Recommendation method and recommendation platform for personalized learning of learner

Abstract

The invention discloses a personalized learning recommendation method for a learner. The method comprises the steps that the learner completes learning style evaluation and learning target setting of the learner; the current learning condition of the learner is subjected to primary research evaluation through the enrollment test module; an initial learner portrait model is established, a learner enters a database for learning, and a learning evaluation module performs staged evaluation on the learning condition of the learner; updating a learner portrait model, and generating a learning path and learning resources adaptive to the learner by using a knowledge graph technology and a reinforcement learning DQN network; updating the learning path database; the new learning path is recommended to the learner; according to the method, the learning data of students in the platform learning process are analyzed to determine the personal basic condition of the students, the learner portrait model is constructed, the knowledge graph technology and the learning recommendation algorithm are utilized to adapt personalized learning features to the learning knowledge element sequence, a personalized learning push path recommendation mode is constructed, and the learning recommendation efficiency is improved. And the learning effect can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a learner personalized learning recommendation method and a recommendation platform thereof. Background Art

[0002] As lifelong learning becomes more popular, most people are improving their abilities through continuous learning. In order to help users learn better, there are many training courses set up for various exams on the market. However, most training courses set up courses for most users. However, each user has different learning interests, cognitive levels, and learning abilities, which will lead to different acceptance levels and learning progress during the learning process, making each user's learning situation uneven, affecting the user's learning efficiency, and also reflecting that the courses or teaching content recommended by such a learning model cannot meet the actual needs of users, affecting their learning effects;

[0003] Even if some platforms are able to launch personalized learning courses, they are unable to make timely adjustments based on the customer's learning situation at different time periods, which will lead to the problem that the teaching content does not match the user's actual situation, seriously affecting their learning results. Therefore, the existing learning system needs to be improved. Summary of the invention

[0004] Purpose of the invention: In order to overcome the above shortcomings, the purpose of the present invention is to provide a personalized learning recommendation method for learners, analyze the learning data of students in the platform learning process to clarify the basic situation of students, and build a learner portrait model, use knowledge graph technology and learning recommendation algorithm to adapt personalized learning features to learning knowledge meta-sequences, and build a personalized learning path recommendation model to help improve learning effects.

[0005] Technical solution: In order to achieve the above-mentioned purpose, the present invention provides a personalized learning recommendation platform, including the following steps:

[0006] Learner interaction interface, which is used as a login port for users to log in to the personalized learning recommendation platform;

[0007] Backstage management interface, used by managers or teachers to log in to the personalized learning recommendation platform port;

[0008] Learning style determination module, used for learning style testing of learners;

[0009] A learning goal setting module is used for learners to set learning goals. The learner interaction interface is connected with the learning style determination module and the learning goal setting module;

[0010] Admission test module, used to test learners’ current learning status;

[0011] Learning process recording module, a module used to record the learner's learning process;

[0012] A learning evaluation module is used to evaluate the collected learning process data of learners, analyze and assess the learning results. The learning evaluation module is bidirectionally connected with the learning process recording module;

[0013] The learner portrait model module is used to establish the learner portrait model and update the learner portrait model according to the learner's later learning situation. The learning style determination module, learning goal setting module, learning process recording module and learning evaluation module are all connected to the learner portrait model module;

[0014] A personalized learning recommendation engine processes the collected user learning data and learning evaluation results to generate a personalized learning recommendation engine for the user, and the personalized learning recommendation engine is connected to the learning evaluation module and the learning process recording module;

[0015] A personalized learning recommendation module, used to provide personalized learning content recommendations and services to users, wherein the personalized learning recommendation content and service module is connected to a personalized learning recommendation engine;

[0016] A learning database is used to provide a data repository for learning-related content. The learning database is connected to the learner portrait model building module, the learning process recording module, the personalized learning recommendation content and service module, and the learning auxiliary tool module, and the personalized learning recommendation engine is bidirectionally connected to the learning database;

[0017] The course content background is a platform for managing all learning content of learners. The course content background is connected with the database and the learning content database in the learning database;

[0018] The knowledge point platform is used to provide the background of knowledge points to the course content background and the knowledge graph in the learning database; it is connected to the knowledge graph in the learning database and the course content background respectively;

[0019] When working, the learner interaction interface, background management interface, learning style determination module, learning goal setting module, entrance test module, learning process recording module, learning assessment module, learning database, course content background and knowledge point platform are the data basis. Every time the learner takes a test in the learning assessment module, the learner portrait model in the personalized learning recommendation platform will be updated in real time. The personalized learning recommendation engine adjusts the recommended learning path and learning content according to the adjusted user portrait model.

[0020] The personalized learning recommendation platform described in the present invention, the learning database includes a learner model database, a learning process database, a learning course database, a learning path database, a learning content database and a knowledge graph, the learner model database, the learning process database, the learning course database, the learning path database, and the learning content database are bidirectionally connected, the learner portrait model establishment module is connected to the learner model database, the learning process recording module is connected to the learning process database, the personalized learning recommendation engine is connected to the learning path database, the learning path database is connected to the personalized learning content recommendation module, the learning content database is connected to the course content background, and the knowledge graph is connected to the knowledge point platform.

[0021] The present invention provides a learner personalized learning recommendation method, and the specific working steps are as follows:

[0022] S1): When learners first enter the personalized learning platform through the learner interaction interface, they must first provide basic personal information and complete registration;

[0023] Afterwards, learners enter the learning style determination module and learning goal setting module respectively under the guidance of the personalized learning platform wizard to complete their own learning style assessment and learning goal setting, including selectively completing the learner's learning style scale questionnaire, filling in a self-description of the learning style and the expected content of the learning goal; and taking the entrance test module to conduct an initial assessment of the learner's current learning situation;

[0024] S2): The manager or educator uses the background management interface to define the knowledge element object structure, teaching strategy, and learning resources through the management component according to the learner's learning goals and teaching structure to establish a knowledge domain model, and store this information in the database; that is, use knowledge graph technology to acquire knowledge, extract knowledge, and use Python code or a large model to align entities, attributes, relationships, and resolve conflicts to complete knowledge integration, establish a logical association between subject knowledge elements and related learning resources, and introduce the established logical association between subject knowledge elements and related learning resources into the subject knowledge graph structure, store this information in the learning content database, and provide data support for the subsequent personalized learning content recommendation to users; S3): The initial learner portrait model is established, that is, the personalized learning recommendation platform constructs a preliminary learner portrait model through the learner portrait model establishment module based on the collected user information; the learner portrait model establishment module processes the collected information and stores it in the user model database;

[0025] S4): The learner enters the database to study, and the learning process recording module records the data of the learner's entire learning process, records the sequence of the learner's accessed pages, learning materials, access time information in real time, and instantly updates the user learning record database;

[0026] S5): The learning assessment module conducts periodic assessments on the learners’ learning status. That is, after each unit of knowledge is learned, the learning assessment module assesses the learners’ learning status recorded by the learning process recording module, and sends the assessment results to the learner portrait model and the personalized learning recommendation engine;

[0027] S6): updating the learner portrait model, that is, updating the learner portrait model according to the evaluation results of the learning evaluation module, and storing the updated learner model in the learner model database;

[0028] S7): Based on the updated learner portrait model and learning process records, the personalized learning recommendation engine calculates the learner's mastery of knowledge elements in real time, generates a learner portrait based on this, and calculates the user's comprehensive feature vector. Then, the knowledge graph technology and the reinforcement learning DQN network are used to adaptively and self-organize the learning path and learning resources that are suitable for the learner based on the calculated user comprehensive feature vector, providing users with accurate personalized learning guidance services;

[0029] S8): Update the learning path database, and store the learning path suitable for the learner newly generated in S7) into the learning path database;

[0030] S9): Personalized learning content recommendation recommends new learning paths to learners from the learning path database;

[0031] S10): Then the learner repeats step 4) to step 9) until all the knowledge points to be learned are completed.

[0032] The learner personalized learning recommendation method described in the present invention, the learner portrait model construction process in S2) is as follows:

[0033] S21): Data collection, collect various data of learners, including learning behavior data (such as learning time, answering status, number of discussions participated, etc.), learning resource interaction data (such as browsed courses, downloaded materials, etc.), test scores, and use association rule algorithms and data mining technology to mine users' learning process data;

[0034] S22): Preprocess the collected data, including cleaning outliers and missing values ​​to ensure data quality. Through attribute matching and feature extraction, combined with learners’ personal attributes and learning styles, various learning portrait modules are integrated using statistical methods to obtain learners’ learning ability, cognitive level, and learning goal portraits.

[0035] S23): Extract the learner's personalized learning features from the three dimensions of learning ability, cognitive level, and learning goals. Use AprioriAll to quantify the feature labels of learning ability, cognitive level, and learning goals to form the learner's learning feature matrix. Each row represents a learner, and each column corresponds to a feature dimension.

[0036] S24): Then, based on the learning feature matrix, a machine learning algorithm (such as a clustering algorithm, a classification algorithm, etc.) is used to group or classify the learners to construct a learner portrait model.

[0037] The reinforcement learning DQN network in the personalized learning recommendation engine makes decisions through the interaction between the agent and the environment, and the decision needs to bring as much reward as possible; the agent here is the personalized learning recommendation engine,

[0038] The environment is the user's status and knowledge graph, and the reward is the benefit of learning effect;

[0039] The specific working process is as follows:

[0040] S61): First, the data is processed to obtain user portrait features.

[0041] The user portrait feature is composed of a learning ability vector c, a cognitive level vector l, and a learning goal vector g. The learning ability vector c, the cognitive level vector l, and the learning goal vector g are calculated respectively, and then the user comprehensive feature vector is processed. The specific process is as follows:

[0042] The following normalization formulas are involved:

[0043]

[0044] Where X min is the minimum value, X max is the maximum value, the purpose is to map the range of data to [0,1];

[0045] The learning ability includes memory, logical reasoning ability, learning speed, and learning concentration:

[0046] The memory dimension is calculated by using the memory-type question score and the total score to calculate the score rate M as an indicator;

[0047]

[0048] Normalization:

[0049]

[0050] The logical reasoning ability dimension uses the score rate L of reasoning questions as an indicator;

[0051]

[0052] Normalization:

[0053]

[0054] Learning speed dimension: the ability of users to effectively complete learning tasks within a unit of time, reflecting the speed at which students accept and master new knowledge; including average learning time, learning concentration

[0055] Average study time:

[0056]

[0057] The learning speed is inversely proportional to the average learning time L kp

[0058]

[0059] Normalization:

[0060]

[0061] Study concentration:

[0062] The learning concentration refers to the ability of students to maintain concentration and avoid distraction during the learning process, reflecting the degree of learning input;

[0063] The main indicators of learning concentration are as follows:

[0064] Continuous learning time period, number of learning interruptions, and other abnormal operations;

[0065] Learning concentration index

[0066]

[0067] Average study time

[0068]

[0069] Learning concentration final score formula

[0070]

[0071] A min and A maxare the minimum and maximum values ​​of the average continuous learning time of users.

[0072] D min and D max are the minimum and maximum values ​​of distraction indicators of all users, respectively;

[0073] Among them, ω1 and ω2 are weights, with a value of 0.5;

[0074] The learning ability matrix is ​​represented by:

[0075] C=[M norm L norm L kp_norm A score ]

[0076] The cognitive levels in the cognitive level vector l are as follows:

[0077]

[0078] Among them, A total is the total score of all tests in the subject for the user; M total is the sum of the full scores of all tests in the subject; l is the ratio of the total score of all tests in the subject to the sum of the full scores of all tests in the subject;

[0079] Normalization:

[0080]

[0081] The learning goal in the learning goal vector g is:

[0082] According to the user's target school and target major, knowledge points are selected from the knowledge graph, and then the proficiency of each knowledge point is calculated based on the target score.

[0083] Assume that the knowledge points obtained by screening according to the target colleges and majors are as follows:

[0084] k=[k1 k2...k n ]

[0085] The weight of each knowledge point is

[0086] ω(k i ), where i is 1…n;

[0087] Normalize the weight of each knowledge point

[0088]

[0089] According to the normalized weight, the target total score S goal Assign to each knowledge point and adjust the base value to ensure that the weight is greater than 1

[0090] S target (k i )=ω′(k i )×(S goal )+1

[0091] The matrix of the user learning target vector g is as follows:

[0092] g=[S target (k1) S target (k2)...S target (ki)]

[0093] Combine the above features to form the user's comprehensive feature vector

[0094] F student =[c, l, g]

[0095] Among them, c is the learning ability vector, l is the cognitive level vector, and g is the learning goal vector;

[0096] Using the comprehensive feature vector F student As clustering features, students are divided into K groups and each student is assigned a cluster label G j (j=1, 2, ..., K), represents the group to which the student belongs, and the cluster label G j As features, incorporated into the state representation of subsequent models;

[0097] S62): Knowledge graph embedding, that is, collecting all knowledge points and constructing a knowledge point set K = k1, k2, ..., k N ;

[0098] The Node2Vec algorithm is used to embed the knowledge points in the knowledge graph into the low-dimensional vector space to obtain the embedding vector e of the i-th knowledge point i ;

[0099] Then add the user's comprehensive feature vector, the embedding vector of the knowledge point, and the student's clustering label to obtain the corresponding user state vector, as follows:

[0100] The user state vector s with the user's comprehensive feature vector added is expressed as follows:

[0101] s=[s1,s2,...,s N ,c,l,g]

[0102] Among them, c is the learning ability vector, l is the cognitive level vector, and g is the learning goal vector; the clustering label G of the students is added j and the embedding vector e of the knowledge point i ,;

[0103] The knowledge point vector is calculated as follows:

[0104]

[0105] in,

[0106] is the mastery level: that is, the students’ i The degree of mastery, range [0,1];

[0107] is the learning frequency: that is, the number of times a student learns knowledge point k i The number of times;

[0108] is the test performance: that is, the student's performance on knowledge point k i Average test scores on

[0109] is the most recent learning time interval: that is, since the last learning of knowledge point k i the time interval since;

[0110] e i Embedding vector of knowledge points;

[0111] f i is a frequent pattern feature;

[0112] Knowledge point k i The support is:

[0113]

[0114] Add the student's cluster label G j The user state vector S after is expressed as follows

[0115] s=[s1,s2,...,s N ,c,l,g,G j ]

[0116] If the user does not fully grasp the knowledge point, the optional action space is as follows:

[0117] A′(s)={k i ∈A(s)|g i >0}

[0118] A(s) is the set of knowledge points that satisfy the prerequisite relationship but are not fully mastered, g i >0 indicates knowledge point k i It is the student’s learning goal;

[0119] Reward learners for completing their learning goals. The specific reward function is as follows

[0120] rt =w(k i )×Δs i ×f(c,l)Δ×G(k i )×PM(k i )×AR(k i )×LF(k i )×FC(k i )

[0121] Among them, w(k i ) is the knowledge point k i Importance weight

[0122] Δs i For students to understand the knowledge point k i Improved mastery

[0123] f(c, l) is the adjustment function of students’ learning ability and cognitive level, as follows:

[0124] f(c,l)=δ1·c+δ2·l, where δ1 and δ2 are weight parameters, with values ​​of 0.7 and 0.3 respectively;

[0125] G(k i ) is the learning objective weighting function

[0126]

[0127] Among them, g i is the i-th element of the student's learning goal vector, indicating the student's understanding of knowledge point k i The degree of learning needs; γ is a constant greater than 1, which is the bonus coefficient for the learning target knowledge points;

[0128] When i >0(Knowledge point k i is the student's learning goal), G(k i ) = γ, the reward is amplified by γ times (usually 1.2-2.0), and the expected reward for selecting this knowledge point is submitted. The personalized learning recommendation engine is more inclined to recommend this knowledge point;

[0129] When i =0, G(k i )=1, the reward remains unchanged, and the personalized learning recommendation engine will not be particularly biased towards recommending this knowledge point;

[0130] PM(k i ) is a frequent pattern weighting function, which adjusts the reward according to the importance of the knowledge point in the frequent item set, reflecting the importance of the knowledge point in the learning group, as follows:

[0131] PM(k i)=1+λ PM ×Support(k i )

[0132] Among them, λ PM To adjust the parameter, the degree of influence on the reward, usually a small positive number such as 0.1 or 0.2;

[0133] Support(k i ) is the knowledge point k i The support degree of k i Frequency of occurrence in frequent itemsets;

[0134] By considering the frequency of occurrence of knowledge points in frequent learning patterns, the personalized learning recommendation engine is guided to recommend knowledge points that are commonly learned in the group;

[0135] In the association rule algorithm, AR(k i )The association rule weighting function is:

[0136] AR(k i )=1+λ AR ×Conf(k i )

[0137] Among them, λ AR To adjust the parameters, control the influence of association rules on rewards, and usually take a positive value;

[0138] Conf(k i )Knowledge point k i The highest confidence in the association rule, denoted by k i The strength of the connection with the knowledge points already learned;

[0139] Using the knowledge learned: By considering k i The association with the knowledge points that students have already learned guides the model to recommend knowledge points that are closely related to what has been learned, thus promoting the coherent learning of knowledge;

[0140] LF(k i )The learning frequency adjustment function is

[0141]

[0142] Among them, λ LF Take w(k i ), the more important the knowledge point is, the smaller the reduced reward is;

[0143] As the learning frequency increases, the function value will gradually decrease, reducing the contribution to the reward and preventing students from excessively repeating familiar knowledge points;

[0144] Forgetting Curve Adjustment Function

[0145]

[0146] Among them, λ FC Take the proportional function of the knowledge point weight, with a value range of 0.5-1; when Increase or decrease to remind students that they need to review this knowledge point;

[0147] S63): Reinforce the learning DQN network to update the network parameters, as follows:

[0148] Input layer: user state vector s

[0149] Output layer: the Q value of each optional action (the Q value is the mathematical expectation of the sum of all future state returns);

[0150] The DQN algorithm network training steps are as follows:

[0151] A. Status acquisition: Get the current status s t ;

[0152] B. Action selection: According to the ∈ greedy strategy, select an action from the set of optional actions;

[0153] C. Execution action: Students learn knowledge points, update their mastery level, and obtain a new state s t+1 ;

[0154] D. Reward calculation: Calculate the immediate reward based on the reward function;

[0155] E. Experience storage: t , a t , r t ,s t+1 ) is stored in the experience replay pool;

[0156] F. Network update: Randomly extract small batches of samples (s j , a j , r j ,s j+1 )

[0157] Conduct training and update network parameters;

[0158] The real-time recommendation process through the recommendation engine is as follows:

[0159] Status acquisition: Get the student's current user status S;

[0160] Action selection: Select the best knowledge point from A′(s) according to the ∈ greedy strategy;

[0161] Knowledge point recommendation: recommend knowledge points to students and provide corresponding learning resources

[0162] S64): Provide feedback and update on learners through user feedback collection, as follows:

[0163] Learning feedback collection: record students’ learning results of recommended knowledge points, update their mastery level, learning frequency, and recent learning time;

[0164] User status update: Update the student's user status S based on learning feedback

[0165] Reinforcement learning DQN network update: Regularly train the reinforcement learning DQN network, incorporate new learning data, and improve model performance;

[0166] Add learner feedback to the experience replay pool

[0167] In reinforcement learning, experience samples are usually represented in the form of four tuples:

[0168] {s t , a t , r t ,s t+1 ) To incorporate students’ feedback into the experience sample, the structure of the experience sample needs to be expanded to include feedback information:

[0169] (s t , a t , r t′ ,s t+1 , f t )

[0170] r t′ Adjusted instant rewards, taking into account student feedback

[0171] f t The student performs action a at time step t t Feedback

[0172] If the student's feedback is positive, increase the reward immediately

[0173] r t′ =r t +δr

[0174] If negative, reduce the reward

[0175] r t′ =r t -δr.

[0176] The learner personalized learning recommendation method described in the present invention, the specific process of constructing the learning path recommendation model in S7) is as follows:

[0177] S601): The learning feature representation is based on the subject knowledge graph, and the subject knowledge elements and related learning resources are extracted using the association rule algorithm to form the learning element of the knowledge graph, which is represented by a triple L = (Ki, Kj, r);

[0178] Among them, r represents the logical relationship between knowledge element Ki and learning resource Kj;

[0179] Then, using knowledge graph technology, we serialize and annotate the attributes of subject knowledge elements and related learning resources, characterize and describe the basic characteristics of learning elements;

[0180] Combined with the learning needs of learners, the learning elements of the learning activity process are formed into a learning element sequence (s1, s2, ..., s N );

[0181] At this time, the user status S is expressed as follows:

[0182] s=[s1 s2...s N ]

[0183] S602): Recommend learning paths, based on the user's current learning state matrix and the prior relationship of knowledge points in the knowledge graph, recommend the next knowledge point with the maximum reward and the corresponding learning materials;

[0184] S603): Learning path evaluation and optimization: During the learning process, learners complete tasks based on the learning paths and resources recommended by personalized learning, and submit feedback on their learning experience and results. The personalized learning recommendation engine collects and analyzes user feedback, combines the learners' goal completion status, compares the expert path with the recommended path, and evaluates the accuracy and practicality of the recommendation;

[0185] Based on evaluation results and user feedback, we continuously optimize the personalized learning recommendation engine to continuously improve the effectiveness of personalized recommendations and user satisfaction.

[0186] In the learner personalized learning recommendation method described in the present invention, the knowledge extraction using the knowledge graph technology in S3) follows the following rules, which are as follows:

[0187] S31): Template-based rules such as regular expression rules, template matching;

[0188] S32): Syntactic and lexical analysis rules: HanLP (Chinese processing library, supports part-of-speech tagging and word segmentation), spaCy (provides fast part-of-speech tagging, Stanford NLP (part-of-speech tagging, supports multiple languages)

[0189] S33): context-dependent rules;

[0190] S34): Statistical learning rules;

[0191] The specific method of establishing the logical association between subject knowledge elements and related learning resources is as follows: first classify and annotate learning resources, which can be divided into textbooks, exercises, videos, cases, experiments and extracurricular materials. Each resource has clear metadata to describe its association with knowledge elements;

[0192] Create a labeling system for knowledge elements and learning resources, ensure the accuracy of logical associations through manual and automatic labeling (natural language processing or large models, analyze text content, extract knowledge elements or label entities), and perform manual verification.

[0193] The specific processing process of the statistical algorithm is as follows:

[0194] S2121): User personal attribute analysis stage:

[0195] Descriptive statistics: Descriptive statistical analysis is performed on learners’ personal attribute data, such as calculating the mean, median, and standard deviation of age and education level; this can help understand the distribution of basic characteristics of the learner group. For example, the average age of learners is 20 years old, and the education level is mainly undergraduate.

[0196] Correlation analysis: Use correlation analysis methods, such as the Pearson correlation coefficient and the Spearman correlation coefficient, to analyze the relationship between personal attributes and learning behavior; for example, study whether there is a correlation between age and learning time, and whether there is a significant correlation between academic qualifications and the accuracy of answering questions;

[0197] S2122): Learning style identification stage:

[0198] Behavioral indicator statistics: Statistical analysis of learners’ learning behavior data is performed to calculate various behavioral indicators. For example, statistics are collected on the number of times learners repeatedly learn the same content, the number of different learning resources they browse, and the frequency of their participation in discussions. These behavioral indicators can be used as characteristics of learning styles and input into subsequent analysis.

[0199] Cluster analysis: Use clustering algorithms, such as K-Means clustering and hierarchical clustering, to perform cluster analysis on learners’ behavioral indicators and language characteristics to discover different learning style groups; for example, learners can be divided into “active” (active learning behavior, rich language expression),

[0200] Different groups such as “conservative and stable” (learning behavior is more regular, language is concise and clear);

[0201] S2123): Integrated learning portrait module stage:

[0202] Feature fusion statistics: When fusing personal attribute features and learning style features, statistical methods can be used to determine the weights of different features. For example, the importance scores of each feature can be calculated through dimensionality reduction methods such as principal component analysis (PCA), and then the weight distribution during fusion can be determined based on the scores;

[0203] Portrait evaluation statistics: Use statistical indicators to evaluate the accuracy and effectiveness of learning portraits. For example, you can calculate indicators such as the consistency ratio between the learning style predicted by the portrait and the actual learning style, the accuracy of personalized recommendations, etc. to evaluate the quality and practicality of the portrait.

[0204] It can be seen from the above technical solution that the present invention has the following beneficial effects:

[0205] 1. The personalized learning recommendation platform of the present invention constructs a learner portrait model based on the user's current actual learning situation and set goals, combined with learning ability, learning level, learning interest, and learning style, records the learning process data through the learning process database, and conducts timely evaluation through the learning evaluation module, and adjusts the learning content in a timely manner according to the evaluation results.

[0206] Analyze the learning data generated by students during the learning process on the platform to clarify their basic personal information and build a learner portrait model. By combining subject knowledge graphs, using knowledge graph technology and learning recommendation algorithms, the personalized learning features are adapted to the learning knowledge element sequence, search and optimize the sequence combination of subject knowledge elements, and build a learning path recommendation model to provide different personalized learning recommendations to different students, helping them improve their learning outcomes.

[0207] 2. The knowledge graph of the present invention provides a visual and structured way to present knowledge and decision-making processes. By embedding the knowledge graph into the framework of deep reinforcement learning, the decision-making interpretability of the system can be enhanced, so that learners and system managers can understand the logic and basis behind the recommended learning path and strategy selection. The knowledge graph can also provide a global explanation for the overall strategy learning process, that is, the system can display the relationship between all knowledge points through the knowledge graph and explain the recommended strategy for the entire learning path.

[0208] 3. The present invention can dynamically adjust the difficulty and progress of learning materials according to the learner's performance, promote the improvement of learning efficiency, and ensure that learners can master the necessary knowledge and skills.

[0209] 4. The machine learning in the present invention can automatically adjust the recommendation strategy through algorithms, and continuously improve the quality of recommendations over time; it supports the modeling of nonlinear relationships and can process complex learning behavior data; it can also automatically identify which factors have the greatest impact on learning outcomes, and optimize recommendations accordingly to better meet user needs.

[0210] 5. The data processing in the present invention supports the storage and rapid query of massive data, ensuring the response speed of the recommendation system; by analyzing large-scale data sets, potential learning trends and patterns are discovered. BRIEF DESCRIPTION OF THE DRAWINGS

[0211] Figure 1 It is a structural schematic diagram of the learner personalized learning recommendation method of the present invention;

[0212] Figure 2 It is a schematic diagram of the learner portrait model in the present invention;

[0213] Figure 3 A framework diagram of the learner personalized learning recommendation method in the present invention;

[0214] Figure 4 A working step diagram of the recommendation method of the learner personalized learning recommendation method in the present invention;

[0215] Figure 5 This is an algorithm flow chart of the reinforcement learning DQN network in the present invention. DETAILED DESCRIPTION

[0216] The present invention is further explained below in conjunction with the accompanying drawings and specific embodiments.

[0217] Example

[0218] like Figures 1 to 3 A personalized learning recommendation platform is shown, comprising:

[0219] Learner interaction interface, which is used as a login port for users to log in to the personalized learning recommendation platform;

[0220] Backstage management interface, used by managers or teachers to log in to the personalized learning recommendation platform port;

[0221] Learning style determination module, used for learning style testing of learners;

[0222] A learning goal setting module is used for learners to set learning goals. The learner interaction interface is connected with the learning style determination module and the learning goal setting module;

[0223] Admission test module, used to test learners’ current learning status;

[0224] Learning process recording module, a module used to record the learner's learning process;

[0225] A learning evaluation module is used to evaluate the collected learning process data of learners, analyze and assess the learning results. The learning evaluation module is bidirectionally connected with the learning process recording module;

[0226] The learner portrait model module is used to establish the learner portrait model and update the learner portrait model according to the learner's later learning situation. The learning style determination module, learning goal setting module, learning process recording module and learning evaluation module are all connected to the learner portrait model module;

[0227] A personalized learning recommendation engine processes the collected user learning data and learning evaluation results to generate a personalized learning recommendation engine for the user, and the personalized learning recommendation engine is connected to the learning evaluation module and the learning process recording module;

[0228] A personalized learning recommendation module, used to provide personalized learning content recommendations and services to users, wherein the personalized learning recommendation content and service module is connected to a personalized learning recommendation engine;

[0229] A learning database is used to provide a data repository for learning-related content. The learning database is connected to the learner portrait model building module, the learning process recording module, the personalized learning recommendation content and service module, and the learning auxiliary tool module, and the personalized learning recommendation engine is bidirectionally connected to the learning database;

[0230] The course content background is a platform for managing all learning content of learners. The course content background is connected with the database and the learning content database in the learning database;

[0231] The knowledge point platform is used to provide the background of knowledge points to the course content background and the knowledge graph in the learning database; it is connected to the knowledge graph in the learning database and the course content background respectively;

[0232] When working, the learner interaction interface, background management interface, learning style determination module, learning goal setting module, entrance test module, learning process recording module, learning assessment module, learning database, course content background and knowledge point platform are the data basis. Every time the learner takes a test in the learning assessment module, the learner portrait model in the personalized learning recommendation platform will be updated in real time. The personalized learning recommendation engine adjusts the recommended learning path and learning content according to the adjusted user portrait model.

[0233] The learning database described in this embodiment includes a learner model database, a learning process database, a learning course database, a learning path database, a learning content database and a knowledge graph. The learner model database, the learning process database, the learning course database, the learning path database and the learning content database are bidirectionally connected to each other. The learner portrait model establishment module is connected to the learner model database, the learning process recording module is connected to the learning process database, the personalized learning recommendation engine is connected to the learning path database, the learning path database is connected to the personalized learning content recommendation module, the learning content database is connected to the course content background, and the knowledge graph is connected to the knowledge point platform.

[0234] Example 2

[0235] The personalized learning recommendation method for learners described in this embodiment, wherein the personalized learning recommendation platform is the same as that in Embodiment 1,

[0236] A learner personalized learning recommendation method, the specific working steps are as follows:

[0237] S1): When learners first enter the personalized learning platform through the learner interaction interface, they must first provide basic personal information and complete registration;

[0238] Afterwards, learners enter the learning style determination module and learning goal setting module respectively under the guidance of the personalized learning platform wizard to complete their own learning style assessment and learning goal setting, including selectively completing the learner's learning style scale questionnaire, filling in a self-description of the learning style and the expected content of the learning goal; and taking the entrance test module to conduct an initial assessment of the learner's current learning situation;

[0239] S2): The manager or educator uses the background management interface to define the knowledge element object structure, teaching strategy, and learning resources through the management component according to the learner's learning goals and teaching structure to establish a knowledge domain model, and store this information in the database; that is, use the knowledge graph technology to acquire knowledge, extract knowledge, and use Python code or a large model to align entities, attributes, relationships, and resolve conflicts to complete knowledge integration, establish a logical association between subject knowledge elements and related learning resources, and introduce the established logical association between subject knowledge elements and related learning resources into the subject knowledge graph structure, store this information in the learning content database, and provide data support for providing personalized learning content recommendations to users in the future;

[0240] S3): Initial learner portrait model establishment, that is, the personalized learning recommendation platform builds a preliminary learner portrait model through the learner portrait model establishment module according to the collected user information; the learner portrait model establishment module processes the collected information and stores it in the user model database;

[0241] S4): The learner enters the database to study, and the learning process recording module records the data of the learner's entire learning process, records the sequence of the learner's accessed pages, learning materials, access time information in real time, and instantly updates the user learning record database;

[0242] S5): The learning assessment module conducts periodic assessments on the learners’ learning status. That is, after each unit of knowledge is learned, the learning assessment module assesses the learners’ learning status recorded by the learning process recording module, and sends the assessment results to the learner portrait model and the personalized learning recommendation engine;

[0243] S6): updating the learner portrait model, that is, updating the learner portrait model according to the evaluation results of the learning evaluation module, and storing the updated learner model in the learner model database;

[0244] S7): Based on the updated learner portrait model and learning process records, the personalized learning recommendation engine calculates the learner's mastery of knowledge elements in real time, generates a learner portrait based on this, and calculates the user's comprehensive feature vector. Then, the knowledge graph technology and the reinforcement learning DQN network are used to adaptively and self-organize the learning path and learning resources that are suitable for the learner based on the calculated user comprehensive feature vector, providing users with accurate personalized learning guidance services;

[0245] S8): updating the learning path database, storing the learning path suitable for the learner newly generated in S7) into the learning path database;

[0246] S9): Personalized learning content recommendation recommends new learning paths to learners from the learning path database;

[0247] S10): Then the learner repeats step 4) to step 9) until all the knowledge points to be learned are completed.

[0248] In the learning cycle, according to the evaluation results of the learning path, the reinforcement learning DQN network is used to adaptively adjust the learning recommendation strategy in the personalized learning recommendation platform by combining deep reinforcement learning and knowledge graph, so as to realize the iterative optimization of personalized learning path recommendation.

[0249] The learner portrait model process in S2) in this embodiment is as follows:

[0250] The learner portrait model construction process in S2) is as follows:

[0251] S21): Data collection, collect various data of learners, including learning behavior data (such as learning time, answering status, number of discussions participated, etc.), learning resource interaction data (such as browsed courses, downloaded materials, etc.), test scores, and use association rule algorithms and data mining technology to mine users' learning process data;

[0252] S22): Preprocess the collected data, including cleaning outliers and missing values ​​to ensure data quality. Through attribute matching and feature extraction, combined with learners’ personal attributes and learning styles, various learning portrait modules are integrated using statistical methods to obtain learners’ learning ability, cognitive level, and learning goal portraits.

[0253] S23): Extract the learner's personalized learning features from the three dimensions of learning ability, cognitive level, and learning goals. Use AprioriAll to quantify the feature labels of learning ability, cognitive level, and learning goals to form the learner's learning feature matrix. Each row represents a learner, and each column corresponds to a feature dimension.

[0254] S24): Then, based on the learning feature matrix, a machine learning algorithm (such as a clustering algorithm, a classification algorithm, etc.) is used to group or classify the learners to construct a learner portrait model.

[0255] In the personalized learning recommendation method for learners described in this embodiment, the reinforcement learning DQN network in the personalized learning recommendation engine makes decisions through the interaction between the agent and the environment, and the decision needs to bring as many rewards as possible; the agent here is the personalized learning recommendation engine, the environment is the user's state and knowledge graph, and the reward is the income of the learning effect;

[0256] The specific working process is as follows:

[0257] S61): First, the data is processed to obtain user portrait features.

[0258] The user portrait feature is composed of a learning ability vector c, a cognitive level vector l, and a learning goal vector g. The learning ability vector c, the cognitive level vector l, and the learning goal vector g are calculated respectively, and then the user comprehensive feature vector is processed. The specific process is as follows:

[0259] The following normalization formulas are involved:

[0260]

[0261] Where X min is the minimum value, X maxis the maximum value, the purpose is to map the range of data to between [0,1];

[0262] The learning ability includes memory, logical reasoning ability, learning speed, and learning concentration:

[0263] The memory dimension is calculated by using the memory-type question score and the total score to calculate the score rate M as an indicator;

[0264]

[0265] Normalization:

[0266]

[0267] The logical reasoning ability dimension uses the score rate L of reasoning questions as an indicator;

[0268]

[0269] Normalization:

[0270]

[0271] Learning speed dimension: the ability of users to effectively complete learning tasks within a unit of time, reflecting the speed at which students accept and master new knowledge; including average learning time, learning concentration

[0272] Average study time:

[0273]

[0274] The learning speed is inversely proportional to the average learning time L kp

[0275]

[0276] Normalization:

[0277]

[0278] Study concentration:

[0279] The learning concentration refers to the ability of students to maintain concentration and avoid distraction during the learning process, reflecting the degree of learning input;

[0280] The main indicators of learning concentration are as follows:

[0281] Continuous learning time period, number of learning interruptions, and other abnormal operations;

[0282] Learning concentration index

[0283]

[0284] Average study time

[0285]

[0286] Learning concentration final score formula

[0287]

[0288] A min and A max are the minimum and maximum values ​​of the average continuous learning time of users.

[0289] D min and D max are the minimum and maximum values ​​of distraction indicators of all users, respectively;

[0290] Among them, ω1 and ω2 are weights, with a value of 0.5;

[0291] The learning ability matrix is ​​represented by:

[0292] C=[M norm L norm L kp_norm A score ]

[0293] The cognitive levels in the cognitive level vector l are as follows:

[0294]

[0295] Among them, A total is the total score of all tests in the subject for the user; M total is the sum of the full scores of all tests in the subject; l is the ratio of the total score of all tests in the subject to the sum of the full scores of all tests in the subject;

[0296] Normalization:

[0297]

[0298] The learning goal in the learning goal vector g is:

[0299] According to the user's target school and target major, knowledge points are selected from the knowledge graph, and then the proficiency of each knowledge point is calculated based on the target score.

[0300] Assume that the knowledge points obtained by screening according to the target colleges and majors are as follows:

[0301] k=[k1 k2...k n ]

[0302] The weight of each knowledge point is

[0303] ω(ki ), where i is 1....n;

[0304] Normalize the weight of each knowledge point

[0305]

[0306] According to the normalized weight, the target total score S goal Assign to each knowledge point and adjust the base value to ensure that the weight is greater than 1

[0307] S target (k i )=ω′(k i )×(S goal )+1

[0308] The matrix of the user learning target vector g is as follows:

[0309] g=[S target (k1) S target (k2)...S target (ki)]

[0310] Combine the above features to form the user's comprehensive feature vector

[0311] F student =[c, l, g]

[0312] Among them, c is the learning ability vector, l is the cognitive level vector, and g is the learning goal vector;

[0313] Using the comprehensive feature vector F student As clustering features, students are divided into K groups and each student is assigned a cluster label G j (j=1, 2, ..., K), represents the group to which the student belongs, and the cluster label G j As features, incorporated into the state representation of subsequent models;

[0314] S62): Knowledge graph embedding, that is, collecting all knowledge points and constructing a knowledge point set K = k1k2, ..., k N ;

[0315] The Node2Vec algorithm is used to embed the knowledge points in the knowledge graph into the low-dimensional vector space to obtain the embedding vector e of the i-th knowledge point i ;

[0316] Then add the user's comprehensive feature vector, the embedding vector of the knowledge point, and the student's clustering label to obtain the corresponding user state vector, as follows:

[0317] The user state vector S with the user's comprehensive feature vector added is expressed as follows:

[0318] s=[s1,s2,...,s N ,c,l,g]

[0319] Among them, c is the learning ability vector, l is the cognitive level vector, and g is the learning goal vector;

[0320] The embedding vector e of the knowledge point is added i After that, the knowledge point vector is calculated as follows:

[0321]

[0322] in,

[0323] is the mastery level: that is, the students’ i The degree of mastery, range [0,1];

[0324] is the learning frequency: that is, the number of times a student learns knowledge point k i The number of times;

[0325] is the test performance: that is, the student's performance on knowledge point k i Average test scores on

[0326] is the most recent learning time interval: that is, since the last learning of knowledge point k i the time interval since;

[0327] e i Embedding vector of knowledge points;

[0328] f i is a frequent pattern feature;

[0329] It should be noted that is the detailed composition of the column data in the above formula, which is the transposition of the column data, just converting the original column into a row. Substituting i=1 into the formula below, it can be understood as: the entire formula is the first column S1 of the above formula, and the first row of S1 is the mastery level, the second row is the learning frequency, and the fifth row is the knowledge point embedding vector e i .

[0330] Knowledge point k i The support is:

[0331]

[0332] Add the student's cluster label G j The user state vector S after is expressed as follows

[0333] s=[s1,s2,...,sN ,c,l,g,G j ]

[0334] If the user does not fully grasp the knowledge point, the optional action space is as follows:

[0335] A′(s)={k i ∈A(s)|g i >0}

[0336] A(s) is the set of knowledge points that satisfy the prerequisite relationship but are not fully mastered, g i >0 indicates knowledge point k i It is the student’s learning goal;

[0337] Reward learners for completing their learning goals. The specific reward function is as follows

[0338] r t =w(k i )×Δs i ×f(c,l)×G(k i )×PM(k i )×AR(k i )×LF(k i )×FC

[0339] Among them, w(k i ) is the knowledge point k i Importance weight

[0340] Δs i For students to understand the knowledge point k i Improved mastery

[0341] f(c, l) is the adjustment function of students’ learning ability and cognitive level, as follows:

[0342] f(c,l)=δ1·c+δ2·l, where δ1 and δ2 are weight parameters, with values ​​of 0.7 and 0.3 respectively;

[0343] G(k i ) is the learning objective weighting function

[0344]

[0345] Among them, g i is the i-th element of the student's learning goal vector, indicating the student's understanding of knowledge point k i The degree of learning needs; γ is a constant greater than 1, which is the bonus coefficient for the learning target knowledge points;

[0346] When i >0(Knowledge point k i is the student's learning goal), G(ki ) = γ, the reward is amplified by γ times (usually 1.2-2.0), and the expected reward for selecting this knowledge point is submitted. The personalized learning recommendation engine is more inclined to recommend this knowledge point;

[0347] When i =0, G(k i )=1, the reward remains unchanged, and the personalized learning recommendation engine will not be particularly biased towards recommending this knowledge point;

[0348] PM(k i ) is a frequent pattern weighting function, which adjusts the reward according to the importance of the knowledge point in the frequent item set, reflecting the importance of the knowledge point in the learning group, as follows:

[0349] PM(k i )=1+λ PM ×Support(k i )

[0350] Among them, λ PM To adjust the parameters, the degree of influence on the reward is usually a small positive number.

[0351] Such as 0.1 or 0.2;

[0352] Support(k i ) is the knowledge point k i The support degree of k i Frequency of occurrence in frequent itemsets;

[0353] By considering the frequency of occurrence of knowledge points in frequent learning patterns, the personalized learning recommendation engine is guided to recommend knowledge points that are commonly learned in the group;

[0354] In the association rule algorithm, AR(k i )The association rule weighting function is:

[0355] AR(k i )=1+λ AR ×Conf(k i )

[0356] Among them, λ AR To adjust the parameters, control the influence of association rules on rewards, and usually take a positive value;

[0357] Conf(k i )Knowledge point k i The highest confidence in the association rule, denoted by k i The strength of the connection with the knowledge points already learned;

[0358] Using the knowledge learned: By considering k iThe association with the knowledge points that students have already learned guides the model to recommend knowledge points that are closely related to what has been learned, thus promoting the coherent learning of knowledge;

[0359] LF(k i )The learning frequency adjustment function is

[0360]

[0361] Among them, λ LF Take w(k i ), the more important the knowledge point is, the smaller the reduced reward is;

[0362] As the learning frequency increases, the function value will gradually decrease, reducing the contribution to the reward and preventing students from excessively repeating familiar knowledge points;

[0363] FC(k i ) Forgetting curve adjustment function

[0364]

[0365] Among them, λ FC Take the proportional function of the knowledge point weight, with a value range of 0.5-1; when Increase, and the reward decreases, prompting students to review this knowledge point;

[0366] S63): Reinforce the learning DQN network to update the network parameters, as follows:

[0367] Input layer: user state vector s

[0368] Output layer: the Q value of each optional action (the Q value is the mathematical expectation of the sum of all future state returns);

[0369] The DQN algorithm network training steps are as follows:

[0370] A. Status acquisition: Get the current status S t ;

[0371] B. Action selection: According to the ∈ greedy strategy, select an action from the set of optional actions;

[0372] C. Execution action: Students learn knowledge points, update their mastery level, and obtain a new state s t+1 ;

[0373] D. Reward calculation: Calculate the immediate reward based on the reward function;

[0374] E. Experience storage: t , a t , r t ,s t+1 ) is stored in the experience replay pool;

[0375] F. Network update: Randomly extract small batches of samples (s j ,s j , r j ,s j+1 )

[0376] Conduct training and update network parameters;

[0377] The real-time recommendation process through the recommendation engine is as follows:

[0378] Status acquisition: Get the student's current user status S;

[0379] Action selection: Select the best knowledge point from A′(s) according to the ∈ greedy strategy;

[0380] Knowledge point recommendation: recommend knowledge points to students and provide corresponding learning resources

[0381] S64): Provide feedback and update on learners through user feedback collection, as follows:

[0382] Learning feedback collection: record students’ learning results of recommended knowledge points, update their mastery level, learning frequency, and recent learning time;

[0383] User status update: Update the student's user status based on learning feedback

[0384] Reinforcement learning DQN network update: Regularly train the reinforcement learning DQN network, incorporate new learning data, and improve model performance;

[0385] Add learner feedback to the experience replay pool

[0386] In reinforcement learning, experience samples are usually represented in the form of four tuples:

[0387] (s t , a t , r t ,s t+1 ) To incorporate students’ feedback into the experience sample, the structure of the experience sample needs to be expanded to include feedback information:

[0388] (s t , a t , r t′ ,s t+1 , f t )

[0389] r t′ Adjusted instant rewards, taking into account student feedback

[0390] f tThe student performs action a at time step t t Feedback

[0391] If the student's feedback is positive, increase the reward immediately

[0392] r t′ =r t +δr

[0393] If negative, reduce the reward

[0394] r t′ =r t -δr.

[0395] The learner personalized learning recommendation method described in this embodiment, the specific process of constructing the learning path recommendation model in S7) is as follows:

[0396] S601): The learning feature representation is based on the subject knowledge graph, and the subject knowledge elements and related learning resources are extracted using the association rule algorithm to form the learning element of the knowledge graph, which is represented by a triple L = (Ki, Kj, r);

[0397] Among them, r represents the logical relationship between knowledge element Ki and learning resource Kj;

[0398] Then, using knowledge graph technology, we serialize and annotate the attributes of subject knowledge elements and related learning resources, characterize and describe the basic characteristics of learning elements;

[0399] Combined with the learning needs of learners, the learning elements of the learning activity process are formed into a learning element sequence (s1, s2, ..., s N );

[0400] At this time, the user status S is expressed as follows:

[0401] s=[s1 s2...s N ]

[0402] S602): Recommend learning paths, based on the user's current learning state matrix and the prior relationship of knowledge points in the knowledge graph, recommend the next knowledge point with the maximum reward and the corresponding learning materials;

[0403] S603): Learning path evaluation and optimization: During the learning process, learners complete tasks based on the learning paths and resources recommended by personalized learning, and submit feedback on their learning experience and results. The personalized learning recommendation engine collects and analyzes user feedback, combines the learners' goal completion status, compares the expert path with the recommended path, and evaluates the accuracy and practicality of the recommendation;

[0404] Based on evaluation results and user feedback, we continuously optimize the personalized learning recommendation engine to continuously improve the effectiveness of personalized recommendations and user satisfaction.

[0405] The learner personalized learning recommendation method described in this embodiment, the knowledge extraction using the knowledge graph technology in S3) follows the following rules, which are as follows:

[0406] S31): Template-based rules such as regular expression rules, template matching;

[0407] S32): Syntactic and lexical analysis rules: HanLP (Chinese processing library, supports part-of-speech tagging and word segmentation), spaCy (provides fast part-of-speech tagging, Stanford NLP (part-of-speech tagging, supports multiple languages)

[0408] S33): context-dependent rules;

[0409] S34): Statistical learning rules;

[0410] The specific method of establishing the logical association between subject knowledge elements and related learning resources is as follows: first classify and annotate learning resources, which can be divided into textbooks, exercises, videos, cases, experiments and extracurricular materials. Each resource has clear metadata to describe its association with knowledge elements;

[0411] Create a labeling system for knowledge elements and learning resources, ensure the accuracy of logical associations through manual and automatic labeling (natural language processing or large models, analyze text content, extract knowledge elements or label entities), and perform manual verification.

[0412] According to the knowledge system and curriculum standards of each subject area, knowledge graph technology is used to acquire and extract knowledge, and Python code or large models are used to align entities, attributes, relationships, and resolve conflicts to complete knowledge fusion. The knowledge fusion process is as follows:

[0413] Entity alignment: Different data sources may use different names to describe the same entity, and entity alignment is needed to identify them as the same object; for example, "Apple" and "Apple Inc." are actually the same entity.

[0414] Attribute alignment: One data source uses "Date of Birth" and another uses "Birthdate", but they are actually the same attribute.

[0415] Relationship alignment: Align relationship types to unify the description of relationships in different data sources. For example, "isemployed by" and "works for" can be aligned to the same relationship type.

[0416] Conflict resolution: Different data sources may provide conflicting attributes about the same entity. For example, one data source says that a person's date of birth is 1980, while another says it is 1981. Conflict resolution techniques are needed to select the most credible version.

[0417] For example, the reward function not only provides feedback based on the learner's task completion or test score, but can also be combined with the knowledge mastery in the knowledge graph for multi-dimensional explanation. By looking at the association of knowledge points in the graph, the system can explain why the learner is rewarded or punished, such as "After completing the recommendation task, the learner has mastered multiple key knowledge points in the knowledge graph, so he received a higher reward."

[0418] The associated paths in the knowledge graph can help the system explain which knowledge points play a key role in the overall progress, which makes the reward mechanism more transparent.

[0419] The above description is only a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements without departing from the principle of the present invention, and these improvements should also be regarded as within the protection scope of the present invention.

Claims

1. A learner personalized learning recommendation method, characterized by: The specific recommended steps are as follows: S1): When learners first enter the personalized learning platform through the learner interaction interface, they must first provide basic personal information and complete registration; Afterwards, learners enter the learning style determination module and learning goal setting module respectively under the guidance of the personalized learning platform wizard to complete their own learning style assessment and learning goal setting, including selectively completing the learner's learning style scale questionnaire, filling in the self-description of learning style and expected content of learning goals; And conduct an initial assessment of the learners’ current learning situation through the entrance test module; S2): The manager or educator uses the background management interface to define the knowledge meta-object structure, teaching strategy, and learning resources to establish a knowledge domain model based on the learner's learning goals and teaching structure, and stores this information in the database; That is, using knowledge graph technology to acquire and extract knowledge, and using Python code or large models to align entities, attributes, relationships, and resolve conflicts to complete knowledge integration, establish logical associations between subject knowledge elements and related learning resources, and introduce the established logical associations between subject knowledge elements and related learning resources into the subject knowledge graph structure, store this information in the learning content database, and provide data support for providing personalized learning content recommendations to users in the future; S3): Initial learner portrait model establishment, that is, the personalized learning recommendation platform builds a preliminary learner portrait model through the learner portrait model establishment module based on the collected user information; The learner portrait model building module processes the collected information and stores it in the user model database; S4): The learner enters the database to study, and the learning process recording module records the data of the learner's entire learning process, records the sequence of the learner's accessed pages, learning materials, access time information in real time, and instantly updates the user learning record database; S5): The learning assessment module conducts periodic assessments on the learners’ learning status. That is, after each unit of knowledge is learned, the learning assessment module assesses the learners’ learning status recorded by the learning process recording module, and sends the assessment results to the learner portrait model and the personalized learning recommendation engine; S6): updating the learner portrait model, that is, updating the learner portrait model according to the evaluation results of the learning evaluation module, and storing the updated learner model in the learner model database; S7): Based on the updated learner portrait model and learning process records, the personalized learning recommendation engine calculates the learner's mastery of knowledge elements in real time, generates a learner portrait based on this, and calculates the user's comprehensive feature vector. Then, the knowledge graph technology and the reinforcement learning DQN network are used to adaptively and self-organize the learning path and learning resources that are suitable for the learner based on the calculated user comprehensive feature vector, providing users with accurate personalized learning guidance services; S8): updating the learning path database, storing the learning path suitable for the learner newly generated in S7) into the learning path database; S9): Personalized learning content recommendation recommends new learning paths to learners from the learning path database; S10): Then the learner repeats step 4) to step 9) until all the knowledge points to be learned are completed.

2. The learner personalized learning recommendation method according to claim 1, characterized in that: The learner portrait model construction process in S2) is as follows: S21): Data collection, collecting various data of learners, including learning behavior data, learning resource interaction data, and test scores, and using association rule algorithms and data mining technology to mine users' learning process data; S22): Preprocess the collected data, including cleaning outliers and missing values ​​to ensure data quality. Through attribute matching and feature extraction, combined with learners’ personal attributes and learning styles, various learning portrait modules are integrated using statistical methods to obtain learners’ learning ability, cognitive level, and learning goal portraits. S23): Extract the learner's personalized learning features from the three dimensions of learning ability, cognitive level, and learning goals. Use AprioriAll to quantify the feature labels of learning ability, cognitive level, and learning goals to form the learner's learning feature matrix. Each row represents a learner, and each column corresponds to a feature dimension. S24): Then, based on the learning feature matrix, a machine learning algorithm is used to group or classify the learners to construct a learner portrait model.

3. The learner personalized learning recommendation method according to claim 1, characterized in that: The reinforcement learning DQN network in the personalized learning recommendation engine makes decisions through the interaction between the agent and the environment, and the decision needs to bring as many rewards as possible; the agent here is the personalized learning recommendation engine, the environment is the user's state and knowledge graph, and the reward is the benefit of the learning effect; The specific working process is as follows: S61): First, the data is processed to obtain user portrait features. The user portrait feature is composed of a learning ability vector c, a cognitive level vector l, and a learning goal vector g. The learning ability vector c, the cognitive level vector l, and the learning goal vector g are calculated respectively, and then the user comprehensive feature vector is processed. The specific process is as follows: The following normalization formulas are involved: Where X min is the minimum value, X max is the maximum value, the purpose is to map the range of data to [0,1]. The learning ability includes memory, logical reasoning ability, learning speed, and learning concentration dimensions: The memory dimension is calculated by using the memory-type question score and the total score to calculate the score rate M as an indicator; Normalization: The logical reasoning ability dimension uses the score rate L of reasoning questions as an indicator; Normalization: Learning speed dimension: the ability of users to effectively complete learning tasks within a unit of time, reflecting the speed at which students accept and master new knowledge; including average learning time, learning concentration Average study time: The learning speed is inversely proportional to the average learning time L kp Normalization: Study concentration: The learning concentration refers to the ability of students to maintain concentration and avoid distraction during the learning process, reflecting the degree of learning input; The main indicators of learning concentration are as follows: Continuous learning time period, number of learning interruptions, and other abnormal operations; Learning concentration index Average study time Learning concentration final score formula A min and A max are the minimum and maximum values ​​of the average continuous learning time of users, respectively. min and D max are the minimum and maximum values ​​of distraction indicators of all users, respectively; Among them, ω1 and ω2 are weights, with a value of 0.5; The learning ability matrix is ​​represented by: C=[M norm L norm L kp_norm A score ] The cognitive levels in the cognitive level vector l are as follows: Among them, A total The total score of all tests in the subject for the user; M total is the sum of the full scores of all tests in the subject; l is the ratio of the total score of all tests in the subject to the sum of the full scores of all tests in the subject; Normalization: The learning goal in the learning goal vector g is: According to the user's target school and target major, knowledge points are selected from the knowledge graph, and then the proficiency of each knowledge point is calculated based on the target score. Assume that the knowledge points obtained by screening according to the target colleges and majors are as follows: k=[k1 k2 ... k n ] The weight of each knowledge point is Normalize the weight of each knowledge point According to the normalized weight, the target total score S goal Assign to each knowledge point and adjust the base value to ensure that the weight is greater than 1 S target (k i )=ω′(k i )×(S goal )+1 The matrix of the user learning target vector g is as follows: 9=[S target (k1) S target (k2) ... S target (ki)] Combine the above features to form the user's comprehensive feature vector F student [c,l,g] Among them, c is the learning ability vector, l is the cognitive level vector, and g is the learning goal vector; Using the comprehensive feature vector F student As clustering features, students are divided into K groups and each student is assigned a cluster label G j (j=1, 2, ..., K), represents the group to which the student belongs, and the cluster label G j As features, incorporated into the state representation of subsequent models; S62): Knowledge graph embedding, that is, collecting all knowledge points and constructing a knowledge point set K = k1, k2, ..., k N ; The Node2Vec algorithm is used to embed the knowledge points in the knowledge graph into the low-dimensional vector space to obtain the embedding vector e of the i-th knowledge point i ; Then add the user's comprehensive feature vector, the embedding vector of the knowledge point, and the student's clustering label to obtain the corresponding user state vector, as follows: The user state vector S with the user's comprehensive feature vector added is expressed as follows: s=[s1,s2,...,s N ,c,l,g] Among them, c is the learning ability vector, l is the cognitive level vector, and g is the learning goal vector; Add the student's cluster label G j and the embedding vector e of the knowledge point i ; The knowledge point vector is calculated as follows: in, is the mastery level: that is, the students’ i The degree of mastery, range [0, 1]; is the learning frequency: that is, the number of times a student learns knowledge point k i The number of times; is the test performance: that is, the student's performance on knowledge point k i Average test scores on is the most recent learning time interval: that is, since the last learning of knowledge point k i the time interval since; e i Embedding vector of knowledge points; f i is a frequent pattern feature; Knowledge point k i The support is: Add the student's cluster label G j The user state vector after It is expressed as follows If the user does not fully grasp the knowledge point, the optional action space is as follows: A(s) is the set of knowledge points that satisfy the prerequisite relationship but are not fully mastered, g i >0 indicates knowledge point k i It is the student’s learning goal; Reward learners for completing their learning goals. The specific reward function is as follows r t =w(k i )×Δs i ×f(c,l)×G(k i )×PM(k i )×AR(k i )×LF(k i )×FC(k i ) Among them, w(k i ) is the knowledge point k i Importance weight Δs i For students to understand the knowledge point k i Improved mastery f(c, l) is the adjustment function of students’ learning ability and cognitive level, as follows: f(c,l)=δ1·c+δ2·l, where δ1 and δ2 are weight parameters, with values ​​of 0.7 and 0.3 respectively; G(k i ) is the learning objective weighting function Among them, g i is the i-th element of the student's learning goal vector, indicating the student's understanding of knowledge point k i The degree of learning needs; γ is a constant greater than 1, which is the bonus coefficient for the learning target knowledge points; When i >0(Knowledge point k i is the student's learning goal), G(k i ) = γ, the reward is amplified by γ times (usually 1.2-2.0), and the expected reward for selecting this knowledge point is submitted. The personalized learning recommendation engine is more inclined to recommend this knowledge point; When i =0, G(k i )=1, the reward remains unchanged, and the personalized learning recommendation engine will not be particularly biased towards recommending this knowledge point; PM(k i ) is a frequent pattern weighting function, which adjusts the reward according to the importance of the knowledge point in the frequent item set, reflecting the importance of the knowledge point in the learning group, as follows: PM(k i )=1+λ PM ×Support(k i ) Among them, λ PM To adjust the parameter, the degree of influence on the reward, usually a small positive number such as 0.1 or 0.2; Support(k i ) is the knowledge point k i The support degree of k i Frequency of occurrence in frequent itemsets; By considering the frequency of occurrence of knowledge points in frequent learning patterns, the personalized learning recommendation engine is guided to recommend knowledge points that are commonly learned in the group; In the association rule algorithm, AR(k i )The association rule weighting function is: OR(k i )=1+λ AR ×Conf(k i ) Among them, λ AR To adjust the parameters, control the influence of association rules on rewards, and usually take a positive value; Conf(k i )Knowledge point k i The highest confidence in the association rule, denoted by k i The strength of the connection with the knowledge points already learned; Using the knowledge learned: By considering k i The association with the knowledge points that students have already learned guides the model to recommend knowledge points that are closely related to what has been learned, thus promoting the coherent learning of knowledge; LF(k i )The learning frequency adjustment function is Among them, λ LF , take w(k i ), the more important the knowledge point is, the smaller the reduced reward is; As the learning frequency increases, the function value will gradually decrease, reducing the contribution to the reward and preventing students from excessively repeating familiar knowledge points; FC(k i ) Forgetting curve adjustment function Among them, λ FC Take the proportional function of the knowledge point weight, with a value range of 0.5-1; when Increase, reward Lower, prompting students to review this knowledge point; S63): Reinforce the learning DQN network to update the network parameters, as follows: Input layer: user state vector s Output layer: the Q value of each optional action (the Q value is the mathematical expectation of the sum of all future state returns); The DQN algorithm network training steps are as follows: A. Status acquisition: Get the current status S t ; B. Action selection: According to the ∈ greedy strategy, select an action from the set of optional actions; C. Execution action: Students learn knowledge points, update their mastery level, and obtain a new state S t+1 ; D. Reward calculation: Calculate the immediate reward based on the reward function; E. Experience storage: t , a t , r t ,s t+1 ) is stored in the experience replay pool; F. Network update: Randomly extract small batches of samples (s j , a j , r j ,s j+1 ) to train and update network parameters; The real-time recommendation process through the recommendation engine is as follows: Status acquisition: Get the student's current user status S; Action selection: Select the best knowledge point from A′(s) according to the ∈ greedy strategy; Knowledge point recommendation: recommend knowledge points to students and provide corresponding learning resources S64): Provide feedback and update on learners through user feedback collection, as follows: Learning feedback collection: record students’ learning results of recommended knowledge points, update their mastery level, learning frequency, and recent learning time; User status update: Update the student's user status S based on learning feedback Reinforcement learning DQN network update: Regularly train the reinforcement learning DQN network, incorporate new learning data, and improve model performance; Add learner feedback to the experience replay pool In reinforcement learning, experience samples are usually represented in the form of a quadruple: (s t ,a t ,r t ,s t+1 ) In order to incorporate students' feedback into experience samples, the structure of experience samples needs to be expanded to include feedback information: (s t ,a t ,r t′ ,s t+1 ,f t ) r t′ Adjusted instant rewards, taking into account student feedback f t The student performs action a at time step t t Feedback If the student's feedback is positive, increase the reward immediately r t′ =r t +δr If negative, reduce the reward r t′ =r t -δr。 4. The learner personalized learning recommendation method according to claim 1, characterized in that: The specific process of constructing the learning path recommendation model in S7) is as follows: S601): The learning feature representation is based on the subject knowledge graph, and the subject knowledge elements and related learning resources are extracted using the association rule algorithm to form the learning element of the knowledge graph, which is represented by a triple L = (Ki, Kj, r); Among them, r represents the logical relationship between knowledge element Ki and learning resource N; Then, using knowledge graph technology, we serialize and annotate the attributes of subject knowledge elements and related learning resources, characterizing and describing the basic characteristics of learning elements. Combined with the learning needs of learners, the learning elements of the learning activity process are formed into a learning element sequence (s1, s2, ..., s N ); At this time, the user status S is expressed as follows: s=[s1 s2 … s N ] S602): Recommend learning paths, based on the user's current learning state matrix and the prior relationship of knowledge points in the knowledge graph, recommend the next knowledge point with the maximum reward and the corresponding learning materials; S603): Learning path evaluation and optimization: During the learning process, learners complete tasks based on the learning paths and resources recommended by personalized learning, and submit feedback on their learning experience and results. The personalized learning recommendation engine collects and analyzes user feedback, combines the learners' goal completion status, compares the expert path with the recommended path, and evaluates the accuracy and practicality of the recommendation; Based on evaluation results and user feedback, we continuously optimize the personalized learning recommendation engine to continuously improve the effectiveness of personalized recommendations and user satisfaction.

5. The learner personalized learning recommendation method according to claim 1, characterized in that: In S3), the knowledge extraction using knowledge graph technology follows the following rules, as follows: S31): Template-based rules such as regular expression rules, template matching; S32): Syntactic and lexical analysis rules: HanLP (Chinese processing library, supports part-of-speech tagging and word segmentation), spaCy (provides fast part-of-speech tagging, Stanford NLP (part-of-speech tagging, supports multiple languages) S33): context-dependent rules; S34): Statistical learning rules; The specific method of establishing the logical association between subject knowledge elements and related learning resources is as follows: first classify and annotate learning resources, which can be divided into textbooks, exercises, videos, cases, experiments and extracurricular materials. Each resource has clear metadata to describe its association with knowledge elements; Create a labeling system for knowledge elements and learning resources, ensure the accuracy of logical associations through manual and automatic labeling (natural language processing or large models, analyze text content, extract knowledge elements or label entities), and perform manual verification.

6. A personalized learning recommendation platform, characterized by: include: Learner interaction interface, which is used as a login port for users to log in to the personalized learning recommendation platform; Backstage management interface, used by managers or teachers to log in to the personalized learning recommendation platform port; Learning style determination module, used for learning style testing of learners; A learning goal setting module is used for learners to set learning goals. The learner interaction interface is connected with the learning style determination module and the learning goal setting module; Admission test module, used to test learners’ current learning status; Learning process recording module, a module used to record the learner's learning process; A learning evaluation module is used to evaluate the collected learning process data of learners, analyze and assess the learning results. The learning evaluation module is bidirectionally connected with the learning process recording module; The learner portrait model module is used to establish the learner portrait model and update the learner portrait model according to the learner's later learning situation. The learning style determination module, learning goal setting module, learning process recording module and learning evaluation module are all connected to the learner portrait model module; A personalized learning recommendation engine processes the collected user learning data and learning evaluation results to generate a personalized learning recommendation engine for the user, wherein the personalized learning recommendation engine is connected to the learning evaluation module and the learning process recording module; A personalized learning recommendation module, used to provide personalized learning content recommendations and services to users, wherein the personalized learning recommendation content and service module is connected to a personalized learning recommendation engine; A learning database is used to provide a data repository for learning-related content. The learning database is connected to the learner portrait model building module, the learning process recording module, the personalized learning recommendation content and service module, and the learning auxiliary tool module, and the personalized learning recommendation engine is bidirectionally connected to the learning database; The course content background is a platform for managing all learning content of learners. The course content background is connected with the database and the learning content database in the learning database; Knowledge point platform, which is used to provide knowledge points to the course content background and knowledge graph in the learning database; It is connected to the knowledge graph in the learning database and the course content background respectively; When working, the learner interaction interface, background management interface, learning style determination module, learning goal setting module, entrance test module, learning process recording module, learning assessment module, learning database, course content background and knowledge point platform are the data basis. Every time the learner takes a test in the learning assessment module, the learner portrait model in the personalized learning recommendation platform will be updated in real time. The personalized learning recommendation engine adjusts the recommended learning path and learning content according to the adjusted user portrait model.

7. The personalized learning recommendation platform according to claim 6, characterized in that: The learning database includes a learner model database, a learning process database, a learning course database, a learning path database, a learning content database and a knowledge graph. The learner model database, the learning process database, the learning course database, the learning path database and the learning content database are bidirectionally connected. The learner portrait model establishment module is connected to the learner model database, the learning process recording module is connected to the learning process database, the personalized learning recommendation engine is connected to the learning path database, the learning path database is connected to the personalized learning content recommendation module, the learning content database is connected to the course content background, and the knowledge graph is connected to the knowledge point platform.

Images