A personalized music teaching content push system

Abstract

The present invention relates to the field of personalized push technology, specifically a personalized music teaching content push system, the system including a user ability assessment module, a teaching content matching module, a learning path planning module, a push strategy optimization module, a behavior analysis and prediction module, a teaching effect feedback module, a dynamic adjustment and optimization module, and a personalized recommendation module. The present invention adopts clustering algorithms, support vector machines, and random forest algorithms to accurately assess learner abilities, K-means clustering and hierarchical analysis method to achieve matching between teaching content and abilities, Dijkstra algorithm and dynamic programming to design personalized learning paths, Q learning and policy gradient method to optimize push strategies, long short-term memory networks and seasonal decomposition time series to predict learning needs, and utilizes item response theory, Markov decision process and Bayesian network to improve feedback adjustment accuracy. Deep Q network and Monte Carlo tree search are used to optimize personalized recommendations and enhance teaching efficiency and results.

Description

Technical Field

[0001] The present invention relates to the field of personalized push technology, and in particular to a personalized music teaching content push system. Background Art

[0002] The field of personalized push technology focuses on customizing and delivering content or services based on a user's specific needs, preferences, behavioral history, and interactive feedback. In educational and learning environments, particularly music instruction, personalized push technology strives to optimize the allocation and use of instructional resources to enhance learning efficiency and effectiveness. By analyzing a user's learning progress, preferences, and feedback, it can recommend instructional content that best suits the user's current learning stage and interests.

[0003] The personalized music instructional content push system is a technical solution that leverages user data, such as learning history, preferences, and behavior, to automatically provide customized music instructional resources. This system aims to enhance the personalization and efficiency of learning by precisely matching users' individual learning needs and interests. It aims to increase user motivation, optimize resource utilization, and enhance learning outcomes. It supports more efficient and targeted interaction between music educators and learners, thereby promoting deeper and broader music learning.

[0004] Traditional music education content delivery systems lack accurate assessment and personalized analysis of learners' abilities, resulting in ineffective matching of teaching content with each learner's actual needs. This leads to a mismatch between teaching content and learners' actual abilities and interests, impacting learning efficiency and motivation. Path planning and delivery strategies often rely on static planning and simple algorithms, lacking personalized and dynamic adjustment capabilities. This leads to irrational allocation of learning resources and prevents learners from obtaining the most appropriate learning content. In terms of behavioral analysis and teaching effectiveness feedback, simple statistical methods are used, which cannot accurately predict learners' behaviors and needs, making it difficult to provide effective teaching adjustments, thus affecting learning outcomes and efficiency. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a personalized music teaching content push system.

[0006] To achieve the above objectives, the present invention adopts the following technical solutions: a personalized music teaching content push system, the system includes a user ability assessment module, a teaching content matching module, a learning path planning module, a push strategy optimization module, a behavior analysis and prediction module, a teaching effect feedback module, a dynamic adjustment and optimization module, and a personalized recommendation module;

[0007] The user ability assessment module uses a clustering algorithm to classify learners' skill levels based on the practice recordings, homework and test results submitted by learners, and uses a support vector machine algorithm and a random forest algorithm to perform data feature analysis and assessment on learners' music theory knowledge, playing skills and creative ability to generate ability assessment results;

[0008] The teaching content matching module uses the K-means clustering algorithm based on the ability assessment results to quantitatively analyze the learner skill distribution, identify learner groups with differentiated skill levels, and analyze the teaching objectives, content difficulty, and learner preferences through the hierarchical analysis method. It then prioritizes the teaching content corresponding to the differentiated skill levels and generates a teaching content matching plan.

[0009] The learning path planning module uses the Dijkstra algorithm to plan the learning path based on the teaching content matching scheme, and combines the learner's personal preferences and learning progress to design a multi-stage learning path through a dynamic programming method to generate personalized learning path information;

[0010] The push strategy optimization module uses Q learning and policy gradient methods based on personalized learning path information to adjust the push strategy. It learns and formulates the push strategy through reinforcement learning technology to generate an optimized push strategy.

[0011] The behavior analysis and prediction module is based on the optimized push strategy, combined with the learner's music learning interaction data, using long short-term memory network and seasonal decomposition time series to analyze the learner's behavior patterns and periodic changes, predict the learner's future behavior and needs, and generate behavior prediction results;

[0012] The teaching effect feedback module evaluates the teaching effect based on the behavior prediction results and the learners' feedback on the pushed content through item response theory and Markov decision process, and formulates matching teaching adjustment strategies to generate teaching effect improvement strategy information;

[0013] The dynamic adjustment and optimization module adjusts and optimizes the learning path and teaching content based on the teaching effect improvement strategy information, combined with the teaching effect feedback, using the dynamic programming algorithm and Bayesian network, by analyzing the learner's progress, effect feedback and change needs, and generates the adjusted learning path and teaching content;

[0014] The personalized recommendation module is based on the adjusted learning path and teaching content, adopts the deep Q network model and Monte Carlo tree search technology to optimize the personalized recommendation strategy, analyzes the relationship between learner behavior, preferences and teaching content through the deep learning model, adjusts the push timing and content, and generates a personalized recommendation plan.

[0015] The present invention has improvements in that the ability assessment results include music theory knowledge scores, playing skill levels, and creative ability evaluations; the teaching content matching plan includes recommended music theory teaching materials, skill practice repertoires, and creative guidance courses; the personalized learning path information includes stage learning goals, recommended learning materials, and expected completion time; the optimized push strategy includes content push frequency, push time period selection, and content preference type; the behavior prediction results include active learning time periods, content preference analysis results, and potential learning obstacle information; the teaching effect improvement strategy information includes teaching content adjustment plans, learning method optimization plans, and auxiliary material update demand information; the adjusted learning path and teaching content include learning material column information, learning progress schedule, and personalized learning plans; the personalized recommendation plan includes recommended teaching video information, recommended music scores and works, and practice tasks.

[0016] The present invention is improved in that the user ability assessment module includes a skill level classification submodule, a data feature analysis submodule, and a comprehensive assessment submodule;

[0017] The skill level classification submodule uses a clustering algorithm based on the practice recordings, homework and test results submitted by learners. It uses the scikit-learn library to perform K-Means clustering, sets the number of clusters, matches the learner ability level classification, uses Euclidean distance for distance calculation, sets the number of iterations to 100, groups the learners, and generates skill level classification results.

[0018] Based on the skill level classification results, the data feature analysis submodule uses the support vector machine algorithm and the random forest algorithm, using the Python Scikit-learn library to perform data feature analysis on the learner's music theory knowledge, playing skills, and creative ability. By executing the SVC function and the RandomForestClassifier function, key features are extracted from the learner's practice recordings, homework, and test results, factors that affect the learner's skill level are identified, and data feature analysis results are generated;

[0019] The comprehensive assessment submodule is based on the results of data feature analysis, adopts a weighted decision matrix method, and combines Python's NumPy library to conduct a comprehensive ability assessment analysis. According to the importance of each skill to the learner's overall ability, weights are assigned to the assessment dimensions of music theory knowledge, playing skills, and creative ability, and weight calculations are performed. The weighted decision matrix is applied to multiply the learner's score on the differentiated skill dimension by the corresponding weight, and the cumulative total is used to obtain the comprehensive ability score of each learner to generate the ability assessment result.

[0020] The present invention is improved in that the teaching content matching module includes a skill quantification analysis submodule, a differentiation identification submodule, and a teaching content priority setting submodule;

[0021] The skill quantification analysis submodule uses the K-means clustering algorithm based on the ability assessment results and the Python Scikit-learn library to perform a quantitative analysis of the learner's skill distribution. By inputting the learner's ability assessment data, including scores on music theory knowledge, playing skills, and creative ability, the module performs clustering using the KMeans function, dividing the learners into differentiated groups based on their skill levels, and generating skill quantification analysis results.

[0022] The differentiation identification submodule uses statistical analysis methods based on the results of skill quantitative analysis, and utilizes Python's Pandas library and NumPy library to perform differentiated identification of skill levels among learner groups. The Pandas library is used for data organization and grouping, and the NumPy library is used for mathematical operations to calculate the mean and standard deviation statistical indicators of the differentiated group skill scores, identify the skill differences among differentiated learner groups, and generate differentiated identification results.

[0023] The teaching content priority setting submodule is based on the differentiated identification results, adopts the hierarchical analysis method, and uses Python's PyAHP library to input the importance of teaching objectives, the difficulty level of teaching content, and the weight of learner preferences. By constructing a judgment matrix and calculating the weight vector, the teaching content priority of learner groups with differentiated skill levels is formulated, and a teaching content matching plan is generated.

[0024] The present invention is improved in that the learning path planning module includes a learning path design submodule, a learning preference integration submodule, and a multi-stage path planning submodule;

[0025] The learning path design submodule is based on the teaching content matching scheme, adopts the Dijkstra algorithm, and uses the NetworkX library to build a graph model. Nodes represent teaching units, and edges represent the logical relationship between teaching units. The weight of the edge is set by the add_weighted_edges_from function in the NetworkX library to reflect the transition difficulty between teaching units. The dijkstra_path function is used to calculate the shortest path of all nodes and generate a basic path framework.

[0026] The learning preference integration submodule is based on the path-based framework and adopts a collaborative filtering algorithm. It uses the pairwise_distances function in the Scikit-learn library to calculate the similarity between user preference vectors and content features, adjusts the learning path based on historical behavior data and the preferences of similar users, and uses the NearestNeighbors model to capture teaching content that matches the current learner's preferences and generate a preference adjustment path.

[0027] The multi-stage path planning submodule adjusts the path based on preferences, adopts a dynamic programming method, uses the NumPy library, defines multi-stage learning goals, allocates learning resources, dynamically adjusts progress parameters according to the learner's current progress and future goals, and calculates the multi-stage optimal learning path through a dynamic programming algorithm, including minimizing learning costs and maximizing learning effects, and generates personalized learning path information.

[0028] The present invention is improved in that the push strategy optimization module includes a push strategy adjustment submodule, a push strategy learning submodule, and a push strategy implementation submodule;

[0029] The push strategy adjustment submodule uses the Q learning algorithm based on personalized learning path information and the NumPy library to set an initial Q table, assign initial values to state-behavior pairs, and define a reward mechanism, including increasing the reward value for learners' positive feedback on the pushed content and reducing the reward value for negative feedback. The learning rate parameter is set to 0.1 and the discount factor is set to 0.9. Through an iterative process, the Q value is updated according to the learner's feedback, and the behavior with the largest Q value is selected as the push strategy to generate a basic push strategy.

[0030] The push strategy learning submodule is based on the basic push strategy and adopts the policy gradient method. It uses the TensorFlow and Keras libraries to build a network model, including an input layer, a hidden layer, and an output layer. The hidden layer uses the ReLU activation function, and the output layer uses the softmax function to generate a probability distribution. The learning rate is set to 0.01, and learner feedback is used as a reward signal. Through the backpropagation algorithm, the network parameters are adjusted, the policy gradient is optimized, and the learner characteristics and current learning status are input. The probability distribution of push behavior is output to generate the push strategy analysis results;

[0031] The push strategy implementation submodule uses the Monte Carlo method and the SciPy library based on the push strategy analysis results to calculate and sample the probability distribution. By analyzing the learner's current learning progress and preferences and using the optimized strategy network, it formulates the push content and frequency, including calculating the probability value corresponding to each push content, selecting content with high probability values as push options, and analyzing the learner's learning time preference to select the push timing, thereby generating an optimized push strategy.

[0032] The present invention is improved in that the behavior analysis and prediction module includes a behavior pattern analysis submodule, a periodic change analysis submodule, and a behavior prediction submodule;

[0033] The behavior pattern analysis submodule is based on an optimized push strategy, adopts a long short-term memory network, and uses the TensorFlow and Keras libraries to build a model to analyze learners' music learning interaction data. The input is the learner's interaction sequence data, including click-through rate, learning time and frequency. The number of hidden layer nodes is set to 128, the relu activation function is used, and the output layer adopts the softmax function. The module identifies and summarizes the learner's behavior pattern, including learning preferences and active time periods. The batch size is set to 32 and the number of iterations is set to 100. The model is trained to generate behavior pattern analysis results.

[0034] The cyclical change analysis submodule uses the seasonal decomposition time series method based on the behavioral pattern analysis results and the statsmodels library to perform seasonal decomposition and analyze the cyclical changes in learner behavior. The time series data is decomposed into trend, seasonal and residual components. The learner's interaction time series data is input through the seasonal_decompose function, and the model is set to an additive model to reveal the cyclical laws of learner behavior and generate cyclical change analysis results.

[0035] The behavior prediction submodule adopts the long short-term memory network based on the results of periodic change analysis, adjusts the long short-term memory network to the prediction mode, inputs the behavior pattern and periodic change data, sets the number of hidden layer nodes to 128, uses the sigmoid activation function to match the prediction task, and adopts the linear function in the output layer to predict the learner's future behavior and needs and generate behavior prediction results.

[0036] The present invention is improved in that the teaching effect feedback module includes a teaching effect evaluation submodule, a teaching adjustment strategy formulation submodule, and a teaching effect improvement submodule;

[0037] The teaching effectiveness evaluation submodule uses item response theory and the R language's ltm package to analyze the behavior prediction results and evaluate learners' feedback on the pushed content. By inputting learners' response data to differentiated pushed content, including accuracy and response time, the module uses the grm function to perform a multi-parameter logical model analysis to assess the sensitivity of the learning content to the learners' ability level and the learners' mastery of the target teaching content, thereby generating teaching effectiveness evaluation results.

[0038] The teaching adjustment strategy formulation submodule uses the Markov decision process based on the teaching effect evaluation results and uses Python's pymdptoolbox library to perform strategy optimization. By inputting teaching effect evaluation information, including learners' mastery of and preferences for differentiated teaching content, the state space is set to the differentiated combination of teaching content, the action space is set to the estimated teaching adjustment measures, and a reward function is set according to the degree of improvement in teaching effect. It is iterated through the mdp.ValueIteration function to capture the optimal teaching adjustment strategy and generate a teaching adjustment strategy plan.

[0039] The teaching effect improvement submodule is based on a teaching adjustment strategy scheme, adopts a feedback adjustment algorithm, and uses Python's SciPy library for mathematical optimization. By inputting the difference between the target teaching effect and the current teaching effect, using the minimize function, setting the goal to minimize the difference between the teaching effect and the target, adjusting the difficulty level of the teaching content, changing the teaching method, and increasing personalized push content to match the needs of learners, the module generates teaching effect improvement strategy information.

[0040] The present invention is improved in that the dynamic adjustment and optimization module includes a learning path adjustment submodule, a teaching content optimization submodule, and a teaching dynamic optimization submodule;

[0041] The learning path adjustment submodule uses a dynamic programming algorithm based on teaching effect improvement strategy information and Python's NumPy library to analyze learners' progress and effect feedback. By defining the state as the learner's current knowledge mastery level and learning progress, the action as the learning path adjustment option, and the objective function as maximizing learning efficiency and meeting the learner's personalized needs, it updates the state value through iterative calculation, captures the optimal learning path, and generates an optimized learning path plan;

[0042] The teaching content optimization submodule is based on the optimization learning path scheme, adopts Bayesian network, and uses Python's pgmpy library to build a model to analyze learners' feedback on teaching content and their demand for changes. By inputting learners' mastery of the current teaching content and feedback on their satisfaction, it calculates the conditional probability of differentiated teaching content adjustment plans, selects content adjustment plans that improve teaching effectiveness, and generates teaching content optimization plans;

[0043] The dynamic teaching optimization submodule is based on the teaching content optimization plan and the learning path optimization plan, combined with teaching effect feedback, adopts an iterative feedback adjustment algorithm, and uses Python's SciPy library to perform mathematical optimization. Through the optimize.minimize function, the goal is set to minimize the difference between teaching content and learner needs. Through the feedback loop, the teaching strategy is adjusted to match the development of learners' abilities and changes in needs, and the adjusted learning path and teaching content are generated.

[0044] The present invention is improved in that the personalized recommendation module includes a recommendation strategy optimization submodule, a recommendation content adjustment submodule, and a recommendation timing optimization submodule;

[0045] The recommendation strategy optimization submodule uses a deep Q network model based on the adjusted learning path and teaching content, and uses the TensorFlow and Keras libraries to build a deep learning model. It inputs the learner's behavior data and the characteristics of the current teaching content, outputs the value evaluation of the recommended action, and evaluates the impact of the recommended action on the learning effect by defining a reward function. The learning rate is set to 0.01 and the discount factor is set to 0.9. The experience replay mechanism is used to improve learning efficiency. The recommendation strategy is optimized through iterative training of the model to generate the recommendation strategy optimization result.

[0046] The recommended content adjustment submodule uses Monte Carlo tree search technology based on the recommendation strategy optimization results and utilizes Python's Monte Carlo tree search library to adjust recommended content. By constructing a search tree to simulate differentiated recommended content selection paths, the long-term benefits of each option are evaluated. By simulating multiple decision-making processes, the optimal recommended content path is selected and a recommended content adjustment plan is generated.

[0047] The recommendation timing optimization submodule is based on the recommendation content adjustment plan, uses the deep Q network model, combines the learner's learning activity pattern and preferences, adopts the TensorFlow and Keras libraries, and defines a reward function based on the learner's activity time data and preference information. It rewards the action of recommending when the learner is able to accept new information. The learning rate is set to 0.005 and the discount factor is set to 0.95. The model is trained using the fit function. By identifying the effective time period of the learner's learning activity and the preferred time to receive new content, a personalized recommendation plan is generated.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, by adopting clustering algorithm, support vector machine and random forest algorithm, learners are divided into skill levels and data feature analysis is carried out, thereby achieving accurate assessment of user capabilities. By using K-means clustering algorithm and hierarchical analysis method, accurate matching of teaching content and learner capabilities is achieved. The application of Dijkstra algorithm and dynamic programming method is used to design multi-stage, personalized learning paths for learners. The combination of Q learning and policy gradient method optimizes the push strategy and improves learning efficiency. The use of long short-term memory network and seasonal decomposition time series enhances the understanding of learners' behavior patterns and the ability to predict future needs. The introduction of item response theory and Markov decision process, as well as the application of dynamic programming algorithm and Bayesian network, improves the feedback and adjustment accuracy of teaching effects. The use of deep Q network model and Monte Carlo tree search technology optimizes personalized recommendation, improves the pertinence and attractiveness of teaching content, enhances learning motivation, and improves teaching efficiency and results. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The present invention proposes a module diagram of a personalized music teaching content push system;

[0051] Figure 2 The present invention proposes a system framework diagram of a personalized music teaching content push system;

[0052] Figure 3 The present invention proposes a user ability assessment module schematic diagram in a personalized music teaching content push system;

[0053] Figure 4 The present invention proposes a teaching content matching module schematic diagram in a personalized music teaching content push system;

[0054] Figure 5 The present invention proposes a schematic diagram of a learning path planning module in a personalized music teaching content push system;

[0055] Figure 6 The present invention proposes a push strategy optimization module schematic diagram in a personalized music teaching content push system;

[0056] Figure 7 The present invention proposes a behavior analysis and prediction module schematic diagram in a personalized music teaching content push system;

[0057] Figure 8 The present invention proposes a teaching effect feedback module schematic diagram in a personalized music teaching content push system;

[0058] Figure 9 The present invention proposes a schematic diagram of a dynamic adjustment and optimization module in a personalized music teaching content push system;

[0059] Figure 10 The present invention proposes a schematic diagram of a personalized recommendation module in a personalized music teaching content push system. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0062] Example

[0063] See also Figure 1 , the present invention provides a technical solution: a personalized music teaching content push system, the system includes a user ability assessment module, a teaching content matching module, a learning path planning module, a push strategy optimization module, a behavior analysis and prediction module, a teaching effect feedback module, a dynamic adjustment and optimization module, and a personalized recommendation module;

[0064] The user ability assessment module uses a clustering algorithm to classify learners' skill levels based on practice recordings, homework, and test results submitted by learners. It also uses support vector machine and random forest algorithms to analyze and evaluate the data characteristics of learners' music theory knowledge, playing techniques, and creative abilities, generating ability assessment results.

[0065] The teaching content matching module uses the K-means clustering algorithm to quantitatively analyze learners' skill distribution based on ability assessment results, identify learner groups with differentiated skill levels, and analyze teaching objectives, content difficulty, and learner preferences through the analytic hierarchy process. It then prioritizes teaching content corresponding to differentiated skill levels and generates a teaching content matching plan.

[0066] The learning path planning module uses the Dijkstra algorithm to plan learning paths based on the teaching content matching solution. It also uses dynamic programming methods to design multi-stage learning paths based on learners' personal preferences and learning progress, and generates personalized learning path information.

[0067] The push strategy optimization module uses Q learning and policy gradient methods to adjust the push strategy based on personalized learning path information. It learns and formulates push strategies through reinforcement learning technology and generates optimized push strategies.

[0068] The behavior analysis and prediction module is based on the optimized push strategy, combined with learners' music learning interaction data, using long-short-term memory networks and seasonal decomposition time series to analyze learners' behavior patterns and cyclical changes, predict learners' future behavior and needs, and generate behavior prediction results;

[0069] The teaching effect feedback module evaluates teaching effectiveness based on behavior prediction results and learners' feedback on pushed content through item response theory and Markov decision process. It then formulates matching teaching adjustment strategies and generates information on teaching effect improvement strategies.

[0070] The dynamic adjustment and optimization module uses information on teaching effect improvement strategies, combined with teaching effect feedback, and uses dynamic programming algorithms and Bayesian networks to adjust and optimize learning paths and teaching content by analyzing learners' progress, effect feedback, and changing needs, and generates adjusted learning paths and teaching content.

[0071] The personalized recommendation module is based on the adjusted learning path and teaching content, and uses deep Q network model and Monte Carlo tree search technology to optimize the personalized recommendation strategy. Through the deep learning model, it analyzes the relationship between learners' behavior, preferences and teaching content, adjusts the push timing and content, and generates personalized recommendation plans.

[0072] The ability assessment results include music theory knowledge scores, playing skill levels, and creative ability evaluations. The teaching content matching plan includes recommended music theory textbooks, skill practice repertoires, and creative guidance courses. Personalized learning path information includes stage learning goals, recommended learning materials, and expected completion time. Optimized push strategies include content push frequency, push time period selection, and content preference types. Behavior prediction results include active learning time periods, content preference analysis results, and potential learning disability information. Teaching effect improvement strategy information includes teaching content adjustment plans, learning method optimization plans, and auxiliary material update needs information. The adjusted learning path and teaching content include learning material list information, learning progress schedule, and personalized learning plans. Personalized recommendation plans include recommended teaching video information, recommended music scores and works, and practice tasks.

[0073] In the user ability assessment module, practice recordings, homework, and test results submitted by learners are received as input data. The data is formatted into feature vectors, which include musicality indicators such as pitch accuracy, rhythm stability, and musical expression. A clustering algorithm is used to perform a preliminary skill level division of learners. The algorithm iteratively optimizes the cluster centers to ensure that learners can be accurately grouped into the corresponding skill levels. The support vector machine algorithm and the random forest algorithm conduct a more in-depth data feature analysis and evaluation of music theory knowledge, performance skills, and creative ability. By constructing a multidimensional feature space and using the support vector machine to determine the classification boundaries, the random forest trains and evaluates the data set by constructing multiple decision trees, thereby improving the accuracy and robustness of the assessment. The ability assessment results are generated, including music theory knowledge scores, performance skill levels, and creative ability evaluations, providing basic data for subsequent modules.

[0074] In the teaching content matching module, based on the results of user ability assessments, the K-means clustering algorithm is used to quantitatively analyze learner skill distribution and identify learner groups with differentiated skill levels. Learners are divided into corresponding groups by calculating the distance between each learner and the cluster center. The Analytic Hierarchy Process (AHP) analyzes teaching objectives, content difficulty, and learner preferences, and prioritizes teaching content corresponding to differentiated skill levels. The AHP ensures that the teaching content matching plan is scientific and reasonable by constructing a judgment matrix, calculating weights, and performing consistency tests. The generated teaching content matching plan includes recommended music theory materials, skill practice repertoire, and creative guidance courses, accurately matching learners' personalized needs.

[0075] In the learning path planning module, the Dijkstra algorithm is used to plan the learning path based on the teaching content matching solution. By constructing a learning node network, each node represents a learning content or stage, and the edge weight reflects the transition cost, that is, the difficulty or time required to transition from one learning stage to another. The Dijkstra algorithm is used to find the path with the smallest weight to ensure the optimal efficiency of the learning path. In combination with the learner's personal preferences and learning progress, a dynamic programming method is used to design multi-stage learning paths. Dynamic programming dynamically adjusts the learning path throughout the learning process by defining state transition equations and optimal substructures to adapt to changes in learner abilities and the evolution of personal preferences. The generated personalized learning path information includes stage learning objectives, recommended learning materials, and expected completion time, providing learners with clear learning guidance.

[0076] In the push strategy optimization module, Q-learning and policy gradient methods are used to adjust push strategies based on personalized learning path information. Q-learning, a model-free reinforcement learning algorithm, learns optimal strategies by updating the value function of state-action pairs. Policy gradient methods optimize strategies by evaluating the performance of the strategies and directly performing gradient ascent updates on the strategy parameters. This module is able to strike a balance between exploration and exploitation, dynamically adjusting push strategies such as content push frequency, push time period selection, and content preference types to maximize learners' learning efficiency and satisfaction. By applying reinforcement learning technology, push strategies are learned and formulated, generating optimized push strategies to ensure that the push of teaching content is more personalized, timely, and engaging.

[0077] In the behavior analysis and prediction module, combining learners' music learning interaction data with optimized push strategies, a long-short-term memory network and seasonal decomposition time series are used to analyze learners' behavior patterns and cyclical changes. The long-short-term memory network captures the long-term dependencies and short-term trends of learners' behavior through time series analysis of learners' behavior data. The seasonal decomposition time series performs seasonal decomposition on the data, identifying and extracting seasonal factors in learning behavior, thereby improving prediction accuracy. This module can accurately analyze learners' behavior patterns and predict their future behavior and needs. The generated behavior prediction results include active learning time periods, content preference analysis results, and information on potential learning barriers. This allows teaching content push to be more tailored to learners' actual needs, improving the effectiveness of personalized teaching.

[0078] In the teaching effectiveness feedback module, item response theory and Markov decision processes are used based on behavior prediction results and learners' feedback on pushed content. Item response theory analyzes learners' responses to various teaching contents, assesses the difficulty of the content and the learners' ability level, thereby achieving more accurate teaching effectiveness evaluation. The Markov decision process optimizes teaching decisions and provides personalized teaching adjustment strategies by considering learners' learning status and possible behavioral choices. It can comprehensively evaluate teaching effectiveness and formulate matching teaching adjustment strategies based on the evaluation results. The generated teaching effectiveness improvement strategy information includes teaching content adjustment plans, learning method optimization plans, and information on the need to update auxiliary materials, thereby achieving continuous optimization of teaching content and methods, improving teaching quality and learning outcomes.

[0079] In the dynamic adjustment and optimization module, based on the teaching effect improvement strategy information and combined with the teaching effect feedback, the dynamic programming algorithm and Bayesian network are used to adjust and optimize the learning path and teaching content. By defining the recursive form of the optimization problem, the dynamic programming algorithm can consider the long-term development of learners in the multi-stage decision-making process and optimize the planning of the learning path. The Bayesian network provides a method for processing uncertain information and performing probabilistic reasoning, which can make more reasonable adjustments to the teaching content based on incomplete feedback information. It can adjust the learning path and teaching content in real time according to the learner's progress, effect feedback and changing needs. The generated adjusted learning path and teaching content include updated learning material column information, learning progress schedule, and personalized learning plan to ensure that the teaching strategy always remains the best fit for the learner's current needs.

[0080] In the personalized recommendation module, a deep Q-network model and Monte Carlo tree search techniques are used to optimize personalized recommendation strategies based on the adjusted learning paths and teaching content. By integrating deep learning and reinforcement learning, the deep Q-network model enables effective decision-making learning when processing high-dimensional feature spaces. Simultaneously, Monte Carlo tree search optimizes recommendation decisions through exploration and utilization strategies, enhancing the exploration capabilities and accuracy of the recommendation system. It can deeply analyze the relationship between learners' behavior, preferences, and teaching content, effectively adjusting the timing and content of push notifications. The resulting personalized recommendation solutions include recommended teaching video information, recommended musical scores and works, and practice tasks, providing more accurate and engaging learning resources, thereby enhancing learners' learning experience and efficiency.

[0081] See also Figure 2 and Figure 3 ,The user capability assessment module includes the skill level classification submodule, the ,data feature analysis submodule, and the comprehensive assessment submodule;

[0082] The skill level classification submodule uses a clustering algorithm based on the practice recordings, homework, and test results submitted by learners. It uses the scikit-learn library to perform K-Means clustering, sets the number of clusters, matches the learner ability level classification, uses Euclidean distance for distance calculation, sets the number of iterations to 100, groups learners, and generates skill level classification results.

[0083] Based on the skill level classification results, the data feature analysis submodule uses the support vector machine algorithm and the random forest algorithm, using Python's Scikit-learn library, to perform data feature analysis on learners' music theory knowledge, playing techniques, and creative abilities. By executing the SVC function and the RandomForestClassifier function, it extracts key features from learners' practice recordings, homework, and test results, identifies factors that affect learners' skill levels, and generates data feature analysis results.

[0084] The comprehensive assessment submodule uses a weighted decision matrix method based on the results of data feature analysis, combined with Python's NumPy library, to conduct a comprehensive ability assessment analysis. According to the importance of each skill to the learner's overall ability, weights are assigned to the assessment dimensions of music theory knowledge, playing skills, and creative ability, and weight calculations are performed. The weighted decision matrix is applied to multiply the learner's score on the differentiated skill dimension by the corresponding weight, and the cumulative total is used to obtain each learner's comprehensive ability score, generating an ability assessment result.

[0085] In the skill level classification submodule, learners submit practice recordings, assignments, and test results. Input data is formatted into feature vectors containing metrics such as pitch accuracy, rhythmic stability, and musical expression. K-Means clustering is performed using the scikit-learn library. The number of clusters is set to match the learners' ability level classifications. Euclidean distance is used as the distance calculation method, and the number of iterations is set to 100 to ensure the stability and accuracy of the clustering process. Learners are grouped into corresponding skill levels by calculating the Euclidean distance between the feature vectors and the cluster centers. The resulting skill level classification provides a precise foundation for subsequent instructional content matching and personalized recommendations.

[0086] In the data feature analysis submodule, based on the skill level classification results, Python's Scikit-learn library is used to employ support vector machine algorithms and random forest algorithms to conduct in-depth data feature analysis of learners' music theory knowledge, performance techniques, and creative abilities. By executing the SVC function and the RandomForestClassifier function, key features are extracted from learners' practice recordings, homework, and test results, such as their understanding of music theory knowledge, their technical mastery of performance, and the innovativeness of their creations. The extraction of key features and the identification of factors influencing learners' skill levels enable the system to more accurately assess and understand learners' specific abilities. The resulting data feature analysis results provide an important basis for matching and recommending personalized teaching content.

[0087] In the comprehensive assessment submodule, the system evaluates and analyzes learners' comprehensive abilities based on data feature analysis results using a weighted decision matrix approach combined with Python's NumPy library. Weights are assigned based on the importance of music theory knowledge, playing techniques, and creative ability to the learner's overall abilities. By applying a weighted decision matrix, the learner's scores on differentiated skill dimensions are multiplied by the corresponding weights, and the results are accumulated to obtain a comprehensive ability score for each learner. The resulting ability assessment results not only provide a quantitative basis for learning path planning and push strategy optimization, but also lay the foundation for the continuous improvement and optimization of teaching effectiveness.

[0088] Suppose a learner submitted a practice recording and music theory test results, where the practice recording feature vector is [0.8 (pitch accuracy), 0.7 (rhythm stability), 0.6 (musical expression)], and the music theory test score is 80 points. In the skill level classification sub-module, K-Means clustering is used to identify the learner as having an intermediate skill level. In the data feature analysis sub-module, the support vector machine and random forest algorithm analyze their playing skills and music theory knowledge, and determine that their music theory knowledge score is 80 points and their playing skills are evaluated as intermediate. In the comprehensive evaluation sub-module, considering that the weights of music theory knowledge and playing skills on overall ability are 0.6 and 0.4 respectively, the learner's comprehensive ability score is 0.680 + 0.4 intermediate level corresponding score, and the final score is 76 points. Detailed ability assessment results are generated for the learner, providing a scientific basis for their subsequent personalized music teaching content push and learning path planning.

[0089] See also Figure 2 and Figure 4 ,The teaching content matching module includes the skill quantification analysis submodule, the ,differentiation identification submodule, and the teaching content priority ,setting submodule;

[0090] The skill quantification analysis submodule uses the K-means clustering algorithm based on the ability assessment results and the Python Scikit-learn library to conduct a quantitative analysis of the learner's skill distribution. By inputting the learner's ability assessment data, including scores on music theory knowledge, playing skills, and creative ability, the module performs clustering using the KMeans function, dividing the learners into differentiated groups based on their skill levels, and generating skill quantification analysis results.

[0091] The differentiation identification submodule uses statistical analysis methods based on the results of skill quantitative analysis, and utilizes Python's Pandas and NumPy libraries to perform differentiated identification of skill levels among learner groups. It uses the Pandas library for data organization and grouping, and the NumPy library for mathematical operations to calculate the mean and standard deviation statistical indicators of the differentiated group skill scores, identify the skill differences among differentiated learner groups, and generate differentiated identification results.

[0092] The teaching content priority setting submodule is based on the differentiated identification results, adopts the hierarchical analysis method, and uses Python's PyAHP library to input the importance of teaching objectives, the difficulty level of teaching content, and the weight of learner preferences. By constructing a judgment matrix and calculating the weight vector, the teaching content priority of learner groups with differentiated skill levels is formulated, and a teaching content matching plan is generated.

[0093] In the skill quantification analysis submodule, the K-Means clustering algorithm is executed through Python's Scikit-learn library to process the learner's ability assessment data. The input data is the score of the learner's music theory knowledge, playing skills and creative ability, formatted as a numerical feature vector. When executing the KMeans function, the preset number of clusters is based on the optimal number of groups determined by the pre-analysis. By setting the init parameter to k-means++, the n_clusters parameter is adjusted according to actual needs to ensure the optimal clustering results. The fit_predict method is used to cluster the learner data, and the learners are divided into different groups according to their skill levels. The learners in each group have similar skill characteristics. The generated skill quantification analysis results provide a scientific basis for the subsequent customization of teaching content and personalized recommendations, ensuring that the teaching strategy matches the learner's actual ability.

[0094] In the differentiation identification submodule, the results of the skill quantitative analysis are processed using the Python Pandas and NumPy libraries. The Pandas library organizes the data, for example, using the DataFrame structure to store skill scores for each group of learners. The groupby method is then used to group learners and categorize them into groups. The NumPy library performs mathematical operations, such as using the mean and std functions to calculate the mean and standard deviation of skill scores for each group, to identify differences in skill levels between learner groups. The resulting differentiation identification results reveal specific differences between groups, providing a basis for developing more targeted teaching strategies.

[0095] In the teaching content prioritization submodule, the Analytic Hierarchy Process (AHP) is applied using the Python PyAHP library to prioritize teaching content. Inputs include the importance of the teaching objectives, the difficulty level of the teaching content, and the weights of learner preferences. These inputs are obtained and formatted using questionnaires or historical data. A judgment matrix is constructed using the PyAHP library, and the library's functionality is leveraged to calculate the weight vector, ensuring consistency and scientificity in the decision-making process. This allows for a quantitative assessment of the contribution of different teaching contents to achieving teaching objectives, generating teaching content matching plans tailored to learner groups with different skill levels, and ensuring the effective allocation and utilization of teaching resources.

[0096] Suppose that three groups of learners have scores for music theory knowledge, performance skills, and creative ability, respectively: [70, 60, 80], [85, 75, 90], and [55, 65, 70]. In the skill quantification analysis submodule, the K-Means clustering algorithm uses a K-Means clustering algorithm with n_clusters set to 3, resulting in the three groups being categorized as 2 beginner, 8th level, and 5th level groups, respectively. In the differentiation identification submodule, calculations reveal that the average music theory knowledge score for the beginner group is 55, the performance skills score is 65, and the creative ability score is 70; the average scores for the intermediate group are 70, 60, and 80, respectively; and the average scores for the advanced group are 85, 75, and 90. In the instructional content prioritization submodule, the instructional objective importance weights are set as 0.5 for music theory, 0.3 for performance, and 0.2 for creative ability. AHP analysis may determine that the advanced group is prioritized for high-difficulty performance skill improvement courses, the intermediate group is prioritized for balanced music theory and performance development courses, and the beginner group is prioritized for basic music theory knowledge. The teaching content matching program ensures that each group receives teaching resources that meet their abilities and needs.

[0097] See also Figure 2 and Figure 5 ,The learning path planning module includes the learning path design ,submodule, the learning preference integration submodule, and the multi-stage path planning ,submodule;

[0098] The learning path design submodule is based on the teaching content matching solution, adopts the Dijkstra algorithm, and uses the NetworkX library to build a graph model. Nodes represent teaching units, and edges represent the logical relationships between teaching units. The add_weighted_edges_from function in the NetworkX library is used to set the weight of the edge to reflect the transition difficulty between teaching units. The dijkstra_path function is used to calculate the shortest path between all nodes and generate the basic path framework.

[0099] The learning preference integration submodule is based on the path-based framework and adopts a collaborative filtering algorithm. It uses the pairwise_distances function in the Scikit-learn library to calculate the similarity between user preference vectors and content features. It adjusts the learning path based on historical behavior data and the preferences of similar users. Through the NearestNeighbors model, it captures teaching content that matches the current learner's preferences and generates a preference adjustment path.

[0100] The multi-stage path planning submodule adjusts the path based on preferences, adopts dynamic programming methods, uses the NumPy library, defines multi-stage learning goals, allocates learning resources, and dynamically adjusts progress parameters according to the learner's current progress and future goals. Through the dynamic programming algorithm, it calculates the multi-stage optimal learning path, including minimizing learning costs and maximizing learning effects, and generates personalized learning path information.

[0101] In the learning path design submodule, a graph model is constructed using Python's NetworkX library to precisely plan learners' learning paths. Nodes in the graph model represent teaching units, such as music theory foundations, harmony, and rhythm practice, while edges represent the logical relationships and transition difficulty between teaching units. In practice, the transition difficulty between teaching units is calculated based on evaluations by educational experts and historical learning data, and edge weights are set in detail using the add_weighted_edges_from function. For example, the transition difficulty from music theory foundations to harmony is 2, and the transition difficulty from harmony to rhythm practice is 1. The dijkstra_path function is used to calculate the shortest path from the starting node to all other nodes, optimizing the learning process and ensuring that learners receive teaching content in the most appropriate order. The resulting path framework provides learners with a clear and logical learning sequence, helping to improve learning efficiency.

[0102] In the learning preference integration submodule, a collaborative filtering algorithm is used to carefully integrate learners' preferences based on the generated path infrastructure. This is achieved by calculating the similarity between the learner's preference vector and the content features of each teaching unit, using the pairwise_distances function in the Scikit-learn library. For example, if a learner has a high interest in harmony but a low interest in rhythm practice, the system analyzes historical behavioral data and the preferences of similar users to identify teaching content that matches this learner's preferences and adjusts the learning path to include more harmony learning content. The NearestNeighbors model ensures that the learning path is not only logical but also tailored to the learner's personal preferences, thereby improving learning motivation and effectiveness.

[0103] In the multi-stage path planning submodule, dynamic programming methods are used to set multi-stage learning goals and allocate learning resources based on the preference-adjusted learning path. The progress parameters of the learning path are dynamically adjusted based on the learner's current learning progress and future learning goals. The NumPy library is used to define multi-stage learning goals. For example, a short-term goal might be to master the basics of music theory, a medium-term goal might be to apply harmonic knowledge, and a long-term goal might be to practice complex rhythmic exercises. By calculating the optimal path to achieve the goal at each stage, the goal is to minimize learning costs while maximizing learning outcomes. The generated personalized learning path information provides a detailed learning plan, including recommended learning materials, expected completion time, and specific learning objectives.

[0104] Suppose a learner has a basic knowledge of music theory and wishes to improve their harmony and composition skills. In the learning path design submodule, a graphical model is constructed based on the teaching units: Music Theory Foundation (A), Harmony (B), Composition Techniques (C), and Rhythm Practice (D), with transition difficulty levels of 2 for A to B, 1 for B to C, and 3 for A to D. Calculations indicate that the recommended path is ABC, aimed at strengthening the learner's harmony and composition skills. In the learning preference integration submodule, analysis of the learner's preferences and historical data reveals that the learner is more interested in composition techniques than harmony. Therefore, the learning path is adjusted to ACB, introducing composition skills earlier. In the multi-stage path planning submodule, based on the learner's current mastery of music theory, the short-term goal is to complete the introductory tutorial on harmony, the medium-term goal is to master basic composition techniques, and the long-term goal is to complete the comprehensive application of advanced harmony and composition skills, ensuring a personalized and practical learning path.

[0105] See also Figure 2 and Figure 6 ,The push strategy optimization module includes a push strategy adjustment submodule, a push strategy learning submodule, and a push strategy implementation submodule;

[0106] The push strategy adjustment submodule uses the Q-learning algorithm based on personalized learning path information and the NumPy library to initialize the Q table, assign initial values to state-behavior pairs, and define a reward mechanism, including increasing rewards for positive feedback from learners on the pushed content and reducing rewards for negative feedback. The learning rate parameter is set to 0.1 and the discount factor is set to 0.9. Through an iterative process, the Q value is updated according to the learner's feedback, and the behavior with the largest Q value is selected as the push strategy to generate the basic push strategy.

[0107] The push policy learning submodule is based on the basic push policy and adopts the policy gradient method. It uses the TensorFlow and Keras libraries to build a network model, including input layer, hidden layer, and output layer. The hidden layer uses the ReLU activation function, and the output layer uses the softmax function to generate probability distribution. The learning rate is set to 0.01, and learner feedback is used as the reward signal. The backpropagation algorithm is used to adjust network parameters and optimize the policy gradient. The learner characteristics and current learning status are input, and the probability distribution of push behavior is output to generate the push policy analysis results.

[0108] The push strategy implementation submodule is based on the push strategy analysis results, adopts the Monte Carlo method, and uses the SciPy library to calculate and sample the probability distribution. By analyzing the learner's current learning progress and preferences, and using the optimized strategy network, it formulates the push content and frequency, including calculating the probability value corresponding to each push content, selecting content with a high probability value as the push option, and analyzing the learner's learning time preference to select the push timing, thereby generating an optimized push strategy.

[0109] In the push strategy adjustment submodule, the push strategy for personalized learning path information is adjusted using the NumPy library and the Q-learning algorithm. An initial Q-table is set, assigning initial values (typically zero) to each state-action pair. A reward mechanism is defined, including increasing rewards for positive feedback on the pushed content and decreasing rewards for negative feedback. The learning rate parameter is set to 0.1, and the discount factor is set to 0.9; these two parameters control the speed of learning and the degree to which future rewards are considered. Through an iterative process, the Q-value is updated based on learner feedback, and the strategy is adjusted by taking actions and observing the results. The action with the largest Q-value is selected as the next push strategy. The resulting basic push strategy provides a quantitative basis for decision-making on subsequent content push, ensuring that content push more closely meets learners' actual needs and preferences.

[0110] In the push policy learning submodule, the policy gradient method is used to further optimize the push policy based on the basic push policy. A neural network model built using the TensorFlow and Keras libraries consists of an input layer, multiple hidden layers, and an output layer. The hidden layers use the ReLU activation function to introduce nonlinearity, and the output layer uses the softmax function to generate the probability distribution of behaviors. The learning rate is set to 0.01, and learner feedback is used as a reward signal. The network parameters are adjusted using the backpropagation algorithm to optimize the policy gradient. The input data includes learner characteristics and the current learning state, and the output data is the probability distribution of push behaviors. The resulting push policy analysis provides more refined and personalized decision support for content push, ensuring that the push content and method best meet learners' needs.

[0111] In the push strategy implementation submodule, Monte Carlo methods are used to implement the optimized push strategy based on the push strategy analysis results. Using the SciPy library to calculate and sample probability distributions, the optimized strategy network is used to determine push content and frequency based on the learner's current learning progress and preferences. This involves calculating the probability of each push content type and selecting high-probability content based on the probability values. Learners' learning time preferences are analyzed to determine the optimal push timing. The resulting optimized push strategy ensures that learning content is delivered in line with learners' preferences and progress, thereby improving learning efficiency and satisfaction.

[0112] Suppose a learner is learning piano. A Q-learning algorithm analyzes the learner's learning behavior and feedback during the learning process. Initially, the Q-value for all piano lesson content pushes is zero. After several rounds of learning, it is found that the learner provides more positive feedback on chord exercises, so the Q-value for chord exercise content pushes is increased. In the push strategy learning submodule, a neural network model optimizes the push strategy based on the learner's feedback. It is found that the learner spends more time studying on weekends, so the push frequency is increased on weekends. In the push strategy implementation submodule, based on the learning and feedback data, a decision is made to push more chord exercise content to the learner on weekends, while reducing the push of rhythm exercise content based on a probability distribution. This adjustment and implementation of the strategy ultimately improves the learner's learning efficiency and satisfaction.

[0113] See also Figure 2 and Figure 7 ,The behavior analysis and prediction module includes a behavior pattern ,analysis submodule, a periodic change analysis submodule, and a behavior ,prediction submodule;

[0114] The behavior pattern analysis submodule uses a long short-term memory network based on an optimized push strategy, and builds a model using the TensorFlow and Keras libraries to analyze learners' music learning interaction data. The module takes the learners' interaction sequence data, including click-through rate, learning time, and frequency, as input. The module sets the number of hidden layer nodes to 128, uses the ReLU activation function, and adopts the Softmax function in the output layer. The module identifies and summarizes learners' behavior patterns, including learning preferences and active time periods. The module also sets the batch size to 32 and the number of iterations to 100 for model training to generate behavior pattern analysis results.

[0115] The cyclical change analysis submodule uses the seasonal decomposition time series method based on the behavioral pattern analysis results. Utilizing the statsmodels library, it performs seasonal decomposition to analyze the cyclical changes in learner behavior. It decomposes the time series data into trend, seasonal, and residual components. Using the seasonal_decompose function, it inputs the learner's interaction time series data and sets the model to an additive one. This reveals the cyclical patterns of learner behavior and generates cyclical change analysis results.

[0116] The behavior prediction submodule adopts the long short-term memory network based on the results of periodic change analysis, adjusts the long short-term memory network to the prediction mode, inputs the behavior pattern and periodic change data, sets the number of hidden layer nodes to 128, uses the sigmoid activation function to match the prediction task, and uses the linear function in the output layer to predict the learner's future behavior and needs and generate behavior prediction results.

[0117] In the behavioral pattern analysis submodule, a long short-term memory network is constructed using the TensorFlow and Keras libraries to analyze learners' music learning interaction data. The input data is formatted as sequence data of learner interactions, including click-through rate, learning time and frequency, and the data is converted into a time series format to adapt to the long short-term memory network. In the model structure, the number of hidden layer nodes is set to 128, and the relu activation function is used to enhance the network's nonlinear fitting ability. The output layer uses the softmax function to summarize the learner's behavior pattern as a probability distribution. During the model training process, the batch size is set to 32 and the number of iterations is set to 100 to ensure that the model can fully learn the data features. The generated behavioral pattern analysis results help identify and summarize learners' learning preferences and active time periods, providing a basis for subsequent personalized push and teaching content adjustments.

[0118] In the cyclical change analysis submodule, based on the behavioral pattern analysis results, a seasonal decomposition time series method is used to analyze cyclical changes in learner behavior. The seasonal_decompose function in the statsmodels library is used to decompose learner interaction time series data into trend, seasonal, and residual components. Input data is formatted as a time series, and the model is set to an additive model to accommodate the characteristics of most teaching interaction data. This reveals cyclical patterns in learner behavior, such as weekly or daily learning patterns. The resulting cyclical change analysis provides in-depth insights into learner behavior and helps optimize the timing of learning content delivery.

[0119] In the behavior prediction submodule, based on the results of cyclical change analysis, the Long Short-Term Memory (LSTM) network was adjusted to a prediction mode, with behavioral patterns and cyclical change data as input. The number of hidden layer nodes was again set to 128, the activation function was changed to a sigmoid to match the characteristics of the prediction task, and a linear function was used in the output layer to predict the learner's future behavior and needs. This enables the LSTM network to predict future behavior based on past behavioral patterns and cyclical changes. The resulting behavior predictions enable personalized learning content and push strategies.

[0120] Suppose a learner's music learning interaction data shows that over the past two months, the learner has been most active on Wednesday nights, with both click-through rates and learning duration exceeding other time periods. In the behavioral pattern analysis submodule, the long short-term memory network model analyzes the learner's time series data, confirms this behavioral pattern, and identifies the learner's preference for harmony learning content. In the cyclical change analysis submodule, seasonal decomposition reveals that the learner's learning activity does show a weekly recurring pattern, especially on Wednesdays. In the behavior prediction submodule, the adjusted long short-term memory network predicts that the learner is likely to maintain similar learning behaviors and preferences in the coming weeks, especially a continued interest in harmony learning. Based on the analysis and prediction results, it is decided to push more harmony learning materials to the learner every Wednesday night to maximize the learner's learning efficiency and satisfaction.

[0121] See also Figure 2 and Figure 8 ,The teaching effect feedback module includes the teaching effect evaluation ,submodule, the teaching adjustment strategy formulation submodule, and the teaching effect improvement ,submodule;

[0122] The teaching effectiveness evaluation submodule uses item response theory and the R language's ltm package to analyze learners' feedback on pushed content based on behavioral prediction results. By inputting learners' response data to differentiated pushed content, including accuracy and response time, and using the grm function to conduct a multi-parameter logical model analysis, it assesses the sensitivity of the learning content to the learners' ability level and the learners' mastery of the target teaching content, thereby generating teaching effectiveness evaluation results.

[0123] The teaching adjustment strategy formulation submodule uses the Markov decision process based on the teaching effectiveness evaluation results and utilizes Python's pymdptoolbox library to optimize the strategy. By inputting teaching effectiveness evaluation information, including learners' mastery of and preferences for differentiated teaching content, the state space is set to the differentiated combination of teaching content, the action space is set to the estimated teaching adjustment measures, and a reward function is set based on the degree of improvement in teaching effectiveness. It then iterates through the mdp.ValueIteration function to capture the optimal teaching adjustment strategy and generate a teaching adjustment strategy plan.

[0124] The teaching effect improvement submodule is based on the teaching adjustment strategy plan, adopts a feedback adjustment algorithm, and uses Python's SciPy library for mathematical optimization. By inputting the difference between the target teaching effect and the current teaching effect, using the minimize function, setting the goal to minimize the difference between the teaching effect and the target, adjusting the difficulty level of the teaching content, changing the teaching methods, and increasing personalized push content to match learners' needs, it generates teaching effect improvement strategy information.

[0125] In the teaching effectiveness evaluation submodule, learners' feedback on differentiated push content was analyzed in detail by employing item response theory and the R language's ltm package. The input data consisted of learners' responses to various push content, including the accuracy rate and response time for each content. These data were formatted for IRT analysis. By executing the grm function in the ltm package, a multi-parameter logistic model analysis was conducted to assess the sensitivity of different learning contents to revealing learners' ability levels, as well as learners' mastery of specific teaching content. The resulting teaching effectiveness evaluation results provide a scientific basis for subsequent teaching adjustments, revealing which teaching content is effective and which needs improvement, thereby making teaching more consistent with learners' actual needs and ability levels.

[0126] In the teaching adjustment strategy formulation submodule, a Markov decision process is used based on the teaching effectiveness evaluation results and the Python pymdptoolbox library for strategy optimization. The input data is teaching effectiveness evaluation information, including learners' mastery of and preferences for differentiated teaching content. The state space is set to differentiated combinations of teaching content, and the action space is set to teaching adjustment measures. The reward function is defined based on the degree of improvement in teaching effectiveness. Using the mdp.ValueIteration function, the strategy is iteratively optimized to capture the optimal teaching adjustment strategy. The resulting teaching adjustment strategy makes the allocation and adjustment of teaching content more personalized and targeted, thereby improving overall teaching efficiency and effectiveness.

[0127] In the teaching effectiveness improvement submodule, a feedback adjustment algorithm and mathematical optimization using the Python SciPy library are employed based on the teaching adjustment strategy plan. Input data includes the difference between the target teaching effect and the current teaching effect. Using the minimize function in the SciPy library, the optimization objective is to minimize the difference between the teaching effect and the target. The difficulty level of the teaching content is adjusted, the teaching methods are varied, and personalized content is added to match learners' needs. The resulting teaching effectiveness improvement strategy information provides clear direction and strategies for the refinement and personalization of teaching content, ensuring that teaching activities more effectively meet learners' needs and improve their learning outcomes.

[0128] Suppose a learner, after studying a series of music theory courses, is found through item response theory analysis to have a significantly lower understanding of harmony than expected. In the teaching effectiveness evaluation sub-module, by analyzing the learner's response data to the harmony content, such as accuracy and response time, specific aspects of the harmony teaching content that need improvement are revealed. In the teaching adjustment strategy formulation sub-module, adjustment strategies are proposed based on the evaluation results, such as strengthening the practical aspects of harmony and reducing the proportion of theoretical explanations. In the teaching effectiveness improvement sub-module, improvement measures are implemented based on the teaching adjustment strategies, such as adjusting the harmony course structure, introducing more case analysis, and providing personalized exercises based on the learner's learning situation. The improved teaching strategy helps to enhance learners' understanding and application capabilities in harmony.

[0129] See also Figure 2 and Figure 9 ,The dynamic adjustment and optimization module includes the learning path adjustment sub-module, the teaching content optimization sub-module, and the teaching dynamic optimization sub-module;

[0130] The learning path adjustment submodule uses dynamic programming algorithms based on teaching effect improvement strategy information and Python's NumPy library to analyze learners' progress and effect feedback. By defining the state as the learner's current knowledge level and learning progress, the action as the learning path adjustment option, and the objective function as maximizing learning efficiency and meeting the learner's personalized needs, it iteratively calculates and updates the state value, captures the optimal learning path, and generates an optimized learning path plan.

[0131] The teaching content optimization submodule is based on the optimization learning path plan, adopts Bayesian networks, and uses Python's pgmpy library to build a model to analyze learners' feedback on teaching content and their demand for changes. By inputting learners' mastery of the current teaching content and feedback on their satisfaction, it calculates the conditional probability of differentiated teaching content adjustment plans, selects content adjustment plans that improve teaching effectiveness, and generates teaching content optimization plans.

[0132] The dynamic teaching optimization submodule is based on the teaching content optimization plan and the learning path optimization plan, combined with teaching effect feedback, and adopts an iterative feedback adjustment algorithm. It uses Python's SciPy library for mathematical optimization and sets the goal of minimizing the difference between teaching content and learner needs through the optimize.minimize function. Through the feedback loop, the teaching strategy is adjusted to match the development of learners' abilities and changes in needs, and the adjusted learning path and teaching content are generated.

[0133] In the learning path adjustment submodule, a dynamic programming algorithm is used to analyze learner progress and feedback using the Python NumPy library to optimize the learning path. Input data is formatted as the learner's current knowledge level and learning progress, converted into a state space, while the action space is defined as optional learning path adjustment options. The objective function aims to maximize learning efficiency and meet the learner's individual needs. Through iterative calculations, the system updates the state value and captures the optimal learning path. The resulting optimized learning path provides a learning roadmap that dynamically adjusts based on learner feedback and progress, ensuring that the learning content and sequence are best adapted to the learner's current needs and abilities, thereby improving learning outcomes.

[0134] In the teaching content optimization submodule, based on the optimized learning path plan, a Bayesian network approach and a model built using the Python pgmpy library were used to analyze learners' feedback on teaching content and their needs for changes. Input data included learners' mastery of and satisfaction with the current teaching content, which was used to calculate the conditional probabilities of different teaching content adjustment plans. By selecting the content adjustment plan that significantly improved teaching effectiveness, the generated teaching content optimization plan provided data support for adjusting and optimizing teaching content, ensuring that the teaching content more closely matched learners' needs, thereby more effectively promoting learners' knowledge acquisition and skill improvement.

[0135] In the dynamic teaching optimization submodule, based on the teaching content optimization plan and the optimized learning path plan, and incorporating teaching effect feedback, an iterative feedback adjustment algorithm is employed, using Python's SciPy library for mathematical optimization. Input data includes the difference between the target teaching effect and the current teaching effect. Using the SciPy library's optimize.minimize function, the goal is to minimize the discrepancy between the teaching content and learner needs. Through a continuous feedback loop, the teaching strategy is adjusted to match the learner's evolving abilities and changing needs. The resulting adjusted learning path and teaching content provide learners with a more personalized and optimized learning experience, ensuring the continuity and adaptability of the teaching strategy, thereby achieving more efficient and effective learning outcomes.

[0136] Suppose a learner in a music theory course demonstrates a lack of mastery of certain topics, such as harmony and rhythmic understanding. In the learning path adjustment submodule, the learner's current learning status and progress are converted into a state space, and the dynamic programming algorithm proposes a plan to adjust the learning path based on the data, such as adding a learning unit on harmony and reducing the music theory knowledge that has already been mastered. In the teaching content optimization submodule, based on the learner's mastery of the harmony content and satisfaction feedback, the Bayesian network model identifies the optimal content adjustment plan to improve teaching effectiveness, such as improving learners' understanding of harmony by adding more interactive exercises. In the teaching dynamic optimization submodule, the teaching strategy is optimized through an iterative feedback adjustment algorithm based on the learner's progress and feedback, ensuring that the teaching content is more in line with the learner's learning needs and abilities, thereby improving learners' learning efficiency and satisfaction.

[0137] See also Figure 2 and Figure 10 ,The personalized recommendation module includes the recommendation strategy optimization ,submodule, the recommendation content adjustment submodule, and the recommendation ,timing optimization submodule;

[0138] The recommendation strategy optimization submodule uses a deep Q-network model based on the adjusted learning path and teaching content, and utilizes the TensorFlow and Keras libraries to build a deep learning model. It inputs learner behavior data and the characteristics of the current teaching content, outputs the value assessment of the recommended action, and evaluates the impact of the recommended action on the learning effect by defining a reward function. The learning rate is set to 0.01 and the discount factor is set to 0.9. The experience replay mechanism is used to improve learning efficiency. The recommendation strategy is optimized through iterative training of the model, generating recommendation strategy optimization results.

[0139] The recommended content adjustment submodule uses Monte Carlo tree search technology and Python's Monte Carlo tree search library to adjust recommended content based on the recommendation strategy optimization results. It simulates differentiated recommendation content selection paths by building a search tree, evaluates the long-term benefits of each option, and selects the optimal recommendation content path by simulating multiple decision-making processes, generating a recommended content adjustment plan.

[0140] The recommendation timing optimization submodule is based on the recommendation content adjustment plan, using the deep Q network model, combined with the learner's learning activity pattern and preferences, using the TensorFlow and Keras libraries, and defining a reward function based on the learner's activity time data and preference information. It rewards the action of recommending when the learner is able to accept new information. The learning rate is set to 0.005 and the discount factor is set to 0.95. The model is trained using the fit function. By identifying the effective time period of the learner's learning activity and the preferred time to receive new content, a personalized recommendation plan is generated.

[0141] In the recommendation strategy optimization submodule, a deep Q-network model is employed and a deep learning model is constructed using the TensorFlow and Keras libraries to analyze learner behavior data and the characteristics of the current instructional content. Input data is formatted to include learner interaction behavior data and instructional content characteristics, such as click-through rate, task completion speed, and accuracy. A reward function is defined to evaluate the impact of recommended actions on learning outcomes. The learning rate and discount factor are set to 0.01 and 0.9, respectively, and an experience replay mechanism is employed to improve learning efficiency. During the iterative model training process, the Q-value is continuously updated based on learner feedback to optimize the recommendation strategy. The resulting optimized recommendation strategy ensures that the recommended content better meets learners' actual needs and improves learning outcomes.

[0142] In the recommendation content adjustment submodule, based on the optimization results of the recommendation strategy, Monte Carlo tree search technology and the Python Monte Carlo tree search library are used to adjust recommended content. A search tree is constructed to simulate different recommendation content selection paths and evaluate the long-term benefits of each choice. By simulating multiple decision-making processes, the optimal recommendation content path is identified. The resulting recommendation content adjustment plan ensures that the recommended teaching content not only meets the learner's current learning status but also maximizes long-term learning benefits.

[0143] In the recommendation timing optimization submodule, based on the recommended content adjustment plan, a deep Q-network model is again used to optimize the recommendations, combined with learners' learning activity patterns and preferences. The model is built using the TensorFlow and Keras libraries, with input data consisting of learners' activity time data and preference information. A reward function is defined to reward recommendations made at the moment when learners are most likely to be receptive to new information. The learning rate is set to 0.005, the discount factor is set to 0.95, and the model is trained using the fit function. The resulting personalized recommendation plan ensures that the recommended content not only meets the learner's needs in terms of content, but also is recommended at a time that best suits the learner's individual learning habits and lifestyle.

[0144] Suppose a learner on a music theory learning platform shows a high interest in improvisation courses but makes slow progress in harmony analysis. In the recommendation strategy optimization submodule, the deep Q network analyzes the learner's behavioral data and course interaction characteristics, identifies the key features of improvisation courses and harmony analysis courses, and adjusts the recommendation strategy to push harmony analysis-related content more frequently. In the recommendation content adjustment submodule, Monte Carlo tree search technology evaluates different recommendation paths and selects a recommendation path that focuses on increasing harmony analysis practice. In the recommendation timing optimization submodule, the deep Q network determines that the best time to recommend harmony analysis content is during the peak learning period of the day based on the learner's learning habits and preferences. The comprehensive application of strategies ensures that learners can receive the right learning content at the right time to promote their learning efficiency and satisfaction.

[0145] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A personalized music teaching content push system, characterized by: The system includes a user ability assessment module, a teaching content matching module, a learning path planning module, a push strategy optimization module, a behavior analysis and prediction module, a teaching effect feedback module, a dynamic adjustment and optimization module, and a personalized recommendation module; The user ability assessment module uses a clustering algorithm to classify learners' skill levels based on the practice recordings, homework and test results submitted by learners, and uses a support vector machine algorithm and a random forest algorithm to perform data feature analysis and assessment on learners' music theory knowledge, playing skills and creative ability to generate ability assessment results; The teaching content matching module uses the K-means clustering algorithm based on the ability assessment results to quantitatively analyze the learner skill distribution, identify learner groups with differentiated skill levels, and analyze the teaching objectives, content difficulty, and learner preferences through the hierarchical analysis method. It then prioritizes the teaching content corresponding to the differentiated skill levels and generates a teaching content matching plan. The learning path planning module uses the Dijkstra algorithm to plan the learning path based on the teaching content matching scheme, and combines the learner's personal preferences and learning progress to design a multi-stage learning path through a dynamic programming method to generate personalized learning path information; The push strategy optimization module uses Q learning and policy gradient methods based on personalized learning path information to adjust the push strategy. It learns and formulates the push strategy through reinforcement learning technology to generate an optimized push strategy. The behavior analysis and prediction module is based on the optimized push strategy, combined with the learner's music learning interaction data, using long short-term memory network and seasonal decomposition time series to analyze the learner's behavior patterns and periodic changes, predict the learner's future behavior and needs, and generate behavior prediction results; The teaching effect feedback module evaluates the teaching effect based on the behavior prediction results and the learners' feedback on the pushed content through item response theory and Markov decision process, and formulates matching teaching adjustment strategies to generate teaching effect improvement strategy information; The dynamic adjustment and optimization module adjusts and optimizes the learning path and teaching content based on the teaching effect improvement strategy information, combined with the teaching effect feedback, using the dynamic programming algorithm and Bayesian network, by analyzing the learner's progress, effect feedback and change needs, and generates the adjusted learning path and teaching content; The personalized recommendation module uses the deep Q network model and Monte Carlo tree search technology to optimize the personalized recommendation strategy based on the adjusted learning path and teaching content. Through the deep learning model, it analyzes the relationship between learners' behavior, preferences and teaching content, adjusts the push timing and content, and generates a personalized recommendation plan; The learning path planning module includes a learning path design submodule, a learning preference integration submodule, and a multi-stage path planning submodule; The learning path design submodule is based on the teaching content matching scheme, adopts the Dijkstra algorithm, and uses the NetworkX library to build a graph model. Nodes represent teaching units, and edges represent the logical relationship between teaching units. The weight of the edge is set by the add_weighted_edges_from function in the NetworkX library to reflect the transition difficulty between teaching units. The dijkstra_path function is used to calculate the shortest path of all nodes and generate a basic path framework. The learning preference integration submodule is based on the path-based framework and adopts a collaborative filtering algorithm. It uses the pairwise_distances function in the Scikit-learn library to calculate the similarity between user preference vectors and content features, adjusts the learning path based on historical behavior data and the preferences of similar users, and uses the NearestNeighbors model to capture teaching content that matches the current learner's preferences and generate a preference adjustment path. The multi-stage path planning submodule adjusts the path based on preferences, adopts dynamic programming methods, uses the NumPy library, defines multi-stage learning goals, allocates learning resources, and dynamically adjusts progress parameters according to the learner's current progress and future goals. Through the dynamic programming algorithm, it calculates the multi-stage optimal learning path, including minimizing learning costs and maximizing learning effects, and generates personalized learning path information; The ability assessment results include music theory knowledge scores, playing skill levels, and creative ability evaluations; the teaching content matching plan includes recommended music theory teaching materials, skill practice repertoires, and creative guidance courses; the personalized learning path information includes stage learning goals, recommended learning materials, and expected completion time; the optimized push strategy includes content push frequency, push time period selection, and content preference type; the behavior prediction results include active learning time periods, content preference analysis results, and potential learning obstacle information; the teaching effect improvement strategy information includes teaching content adjustment plans, learning method optimization plans, and auxiliary material update requirements; the adjusted learning path and teaching content include learning material list information, learning progress schedule, and personalized learning plans; the personalized recommendation plan includes recommended teaching video information, recommended music scores and works, and practice tasks; The user ability assessment module includes a skill level classification submodule, a data feature analysis submodule, and a comprehensive assessment submodule; The skill level classification submodule uses a clustering algorithm based on the practice recordings, homework and test results submitted by learners. It uses the scikit-learn library to perform K-Means clustering, sets the number of clusters, matches the learner ability level classification, uses Euclidean distance for distance calculation, sets the number of iterations to 100, groups the learners, and generates skill level classification results. Based on the skill level classification results, the data feature analysis submodule uses the support vector machine algorithm and the random forest algorithm, using the Python Scikit-learn library to perform data feature analysis on the learner's music theory knowledge, playing skills, and creative ability. By executing the SVC function and the RandomForestClassifier function, key features are extracted from the learner's practice recordings, homework, and test results, factors that affect the learner's skill level are identified, and data feature analysis results are generated; The comprehensive assessment submodule uses a weighted decision matrix method based on the data feature analysis results, combined with Python's NumPy library, to conduct a comprehensive ability assessment analysis. According to the importance of each skill to the learner's overall ability, weights are assigned to the assessment dimensions of music theory knowledge, performance skills, and creative ability, and weight calculations are performed. The weighted decision matrix is applied to multiply the learner's score on the differentiated skill dimension by the corresponding weight, and the cumulative total is used to obtain each learner's comprehensive ability score, generating an ability assessment result. The teaching content matching module includes a skill quantitative analysis submodule, a differentiation identification submodule, and a teaching content priority setting submodule; The skill quantification analysis submodule uses the K-means clustering algorithm based on the ability assessment results and the Python Scikit-learn library to perform a quantitative analysis of the learner's skill distribution. By inputting the learner's ability assessment data, including scores on music theory knowledge, playing skills, and creative ability, the module performs clustering using the KMeans function, dividing the learners into differentiated groups based on their skill levels, and generating skill quantification analysis results. The differentiation identification submodule uses statistical analysis methods based on the results of skill quantitative analysis, and utilizes Python's Pandas library and NumPy library to perform differentiated identification of skill levels among learner groups. The Pandas library is used for data organization and grouping, and the NumPy library is used for mathematical operations to calculate the mean and standard deviation statistical indicators of the differentiated group skill scores, identify the skill differences among differentiated learner groups, and generate differentiated identification results. The teaching content priority setting submodule adopts the hierarchical analysis method based on the differentiation identification results, uses Python's PyAHP library, inputs the importance of teaching objectives, the difficulty level of teaching content and the weight of learner preferences, constructs a judgment matrix and calculates the weight vector, sets the teaching content priority for learner groups with different skill levels, and generates a teaching content matching plan; The push strategy optimization module includes a push strategy adjustment submodule, a push strategy learning submodule, and a push strategy implementation submodule; The push strategy adjustment submodule uses the Q learning algorithm based on personalized learning path information and the NumPy library to set an initial Q table, assign initial values to state-behavior pairs, and define a reward mechanism, including increasing the reward value for learners' positive feedback on the pushed content and reducing the reward value for negative feedback. The learning rate parameter is set to 0.1 and the discount factor is set to 0.

9. Through an iterative process, the Q value is updated according to the learner's feedback, and the behavior with the largest Q value is selected as the push strategy to generate a basic push strategy. The push strategy learning submodule is based on the basic push strategy and adopts the policy gradient method. It uses the TensorFlow and Keras libraries to build a network model, including an input layer, a hidden layer, and an output layer. The hidden layer uses the ReLU activation function, and the output layer uses the softmax function to generate a probability distribution. The learning rate is set to 0.01, and learner feedback is used as a reward signal. Through the backpropagation algorithm, the network parameters are adjusted, the policy gradient is optimized, and the learner characteristics and current learning status are input. The probability distribution of push behavior is output to generate the push strategy analysis results; The push strategy implementation submodule uses the Monte Carlo method and the SciPy library to calculate and sample probability distributions based on the push strategy analysis results. By analyzing the learner's current learning progress and preferences and using the optimized strategy network, it determines the push content and frequency. This includes calculating the probability value corresponding to each push content, selecting content with high probability values as push options, and analyzing the learner's learning time preferences to select the push timing, thereby generating an optimized push strategy. The behavior analysis and prediction module includes a behavior pattern analysis submodule, a periodic change analysis submodule, and a behavior prediction submodule; The behavior pattern analysis submodule is based on an optimized push strategy, adopts a long short-term memory network, and uses the TensorFlow and Keras libraries to build a model to analyze learners' music learning interaction data. The input is the learner's interaction sequence data, including click-through rate, learning time and frequency. The number of hidden layer nodes is set to 128, the relu activation function is used, and the output layer adopts the softmax function. The module identifies and summarizes the learner's behavior pattern, including learning preferences and active time periods. The batch size is set to 32 and the number of iterations is set to 100. The model is trained to generate behavior pattern analysis results. The cyclical change analysis submodule uses the seasonal decomposition time series method based on the behavioral pattern analysis results and the statsmodels library to perform seasonal decomposition and analyze the cyclical changes in learner behavior. The time series data is decomposed into trend, seasonal and residual components. The learner's interaction time series data is input through the seasonal_decompose function, and the model is set to an additive model to reveal the cyclical laws of learner behavior and generate cyclical change analysis results. The behavior prediction submodule uses a long short-term memory network based on the results of periodic change analysis, adjusts the long short-term memory network to a prediction mode, inputs behavior patterns and periodic change data, sets the number of hidden layer nodes to 128, uses a sigmoid activation function to match the prediction task, and uses a linear function in the output layer to predict the learner's future behavior and needs and generate behavior prediction results; The teaching effect feedback module includes a teaching effect evaluation submodule, a teaching adjustment strategy formulation submodule, and a teaching effect improvement submodule; The teaching effectiveness evaluation submodule uses item response theory and the R language's ltm package to analyze the behavior prediction results and evaluate learners' feedback on the pushed content. By inputting learners' response data to differentiated pushed content, including accuracy and response time, the module uses the grm function to perform a multi-parameter logical model analysis to assess the sensitivity of the learning content to the learners' ability level and the learners' mastery of the target teaching content, thereby generating teaching effectiveness evaluation results. The teaching adjustment strategy formulation submodule uses the Markov decision process based on the teaching effect evaluation results and uses Python's pymdptoolbox library to perform strategy optimization. By inputting teaching effect evaluation information, including learners' mastery of and preferences for differentiated teaching content, the state space is set to the differentiated combination of teaching content, the action space is set to the estimated teaching adjustment measures, and a reward function is set according to the degree of improvement in teaching effect. It is iterated through the mdp.ValueIteration function to capture the optimal teaching adjustment strategy and generate a teaching adjustment strategy plan. The teaching effect improvement submodule is based on a teaching adjustment strategy scheme, adopts a feedback adjustment algorithm, and uses Python's SciPy library to perform mathematical optimization. By inputting the difference between the target teaching effect and the current teaching effect, the minimize function is used to set the goal to minimize the difference between the teaching effect and the target. The difficulty level of the teaching content is adjusted, the teaching method is changed, and personalized push content is added to match the learner's needs to generate teaching effect improvement strategy information; The dynamic adjustment and optimization module includes a learning path adjustment submodule, a teaching content optimization submodule, and a teaching dynamic optimization submodule; The learning path adjustment submodule uses a dynamic programming algorithm based on teaching effect improvement strategy information and Python's NumPy library to analyze learners' progress and effect feedback. By defining the state as the learner's current knowledge mastery level and learning progress, the action as the learning path adjustment option, and the objective function as maximizing learning efficiency and meeting the learner's personalized needs, it updates the state value through iterative calculation, captures the optimal learning path, and generates an optimized learning path plan; The teaching content optimization submodule is based on the optimization learning path scheme, adopts Bayesian network, and uses Python's pgmpy library to build a model to analyze learners' feedback on teaching content and their demand for changes. By inputting learners' mastery of the current teaching content and feedback on their satisfaction, it calculates the conditional probability of differentiated teaching content adjustment plans, selects content adjustment plans that improve teaching effectiveness, and generates teaching content optimization plans; The dynamic teaching optimization submodule is based on the teaching content optimization plan and the learning path optimization plan, combined with teaching effect feedback, and adopts an iterative feedback adjustment algorithm. It uses the Python SciPy library to perform mathematical optimization. Through the optimize.minimize function, it sets the goal to minimize the difference between teaching content and learner needs. Through the feedback loop, it adjusts the teaching strategy to match the development of learners' abilities and changes in needs, and generates adjusted learning paths and teaching content. The personalized recommendation module includes a recommendation strategy optimization submodule, a recommendation content adjustment submodule, and a recommendation timing optimization submodule; The recommendation strategy optimization submodule uses a deep Q network model based on the adjusted learning path and teaching content, and uses the TensorFlow and Keras libraries to build a deep learning model. It inputs the learner's behavior data and the characteristics of the current teaching content, outputs the value evaluation of the recommended action, and evaluates the impact of the recommended action on the learning effect by defining a reward function. The learning rate is set to 0.01 and the discount factor is set to 0.

9. The experience replay mechanism is used to improve learning efficiency. The recommendation strategy is optimized through iterative training of the model to generate the recommendation strategy optimization result. The recommended content adjustment submodule uses Monte Carlo tree search technology based on the recommendation strategy optimization results and utilizes Python's Monte Carlo tree search library to adjust recommended content. By constructing a search tree to simulate differentiated recommended content selection paths, the long-term benefits of each option are evaluated. By simulating multiple decision-making processes, the optimal recommended content path is selected and a recommended content adjustment plan is generated. The recommendation timing optimization submodule is based on the recommendation content adjustment plan, uses the deep Q network model, combines the learner's learning activity pattern and preferences, adopts the TensorFlow and Keras libraries, and defines a reward function based on the learner's activity time data and preference information. It rewards the action of recommending when the learner is able to accept new information. The learning rate is set to 0.005 and the discount factor is set to 0.

95. The model is trained using the fit function. By identifying the effective time period of the learner's learning activity and the preferred time to receive new content, a personalized recommendation plan is generated.

Images