method can automatically analyze the user's authorization mode for application permissions, thereby intelligently determining the processing method of permission requests, effectively improving the efficiency and accuracy of permission management, and is applicable to various mobile devices and operating system environments.

[0029] In some embodiments, the recognition result includes whether the permission request complies with the authorization practice, or whether the permission request does not comply with the authorization practice. The permission requests corresponding to different recognition results are processed in different ways.

[0030] In some embodiments, step S206 may include the following steps: step S206A, in response to the recognition result that the permission request complies with the authorization habit, authorizing the permission request; step S206B, in response to the recognition result that the permission request does not comply with the authorization habit, refusing to authorize the permission request; or, in response to the recognition result that the permission request does not comply with the authorization habit, prompting on the display interface whether to agree to authorize the permission request. Further, if the display interface prompts whether to agree to authorize the permission request, after the prompt, the terminal can process the permission request according to the user operation (selecting to agree to authorize or refuse authorization). This processing method can automatically authorize or automatically reject permission requests according to the user's authorization habits, and provide a manual confirmation option when necessary, which not only ensures user experience but also enhances security. It is particularly suitable for application scenarios where users frequently use and have changing permission requirements.

[0031] In some embodiments, compliance with authorization habits can be understood as being more inclined to authorization. Exemplarily, for low-intensity or non-sensitive permission requests, authorization habits are often complied with, while for sensitive or unconventional permission requests, authorization will be cautious. Accordingly, the machine learning model learns the user's authorization habits and makes decisions based on the user's authorization habits. When the recognition result is that the permission request complies with the authorization habit, the terminal will automatically authorize the permission request, reducing cumbersome authorization operations and improving user experience. When the recognition result is that the permission request does not comply with the authorization habit, the terminal will automatically refuse to authorize the permission request, or prompt in the display interface, enhancing the controllability of permission management.

[0032] In some embodiments, the specific implementation of step S204 is as follows: Figure 3 shown.

[0033] Figure 3 FIG. 1 is a flow chart of an embodiment of the present application for identifying whether a permission request complies with authorization practices through a machine learning model. Figure 3 As shown, the process may include the following steps:

[0034] Step S2042, obtaining operation data of multiple applications related to the permission request;

[0035] Step S2044, pre-processing the operation data to obtain characteristic parameters of the target type, wherein the characteristic parameters of the target type include: the application type of the requester, the usage frequency of the same type of applications, the permission request history, and the mode of the user accepting the permission request;

[0036] Step S2044, input the characteristic parameters of the target type into the machine learning model to obtain the recognition result output by the machine learning model, wherein the recognition result includes whether the permission request complies with the authorization practice.

[0037] In an embodiment of the present application, preprocessing of operation data can ensure the input data quality of the machine learning model and improve the recognition accuracy of the model. The feature parameter can be expressed as a categorical feature parameter or a numerical feature parameter. For example, if it is expressed as a categorical feature parameter, the application type of the application requester can be divided into social, tool, and game types, the application usage frequency can be divided into high frequency, medium frequency, and low frequency, and the user's acceptance mode of permission request can be divided into default acceptance, manual selection, etc. If it is expressed as a numerical feature parameter, the application usage frequency can be the numerical value of the number of times the application is used, and the permission request history can be the historical number of acceptances of permission requests, the historical number of rejections of permission requests, etc. This application does not limit the specific data content and representation of the feature parameters of each target type.

[0038] In the embodiment of the present application, different application types may require different permission sets. For example, it is a common requirement for social media applications to request access to contact permissions, while educational applications rarely request such permissions. By identifying the application type, the model can better evaluate the rationality and necessity of the permission request. The frequency of use can reflect the user's trust and usage habits for a certain type of application. High frequency use may mean that the user is more willing to grant more permissions to such applications, while low frequency use may indicate that the user is more cautious and tends to limit permissions. This feature helps the model identify the user's preference trend for permission requests. The permission request history records the user's past responses to permission requests, including the number of acceptances and rejections. This is an important indicator that directly reflects the user's sensitivity to permissions and authorization habits. By analyzing historical data, the model can learn the user's authorization status under specific permission requests, thereby predicting the processing results of future requests. The user's mode of accepting permission requests, such as default acceptance, manual selection, etc., provides the user's personal preference information for the permission authorization process. Users who prefer default acceptance may prefer convenience, while users who prefer manual selection may pay more attention to privacy control. This parameter can help the machine learning model understand the user's level of privacy awareness and control preference for permissions. The above-mentioned characteristic parameters are key components of the machine learning model input. They work together to enable the model to evaluate permission requests from multiple dimensions and make intelligent judgments based on the user's personal habits and preferences. In this way, the system can intelligently identify and process permission requests, reduce the user's operational burden, and enhance privacy protection.

[0039] In some embodiments, the preprocessing method includes at least one of the following: deduplication, missing value processing, feature engineering, and one-hot encoding. These preprocessing steps can eliminate data noise, improve the quality of feature parameters, enable the model to extract useful information from complex and diverse data, and improve the performance of the machine learning model, thereby improving the accuracy and reliability of the recognition results.

[0040] In some embodiments, the type of machine learning model includes: a decision tree-based machine learning model.

[0041] In some embodiments, the decision tree-based machine learning model constructs a tree-like structure model for classification by conditionally judging the characteristic parameters of the target type, which is easy to understand and explain and can process multiple types of data. Exemplarily, the machine learning model can use the decision tree model in Scikit-Learn (an open source machine learning library). However, the present application is not limited to this.

[0042] In an exemplary embodiment, the relevant operation data of the permission request of the application includes the application type of the application requester (e.g., social, tool, game), the frequency of use of the application (e.g., high frequency, medium frequency, low frequency), and the permission request history (e.g., the number of historical acceptances of permission requests, the number of historical rejections of permission requests). The relevant operation data is pre-processed and input into the Scikit-Learn decision tree model. The root node of the decision tree model selects the permission request history and makes a judgment. If the number of historical acceptances of the permission request is less than the preset value, it is considered that it does not comply with the authorization habit. If the number of historical acceptances of the permission request is greater than or equal to the preset value, the next node makes a judgment based on the frequency of use of the application, and so on, until the identification result of the permission request is obtained.

[0043] In some embodiments, before executing step S204, the method further includes: step S201, training a machine learning model through historical operation data and authorization status. The specific implementation of step S201 is as follows: Figure 4 shown.

[0044] Figure 4 is a flow chart of training a machine learning model in one embodiment of the present application, such as Figure 4 As shown, the process may include the following steps:

[0045] Step S2012, collecting historical operation data related to historical permission requests and corresponding authorization status, wherein the authorization status includes approval of authorization or rejection of authorization;

[0046] Step S2014, pre-processing the historical operation data and authorization status to obtain historical characteristic parameters of the target type, wherein the historical characteristic parameters of the target type include: the application type of the requester, the frequency of use of the same type of applications, the permission request history, the mode of user acceptance of permission requests, and the authorization status;

[0047] Step S2016, training the machine learning model using the historical feature parameters of the target type.

[0048] In some embodiments, the historical operation data includes at least one of the following: the requester's application type, application usage frequency, application usage time, permission request type, permission level, and permission request triggering scenario. These data can fully reflect the application's permission request behavior and the user's usage habits, provide rich training materials for machine learning models, and are suitable for application scenarios that require refined permission management.

[0049] In an exemplary embodiment, the application type of the requesting party may include at least one of the following: social, tool, game; the application usage frequency may include at least one of the following: high frequency, medium frequency, low frequency; the application usage time may include at least one of the following: long time, short time; the permission request type may include at least one of the following: permission request based on function usage, permission request based on data access, permission request based on system resources; the permission level may include at least one of the following: basic permission, sensitive permission, unconventional permission; the permission request trigger scenario may include at least one of the following: specific event trigger, periodic trigger. Exemplarily, the specific event may refer to user operation trigger, application behavior trigger, location change trigger, network environment change trigger, etc., which is not limited in this application. Exemplarily, the application usage frequency can be quantified as the number of times the application is used, and the application usage time can be quantified as a specific length of time (such as minutes).

[0050] In some embodiments, the method further includes: at intervals of a preset time period, updating the machine learning model using historical operation data related to permission requests within the preset time period and corresponding authorization status.

[0051] In this embodiment, since the user's authorization habits or the user's authorization decisions may change, regularly updating the machine learning model using the historical operation data related to the permission requests within a preset time period and the corresponding authorization status can adapt to changes in the user's authorization habits, thereby improving the accuracy of the machine learning model recognition results to further improve the user data experience. This application does not limit the interval preset time period. It can be understood by those skilled in the art that updating the machine learning model means using the historical operation data related to the permission requests within a preset time period and the corresponding authorization status to continue training the original machine learning model, or to retrain a new machine learning model.

[0052] In some embodiments, before executing step S204, the method may further include step S203, determining a target processing strategy according to the permission request.

[0053] In some embodiments, step S203 may include the following steps:

[0054] Step S2032, determining the target permission level of the permission request;

[0055] Step S2034, determining a target processing strategy corresponding to the target authority level according to a mapping relationship between the plurality of authority levels and the plurality of processing strategies.

[0056] In this embodiment, this permission level-based policy can realize hierarchical processing of permission management, improve the flexibility of permission management, and is suitable for application scenarios with complex and changeable permission requirements. Among them, the mapping relationship between multiple permission levels and multiple processing strategies can be set as a one-to-one mapping relationship or a many-to-one mapping relationship as needed, and this application does not limit this.

[0057] In some embodiments, the division of permission levels can be based on the application function and the nature of the application itself. This application does not limit the division method of permission levels. Exemplarily, permission levels may include at least one of the following: basic permissions, sensitive permissions, and unconventional permissions. The division of permission levels can also be more detailed, such as divided into 1 to 10 levels of permissions, which this application does not limit.

[0058] In some embodiments, the processing strategy includes at least one of the following: determining the authorization status of the permission request through a machine learning model, wherein the authorization status includes agreeing to the authorization or refusing the authorization; authorizing the permission request; refusing to authorize the permission request; prompting on the display interface whether to agree to authorize the permission request; prompting on the display interface whether to agree to the authorization status determined by the machine learning model.

[0059] In an exemplary embodiment, for permission requests for non-routine permissions, the corresponding target processing strategy is to prompt on the display interface whether to agree to authorize the permission request, that is, the user is required to perform a second confirmation.

[0060] In some embodiments, by distinguishing the importance of different permission requests and implementing hierarchical management of permissions, the flexibility and pertinence of permission management are improved, and the burden of permission management on users is effectively reduced.

[0061] In some embodiments, the method may further include: generating a permission usage report according to a permission request of a preset permission level and a corresponding authorization status; and prompting the permission usage report on a display interface.

[0062] In some embodiments, the permission usage report may include at least one of the following: a permission usage transparency report and an authorization habit assessment report. The permission usage transparency report is used to let users understand how their operation data is collected, stored, and used, so as to improve users' trust in the application and allow users to better control data; the authorization habit assessment report is used to regularly assess the association between users' authorization habits and permission requests at preset permission levels, and exemplarily assess the frequency of users authorizing permission requests (including unconventional permissions) with higher target permission levels.

[0063] In the embodiment of the present application, the permission usage report can help users understand the usage of application permissions, improve the transparency of permission management for users, and is suitable for application scenarios that need to enhance user privacy awareness. For example, the terminal can be set to generate a permission usage transparency report for sensitive permission requests.

[0064] In some embodiments, the terminal can also provide permission management suggestions based on the permission usage report. In an exemplary embodiment, the terminal can combine the permission usage report with preset data protection expertise to provide intelligent authorization suggestions. If there are risks in the user's authorization habits, the terminal can prompt and explain the relevant risks to help the user make a more informed decision. In another exemplary embodiment, the terminal can regularly evaluate the user's authorization habits and provide authorization improvement suggestions. If the user frequently authorizes higher-risk applications, the terminal can prompt on the display interface and provide authorization improvement suggestions. In this way, the terminal can help users become aware of potential security issues and encourage them to take improvement measures corresponding to the improvement suggestions, thereby improving the terminal security performance and reducing security risks during application use.

[0065] In some embodiments, the terminal can also set permissions based on the permission usage report. Exemplarily, during the application installation stage, the terminal analyzes the application's permission requests and the user's past installation habits through the permission usage report, and intelligently recommends a set of default permission settings. Reduce the number of times users need to manually adjust permissions after installation, while ensuring that the application can run with minimal interruption. Alternatively, the terminal can also analyze the user's usage habits and preferences based on the permission usage report and provide personalized permission setting recommendations. Exemplarily, for users who value privacy, stricter permission settings are recommended; for users who pursue convenience, more flexible permission settings are recommended.

[0066] In some embodiments, the method also includes: the terminal can establish a user control center, and the user can view and manage the permission settings of all applications through the user control center. The management methods that the user can operate include but are not limited to revoking authorized permissions with one click, or the user can also adjust the permission settings as needed.

[0067] In some embodiments, when the terminal first installs an application, it can provide a brief educational prompt on the display interface, explaining the permissions required by the application and how the permissions are used. This helps improve the user's understanding of permission requests and reduce the situation of refusing authorization due to misunderstanding.

[0068] In various embodiments of the present application, the authorization habits of application permission requests are automatically identified through machine learning models, which realizes intelligent and personalized permission management, effectively reduces the burden of users in permission management, and improves user experience. At the same time, by regularly updating the machine learning model, it can adapt to changes in user authorization habits and ensure the timeliness and accuracy of permission management strategies. In practical applications, this method can significantly improve the efficiency of permission management, reduce the risk of user misauthorization, and protect user privacy and data security.

[0069] Figure 5 is a flowchart of a rights management method in one embodiment of the present application. Figure 5 As shown, the process includes the following steps:

[0070] Step S501, the terminal collects historical operation data of multiple applications and corresponding authorization status;

[0071] Step S502, training a machine learning model through historical operation data of multiple applications and corresponding authorization situations;

[0072] Step S503: When an application requests permission, the trained machine learning model is automatically called to determine whether the permission request complies with the authorization convention;

[0073] Step S504, the terminal analyzes the user's authorization habits and provides intelligent authorization suggestions;

[0074] Step S505, the terminal adjusts the permission settings according to the user's feedback;

[0075] Step S506: The data security server integrates all desensitized data features and updates the basic standards for authorization recommendations.

[0076] In some embodiments, the process may further include the following steps:

[0077] Step S507: At every preset time period, the machine learning model is updated using the historical operation data related to the permission request within the preset time period and the corresponding authorization status.

[0078] In an exemplary embodiment, the machine learning model may be a Scikit-Learn decision tree model.

[0079] In this embodiment, the machine learning model is used to realize intelligent and automated permission management, reduce the user's permission operations, and improve the user experience. In addition, the permission settings are adjusted according to user feedback, making permission management more flexible and able to adapt to changes in user authorization behavior.

[0080] Figure 6 Flow chart of smart clipboard permission management in one embodiment of the present application. Figure 6As shown, the process may include the following steps:

[0081] Step S601, when the user uses the clipboard function, the terminal learns the user's authorization habits for the clipboard permission through a machine learning model;

[0082] Step S602: When an application requests clipboard permission, the terminal automatically calls a machine learning model to determine whether the permission request complies with the authorization convention;

[0083] Step S603A, if the permission request complies with the authorization custom, the terminal automatically performs the authorization without user intervention;

[0084] Step S603B, if the permission request does not comply with the authorization practice, the terminal prompts the user and provides detailed instructions for using the clipboard permission;

[0085] Step S604: The terminal provides intelligent authorization suggestions based on preset data protection expertise, and regularly prompts the user to set personalized permissions.

[0086] In this embodiment, the machine learning model may be a Scikit-Learn decision tree model, but the present application is not limited thereto.

[0087] Figure 7 is a flow chart of network rights management in one embodiment of the present application, such as Figure 7 As shown, the process includes the following steps:

[0088] Step S701: When a user uses an application, the terminal learns the user's authorization habits for network permissions through a machine learning model;

[0089] Step S702: When a user uses an application and needs to request network access permission, the terminal automatically calls the machine learning model to determine whether the permission request complies with the authorization habit;

[0090] Step S703A, if the permission request complies with the authorization custom, the terminal automatically performs the authorization without user intervention;

[0091] Step S703B, if the permission request does not comply with the authorization practice, the terminal prompts the user and provides detailed instructions for using the network permission;

[0092] Step S704: The terminal provides intelligent authorization suggestions based on preset data protection expertise, and regularly prompts the user to set personalized permissions.

[0093] In this embodiment, the machine learning model may be a Scikit-Learn decision tree model, but the present application is not limited thereto. The data protection expertise may be generated by integrating the permission usage history records of the user group and the opinions of professionals.

[0094] In this embodiment, the authorization habits of application permission requests are automatically identified through a machine learning model, which realizes intelligent and personalized permission management, effectively reduces the burden of user permission management, and improves user experience. The method can also promote users to form good permission management habits by generating intelligent authorization suggestions.

[0095] In the embodiments of the present application, a rights management device is also provided, which is used to implement the above-mentioned embodiments and exemplary implementations, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0096] Figure 8 is a block diagram of a rights management device according to an embodiment of the present application. Figure 8 As shown, the rights management device may include the following structure:

[0097] An acquisition module 82 is used to obtain the permission request of the application;

[0098] An identification module 84 is used to identify whether the permission request complies with the authorization habit through a machine learning model;

[0099] The processing module 86 is used to process the permission request according to the recognition result.

[0100] In this embodiment, the recognition result may include that the permission request complies with the authorization habit, or that the permission request does not comply with the authorization habit. By automatically analyzing the user's authorization mode for application permissions, and thus intelligently determining the processing method of the permission request, the efficiency and accuracy of permission management can be effectively improved, and it is applicable to various mobile devices and operating system environments.

[0101] In some embodiments, the processing module 86 may include:

[0102] A first processing unit, configured to authorize the permission request in response to an identification result that the permission request complies with the authorization custom;

[0103] The second processing unit is used to refuse to authorize the permission request in response to the recognition result that the permission request does not comply with the authorization practice, or to prompt on the display interface whether to agree to authorize the permission request in response to the recognition result that the permission request does not comply with the authorization practice.

[0104] In some embodiments, the identification module 84 may include:

[0105] An acquisition unit, used to acquire operation data of multiple applications related to the permission request;

[0106] A first preprocessing unit, configured to preprocess the operation data to obtain characteristic parameters of the target type, wherein the characteristic parameters of the target type include: the application type of the requesting party, the usage frequency of the same type of applications, the permission request history, and the mode of the user accepting the permission request;

[0107] The input unit is used to input the characteristic parameters of the target type into the machine learning model to obtain the recognition result output by the machine learning model, wherein the recognition result includes whether the permission request complies with the authorization practice.

[0108] In some embodiments, the preprocessing method may include at least one of the following: deduplication, missing value processing, feature engineering, and one-hot encoding.

[0109] In some embodiments, the rights management device may further include:

[0110] A collection unit, used to collect historical operation data related to historical permission requests and corresponding authorization status, wherein the authorization status includes approval or rejection of authorization;

[0111] A second preprocessing unit is used to preprocess the historical operation data and the authorization status to obtain historical characteristic parameters of the target type, wherein the historical characteristic parameters of the target type include: the application type of the requester, the frequency of use of the same type of applications, the permission request history, the mode of user acceptance of permission requests, and the authorization status;

[0112] The training unit is used to train the machine learning model using the historical feature parameters of the target type.

[0113] In some embodiments, the rights management device may further include:

[0114] The update module is used to update the machine learning model at intervals of a preset time period using historical operation data related to permission requests within a preset time period and the corresponding authorization status.

[0115] In some embodiments, the rights management device may further include:

[0116] A permission determination module, used to determine a target permission level for a permission request;

[0117] A policy determination module is used to determine a target processing strategy corresponding to a target permission level based on a mapping relationship between multiple permission levels and multiple processing strategies, wherein the processing strategy includes at least one of the following: determining the authorization status of a permission request through a machine learning model, wherein the authorization status includes agreeing to authorize or rejecting authorization; authorizing the permission request; rejecting authorization of the permission request; prompting on a display interface whether to agree to authorize the permission request; prompting on a display interface whether to agree to the authorization status determined by the machine learning model.

[0118] In some embodiments, the rights management device may further include:

[0119] A generation module generates a permission usage report based on permission requests at preset permission levels and corresponding authorization conditions;

[0120] The prompt module prompts the permission usage report on the display interface.

[0121] In various embodiments of the present application, the authorization habits of application permission requests are automatically identified through a machine learning model, which realizes the intelligence and personalization of permission management, effectively reduces the burden of users in permission management, and improves the user experience. At the same time, by regularly updating the machine learning model, it can adapt to changes in user authorization habits and ensure the timeliness and accuracy of permission management policies. In practical applications, this method can significantly improve the efficiency of permission management, reduce the risk of user misauthorization, and protect user privacy and data security. In addition, the method can also enhance users' awareness of application permission usage by generating permission usage reports, promote users to form good permission management habits, and further enhance data protection awareness. In future smart devices and applications, this method will become an important part of permission management, providing users with a safer and more convenient user experience.

[0122] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0123] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0124] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0125] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0126] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0127] An embodiment of the present application further provides a computer program product, including a computer program, which implements the steps in any of the above method embodiments when executed by a processor.

[0128] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0129] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0130] The above is only an exemplary embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A rights management method, characterized in that: include: Get the app's permission request; Identifying whether the permission request complies with the authorization practice through a machine learning model, wherein the machine learning model is pre-trained using historical operation data of multiple applications; The permission request is processed according to the identification result.

2. The method according to claim 1, characterized in that The processing of the permission request according to the identification result includes: In response to the identification result that the permission request complies with the authorization custom, authorizing the permission request; In response to the identification result that the permission request does not comply with the authorization custom, refusing to authorize the permission request; or In response to the identification result that the permission request does not comply with the authorization custom, a prompt is displayed on the interface as to whether to agree to authorize the permission request.

3. The method according to claim 1, characterized in that The identifying whether the permission request complies with the authorization practice by the machine learning model includes: Acquire operation data of multiple applications related to the permission request; Preprocessing the operation data to obtain characteristic parameters of the target type, wherein the characteristic parameters of the target type include: the application type of the requester, the frequency of use of applications of the same type, the permission request history, and the mode of user acceptance of permission requests; The characteristic parameters of the target type are input into the machine learning model to obtain a recognition result output by the machine learning model, wherein the recognition result includes whether the permission request complies with the authorization habit.

4. The method according to claim 1, characterized in that: Before identifying whether the permission request complies with the authorization habit through the machine learning model, the method further includes: Collect the historical operation data and corresponding authorization status related to the historical permission request, wherein the authorization status includes approval or rejection of authorization; Preprocessing the historical operation data and the authorization status to obtain historical characteristic parameters of the target type, wherein the historical characteristic parameters of the target type include: the application type of the requester, the frequency of use of applications of the same type, the permission request history, the mode of user acceptance of permission requests, and the authorization status; The machine learning model is trained using historical feature parameters of the target type.

5. The method according to claim 3 or 4, characterized in that: The preprocessing method includes at least one of the following: deduplication, missing value processing, feature engineering, and one-hot encoding.

6. The method according to claim 4, characterized in that The historical operation data includes at least one of the following: the application type of the requester, the application usage frequency, the application usage time, the permission request type, the permission level, and the permission request triggering scenario.

7. The method according to claim 1, characterized in that The method further comprises: At every preset time period, the machine learning model is updated using historical operation data related to the permission requests within the preset time period and the corresponding authorization status.

8. The method according to claim 1, characterized in that Before identifying whether the permission request complies with the authorization habit through the machine learning model, the method further includes: Determining a target permission level for the permission request; A target processing strategy corresponding to the target authority level is determined according to a mapping relationship between multiple authority levels and multiple processing strategies.

9. The method according to claim 8, characterized in that The processing strategy includes at least one of the following: Determining the authorization status of the permission request by using the machine learning model, wherein the authorization status includes agreeing to the authorization or rejecting the authorization; Authorizing the permission request; Refuse to authorize the permission request; Prompt whether to authorize the permission request on the display interface; The display interface prompts whether to agree with the authorization situation determined by the machine learning model.

10. The method according to claim 1, characterized in that The method further comprises: Generate permission usage reports based on permission requests at preset permission levels and corresponding authorization situations; The permission usage report is prompted on the display interface.

11. The method according to claim 1, characterized in that: The types of the machine learning models include: machine learning models based on decision trees.

12. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 11 when executed by a processor.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 11 are implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 11 are implemented.

Images