Intelligent permission recommendation method and device based on AI analysis, equipment and medium

Abstract

The invention relates to the technical field of permission recommendation, and discloses an intelligent permission recommendation method and device based on AI analysis, equipment and a medium, and the method comprises the steps: obtaining user behavior data and historical permission data; identifying a user behavior pattern according to the user behavior data based on AI analysis; generating a target recommendation scheme according to the user behavior mode and the historical permission data; and obtaining feedback information of the user on the target recommendation scheme, and dynamically adjusting the target recommendation scheme based on the feedback information by using a reinforcement learning algorithm. The user behavior and historical data can be deeply analyzed, the target recommendation scheme is dynamically adjusted through the feedback information of the user, and the accuracy and effectiveness of the recommendation scheme are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of permission recommendation, and in particular to an intelligent permission recommendation method, device, equipment and medium based on AI analysis. Background Art

[0002] In traditional permission management systems, the allocation and management of permissions are usually done manually by administrators. This method is not only time-consuming and labor-intensive, but also prone to errors. As the scale and complexity of the system increase, permission management becomes increasingly difficult. At the same time, traditional methods are difficult to adapt to rapidly changing business needs and lack flexibility and intelligence.

[0003] Some existing solutions attempt to introduce automation and intelligence, but most of them rely on static rules and predefined strategies, making it difficult to make dynamic adjustments based on real-time feedback and business changes, and thus respond to user needs in real time, resulting in inaccurate and ineffective recommendation results. Summary of the invention

[0004] In view of this, the present invention provides an intelligent permission recommendation method, device, equipment and medium based on AI analysis to solve or partially solve the technical problem that the existing recommendation method cannot dynamically adjust the recommendation scheme, resulting in inaccurate recommendation results.

[0005] In a first aspect, the present invention provides an intelligent permission recommendation method based on AI analysis, comprising: obtaining user behavior data and historical permission data; based on AI analysis, identifying user behavior patterns according to the user behavior data; generating a target recommendation scheme according to the user behavior patterns and historical permission data; obtaining user feedback information on the target recommendation scheme, and using a reinforcement learning algorithm to dynamically adjust the target recommendation scheme based on the feedback information.

[0006] The present invention provides an intelligent permission recommendation method based on AI analysis, which obtains user behavior data and historical permission data, identifies user behavior patterns based on the user behavior data based on AI analysis, generates a target recommendation plan based on the user behavior pattern and historical permission data, obtains user feedback on the target recommendation plan, and uses a reinforcement learning algorithm to dynamically adjust the target recommendation plan based on the feedback information. It can conduct in-depth analysis of user behavior and historical data, and dynamically adjust the target recommendation plan based on user feedback information, realize real-time monitoring and strategy adjustment, ensure the flexibility of the recommendation plan and that the recommendation plan can be continuously optimized, form a closed-loop feedback mechanism, and improve the accuracy and effectiveness of the recommendation plan.

[0007] Optionally, based on AI analysis, identifying user behavior patterns according to the user behavior data, including: based on AI analysis, extracting user behavior features according to the user behavior data; clustering the user behavior features using a clustering algorithm to identify user behavior patterns.

[0008] In this way, by extracting user behavior features and using clustering algorithms, user behavior patterns can be identified more accurately.

[0009] Optionally, a target recommendation scheme is generated according to the user behavior pattern and historical authority data, including: based on the user behavior pattern, using a collaborative filtering algorithm or a content recommendation algorithm to generate several initial recommendation schemes; optimizing the initial recommendation schemes to obtain a target recommendation scheme.

[0010] In this way, the collaborative filtering algorithm and the content recommendation algorithm are combined to generate the initial recommendation scheme, which can improve the diversity and coverage of the recommendation. Through the optimization process, the recommendation scheme that better meets the user's needs can be screened out.

[0011] Optionally, the initial recommendation scheme is optimized to obtain a target recommendation scheme, including: using several of the initial recommendation schemes as the initial population of the genetic algorithm; using a fitness function to evaluate the fitness of each of the initial recommendation schemes; selecting the initial recommendation schemes with a fitness higher than a preset value to perform crossover and mutation to generate new recommendation schemes and repeat iterations, and outputting the target recommendation scheme after the iteration is terminated.

[0012] In this method, the initial recommendation scheme is iteratively optimized using a genetic algorithm, which can simulate the natural selection process. Through fitness function evaluation, it is ensured that only high-quality recommendation schemes are retained and further optimized to find better recommendation schemes.

[0013] Optionally, feedback information from users on the target recommendation scheme is obtained, and a reinforcement learning algorithm is used to dynamically adjust the target recommendation scheme based on the feedback information, including: obtaining feedback from users on the target recommendation scheme and determining the type of the feedback information; if the type of the feedback information is an acceptance recommendation, analyzing the acceptance feedback data in the feedback information using a reinforcement learning algorithm and adjusting the target recommendation scheme based on the analysis results.

[0014] In this way, by analyzing the recommendations accepted by users, effective recommendation strategies in the recommendation system can be strengthened and the performance of the recommendation system can be continuously improved.

[0015] Optionally, after obtaining the user's feedback information on the target recommendation scheme and determining the type of the feedback information, it also includes: if the type of the feedback information is a rejection of the recommendation, using a reinforcement learning algorithm to analyze the rejection feedback data in the feedback information and adjusting the target recommendation scheme based on the analysis results.

[0016] In this approach, by analyzing the recommendations rejected by users, unpopular recommendation strategies can be identified and avoided, and by adjusting the recommendation scheme to reduce the number of recommendations rejected by users, the overall user satisfaction can be improved.

[0017] In a second aspect, the present invention provides an intelligent permission recommendation device based on AI analysis, comprising: a data collection module for acquiring user behavior data and historical permission data; an AI analysis module for identifying user behavior patterns based on the user behavior data based on AI analysis; an intelligent recommendation module for generating a target recommendation scheme based on the user behavior pattern and historical permission data; and a dynamic adjustment module for acquiring user feedback information on the target recommendation scheme, and using a reinforcement learning algorithm to dynamically adjust the target recommendation scheme based on the feedback information.

[0018] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute the intelligent permission recommendation method based on AI analysis of the above-mentioned first aspect or any corresponding embodiment thereof.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the intelligent permission recommendation method based on AI analysis of the above-mentioned first aspect or any corresponding embodiment thereof.

[0020] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the intelligent permission recommendation method based on AI analysis as in the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 11 is a flow chart of an intelligent permission recommendation method based on AI analysis according to an embodiment of the present invention;

[0023] Figure 2 is a flowchart of another intelligent permission recommendation method based on AI analysis according to an embodiment of the present invention;

[0024] Figure 3 is a flowchart of another intelligent permission recommendation method based on AI analysis according to an embodiment of the present invention;

[0025] Figure 4 is a flowchart of another intelligent permission recommendation method based on AI analysis according to an embodiment of the present invention;

[0026] Figure 5 is a structural block diagram of an intelligent permission recommendation device based on AI analysis according to an embodiment of the present invention;

[0027] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0029] In view of the problem that permission management becomes increasingly difficult as the scale and complexity of traditional computer systems increase, an embodiment of the present invention provides an intelligent permission recommendation method based on AI analysis, aiming to solve the inefficiency and error-prone problems in traditional permission management systems. By introducing AI analysis technology, intelligent permission recommendations are provided, the efficiency and accuracy of permission management are improved, and rapidly changing business needs are met.

[0030] According to an embodiment of the present invention, an embodiment of an intelligent permission recommendation method based on AI analysis is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0031] In this embodiment, an intelligent permission recommendation method based on AI analysis is provided, which can be used in mobile terminals such as mobile phones, tablet computers, etc. Figure 1 As shown, the process includes the following steps:

[0032] Step S101, obtaining user behavior data and historical permission data.

[0033] Specifically, user behavior data includes the user's login time, resource access frequency, operation type, etc., and historical permission data includes permission data allocated to the user in the past.

[0034] Collect and integrate user behavior data and historical permission data from multiple sources in real time to ensure the comprehensiveness and accuracy of analysis results.

[0035] Step S102, based on AI analysis, identifying user behavior patterns according to user behavior data.

[0036] Artificial Intelligence (AI) refers to computer systems that simulate human intelligence, including technologies such as machine learning and natural language processing, which are used to analyze data, make decisions and predictions.

[0037] Based on AI analysis, machine learning and data mining technologies are used to analyze the collected data, conduct in-depth analysis of massive data, explore the potential rules of permission allocation, and then identify user behavior patterns.

[0038] Step S103, generating a target recommendation plan based on the user behavior pattern and historical authority data.

[0039] Generate target recommendation plans based on the analyzed user behavior patterns and historical permission data, assign permission configurations corresponding to each user's behavior patterns, implement personalized recommendations, and improve the efficiency and accuracy of permission allocation.

[0040] Step S104, obtaining user feedback information on the target recommendation scheme, and using a reinforcement learning algorithm to dynamically adjust the target recommendation scheme based on the feedback information.

[0041] Monitor the usage of permissions and user feedback in the computer system and collect user feedback information. Based on the feedback information, use the reinforcement learning algorithm to adjust the target recommendation scheme to ensure the flexibility and continuous optimization of permission allocation. Further, apply the adjusted target recommendation scheme to the system, and continue to monitor and optimize to form a closed-loop feedback mechanism.

[0042] An intelligent permission recommendation method based on AI analysis in an embodiment of the present invention obtains user behavior data and historical permission data, identifies user behavior patterns based on user behavior data based on AI analysis, generates a target recommendation plan based on user behavior patterns and historical permission data, obtains user feedback on the target recommendation plan, and uses a reinforcement learning algorithm to dynamically adjust the target recommendation plan based on the feedback information. It can conduct in-depth analysis of user behavior and historical data, and dynamically adjust the target recommendation plan based on user feedback information, realize real-time monitoring and strategy adjustment, ensure the flexibility of the recommendation plan and the continuous optimization of the recommendation plan, form a closed-loop feedback mechanism, and improve the accuracy and effectiveness of the recommendation plan.

[0043] In some embodiments, step S102, based on AI analysis, identifying user behavior patterns according to user behavior data, includes:

[0044] Step S1021, based on AI analysis, extract user behavior features according to user behavior data.

[0045] Specifically, the collected user behavior data and historical permission data are preprocessed, including cleaning, deduplication and normalization of the collected data to ensure data quality and consistency. User behavior features are extracted from the preprocessed data, such as user operation frequency, resource access mode, etc.

[0046] Step S1022: clustering the user behavior features using a clustering algorithm to identify the user behavior pattern.

[0047] The clustering algorithm uses the KMeans clustering algorithm to cluster user behavior features and then identify user behavior patterns.

[0048] In this way, by extracting user behavior features and using clustering algorithms, user behavior patterns can be identified more accurately.

[0049] In some embodiments, step S103, generating a target recommendation scheme based on the user behavior pattern and historical permission data, includes:

[0050] Step S1031 , based on the user behavior pattern, using collaborative filtering algorithm or content recommendation algorithm, generate several initial recommendation schemes.

[0051] Based on user behavior patterns and permission usage history, a recommendation list is generated using a collaborative filtering algorithm or a content recommendation algorithm, and the recommendation list includes several initial recommendation solutions.

[0052] Step S1032, optimizing the initial recommendation scheme to obtain a target recommendation scheme.

[0053] Specifically, the initially generated initial recommendation scheme is optimized through a genetic algorithm or an ant colony algorithm to ensure the accuracy and effectiveness of the recommendation results.

[0054] In this way, the collaborative filtering algorithm and the content recommendation algorithm are combined to generate the initial recommendation scheme, which can improve the diversity and coverage of the recommendation. Through the optimization process, the recommendation scheme that better meets the user's needs can be screened out.

[0055] Furthermore, in step S1032, the initial recommendation scheme is optimized to obtain a target recommendation scheme, including:

[0056] Step S10321, using several initial recommended solutions as the initial population of the genetic algorithm.

[0057] In genetic algorithms, the term initial population refers to the set of candidate solutions generated at the beginning of the genetic algorithm.

[0058] Step S10322: Use the fitness function to evaluate the fitness of each initial recommendation solution.

[0059] The fitness function is used to evaluate the quality of each candidate solution. It is usually based on accuracy and efficiency. The fitness function is used to evaluate the fitness of each initial recommended solution, and then evaluate its quality.

[0060] Step S10323, select an initial recommendation scheme with a fitness higher than a preset value, perform crossover and mutation to generate a new recommendation scheme and repeat the iteration, and output the target recommendation scheme after the iteration is terminated.

[0061] The preset value can be set according to the actual situation, so as to select the initial recommended solution with higher fitness for crossover and mutation. Crossover refers to combining two candidate solutions to generate a new candidate solution. Mutation refers to randomly modifying the candidate solution to increase diversity.

[0062] Repeat the above steps for iterative optimization until the optimal recommendation solution, i.e., the target recommendation solution, is obtained.

[0063] The optimized target recommendation plan is presented to the administrator or user in a friendly interface, providing detailed reasons for the recommendation and relevant data support.

[0064] In this method, the initial recommendation scheme is iteratively optimized using a genetic algorithm, which can simulate the natural selection process. Through fitness function evaluation, it is ensured that only high-quality recommendation schemes are retained and further optimized to find better recommendation schemes.

[0065] In an embodiment of the present invention, a document processing method is provided, which can be used in a mobile terminal, such as a mobile phone, a tablet computer, etc. Figure 2 As shown, the process includes the following steps:

[0066] Step S201, obtain user behavior data and historical permission data. For details, see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0067] Step S202: Based on AI analysis, identify user behavior patterns according to user behavior data. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0068] Step S203: Generate a target recommendation plan based on the user behavior pattern and historical authority data. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0069] Step S204, obtaining user feedback information on the target recommendation scheme, and using a reinforcement learning algorithm to dynamically adjust the target recommendation scheme based on the feedback information.

[0070] Specifically, see Figure 3 and Figure 4 , step S204 includes:

[0071] Step S2041, obtaining the user's feedback information on the target recommendation solution and determining the type of the feedback information.

[0072] After the user responds to the target recommendation solution, the user's feedback information is collected, and the feedback information includes two types, namely, acceptance or rejection. Each type of feedback information may also include a corresponding description or score, etc.

[0073] Step S2042: If the type of the feedback information is acceptance recommendation, the acceptance feedback data in the feedback information is analyzed using a reinforcement learning algorithm and the target recommendation scheme is adjusted based on the analysis result.

[0074] Specifically, the feedback data received in the feedback information includes the user's satisfaction and feedback suggestions, etc. If the user accepts the target recommendation plan, the feedback data received is analyzed and the target recommendation plan is adjusted based on the analysis result.

[0075] By analyzing the recommendations accepted by users, we can strengthen the effective recommendation strategies in the recommendation system and continuously improve the performance of the recommendation system.

[0076] Furthermore, step S204 further includes:

[0077] Step S2043: If the type of the feedback information is rejection of recommendation, the rejection feedback data in the feedback information is analyzed using a reinforcement learning algorithm and the target recommendation scheme is adjusted based on the analysis result.

[0078] Furthermore, the rejection feedback data includes rejection reasons and scores, and the rejection feedback data is analyzed and the target recommendation solution is adjusted based on the analysis results.

[0079] By analyzing the recommendations rejected by users, unpopular recommendation strategies can be identified and avoided. By adjusting the recommendation scheme to reduce the number of recommendations rejected by users, the overall user satisfaction can be improved.

[0080] In one example, the reinforcement learning algorithm adopts a Q learning algorithm, which includes the following steps:

[0081] 1. Initialize the Q-value table: First, initialize the Q-value table and set the Q-value of all state-action pairs to 0. This means that at the beginning, we have no prior knowledge of the value of any recommended strategy.

[0082] 2. Action selection: Select actions according to the ε-greedy strategy. This means that most of the time the action with the highest current Q value is selected (greedy), and occasionally an action is randomly selected (exploration). This helps to strike a balance between exploring new strategies and exploiting known strategies.

[0083] 3. Perform an action: Perform the selected action a in the current state s, and then observe the reward r given by the environment and the new state s'. In the context of a recommendation system, an action can be recommending an item to a user, and a reward can be the user's feedback on the recommended item (for example, whether the user clicks on the recommended item).

[0084] 4. Update Q value: Use the following formula to update the Q value:

[0085] Q(s,a)←Q(s,a)+α[r+γmax a′ (Q(s′,a′)-Q(s,α)]

[0086] Among them, α is the learning rate, γ is the discount factor, r is the reward obtained after executing the action, and max a′ (Q(s′,a′) is the maximum Q-value of all possible actions in the new state s′.

[0087] 5. Get user feedback: After the user responds to the recommended item, collect user feedback information, such as feedback type, rating or comment.

[0088] 6. Analyze feedback information: Based on the user's feedback information, determine the type of feedback (accept or reject). If the user accepts the recommendation, analyze the acceptance feedback data and adjust the target recommendation plan based on the analysis results. If the user rejects the recommendation, analyze the rejection feedback data and adjust the target recommendation plan based on the analysis results.

[0089] 7. Dynamically adjust recommendation strategies: Use reinforcement learning algorithms to analyze feedback information and update the Q value table based on the analysis results. This will affect future recommendation decisions and enable the system to learn which recommendation strategies are more effective.

[0090] 8. Repeated iteration: Repeat the steps of selecting actions, executing actions, updating Q values, and obtaining user feedback until the strategy converges. This means that over time, the recommendation strategy will be continuously optimized to maximize user satisfaction and engagement.

[0091] Through this process, the reinforcement learning algorithm is able to dynamically adjust the recommendation strategy based on real-time user feedback, thereby improving the accuracy and efficiency of recommendations. This approach is particularly suitable for recommendation systems because user preferences may change over time and user feedback can provide real-time information about the quality of recommendations.

[0092] The present invention has the following effects:

[0093] By collecting user data and identifying user behavior patterns, target recommendation plans are generated for automated recommendations, reducing the workload of administrators and improving the efficiency of authority allocation.

[0094] By using AI analysis technology to generate target recommendation solutions based on user behavior data and historical permission data, accurate permission recommendations can be provided, reducing the risk of misconfiguration.

[0095] Dynamically adjust recommendation strategies based on reinforcement learning algorithms to respond to business changes in real time, meet diverse permission management needs, and ensure system flexibility and continuous optimization.

[0096] The embodiment of the present invention also provides an intelligent permission recommendation device based on AI analysis, such as Figure 5 As shown, including:

[0097] Data collection module 501, used to obtain user behavior data and historical permission data;

[0098] AI analysis module 502, used to identify user behavior patterns based on user behavior data based on AI analysis;

[0099] Intelligent recommendation module 503, used to generate target recommendation solutions based on user behavior patterns and historical authority data;

[0100] The dynamic adjustment module 504 is used to obtain user feedback information on the target recommendation solution, and use a reinforcement learning algorithm to dynamically adjust the target recommendation solution based on the feedback information.

[0101] An intelligent permission recommendation device based on AI analysis of the present invention obtains user behavior data and historical permission data, identifies user behavior patterns based on user behavior data based on AI analysis, generates a target recommendation plan based on user behavior patterns and historical permission data, obtains user feedback on the target recommendation plan, and uses a reinforcement learning algorithm to dynamically adjust the target recommendation plan based on the feedback information. It can conduct in-depth analysis of user behavior and historical data, and dynamically adjust the target recommendation plan based on user feedback information, realize real-time monitoring and strategy adjustment, ensure the flexibility of the recommendation plan and that the recommendation plan can be continuously optimized, form a closed-loop feedback mechanism, and improve the accuracy and effectiveness of the recommendation plan.

[0102] In some embodiments, the AI ​​analysis module 502 includes:

[0103] Feature extraction module, used to extract user behavior features based on user behavior data based on AI analysis;

[0104] The behavior recognition module is used to cluster user behavior features using a clustering algorithm and identify user behavior patterns.

[0105] In some embodiments, the intelligent recommendation module 503 includes:

[0106] The initial recommendation module is used to generate several initial recommendation schemes based on user behavior patterns using collaborative filtering algorithms or content recommendation algorithms;

[0107] The recommendation optimization module is used to optimize the initial recommendation scheme to obtain the target recommendation scheme.

[0108] In some embodiments, the recommendation optimization module includes:

[0109] A population initialization module is used to use several initial recommendation schemes as the initial population of the genetic algorithm;

[0110] A fitness evaluation module is used to evaluate the fitness of each initial recommendation solution using a fitness function;

[0111] The solution iteration module is used to select the initial recommendation solution with a fitness higher than the preset value for crossover and mutation to generate a new recommendation solution and repeat the iteration, and output the target recommendation solution after the iteration is terminated.

[0112] In some embodiments, the dynamic adjustment module 504 includes:

[0113] A feedback acquisition module is used to obtain user feedback information on the target recommendation solution and determine the type of feedback information;

[0114] The first solution adjustment module is used to use a reinforcement learning algorithm to analyze the acceptance feedback data in the feedback information and adjust the target recommendation solution based on the analysis result if the type of the feedback information is acceptance recommendation.

[0115] In some embodiments, the dynamic adjustment module 504 further includes:

[0116] The second solution adjustment module is used to use a reinforcement learning algorithm to analyze the rejection feedback data in the feedback information and adjust the target recommendation solution based on the analysis result if the type of the feedback information is rejection recommendation.

[0117] The embodiment of the present invention also provides a schematic diagram of the structure of a computer device, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0118] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0119] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0120] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device 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.

[0121] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0122] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0123] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0124] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0125] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0126] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope of protection.

Claims

1. An intelligent permission recommendation method based on AI analysis, characterized in that: include: Obtain user behavior data and historical permission data; Based on AI analysis, identifying user behavior patterns according to the user behavior data; Generate a target recommendation plan based on the user behavior pattern and historical permission data; Obtain user feedback information on the target recommendation scheme, and use a reinforcement learning algorithm to dynamically adjust the target recommendation scheme based on the feedback information.

2. The intelligent permission recommendation method based on AI analysis according to claim 1 is characterized in that: Based on AI analysis, identifying user behavior patterns according to the user behavior data, including: Based on AI analysis, extract user behavior features according to the user behavior data; The user behavior features are clustered using a clustering algorithm to identify user behavior patterns.

3. The intelligent permission recommendation method based on AI analysis according to claim 1 is characterized in that: Generate a target recommendation plan based on the user behavior pattern and historical permission data, including: Based on the user behavior pattern, using a collaborative filtering algorithm or a content recommendation algorithm, generating several initial recommendation solutions; The initial recommendation scheme is optimized to obtain a target recommendation scheme.

4. The intelligent permission recommendation method based on AI analysis according to claim 3 is characterized in that: The initial recommendation scheme is optimized to obtain a target recommendation scheme, including: Using the several initial recommended solutions as the initial population of the genetic algorithm; Using a fitness function to evaluate the fitness of each of the initial recommended solutions; The initial recommendation scheme with a fitness higher than a preset value is selected for crossover and mutation to generate a new recommendation scheme and iterate repeatedly, and the target recommendation scheme is output after the iteration is terminated.

5. The intelligent permission recommendation method based on AI analysis according to claim 1 is characterized in that: Acquiring user feedback information on the target recommendation scheme, and using a reinforcement learning algorithm to dynamically adjust the target recommendation scheme based on the feedback information, including: Obtaining user feedback information on the target recommendation scheme and determining the type of the feedback information; If the type of the feedback information is acceptance recommendation, a reinforcement learning algorithm is used to analyze the acceptance feedback data in the feedback information and adjust the target recommendation scheme based on the analysis result.

6. The intelligent permission recommendation method based on AI analysis according to claim 5 is characterized in that: After obtaining the user's feedback information on the target recommendation scheme and determining the type of the feedback information, the method further includes: If the type of the feedback information is rejection of recommendation, a reinforcement learning algorithm is used to analyze the rejection feedback data in the feedback information and adjust the target recommendation scheme based on the analysis result.

7. An intelligent permission recommendation device based on AI analysis, characterized in that: include: Data collection module, used to obtain user behavior data and historical permission data; An AI analysis module, for identifying user behavior patterns based on the user behavior data based on AI analysis; An intelligent recommendation module, used to generate a target recommendation plan based on the user behavior pattern and historical permission data; The dynamic adjustment module is used to obtain user feedback information on the target recommendation scheme, and use a reinforcement learning algorithm to dynamically adjust the target recommendation scheme based on the feedback information.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the intelligent permission recommendation method based on AI analysis as described in any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the intelligent permission recommendation method based on AI analysis according to any one of claims 1 to 6.

10. A computer program product, characterized in that It includes computer instructions, and the computer instructions are used to enable a computer to execute the intelligent permission recommendation method based on AI analysis as described in any one of claims 1 to 6.

Images