Task package permission allocation method and device, computer equipment and storage medium

Abstract

The invention discloses a task package permission allocation method and device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. According to the method, firstly, a permission adjustment scheme is selected from a strategy library according to a security risk balance point, and task package permission is finely adjusted; meanwhile, the user operation behavior is monitored in real time, safety audit log analysis is triggered by using the abnormal behavior detection index, and the risk of the abnormal behavior of the user is evaluated. Furthermore, in combination with a risk assessment result and user behavior preferences, permission boundary setting is optimized by applying a genetic algorithm, and permission level boundaries are dynamically adjusted, so that the balance between system security and user experience is ensured. The mechanism effectively deals with authority conflicts and potential security threats, and realizes intelligence and dynamics of authority management. Through personalized authority distribution and real-time security monitoring, flexibility and high efficiency of authority management are realized, system security is guaranteed, and user experience is improved.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a task package authority allocation method, device, computer equipment and storage medium. Background Art

[0002] The task package permission management system faces a complex technical challenge when designing it, namely, how to accurately grasp and dynamically respond to user behavior preferences while ensuring system security. The core of this problem lies in the inherent contradiction between the permission allocation mechanism and user preference recommendation. The system needs to continuously analyze user operation behavior, task selection tendency and other data to build a personalized user portrait.

[0003] However, recommending high-privilege task packages based solely on user preferences may lead to excessive openness of permissions and increase system security risks. On the other hand, overly conservative permission control will limit user experience and reduce the usability and efficiency of the system. This requires the system to seek a balance between static permission boundaries and dynamic adjustment mechanisms. Static permission boundaries provide basic protection for system security, while dynamic adjustment mechanisms require real-time trade-offs between multi-dimensional factors such as user behavior, task characteristics, and system load. The key challenge is how to design an adaptive permission adjustment algorithm that can meet user personalized needs to the greatest extent while maintaining system security. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a method, device, computer equipment and storage medium for allocating task package permissions, which mainly solves how to dynamically adjust the permissions of task packages according to user behavior preferences while ensuring system security, so as to achieve the goal of satisfying user operation needs without sacrificing system security.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a task package authority allocation method, which adopts the following technical solution:

[0006] A task package authority allocation method, comprising:

[0007] The user behavior preference score is calculated based on the user's historical operation records and the frequency of task package usage. The collaborative filtering algorithm is used to cluster users based on the behavior preference score, extract the feature vector of the cluster center, and build a user preference model through the feature vector of the cluster center.

[0008] Obtain the task package permission level information, calculate the security risk score for each permission level, and determine the security risk balance point of the task package permission by combining the security risk score and user behavior preference data, where the user behavior preference data is the recommendation result output by the user preference model;

[0009] Based on the dynamic permission adjustment mechanism, a permission adjustment scheme that matches the security risk balance point is selected from the permission conflict resolution strategy library, and the permission level of the task package is dynamically fine-tuned through the permission adjustment scheme;

[0010] Real-time monitoring of user operation behaviors is performed through abnormal behavior detection indicators. If abnormal behavior is detected, the security audit log analysis process is triggered to analyze the security audit log and obtain the security risk assessment results of the user's abnormal behavior;

[0011] According to the security risk assessment results and user behavior preference data, the genetic algorithm is used to optimize the permission boundary setting rules and dynamically adjust the boundaries of the permission levels of the task packages.

[0012] In order to solve the above technical problems, the embodiment of the present application further provides a task package authority allocation device, which adopts the following technical solution:

[0013] A task package authority allocation device, comprising:

[0014] The clustering grouping module is used to calculate the user behavior preference score based on the user's historical operation records and the frequency of use of the task package, cluster the users based on the behavior preference score using the collaborative filtering algorithm, extract the feature vector of the cluster center, and build the user preference model through the feature vector of the cluster center;

[0015] The security scoring module is used to obtain the task package permission level information, calculate the security risk score for each permission level, and determine the security risk balance point of the task package permission by combining the security risk score and user behavior preference data, where the user behavior preference data is the recommendation result output by the user preference model;

[0016] The permission fine-tuning module is used to select a permission adjustment scheme that matches the security risk balance point from the permission conflict resolution strategy library based on the permission dynamic adjustment mechanism, and dynamically fine-tune the permission level of the task package through the permission adjustment scheme;

[0017] The log analysis module is used to monitor user operation behaviors in real time through abnormal behavior detection indicators. If abnormal behavior is detected, the security audit log analysis process is triggered to analyze the security audit log and obtain the security risk assessment results of the user's abnormal behavior;

[0018] The dynamic adjustment module is used to optimize the permission boundary setting rules using genetic algorithms based on security risk assessment results and user behavior preference data, and dynamically adjust the boundaries of the permission levels of task packages.

[0019] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0020] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of any one of the above-mentioned task package authority allocation methods when executing the computer-readable instructions.

[0021] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0022] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the task package authority allocation method as described in any one of the above.

[0023] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0024] The present application discloses a task package authority allocation method, device, computer equipment and storage medium, belonging to the field of artificial intelligence technology. First, based on the user's historical operation records and the frequency of use of the task package, the collaborative filtering algorithm is used to cluster the users and build a user preference model; then, the security risk balance point of the authority allocation is determined by combining the security risk score of the task package authority level with the user preference model; and a dynamic adjustment mechanism is adopted to select an appropriate solution from the authority conflict resolution strategy library to fine-tune the authority level. At the same time, by real-time monitoring of user operation behavior, abnormal behavior is detected and security audit log analysis is triggered to assess security risks; finally, based on the security risk assessment results and user behavior preferences, the genetic algorithm is used to optimize the authority boundary setting to achieve dynamic adjustment of the authority level boundary. The present application realizes accurate authority allocation through user behavior analysis and clustering modeling, and combines security risk assessment and dynamic adjustment mechanism to make authority management more flexible and able to adapt to different security environments and user needs. Real-time abnormal behavior monitoring and security auditing enhance the system's defense capabilities, timely discover and respond to potential threats, and finally, the genetic algorithm is used to optimize the authority boundary setting to ensure that the authority allocation meets security requirements without affecting user operations, thereby improving the overall security and user experience of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0027] Figure 2 A flowchart of an embodiment of a task package authority allocation method according to the present application is shown;

[0028] Figure 3 Shows Figure 2 A flowchart of an embodiment of step S201;

[0029] Figure 4 Shows Figure 2 A flowchart of an embodiment of step S202;

[0030] Figure 5 Shows Figure 2 A flowchart of an embodiment of step S203;

[0031] Figure 6 Shows Figure 2 A flowchart of an embodiment of step S205;

[0032] Figure 7 A schematic diagram showing the structure of an embodiment of a task package authority allocation device according to the present application is shown;

[0033] Figure 8 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0037] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0038] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0039] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0040] Server 105 can be a server that provides various services, such as a background server that provides support for pages displayed on terminal devices 101, 102, and 103. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDNs), and big data and artificial intelligence platforms.

[0041] It should be noted that the task package authority allocation method provided in the embodiment of the present application is generally executed by a server, and accordingly, the task package authority allocation device is generally set in the server.

[0042] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0043] Continue to refer Figure 2, showing a flow chart of an embodiment of the task package authority allocation method according to the present application. The present application embodiment can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0044] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0045] The task package authority allocation method comprises the following steps:

[0046] S201, calculate the user behavior preference score based on the user's historical operation records and the frequency of task package usage, use the collaborative filtering algorithm to cluster the users based on the behavior preference score, extract the feature vector of the cluster center point, and build a user preference model through the feature vector of the cluster center.

[0047] Specifically, by analyzing the user's historical operation records and the frequency of task package usage, the user's behavioral preference score is statistically calculated, and a collaborative filtering algorithm is used to cluster and group users according to their behavioral preference scores. The collaborative filtering algorithm uses the similarities between users to predict the user's preference for a certain task package. The result of the clustering process is to extract the center point of each cluster, and the feature vectors of these center points are used to construct a user preference model.

[0048] By modeling user behavior preferences, users' operating habits and preferences can be effectively identified, which makes permission allocation more personalized and accurate, improving user experience. At the same time, clustering methods reduce computational complexity, making large-scale user behavior analysis feasible and efficient.

[0049] S202, obtaining task package authority level information, calculating a security risk score for each authority level, and determining a security risk balance point of the task package authority by combining the security risk score and user behavior preference data, wherein the user behavior preference data is a recommendation result output by a user preference model.

[0050] Specifically, the permission level information of the task package is obtained. The permission level information of the task package includes a series of information describing the scope of resources accessible to the task package, the depth of operation, and the sensitivity of data, such as access scope, operation permissions, data sensitivity labels, historical security records, etc. The security risk score is calculated for each permission level, and the security risk balance point of the task package permission is determined by combining the security risk score with the recommendation results of the user preference model. The security risk score takes into account the potential threats that may be brought by the permission level. By combining it with the user preference model, the balance point between security and user needs can be found, so as to make reasonable permission allocation.

[0051] By comprehensively considering security risks and user preferences, a balance in permission allocation is achieved, which ensures the security of the system, meets the actual needs of users, and avoids excessive restrictions on user permissions that affect work efficiency.

[0052] S203, based on the permission dynamic adjustment mechanism, select a permission adjustment scheme that matches the security risk balance point from the permission conflict resolution strategy library, and dynamically fine-tune the permission level of the task package through the permission adjustment scheme.

[0053] Specifically, based on the dynamic permission adjustment mechanism, permission adjustment plans that match the security risk balance point are selected from the permission conflict resolution strategy library. According to these plans, the permission level of the task package is dynamically fine-tuned. The permission conflict resolution strategy library contains a variety of solutions, and the optimal strategy can be selected for permission adjustment according to the specific situation.

[0054] The dynamic adjustment mechanism makes permission allocation flexible and adaptive. By adjusting permission levels in real time, it can respond to the ever-changing security environment and user needs, and maintain the security of the system and the optimal user experience.

[0055] S204, real-time monitoring of user operation behavior is performed through abnormal behavior detection indicators. If abnormal behavior is detected, the security audit log analysis process is triggered to analyze the security audit log to obtain a security risk assessment result of the user's abnormal behavior.

[0056] Specifically, user operation behaviors are monitored in real time through abnormal behavior detection indicators. If abnormal behavior is detected, the security audit log analysis process is triggered. By analyzing the security audit log, the security risk assessment results of the user's abnormal behavior are obtained. Abnormal behavior detection uses real-time monitoring technology to quickly discover potential security threats.

[0057] Real-time abnormal behavior detection can promptly discover and respond to security threats, enhance the system's defense capabilities, and through security audit log analysis, accurately assess the risks of user abnormal behavior, provide a reliable basis for decision-making, and further improve the security of the system.

[0058] S205, based on the security risk assessment results and user behavior preference data, the permission boundary setting rules are optimized using a genetic algorithm to dynamically adjust the permission level boundary of the task package.

[0059] Specifically, based on the security risk assessment results and user behavior preference data, genetic algorithms are used to optimize the permission boundary setting rules. Through genetic algorithms, the boundaries of the permission levels of task packages can be dynamically adjusted. Genetic algorithms are a global optimization algorithm that can find the optimal permission level boundary setting scheme by simulating the natural selection process.

[0060] By using genetic algorithms to optimize permission boundary settings, dynamic optimization of permission allocation can be achieved. Permission boundaries can be adjusted according to real-time conditions to ensure that security requirements are met without affecting normal user operations, thereby improving the overall security of the system and user experience.

[0061] In the above embodiment, the present application discloses a task package authority allocation device, which belongs to the field of artificial intelligence technology. First, based on the user's historical operation records and the frequency of task package use, the collaborative filtering algorithm is used to cluster users and build a user preference model; then, the security risk balance point of authority allocation is determined by combining the security risk score of the task package authority level with the user preference model; and a dynamic adjustment mechanism is used to select appropriate solutions from the authority conflict resolution policy library to fine-tune the authority level. At the same time, by real-time monitoring of user operation behavior, abnormal behavior is detected and security audit log analysis is triggered to assess security risks; finally, based on the security risk assessment results and user behavior preferences, a genetic algorithm is used to optimize the authority boundary setting to achieve dynamic adjustment of the authority level boundary. This application achieves flexibility and efficiency of authority management through personalized authority allocation and real-time security monitoring, ensures system security and improves user experience.

[0062] Further, refer to Figure 3 , Figure 3 Shows Figure 2 The flowchart of an embodiment of step S201 in FIG. 1 is to calculate the user behavior preference score according to the user's historical operation record and the task package usage frequency statistics, cluster the users based on the behavior preference score using a collaborative filtering algorithm, extract the feature vector of the cluster center point, and construct a user preference model through the feature vector of the cluster center, including:

[0063] S301, obtaining the user's historical operation records and task package usage frequency data, and obtaining the user behavior preference score vector based on statistical analysis and calculation;

[0064] S302, clustering and grouping users according to the user behavior preference score vector using a K-means clustering algorithm to obtain user cluster centers with different preferences;

[0065] S303, for each user cluster center, extracting a feature vector of the cluster center point as a common preference feature of the clustered user group;

[0066] S304: Using the feature vector of the cluster center point as a parameter of the user preference model to construct the user preference model.

[0067] In this embodiment, by collecting and analyzing the user's historical operation records and the frequency of use of task packages, the user's behavior preferences are quantified into a score vector. Subsequently, the K-means clustering algorithm is used to group users and identify user groups with different behavior preferences and their cluster centers. Next, feature vectors are extracted from each cluster center, and these vectors accurately reflect the preference characteristics of various types of users. Finally, a user preference model is constructed with the cluster center feature vector as a parameter to achieve accurate characterization and prediction of user preferences, providing data support for personalized recommendations, service optimization, etc. When constructing the user preference model, the vector space model VSM is used to represent the user's preference for different task packages based on the feature vector of the cluster center point, forming a user preference feature space. Finally, a user preference model based on the vector space model VSM and with the cluster center feature vector as a parameter is obtained.

[0068] Exemplarily, the frequency of each user's access to different task packages is first obtained from the interaction log between the user and the task package. For example, user A visits task package X 20 times in a month, and visits task package Y 5 times. Using these data, it can be calculated that user A's frequency of use of task package X is high frequency, while that of task package Y is low frequency. Based on these frequency data, a weighted scoring method is used to calculate the user's behavioral preference score for the task package, such as giving a higher weight to the task package with high frequency access. Next, a collaborative filtering algorithm is used, specifically a user-based collaborative filtering technology, and user clustering is performed by calculating the similarity between users. For example, if user A and user B have similar frequency of use and behavioral preference scores for multiple similar task packages, it is considered that the two users have a high similarity. Through this method, users are divided into multiple groups, and users in each group show similar task package usage behaviors. Then, the cluster center feature vector of each user group is determined. These feature vectors are the average values ​​of the behavioral preference scores of all users in the group, which can represent the overall preference characteristics of the users in the group. For example, if the cluster center feature vector of a group has a higher score on task package X and task package Z, it means that the users in the group generally prefer these two task packages. Using the feature vector of the cluster center, a preference model for each user is constructed. This model is based on the cluster center feature vector of the group to which the user belongs, and is adjusted in combination with the user's personal preference score to more accurately reflect the individual's preference. Finally, based on the constructed user preference model, task packages that may be of interest to the user are recommended.

[0069] Through the above steps, by analyzing the user's historical operation records and the frequency of task package use, the system calculates the user behavior preference score vector, and uses the K-means clustering algorithm to group users and extract the feature vector of each cluster center. These feature vectors are used as parameters of the user preference model to build a user preference model, which can provide personalized permission allocation by accurately identifying and predicting user operation habits, achieve more efficient user behavior management and permission control, and improve the flexibility of the system and user experience.

[0070] Furthermore, the user's historical operation records and task package usage frequency data are obtained, and the user behavior preference score vector is obtained through statistical analysis and calculation, including:

[0071] According to the historical operation records of users, the data statistical analysis method is used to obtain the frequency data of each user's use of different task packages;

[0072] By using the frequency data, a user-task package preference matrix is ​​constructed. Each element in the user-task package preference matrix represents a user's preference score for a task package.

[0073] Based on the user-task package preference matrix, a collaborative filtering algorithm is used to predict the user's predicted preference score for unused task packages.

[0074] The content features of the task package are introduced, and the content recommendation algorithm is used to calculate the user's content preference score for the task package based on the content features of the task package;

[0075] The predicted preference score and the content preference score are weighted and fused to obtain the user behavior preference score vector.

[0076] In this embodiment, according to the historical operation records of the user, a data statistical analysis method is used to obtain the frequency data of each user's use of different task packages. Through the frequency data, a user-task package preference matrix is ​​constructed, and each element in the matrix represents a preference score of a certain user for a certain task package. After obtaining the user-task package preference matrix, a collaborative filtering algorithm is used to predict the user's preference score for unused task packages based on the similarity between users. The collaborative filtering algorithm analyzes the similarity between users and finds the preference trend of similar users for task packages, thereby predicting the target user's preference for the same task package.

[0077] On the basis of collaborative filtering algorithm, the content features of task packages are introduced, and a content-based recommendation algorithm is adopted. According to the content features of task packages, the user's preference score for task packages is calculated. The content-based recommendation algorithm analyzes the content features of task packages and finds the user's preference trend for task packages with similar content features, thereby predicting the user's preference for new task packages. The preference scores obtained by the collaborative filtering algorithm and the content-based recommendation algorithm are weighted and fused to obtain the final user-task package preference score matrix. According to the final user-task package preference score matrix, the task package preference score of each user is sorted to obtain the task package preference ranking list of each user. The higher the preference score, the stronger the user's preference for the task package and the higher the ranking. If the user's preference score for a task package exceeds the preset threshold, it is judged that the user has a strong behavioral preference for the task package. If the preference score is lower than the threshold, it is judged that the user has a weak preference for the task package.

[0078] Through the above steps, by obtaining the user's historical operation records and task package usage frequency data, the system uses statistical analysis methods to construct a user-task package preference matrix. Each element in the matrix represents the user's preference score for a specific task package. By accurately quantifying the user's preference for different task packages, it provides a data-driven foundation, lays the foundation for subsequent user clustering and authority allocation, and improves the system's personalized service capabilities and user experience.

[0079] Further, refer to Figure 4 , Figure 4 Shows Figure 2The flowchart of an embodiment of step S202 in the embodiment of the present invention is to obtain task package authority level information, calculate the security risk score for each authority level, and determine the security risk balance point of the task package authority by combining the security risk score and user behavior preference data, including:

[0080] S401, obtaining the authority level information of the task package, and using a preset authority risk assessment model to calculate a security risk score for each authority level;

[0081] S402, generating personalized permission recommendation results through collaborative filtering algorithm according to the user preference model to obtain user behavior preference data;

[0082] S403, weighted fusion of security risk score and user behavior preference data, and a multi-objective optimization algorithm is used. With security risk and user preference satisfaction as optimization targets, the permission configuration space is searched through a genetic algorithm to find the security risk balance point of the permission task package.

[0083] In this embodiment, the authority level information of the task package and the authority boundary setting rules preset by the system are obtained, and the authority risk assessment algorithm is used to calculate the security risk score for each authority level. The algorithm constructs a permission risk assessment matrix, combines multiple dimensions such as the frequency of permission use, the scope of permission impact, and the sensitivity of permission, and uses a fuzzy comprehensive evaluation method to obtain the security risk score of each permission level. According to the user preference model, a personalized permission recommendation result is generated through a collaborative filtering algorithm. The algorithm constructs a user-permission preference matrix based on the user's historical permission setting behavior and the permission preferences of similar users, and uses the alternating least squares method to perform matrix decomposition to obtain the user's preference for different permissions. The security risk score and the recommendation results of the user preference model are weighted and fused, and a multi-objective optimization algorithm is used. With security risk and user preference satisfaction as the optimization goals, the permission configuration space is searched through a genetic algorithm to find the security risk balance point of the permission task package.

[0084] The fuzzy comprehensive evaluation method is used to calculate the security risk score of each permission level. It performs well in dealing with complex, uncertain and ambiguous problems, and is particularly suitable for the field of risk assessment. The fuzzy comprehensive evaluation method constructs an evaluation matrix and combines multiple dimensions (such as permission usage frequency, permission impact scope, permission sensitivity, etc.) to comprehensively evaluate the security risks of each permission level. The multi-objective optimization algorithm is used to find a balance between security risk and user preference satisfaction. It can consider multiple goals at the same time and find the optimal solution or a set of solutions (Pareto optimal solution) that meet all goals. The genetic algorithm is a heuristic search algorithm that simulates natural selection and genetic mechanisms. It is used to solve optimization and search problems. It is used to search the permission configuration space and find the balance between security risk and user preference satisfaction.

[0085] Through the above steps, by obtaining the authority level information of the task package, the fuzzy comprehensive evaluation method is used to calculate the security risk score, and the personalized authority recommendation results are generated in combination with the user preference model. By weighted fusion of the security risk score and the user preference recommendation results, the multi-objective optimization algorithm and genetic algorithm are used to find the security risk balance point of the authority configuration, which effectively balances the system security and user needs, improves the accuracy and flexibility of authority allocation, ensures the system security, and improves user satisfaction.

[0086] Furthermore, after obtaining the task package permission level information, calculating the security risk score for each permission level, and combining the security risk score with the recommendation result of the user preference model to determine the security risk balance point of the task package permission, it also includes:

[0087] According to the permission configuration scheme corresponding to the security risk balance point, a rule-based reasoning engine is used to convert the permission configuration scheme into system permission setting instructions;

[0088] Based on the system permission setting instructions, the permission management interface is used to realize the adaptive allocation and dynamic adjustment of the permissions of the task package;

[0089] During the adaptive allocation of permissions, the permission usage of task packages is continuously monitored, and an abnormal behavior detection algorithm is used to identify abnormal permission usage in real time;

[0090] When abnormal permission usage is identified, an abnormal warning is triggered, and based on the permission recovery mechanism, the task package permissions are dynamically adjusted within the preset permission security boundary to obtain feedback data on the permission usage of the task package;

[0091] An incremental learning algorithm is used to continuously optimize and update the permission risk assessment model and user preference model based on the feedback data on task package permission usage.

[0092] In this embodiment, according to the authority configuration scheme of the security risk balance point, a rule-based reasoning engine is used to convert the authority configuration into specific system authority setting instructions, and the authority adaptive allocation and dynamic adjustment of the task package are realized through the authority management interface. In the process of adaptive authority allocation, the authority usage of the task package is continuously monitored, and an abnormal behavior detection algorithm is used to identify abnormal authority usage. Early warnings are triggered in time for suspicious abnormalities, and based on an automated authority recovery mechanism, it is ensured that the authority of the task package is dynamically adjusted within the security boundary, and feedback data on the authority usage of the task package is output. Finally, an incremental learning algorithm is used to continuously optimize and update the authority risk assessment model and the user preference model according to the feedback data on the authority usage of the task package, and the accuracy and security of the adaptive authority allocation are continuously improved through the feedback control mechanism.

[0093] A rule-based reasoning engine is a computer system that uses a predefined set of rules to make decisions and inferences, and is used to convert permission configuration schemes under security risk balance points into specific system permission setting instructions. These rules are usually based on business logic, security policies, user behavior patterns, etc., and define how to convert high-level permission configuration requirements (such as permission levels, permission ranges, etc.) into low-level permission settings (such as file access permissions, database query permissions, etc.) that the system can understand and execute.

[0094] The permission recovery mechanism is a security measure used to automatically or manually revoke or restrict the permissions of users or task packages when abnormal behavior or security policy violations are detected. Incremental learning is a machine learning paradigm that allows a model to gradually update its knowledge and capabilities as it receives new data without retraining the entire model. The parameters of the model are adjusted through optimization algorithms (such as gradient descent, genetic algorithms, etc.) to improve the model's performance in prediction and recommendation. New rules can be optimized or added based on new data and feedback to improve the accuracy and efficiency of reasoning.

[0095] Furthermore, after continuously optimizing and updating the permission risk assessment model and user preference model based on the feedback data of the permission usage of the task package using the incremental learning algorithm, it also includes:

[0096] Through the access permission management database, the permission level data corresponding to each task package is obtained to obtain the permission configuration information;

[0097] Use a security risk assessment algorithm to determine the risk score of each level based on the permission level and preset security boundaries;

[0098] Based on user historical behavior data, build a model that reflects each user's preferences and determine the most suitable permission configuration plan.

[0099] In this embodiment, the permission level data corresponding to each task package is obtained through the access rights management database. According to the permission level data, the decision tree algorithm is used to classify the permission configuration information to obtain a detailed permission configuration classification result. The permission level and boundary information are obtained, and then the importance of each indicator is determined by constructing a judgment matrix. The eigenvalue method is used to calculate the weight of each indicator to obtain a weight vector. According to the weight vector, the weighted average method is used to calculate the security risk score of each level. According to the user's historical behavior data, a collaborative filtering algorithm is used to build a user preference model. The collaborative filtering algorithm analyzes the user's historical behavior and finds the similarity between users, thereby predicting the user's preference for unknown projects. According to the predicted user preference score, a greedy algorithm is used to generate the optimal permission configuration plan.

[0100] Through the above steps, based on the incremental learning algorithm, according to the feedback data of task package permission usage, the permission risk assessment model and user preference model are continuously optimized and updated, the access permission management database obtains permission configuration information, and uses the security risk assessment algorithm to determine the risk score. The user preference model is built based on the user's historical behavior data to determine the most suitable permission configuration plan, realizing dynamic optimization of permission management, improving security and adaptability, and ensuring that the system maintains efficient risk control while meeting user needs.

[0101] Further, refer to Figure 5 , Figure 5 Shows Figure 2 The flowchart of an embodiment of step S203 in FIG. 1 is a flowchart of an embodiment of step S203 in FIG. 1 , based on the permission dynamic adjustment mechanism, selecting a permission adjustment scheme that is in line with the security risk balance point from the permission conflict resolution strategy library, and dynamically fine-tuning the permission level of the task package through the permission adjustment scheme, including:

[0102] S501, using a fuzzy comprehensive evaluation method to select a permission adjustment plan that preliminarily matches the security risk balance point from the permission conflict resolution strategy library;

[0103] S502, quantifying the permission level and the security risk score into fuzzy values ​​through a preset fuzzy membership function;

[0104] S503, calculating the comprehensive evaluation value of the initially matched authority adjustment scheme by using fuzzy matrix synthesis operation;

[0105] S504, determining the optimal permission adjustment scheme based on the degree of proximity between the comprehensive evaluation value and the security risk balance point, and obtaining a permission adjustment scheme that matches the security risk balance point;

[0106] S505, modifying the authority level of the task package through the specific parameter values ​​in the optimal authority adjustment solution.

[0107] In this embodiment, a fuzzy comprehensive evaluation method is used to screen out permission adjustment plans that preliminarily match the current system security risk status from a pre-built permission conflict resolution policy library. By utilizing the ability of the fuzzy comprehensive evaluation method to handle ambiguity and uncertainty, the complex permission adjustment problem is transformed into a quantifiable evaluation process. By comparing the degree of fit between different policy plans and the current security risks, the potential adjustment direction is preliminarily locked in.

[0108] A preset fuzzy membership function is introduced as a processing function for quantifying permission levels and security risk scores. The fuzzy membership function converts the originally clearly defined values ​​into continuous values ​​with a certain degree of fuzziness by defining the degree of membership of elements to fuzzy sets. The conversion process not only retains the rich information of the original data, but also enables data of different dimensions to be compared and integrated under the same framework.

[0109] The fuzzy matrix synthesis operation is used to conduct a comprehensive evaluation of the initially selected permission adjustment schemes. The fuzzy matrix synthesis operation constructs a fuzzy relationship matrix containing multiple evaluation factors, and combines the weight distribution of each factor to calculate the comprehensive evaluation value of each scheme. It fully considers multiple aspects involved in permission adjustment, such as the coverage, sensitivity, and frequency of use of permissions, ensuring the comprehensiveness and objectivity of the evaluation results.

[0110] Based on the degree of proximity between the comprehensive evaluation value and the security risk balance point, the optimal permission adjustment plan is determined through comparison and sorting, which can effectively reduce security risks, minimize permission conflicts and redundancy, and improve the overall operation efficiency of the system.

[0111] According to the specific parameter values ​​in the optimal permission adjustment plan, the permission level of the task package is precisely modified, realizing the instant update and dynamic adjustment of the permission configuration.

[0112] In the above embodiments, by introducing advanced methods such as fuzzy comprehensive evaluation method, fuzzy membership function and fuzzy matrix synthesis operation, accurate matching of the authority adjustment plan and the security risk balance point is achieved, which not only improves the scientificity and accuracy of authority management, but also provides strong support for the continuous and safe operation of the system.

[0113] Further, refer to Figure 6 , Figure 6 Shows Figure 2 The flowchart of an embodiment of step S205 in the embodiment of the present invention is to optimize the permission boundary setting rules by using a genetic algorithm according to the security risk assessment results and the user behavior preference data, and dynamically adjust the permission level boundary of the task package, including:

[0114] S601, constructing a permission boundary optimization model based on the security risk assessment results and the behavior preference data, wherein the permission boundary optimization model uses the permission boundary threshold as an optimization variable and the security risk and permission level as optimization targets;

[0115] S602, iteratively optimizing the permission boundary threshold of the permission boundary optimization model using a genetic algorithm until the optimization target is met or the upper limit of the number of iterations is reached;

[0116] S603, dynamically adjusting the authority level boundary of the task package based on the optimal authority boundary threshold value obtained by solving the genetic algorithm.

[0117] In this embodiment, the user behavior data is analyzed by the security risk assessment model to obtain the user's security risk assessment result, which includes information such as the user's risk level, risk type, and risk occurrence probability. At the same time, the user's behavior preference data is obtained, which includes information such as the user's commonly used applications, visited websites, and used devices. According to the security risk assessment results and user behavior preference data obtained in the previous step, an optimization model for the permission boundary setting rules is constructed. The model uses the permission boundary threshold as the optimization variable, and the security risk and permission level as the optimization target to form a multi-objective optimization problem. The optimization problem is solved by a genetic algorithm. Through genetic operations such as selection, crossover, and mutation, the permission boundary threshold is continuously iterated and optimized until the optimization target is met or the upper limit of the number of iterations is reached. According to the optimal permission boundary threshold obtained by the genetic algorithm, the permission level boundary of the task package is dynamically adjusted. If the user's security risk level is high, the permission level boundary threshold of the task package is reduced, and the operation restrictions are increased; if the user's security risk level is low, the permission level boundary threshold of the task package is increased, and the operation restrictions are reduced.

[0118] Specifically, when designing a system for dynamically adjusting the task package permission stage, first analyze the existing security risk assessment reports to determine the risk level, risk type, and probability of risk occurrence of various tasks. For example, a certain type of data processing task may be rated as a high risk level, the type is data leakage, and the probability of occurrence is 3. Based on this information, an initial permission threshold can be calculated and set as the product of the risk probability and the risk level. For the above task, the initial permission threshold may be set to 9. Next, by analyzing user behavior preference data, such as using log analysis tools to monitor the user's operation frequency and main activity time period in the past month, it may be found that users usually perform a large number of data input operations in the morning on weekdays. These behavioral data will help adjust the operation restrictions of the task package to better meet the user's actual usage habits, such as adjusting the accessible time of the data input task package to the user's most active time period. Thereafter, combining the initial permission threshold and the adjusted operation restrictions, a fitness function is designed, which mainly evaluates the security and usability of the candidate permission boundary settings. The fitness function may take the following form: fitness = (1-risk probability) × user satisfaction index, where the user satisfaction index is calculated based on the matching degree between user behavior preferences and operation restrictions. After that, set the parameters of the genetic algorithm: the population size is set to 100, the crossover probability is 8, and the mutation probability is 1. These parameters will guide the operation of the genetic algorithm and find the best permission setting through iterative optimization. During the operation of the algorithm, each round of iteration will produce candidate solutions with higher fitness, which will be used for the next round of iteration. Finally, the permission level and operation restrictions of the task package will be dynamically adjusted according to the output of the genetic algorithm to ensure both the security of the system and the convenience of user operation. For the stability and responsiveness of the system, the dynamic adjustment frequency and adjustment range of the permission boundary will be limited, such as once a quarter, and each adjustment shall not exceed 10% of the previous setting.

[0119] Through the above steps, by dynamically adjusting the permission boundaries and operation restrictions of the task package, while ensuring system security, the user's behavioral preferences are met to the greatest extent and the user experience is improved.

[0120] In this embodiment, the task package authority allocation method is executed on the electronic device (eg Figure 1 The server shown in the figure) can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0121] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned user historical operation records, the above-mentioned user historical operation records can also be stored in a blockchain node.

[0122] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0123] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0124] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0125] Further references Figure 7 , as a response to the above Figure 2 The present application provides an embodiment of a task package authority allocation device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0126] like Figure 7 As shown, the task package authority allocation device 700 described in this embodiment includes:

[0127] Clustering and grouping module 701, used to calculate the user behavior preference score according to the user's historical operation records and the frequency of use of the task package, cluster the users based on the behavior preference score using a collaborative filtering algorithm, extract the feature vector of the cluster center point, and construct a user preference model through the feature vector of the cluster center;

[0128] The security scoring module 702 is used to obtain the task package authority level information, calculate the security risk score for each authority level, and determine the security risk balance point of the task package authority by combining the security risk score and the user behavior preference data, wherein the user behavior preference data is the recommendation result output by the user preference model;

[0129] The permission fine-tuning module 703 is used to select a permission adjustment scheme that matches the security risk balance point from the permission conflict resolution strategy library based on the permission dynamic adjustment mechanism, and dynamically fine-tune the permission level of the task package through the permission adjustment scheme;

[0130] The log analysis module 704 is used to monitor the user operation behavior in real time through abnormal behavior detection indicators. If abnormal behavior is detected, the security audit log analysis process is triggered to analyze the security audit log to obtain the security risk assessment result of the user's abnormal behavior;

[0131] The dynamic adjustment module 705 is used to optimize the permission boundary setting rules using a genetic algorithm according to the security risk assessment results and user behavior preference data, and dynamically adjust the boundary threshold and operation restrictions of the permission level of the task package.

[0132] In the above embodiment, the present application discloses a task package authority allocation device, which belongs to the field of artificial intelligence technology. First, based on the user's historical operation records and the frequency of task package use, the collaborative filtering algorithm is used to cluster users and build a user preference model; then, the security risk balance point of authority allocation is determined by combining the security risk score of the task package authority level with the user preference model; and a dynamic adjustment mechanism is used to select appropriate solutions from the authority conflict resolution policy library to fine-tune the authority level. At the same time, by real-time monitoring of user operation behavior, abnormal behavior is detected and security audit log analysis is triggered to assess security risks; finally, based on the security risk assessment results and user behavior preferences, a genetic algorithm is used to optimize the authority boundary setting to achieve dynamic adjustment of the authority level boundary. This application achieves flexibility and efficiency of authority management through personalized authority allocation and real-time security monitoring, ensures system security and improves user experience.

[0133] To solve the above technical problems, the present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0134] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 8 with components 81-83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmab l eGate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0135] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0136] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk equipped on the computer device 8, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions of the task package authority allocation method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0137] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run computer-readable instructions or process data stored in the memory 81, such as computer-readable instructions for running the task package authority allocation method.

[0138] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0139] In the above embodiment, the present application discloses a computer device, which belongs to the field of artificial intelligence technology. First, based on the user's historical operation records and the frequency of use of task packages, the collaborative filtering algorithm is used to cluster users and build a user preference model; then, the security risk balance point of the permission allocation is determined by combining the security risk score of the task package permission level with the user preference model; and a dynamic adjustment mechanism is used to select appropriate solutions from the permission conflict resolution policy library to fine-tune the permission level. At the same time, by real-time monitoring of user operation behavior, abnormal behavior is detected and security audit log analysis is triggered to assess security risks; finally, based on the security risk assessment results and user behavior preferences, a genetic algorithm is used to optimize the permission boundary setting to achieve dynamic adjustment of the permission level boundary. This application achieves flexibility and efficiency of permission management through personalized permission allocation and real-time security monitoring, ensures system security and improves user experience.

[0140] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the task package authority allocation method as described above.

[0141] In the above embodiments, the present application discloses a computer-readable storage medium, which belongs to the field of artificial intelligence technology. First, based on the user's historical operation records and the frequency of use of task packages, the collaborative filtering algorithm is used to cluster users and build a user preference model; then, the security risk balance point of the permission allocation is determined by combining the security risk score of the task package permission level with the user preference model; and a dynamic adjustment mechanism is used to select appropriate solutions from the permission conflict resolution policy library to fine-tune the permission level. At the same time, by real-time monitoring of user operation behavior, abnormal behavior is detected and security audit log analysis is triggered to assess security risks; finally, based on the security risk assessment results and user behavior preferences, a genetic algorithm is used to optimize the permission boundary setting to achieve dynamic adjustment of the permission level boundary. This application achieves flexibility and efficiency of permission management through personalized permission allocation and real-time security monitoring, ensures system security and improves user experience.

[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0143] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0144] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A task package authority allocation method, characterized in that: include: Calculate the user behavior preference score based on the user's historical operation records and the frequency of use of the task package, use the collaborative filtering algorithm to cluster the users based on the behavior preference score, extract the feature vector of the cluster center, and build a user preference model through the feature vector of the cluster center; Obtaining task package authority level information, calculating a security risk score for each authority level, and determining a security risk balance point of the task package authority by combining the security risk score and user behavior preference data, wherein the user behavior preference data is a recommendation result output by the user preference model; Based on the dynamic permission adjustment mechanism, a permission adjustment scheme matching the security risk balance point is selected from the permission conflict resolution strategy library, and the permission level of the task package is dynamically fine-tuned through the permission adjustment scheme; Real-time monitoring of user operation behaviors is performed through abnormal behavior detection indicators. If abnormal behavior is detected, the security audit log analysis process is triggered to analyze the security audit log to obtain the security risk assessment results of the user's abnormal behavior; According to the security risk assessment results and the user behavior preference data, a genetic algorithm is used to optimize the authority boundary setting rules and dynamically adjust the boundaries of the authority levels of the task packages.

2. The task package authority allocation method according to claim 1, characterized in that: The user behavior preference score is calculated based on the user's historical operation records and the frequency of use of the task package, the collaborative filtering algorithm is used to cluster the users based on the behavior preference score, the feature vector of the cluster center is extracted, and the user preference model is constructed through the feature vector of the cluster center, including: Obtain the user's historical operation records and task package usage frequency data, and calculate the user behavior preference score vector based on statistical analysis; According to the user behavior preference score vector, the K-means clustering algorithm is used to cluster the users and obtain user cluster centers with different preferences; For each user cluster center, extract the feature vector of the cluster center point; The characteristic vector of the cluster center point is used as a parameter of the user preference model to construct the user preference model.

3. The task package authority allocation method as claimed in claim 2, characterized in that: The method of obtaining the user's historical operation records and task package usage frequency data and obtaining the user behavior preference score vector through statistical analysis and calculation includes: According to the historical operation records of users, the data statistical analysis method is used to obtain the frequency data of each user's use of different task packages; Constructing a user-task package preference matrix through the usage frequency data, wherein each element in the user-task package preference matrix represents a user's preference score for a task package; Based on the user-task package preference matrix, a collaborative filtering algorithm is used to predict the user's predicted preference score for unused task packages. The content features of the task package are introduced, and the content recommendation algorithm is used to calculate the user's content preference score for the task package based on the content features of the task package; The predicted preference score and the content preference score are weightedly fused to obtain the user behavior preference score vector.

4. The task package authority allocation method according to claim 1, characterized in that: The obtaining of task package authority level information, calculating a security risk score for each authority level, and combining the security risk score with the user behavior preference data to determine a security risk balance point of the task package authority includes: Obtaining the authority level information of the task package, and using a preset authority risk assessment model to calculate the security risk score for each authority level; According to the user preference model, a personalized permission recommendation result is generated through a collaborative filtering algorithm to obtain the user behavior preference data; The security risk score and the user behavior preference data are weighted and fused, and a multi-objective optimization algorithm is adopted. With security risk and user preference satisfaction as optimization targets, the permission configuration space is searched through a genetic algorithm to find the security risk balance point of the permission task package.

5. The task package authority allocation method as claimed in claim 4, characterized in that: After obtaining the task package authority level information, calculating the security risk score for each authority level, and determining the security risk balance point of the task package authority by combining the security risk score and the user behavior preference data, the method further includes: According to the permission configuration scheme corresponding to the security risk balance point, a rule-based reasoning engine is used to convert the permission configuration scheme into a system permission setting instruction; Based on the system permission setting instruction, adaptive allocation and dynamic adjustment of permissions of the task package are realized through the permission management interface; During the adaptive allocation of permissions, the permission usage of task packages is continuously monitored, and an abnormal behavior detection algorithm is used to identify abnormal permission usage in real time; When abnormal permission usage is identified, an abnormal warning is triggered, and based on the permission recovery mechanism, the task package permissions are dynamically adjusted within the preset permission security boundary to obtain feedback data on the permission usage of the task package; An incremental learning algorithm is used to continuously optimize and update the permission risk assessment model and the user preference model according to the permission usage feedback data of the task package.

6. The task package authority allocation method according to claim 1, characterized in that: The permission-based dynamic adjustment mechanism selects a permission adjustment scheme that matches the security risk balance point from the permission conflict resolution strategy library, and dynamically fine-tunes the permission level of the task package through the permission adjustment scheme, including: Selecting a permission adjustment scheme that preliminarily matches the security risk balance point from the permission conflict resolution strategy library by using a fuzzy comprehensive evaluation method; quantifying the authority level and the security risk score into fuzzy values ​​through a preset fuzzy membership function; The comprehensive evaluation value of the initially matched authority adjustment scheme is calculated by using the fuzzy matrix synthesis operation; Determine the optimal permission adjustment scheme based on the degree of proximity between the comprehensive evaluation value and the security risk balance point, and obtain the permission adjustment scheme that matches the security risk balance point; The authority level of the task package is modified by using the specific parameter values ​​in the optimal authority adjustment scheme.

7. The task package authority allocation method according to claim 1, characterized in that: The method of optimizing the permission boundary setting rules by using a genetic algorithm according to the security risk assessment results and the user behavior preference data, and dynamically adjusting the permission level boundaries of the task package includes: According to the security risk assessment results and the behavior preference data, a permission boundary optimization model is constructed, wherein the permission boundary optimization model uses the permission boundary threshold as an optimization variable and the security risk and permission level as optimization targets; Iteratively optimizing the permission boundary threshold of the permission boundary optimization model using a genetic algorithm until the optimization goal is met or the upper limit of the number of iterations is reached; An optimal authority boundary threshold is obtained by solving the genetic algorithm, and the authority level boundary of the task package is dynamically adjusted based on the optimal authority boundary threshold.

8. A task package authority allocation device, characterized in that: include: A clustering grouping module is used to calculate the user behavior preference score based on the user's historical operation records and the frequency of use of the task package, cluster the users based on the behavior preference score using a collaborative filtering algorithm, extract the feature vector of the cluster center point, and construct a user preference model through the feature vector of the cluster center point; A security scoring module is used to obtain task package authority level information, calculate a security risk score for each authority level, and determine a security risk balance point of the task package authority by combining the security risk score and user behavior preference data, wherein the user behavior preference data is a recommendation result output by the user preference model; A permission fine-tuning module is used to select a permission adjustment scheme that matches the security risk balance point from the permission conflict resolution strategy library based on the permission dynamic adjustment mechanism, and dynamically fine-tune the permission level of the task package through the permission adjustment scheme; The log analysis module is used to monitor user operation behaviors in real time through abnormal behavior detection indicators. If abnormal behavior is detected, the security audit log analysis process is triggered to analyze the security audit log and obtain the security risk assessment results of the user's abnormal behavior; The dynamic adjustment module is used to optimize the authority boundary setting rules using a genetic algorithm according to the security risk assessment results and the user behavior preference data, and dynamically adjust the boundaries of the authority levels of the task packages.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the task package authority allocation method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the task package authority allocation method according to any one of claims 1 to 7 are implemented.

Images