CN113868515A - Self-adaptive learning path recommendation method based on ant colony algorithm - Google Patents

Self-adaptive learning path recommendation method based on ant colony algorithm Download PDF

Info

Publication number
CN113868515A
CN113868515A CN202111043932.0A CN202111043932A CN113868515A CN 113868515 A CN113868515 A CN 113868515A CN 202111043932 A CN202111043932 A CN 202111043932A CN 113868515 A CN113868515 A CN 113868515A
Authority
CN
China
Prior art keywords
knowledge
learner
learning
point
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111043932.0A
Other languages
Chinese (zh)
Other versions
CN113868515B (en
Inventor
王磊
张佳婷
江巧永
费蓉
马永娟
王彬
王焱龙
罗颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian University of Technology
Original Assignee
Xian University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian University of Technology filed Critical Xian University of Technology
Priority to CN202111043932.0A priority Critical patent/CN113868515B/en
Publication of CN113868515A publication Critical patent/CN113868515A/en
Application granted granted Critical
Publication of CN113868515B publication Critical patent/CN113868515B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Educational Technology (AREA)
  • Educational Administration (AREA)
  • Animal Behavior & Ethology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The invention discloses an ant colony algorithm-based personalized learning path recommendation method, which specifically comprises the following steps: step 1, establishing a similar learner model; step 2, determining a similar learner set according to the similar learner model, and identifying adjacent learners of the target learner; step 3, establishing a knowledge point characteristic model; step 4, constructing a knowledge graph of the corresponding field; step 5, finding a learning starting point for the learner to learn; step 6, generating individual knowledge subgraphs unique to each learner according to the learning starting point and the learning target; and 7, combining an ant colony algorithm, recommending the optimal path selection of the adjacent learner to the target learner, and recommending an optimal learning path for the learner. The invention recommends a learning path for the learner by combining the domain knowledge map based on the individual characteristics of the learner by utilizing the behavior data of the learner on the learning platform.

Description

Self-adaptive learning path recommendation method based on ant colony algorithm
Technical Field
The invention belongs to the technical field of intelligent education methods, and relates to an ant colony algorithm-based personalized learning path recommendation method.
Background
The adaptive learning is a leap of remote education development quality, and the education modernization requires education to provide high-quality personalized learning for students, so that learners can actively learn, learn according to the needs of the learners and learn in a mode suitable for the learners. With the development of information technology and the increase of the number of network resources, the personalized requirements of learners are increasing day by day, however, the information overload and the network navigation in the big data era become the barriers of the personalized learning of learners, and the traditional teachers can hardly meet the personalized learning requirements of learners through unified lessons and arrangement operations. Therefore, the study scheme suitable for the learner is planned for the learner, so that the learner can study more specifically, and the study efficiency of the learner is improved.
The recommendation system is an important means for information filtering and is a very potential method for solving the problem of information overload. Adaptive learning path recommendation is considered to be an effective means to solve the knowledge maze phenomenon in online learning. Learners in the adaptive learning guidance system need to perform a series of learning objects to accomplish learning objectives, and learning orders and content organization ways of learning objects are different for learners with different learning purposes and different cognitive abilities. How to make the learner complete the learning task in the shortest time through the combination of the sequence of the learning objects becomes the main content of the learning path research.
The existing learning path recommendation methods mostly adopt a unified learning course planning scheme, adopt a unified teaching mode for the same course, are difficult to provide the most suitable learning route for different learners by learning according to the textbook sequence, and have low learning efficiency.
Disclosure of Invention
The invention aims to provide an ant colony algorithm-based personalized learning path recommendation method, which is used for recommending a learning path to a learner by utilizing behavior data of the learner on a learning platform and starting from personalized features of the learner and combining a domain knowledge map.
The technical scheme adopted by the invention is that the method for recommending the personalized learning path based on the ant colony algorithm is implemented according to the following method:
step 1, establishing a similar learner model, wherein the similar learner model comprises a learning target, a learning style, a knowledge level and a learning motivation of a learner;
step 2, determining a similar learner set according to the established similar learner model, and identifying adjacent learners of the target learner;
step 3, establishing a knowledge point characteristic model;
step 4, constructing a knowledge graph of the corresponding field;
step 5, searching and matching are carried out according to the learning target of the similar learner and the knowledge map established in the step 4, and a learning starting point required to be learned by the learner is found;
step 6, generating individual knowledge subgraphs unique to each learner by combining the knowledge graph according to the learning starting point and the learning target;
and 7, combining an ant colony algorithm, recommending the optimal path selection of the adjacent learner to the target learner, and recommending an optimal learning path for the learner.
The present invention is also characterized in that,
the learning goal of the learner in the step 1 is to select the learner with the same learning goal as a class of similar learners to carry out clustering by counting the behavior data of the learner in the learning platform;
learning styles are classified into convergent type, divergent type, assimilation type and regulation type according to a Knob learning style division method, one learner shows a plurality of learning type trends, and different learners have different trend degrees on various learning styles, so that a vector S (S) is used1,s2,s3,s4) Describing the style tendency of the learner, wherein s1,s2,s3,s4Respectively representing the degrees of the learner belonging to convergent type, divergent type, assimilation type and regulation type, and s is more than or equal to 0i≤1，i＝1,2,3,4，s1+s2+s3+s4＝1；
The knowledge level of the learner is obtained through a learning test, and the knowledge level of the learner is divided into three levels, namely general, medium and excellent, specifically:
after the learner enters the self-adaptive learning guidance system, the learner firstly selects the knowledge point to be learned and enters a pre-learning test page of the corresponding knowledge point, and the initial knowledge level of the learner, namely the mastery degree W of the knowledge point, is obtained through the test; the mastery degree of the knowledge point of the learner is mapped to a certain value in the interval of [0,1] through the test question score, and the following steps are specified: when the mastery degree of the learner on a knowledge point is more than or equal to 0 and less than or equal to 0.3, the knowledge level of the learner is general; when the mastery degree of the knowledge point of the learner is more than 0.3 and less than or equal to 0.6, the knowledge level of the learner is medium; when the mastery degree of the knowledge point of the learner is more than 0.6 and less than or equal to 1, the knowledge level of the learner is excellent;
the learning motivation of the learner is divided into three levels of understanding, mastering and proficiency, and the learning motivation of the learner is selected by the learner according to the importance degree of the corresponding knowledge point.
In step 2, the step of determining the similar learner set according to the established similar learner model specifically comprises the following steps: firstly, a learner selects a learning objective and a learning motivation after entering a learning platform, and a learner group which selects the same learning objective and the same learning motivation forms a similar learner set.
The step 2 of identifying the adjacent learners specifically comprises the following steps:
determining adjacent learners in the determined similar learner set according to the knowledge level and the learning style, and specifically:
step 2.1, determining a learner group with similar knowledge level in the similar learner set
Figure BDA0003250442390000041
Let L be { L ═ L1,L2,…,LmDenotes the set of all learners who completed the learning task, ljJ-1, 2, …, m, indicating the knowledge level of the jth learner in the set of similar learners, let L0Representing the target learner l0Representing the knowledge level of the target learner by r1A neighborhood parameter representing the knowledge level, 0 ≦ r1The learner group with similar knowledge level is less than or equal to 1
Figure BDA0003250442390000042
Expressed as:
Figure BDA0003250442390000043
step 2.2, learner groups of similar knowledge levels obtained in step 2.1
Figure BDA0003250442390000044
Determining a group L of adjacent learners of a target learner according to a learning style of the learnero,similarThe method specifically comprises the following steps:
by using
Figure BDA0003250442390000045
Represents a learning style vector of a target learner,
Figure BDA0003250442390000046
respectively indicates that the target learner belongs to convergent type, divergent type, assimilation type and regulation typeTo a degree of and have
Figure BDA0003250442390000047
Figure BDA0003250442390000048
Representation collection
Figure BDA0003250442390000049
The learning style vector of the middle learner,
Figure BDA00032504423900000410
let r be2Representing a proximity parameter between learning styles, 0 ≦ r2≤1，|so-skI denotes the vector soAnd skThe euclidean distance between them, the adjacent learner group of the target learner is determined as:
Figure BDA00032504423900000411
the knowledge point feature model in step 3 includes the degree of the knowledge points using various expression modes and the difficulty coefficient d of the knowledge points, where the degree of the knowledge points using various expression modes is represented by a vector C, and C ═ C1,c2,c3,c4) Wherein c is1,c2,c3,c4Respectively representing the proportion of the knowledge content of one knowledge point expressed by courseware PPT, video, audio and document to the total knowledge content of the knowledge point, and c is more than or equal to 0i≤1(i＝1,2,3,4),c1+c2+c3+c41 is ═ 1; d is more than or equal to 0 and less than or equal to 1, the closer d is to 0, the smaller the difficulty of the knowledge point is, and the closer d is to 1, the greater the difficulty of the knowledge point is.
The step 4 specifically comprises the following steps:
step 4.1, classifying the electronic textbooks of the corresponding fields according to a three-layer knowledge frame, wherein the first layer is an outline of knowledge of the corresponding fields, namely chapters, the second layer is each section corresponding to the lower part of the chapter, and the third layer is meta-knowledge, wherein fields contained in the chapter comprise chapter id, chapter name, description of the chapter and section id contained under the chapter; the fields contained in the sections comprise section id, section name, section description and the affiliated chapter id; the meta knowledge is not subdivided, and the fields comprise meta knowledge id, meta knowledge name, precursor knowledge point id, successor knowledge point id, other relation knowledge point id and belonging node id, so that the construction of the corresponding knowledge field body structure is completed;
step 4.2, manually extracting entities, relations and attributes in the body structure, wherein the entities are the chapter, section and meta knowledge, the relations refer to the connection of the two entities through edges, and the attributes refer to the characteristics of entity objects, so that the primary construction of a knowledge graph is realized;
step 4.3, using an octopus data collector to crawl Baidu encyclopedia data: firstly, importing the network addresses of the collected corresponding domain knowledge points, then customizing keywords, abstracts, English names, brief descriptions and fields required to be crawled by a directory, and processing the imported corresponding domain knowledge points in batches to obtain crawled data;
step 4.4, manually labeling the data crawled in the step 4.3, namely partial corpus sentence data, extracting entities from the labeled data, performing non-repeated pairwise team formation on a plurality of entities contained in one corpus, storing the extracted result into a Mysql database, and removing duplication of the data with two entities in the same extracted result;
and 4.5, extracting the relation, manually judging the relation among the entities of a part of the data after the duplication removal obtained in the step 3.4 to generate data in the format of the entity, the relation and the corpus sentence, and fusing the extracted triple entity, the relation and the corpus sentence with the manually and preliminarily established knowledge map to realize the construction of the domain knowledge map.
The step 5 specifically comprises the following steps:
step 5.1, extracting the relation of the knowledge graph established in the step 4 to obtain the semantic relation existing among the knowledge points, wherein the semantic relation comprises seven relations of dependence, inclusion, belonging, near sense, antisense and same position;
step 5.2, positioning the learning targets of similar learners into the constructed hierarchical knowledge map, if the target knowledge points are first-layer knowledge points, inquiring all second-layer sub-knowledge points of the knowledge points through parent-child relationship, then respectively inquiring third-layer sub-knowledge points of the knowledge points through all second-layer knowledge points, and randomly distributing the third-layer knowledge points to each similar learner as learning starting points;
if the target knowledge point is a knowledge point of the second layer, inquiring all sub knowledge points of the third layer of the knowledge point through a parent-child relationship, and randomly distributing the knowledge points of the third layer to each similar learner as learning starting points; and if the target knowledge point is the third-layer meta knowledge, randomly distributing the third-layer knowledge point as a learning starting point to each similar learner.
The personalized knowledge subgraph in step 6 is that: and one or more learning paths connected by the knowledge points between the learning starting point and the learning target form an individual knowledge subgraph of the learner.
The step 7 specifically comprises the following steps:
step 7.1, initializing each parameter in the ant colony algorithm: setting of an influencing parameter alpha1，α2Beta and information volatility, initializing pheromone tau for each road segmentij(t), initializing the target learner LoKnowledge level of loAnd learning style So；
7.2, determining the adjacent learner group L in the step 2o,similarEach learner of (1) is used as an ant, and a learning start point o is randomly allocated to each adjacent learner according to the learning target of the target learner and the allocation method of the learning start points in the step 5iNamely, each ant is allocated with a learning starting point;
step 7.3, if the ant has already learned and finished the distributed learning starting point knowledge point oiTraversing all the next-level knowledge points o corresponding to the learning starting points according to the arrangement sequence of the knowledge points in the personalized knowledge subgraphjCalculating ant to select next knowledge point ojThe probability of learning as the next knowledge point is:
Figure BDA0003250442390000071
wherein the content of the first and second substances,
Figure BDA0003250442390000072
from knowledge point o for antsiTo the knowledge point ojIs selected probability of, τij(t) denotes the path o at the point in time ti→ojThe number of pheromones retained on the surface,
Figure BDA0003250442390000073
representing the learner's knowledge level and point of knowledge ojThe degree of match between the difficulties of the two,
Figure BDA0003250442390000074
representing the target learner LoLearning style and knowledge points ojDegree of match between expression patterns of, alpha1And alpha2Respectively represent
Figure BDA0003250442390000075
And
Figure BDA0003250442390000076
for the impact parameter of the decision, β represents the pheromone τij(t) impact parameters on the decision;
Figure BDA0003250442390000077
calculated according to the following formula:
Figure BDA0003250442390000078
wherein loShows the learner LoKnowledge level of djRepresenting a knowledge point ojThe difficulty factor of (c);
Figure BDA0003250442390000079
calculated according to the following formula:
Figure BDA00032504423900000710
wherein is made of
Figure BDA00032504423900000711
Represents a learning style vector of a target learner,
Figure BDA00032504423900000712
respectively representing the degrees of the target learners belonging to convergent type, divergent type, assimilation type and regulation type,
Figure BDA00032504423900000713
representing a knowledge point ojFeature vectors of knowledge expression, wherein
Figure BDA00032504423900000714
Respectively representing a knowledge point ojThe proportion of the knowledge content expressed by the courseware PPT, the video, the audio and the document to the total knowledge content of the knowledge point is adopted;
j (i) at the knowledge point oiThe ant of (1) the set of all selectable paths next;
step 7.4, selecting the knowledge point o with the maximum probabilityjLearning as the next knowledge point, and proceeding from the knowledge point o after the learner finishes learningiTo the knowledge point ojUpdating pheromones on the road section, wherein the updated pheromones are as follows:
Figure BDA00032504423900000715
wherein rho is an information volatility factor, rho is more than or equal to 0 and less than or equal to 1,
Figure BDA00032504423900000716
for learners to the knowledge point oiTo the knowledge point ojRating of road sections, i.e.That is, the learner is on the road section oi→ojThe pheromone produced above;
step 7.5, then the knowledge point ojRepeatedly executing the steps 7.3-7.4 as a starting point to select the next knowledge point until reaching the end point, and generating a learning path J (i), namely generating a learning path J (i) for each adjacent learner;
step 7.6, for all sections o on the generated learned path J (i)i→ojUpdating pheromone intensity, and the formula is as follows:
Figure BDA0003250442390000081
step 7.7, calculate the overall probability of each adjacent learner finally selecting and generating learning path J (i)
Figure BDA0003250442390000082
Figure BDA0003250442390000083
That is, the product of the probabilities of selecting each segment of the path on path J (i) will be learned;
7.8, sequencing the overall probability of all adjacent learners generating the learning path J (i), and sequencing the probabilities
Figure BDA0003250442390000084
The maximum learning path is recommended to the learner.
The invention has the beneficial effects that:
(1) the method effectively utilizes various behavior data of the learner on the learning platform, the learner learns and takes a series of behaviors of examination and participation in forum discussion in the self-adaptive learning guide platform, a learner model can be established based on the data, and important indexes required by path recommendation, namely the cognitive level of the learner, are obtained.
(2) The method takes the influence of the difference of the learner on the learning style on the learning path selection into consideration, recommends the learning path for the learner, and can improve the accuracy of recommending the learning path and recommend the learning path more suitable for the learner to the learner, wherein the learning path is required to meet the uniform learning style of a similar learner group.
(3) The invention establishes the knowledge map in the field of junior high school mathematics, provides a visual knowledge point relation map for a learner, enables the learner to more intuitively acquire the relation between knowledge points, generates an individualized knowledge subgraph for the learner by extracting the semantic relation between the knowledge points, and provides a learning path guidance scheme for the learner in a targeted manner.
Drawings
FIG. 1 is a flowchart of an ant colony algorithm-based personalized learning path recommendation method according to the present invention;
fig. 2 is a logic diagram of an ant colony algorithm-based personalized learning path recommendation method according to the invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention relates to an ant colony algorithm-based personalized learning path recommendation method, the flow of which is shown in the figure 1-2, and the method is specifically implemented according to the following method:
step 1, establishing a similar learner model, wherein the similar learner model comprises a learning target, a learning style, a knowledge level and a learning motivation of a learner;
the learning target of the learner is to take the learner with the same learning target as a similar learner to carry out clustering by counting the behavior data of the learner in the learning platform;
learning styles are classified into convergent type, divergent type, assimilation type and regulation type according to a Knob learning style division method, one learner shows a plurality of learning type trends, and different learners have different trend degrees on various learning styles, so that a vector S (S) is used1,s2,s3,s4) Describing the style tendency of the learner, wherein s1,s2,s3,s4Respectively represent the learner genusIn the degree of polymerization, divergence, assimilation and regulation, and s is 0. ltoreq.si≤1，i＝1,2,3,4，s1+s2+s3+s4＝1；
The knowledge level of the learner is obtained through a learning test, and the knowledge level of the learner is divided into three levels, namely general, medium and excellent, specifically:
after the learner enters the self-adaptive learning guidance system, the learner firstly selects the knowledge point to be learned and enters a pre-learning test page of the corresponding knowledge point, and the initial knowledge level of the learner, namely the mastery degree W of the knowledge point, is obtained through the test; the mastery degree of the knowledge point of the learner is mapped to a certain value in the interval of [0,1] through the test question score, and the following steps are specified: when the mastery degree of the learner on a knowledge point is more than or equal to 0 and less than or equal to 0.3, the knowledge level of the learner is general; when the mastery degree of the knowledge point of the learner is more than 0.3 and less than or equal to 0.6, the knowledge level of the learner is medium; when the mastery degree of the knowledge point of the learner is more than 0.6 and less than or equal to 1, the knowledge level of the learner is excellent;
the learning motivation of the learner is divided into three levels of understanding, mastering and proficiency, and the learning motivation of the learner is selected by the learner according to the importance degree of the corresponding knowledge points;
step 2, determining a similar learner set according to the established similar learner model, and identifying adjacent learners of the target learner;
wherein, the determination of the similar learner set according to the established similar learner model specifically comprises the following steps: firstly, a learner selects a learning target and a learning motivation after entering a learning platform, and a similar learner set is formed by a learner cluster which selects the same learning target and the same learning motivation;
the method specifically comprises the following steps of identifying adjacent learners:
determining adjacent learners in the determined similar learner set according to the knowledge level and the learning style, and specifically:
step 2.1, determining a learner group with similar knowledge level in the similar learner set
Figure BDA0003250442390000101
Let L be { L ═ L1,L2,…,LmDenotes the set of all learners who completed the learning task, ljJ-1, 2, …, m, indicating the knowledge level of the jth learner in the set of similar learners, let L0Representing the target learner l0Representing the knowledge level of the target learner by r1A neighborhood parameter representing the knowledge level, 0 ≦ r1The learner group with similar knowledge level is less than or equal to 1
Figure BDA0003250442390000102
Expressed as:
Figure BDA0003250442390000103
step 2.2, learner groups of similar knowledge levels obtained in step 2.1
Figure BDA0003250442390000111
Determining a group L of adjacent learners of a target learner according to a learning style of the learnero,similarThe method specifically comprises the following steps:
by using
Figure BDA0003250442390000112
Represents a learning style vector of a target learner,
Figure BDA0003250442390000113
respectively indicate the degree of the target learner belonging to convergent type, divergent type, assimilation type and accommodation type, and have
Figure BDA0003250442390000114
Figure BDA0003250442390000115
Representation collection
Figure BDA0003250442390000116
The learning style vector of the middle learner,
Figure BDA0003250442390000117
let r be2Representing a proximity parameter between learning styles, 0 ≦ r2≤1，|so-skI denotes the vector soAnd skThe euclidean distance between them, the adjacent learner group of the target learner is determined as:
Figure BDA0003250442390000118
step 3, establishing a knowledge point characteristic model;
the knowledge point feature model comprises the degrees of the knowledge points adopting various expression modes and a difficulty coefficient d of the knowledge points, wherein the degrees of the knowledge points adopting various expression modes are represented by a vector C, and C is (C ═ C)1,c2,c3,c4) Wherein c is1,c2,c3,c4Respectively representing the proportion of the knowledge content of one knowledge point expressed by courseware PPT, video, audio and document to the total knowledge content of the knowledge point, and c is more than or equal to 0i≤1(i＝1,2,3,4),c1+c2+c3+c41 is ═ 1; d is more than or equal to 0 and less than or equal to 1, the closer d is to 0, the smaller difficulty of the knowledge point is represented, and the closer d is to 1, the larger difficulty of the knowledge point is;
step 4, constructing a knowledge graph of the corresponding field; the method specifically comprises the following steps:
step 4.1, classifying the electronic textbooks of the corresponding fields according to a three-layer knowledge frame, wherein the first layer is an outline of knowledge of the corresponding fields, namely chapters, the second layer is each section corresponding to the lower part of the chapter, and the third layer is meta-knowledge, wherein fields contained in the chapter comprise chapter id, chapter name, description of the chapter and section id contained under the chapter; the fields contained in the sections comprise section id, section name, section description and the affiliated chapter id; the meta knowledge is not subdivided, and the fields comprise meta knowledge id, meta knowledge name, precursor knowledge point id, successor knowledge point id, other relation knowledge point id and belonging node id, so that the construction of the corresponding knowledge field body structure is completed;
step 4.2, manually extracting entities, relations and attributes in the body structure, wherein the entities are chapters, sections and meta-knowledge, the relations refer to connecting the two entities through edges, the attributes refer to the characteristics of entity objects, and the relations are connection relations between the two entities, for example, the entities are rational numbers and positive numbers, the rational numbers comprise positive numbers, and the relations between the rational numbers and the positive numbers are inclusion relations; the attribute is the characteristic of the knowledge point of the rational number, and the positive number is the characteristic of the knowledge point. Note: in general, map construction only uses entities and relations, and attributes are contained in the entities and are not reflected on the map. For example, a person is an entity, and the attributes of a person are something inherent in the person, for example: the < positive number, synonymy, negative number > triple indicates that the relationship between positive numbers and negative numbers is a synonymy relationship, and the attribute includes 17 types: definitions, addition, subtraction, multiplication, division rules, commutative rules, associative rules, distribution rules, meanings, properties, ground truth, calculation rules, property theorems, decision theorems, inferences, ground truth, decision methods, formulas, algorithms, such as: the attribute value is represented by < rational number, proposed time, 0580 years before the notary > proposed time is the attribute of the rational number, and 0580 years before the notary is the attribute value; thereby artificially constructing a three-level mesh junior middle school mathematics knowledge map of chapter-section-element knowledge from top to bottom; realizing preliminary construction of a knowledge graph;
step 4.3, using an octopus data collector to crawl Baidu encyclopedia data: firstly, importing the network addresses of the collected corresponding domain knowledge points, then customizing keywords, abstracts, English names, brief descriptions and fields required to be crawled by a directory, and processing the imported corresponding domain knowledge points in batches to obtain crawled data;
step 4.4, manually labeling the data crawled in the step 4.3, namely partial corpus sentence data, extracting entities from the labeled data, performing non-repeated pairwise team formation on a plurality of entities contained in one corpus, storing the extracted result into a Mysql database, and removing duplication of the data with two entities in the same extracted result;
step 4.5, extracting the relation, manually judging the relation among the entities of a part of the data after the duplication removal obtained in the step 3.4 to generate data in the format of the entity, the relation and the corpus sentence, and fusing the extracted triple entity, the relation and the corpus sentence with the knowledge graph preliminarily established manually to realize the construction of the domain knowledge graph;
step 5, searching and matching are carried out according to the learning target of the similar learner and the knowledge map established in the step 4, and a learning starting point required to be learned by the learner is found; the method specifically comprises the following steps:
step 5.1, extracting the relation of the knowledge graph established in the step 4 to obtain the semantic relation existing among the knowledge points, wherein the semantic relation comprises seven relations of dependence, inclusion, belonging, near sense, antisense and same position;
step 5.2, positioning the learning targets of similar learners into the constructed hierarchical knowledge map, if the target knowledge points are first-layer knowledge points, inquiring all second-layer sub-knowledge points of the knowledge points through parent-child relationship, then respectively inquiring third-layer sub-knowledge points of the knowledge points through all second-layer knowledge points, and randomly distributing the third-layer knowledge points to each similar learner as learning starting points;
if the target knowledge point is a knowledge point of the second layer, inquiring all sub knowledge points of the third layer of the knowledge point through a parent-child relationship, and randomly distributing the knowledge points of the third layer to each similar learner as learning starting points; if the target knowledge point is the third-layer meta-knowledge, randomly distributing the third-layer knowledge point as a learning starting point to each similar learner;
step 6, generating individual knowledge subgraphs unique to each learner by combining the knowledge graph according to the learning starting point and the learning target; wherein, the personalized knowledge subgraph is that: one or more learning paths formed by connecting knowledge points between a learning starting point and a learning target form an individual knowledge sub-graph of the learner;
the learning origin and learning goal are unique for each learner, but the learning origin traversed in the knowledge-graph by the goal is not unique, and the path from the learning origin to the learning destination is not unique because a knowledge point has at least one relationship node associated with it, e.g., a rational number mixing operation involving four sub-nodes of addition of rational numbers, subtraction of rational numbers, multiplication of rational numbers, and division of rational numbers will branch into four branches, resulting in at least four paths. Therefore, one learning target may correspond to one or more learning starting points. One or more learning paths connected by the knowledge points between the learning starting point and the learning target form an individual knowledge sub-graph of the learner;
step 7, combining an ant colony algorithm, recommending the optimal path selection of the adjacent learner to the target learner, and recommending an optimal learning path for the learner; the method specifically comprises the following steps:
step 7.1, initializing each parameter in the ant colony algorithm: setting of an influencing parameter alpha1，α2Beta and information volatility, initializing pheromone tau for each road segmentij(t), initializing the target learner LoKnowledge level of loAnd learning style So；
7.2, determining the adjacent learner group L in the step 2o,similarEach learner of (1) is used as an ant, and a learning start point o is randomly allocated to each adjacent learner according to the learning target of the target learner and the allocation method of the learning start points in the step 5iNamely, each ant is allocated with a learning starting point;
step 7.3, if the ant has already learned and finished the distributed learning starting point knowledge point oiTraversing all the next-level knowledge points o corresponding to the learning starting points according to the arrangement sequence of the knowledge points in the personalized knowledge subgraphjCalculating ant to select next knowledge point ojThe probability of learning as the next knowledge point is:
Figure BDA0003250442390000141
wherein the content of the first and second substances,
Figure BDA0003250442390000142
from knowledge point o for antsiTo the knowledge point ojIs selected probability of, τij(t) denotes the path o at the point in time ti→ojThe number of pheromones retained on the surface,
Figure BDA0003250442390000143
representing the learner's knowledge level and point of knowledge ojThe degree of match between the difficulties of the two,
Figure BDA0003250442390000144
representing the target learner LoLearning style and knowledge points ojDegree of match between expression patterns of, alpha1And alpha2Respectively represent
Figure BDA0003250442390000145
And
Figure BDA0003250442390000146
for the impact parameter of the decision, β represents the pheromone τij(t) impact parameters on the decision;
Figure BDA0003250442390000147
calculated according to the following formula:
Figure BDA0003250442390000151
wherein loShows the learner LoKnowledge level of djRepresenting a knowledge point ojThe difficulty factor of (c);
Figure BDA0003250442390000152
calculated according to the following formula:
Figure BDA0003250442390000153
wherein is made of
Figure BDA0003250442390000154
Represents a learning style vector of a target learner,
Figure BDA0003250442390000155
respectively representing the degrees of the target learners belonging to convergent type, divergent type, assimilation type and regulation type,
Figure BDA0003250442390000156
representing a knowledge point ojFeature vectors of knowledge expression, wherein
Figure BDA0003250442390000157
Respectively representing a knowledge point ojThe proportion of the knowledge content expressed by the courseware PPT, the video, the audio and the document to the total knowledge content of the knowledge point is adopted;
j (i) at the knowledge point oiThe ant of (1) the set of all selectable paths next;
step 7.4, selecting the knowledge point o with the maximum probabilityjLearning as the next knowledge point, and proceeding from the knowledge point o after the learner finishes learningiTo the knowledge point ojUpdating pheromones on the road section, wherein the updated pheromones are as follows:
Figure BDA0003250442390000158
wherein rho is an information volatility factor, rho is more than or equal to 0 and less than or equal to 1,
Figure BDA0003250442390000159
for learners to the knowledge point oiTo the knowledge point ojScoring of road sections, i.e. learner on road section oi→ojThe pheromone produced above;
step 7.5, then the knowledge point ojRepeating the steps 7.3-7.4 as a starting point to select the next knowledge point until the end point is reached, resulting in a learning path J (i), i.e. for each neighborThe learner generates a learning path J (i);
step 7.6, for all sections o on the generated learned path J (i)i→ojUpdating pheromone intensity, and the formula is as follows:
Figure BDA00032504423900001510
step 7.7, calculate the overall probability of each adjacent learner finally selecting and generating learning path J (i)
Figure BDA0003250442390000161
Figure BDA0003250442390000162
That is, the product of the probabilities of selecting each segment of the path on path J (i) will be learned;
7.8, sequencing the overall probability of all adjacent learners generating the learning path J (i), and sequencing the probabilities
Figure BDA0003250442390000163
The maximum learning path is recommended to the learner.

Claims (9)

1. An ant colony algorithm-based personalized learning path recommendation method is characterized by being implemented according to the following method:
step 1, establishing a similar learner model, wherein the similar learner model comprises a learning target, a learning style, a knowledge level and a learning motivation of a learner;
step 2, determining a similar learner set according to the established similar learner model, and identifying adjacent learners of the target learner;
step 3, establishing a knowledge point characteristic model;
step 4, constructing a knowledge graph of the corresponding field;
step 5, searching and matching are carried out according to the learning target of the similar learner and the knowledge map established in the step 4, and a learning starting point required to be learned by the learner is found;
step 6, generating individual knowledge subgraphs unique to each learner by combining the knowledge graph according to the learning starting point and the learning target;
and 7, combining an ant colony algorithm, recommending the optimal path selection of the adjacent learner to the target learner, and recommending an optimal learning path for the learner.
2. The method for recommending an individualized learning path based on ant colony algorithm as claimed in claim 1, wherein the learning objective of the learner in step 1 is to group learners selecting the same learning objective as a class of similar learners by means of statistics of behavior data of learners in the learning platform;
the learning styles are classified into an aggregation type, a divergence type, an assimilation type and an accommodation type according to a Knob learning style division method, one learner shows a plurality of learning type tendencies, and different learners have different tendency degrees on various learning styles, so that a vector S (S) is used1,s2,s3,s4) Describing the style tendency of the learner, wherein s1,s2,s3,s4Respectively representing the degrees of the learner belonging to convergent type, divergent type, assimilation type and regulation type, and s is more than or equal to 0i≤1，i＝1,2,3,4，s1+s2+s3+s4＝1；
The knowledge level of the learner is obtained through a learning test, and the knowledge level of the learner is divided into three levels, namely general, medium and excellent, and specifically comprises the following steps:
after the learner enters the self-adaptive learning guidance system, the learner firstly selects the knowledge point to be learned and enters a pre-learning test page of the corresponding knowledge point, and the initial knowledge level of the learner, namely the mastery degree W of the knowledge point, is obtained through the test; the mastery degree of the knowledge point of the learner is mapped to a certain value in the interval of [0,1] through the test question score, and the following steps are specified: when the mastery degree of the learner on a knowledge point is more than or equal to 0 and less than or equal to 0.3, the knowledge level of the learner is general; when the mastery degree of the knowledge point of the learner is more than 0.3 and less than or equal to 0.6, the knowledge level of the learner is medium; when the mastery degree of the knowledge point of the learner is more than 0.6 and less than or equal to 1, the knowledge level of the learner is excellent;
the learning motivation of the learner is divided into three levels of understanding, mastering and proficiency, and the learning motivation of the learner is selected by the learner according to the importance degree of the corresponding knowledge point.
3. The method as claimed in claim 2, wherein the step 2 of determining the set of similar learners according to the established model of similar learners specifically comprises: firstly, a learner selects a learning objective and a learning motivation after entering a learning platform, and a learner group which selects the same learning objective and the same learning motivation forms a similar learner set.
4. The method for recommending an individualized learning path based on ant colony algorithm as claimed in claim 3, wherein the step 2 of identifying the adjacent learners specifically comprises:
determining adjacent learners in the determined similar learner set according to the knowledge level and the learning style, and specifically:
step 2.1, determining a learner group with similar knowledge level in the similar learner set
Figure FDA0003250442380000031
Let L be { L ═ L1,L2,…,LmDenotes the set of all learners who completed the learning task, ljJ-1, 2, …, m, indicating the knowledge level of the jth learner in the set of similar learners, let L0Representing the target learner l0Representing the knowledge level of the target learner by r1A neighborhood parameter representing the knowledge level, 0 ≦ r1The learner group with similar knowledge level is less than or equal to 1
Figure FDA0003250442380000032
Expressed as:
Figure FDA0003250442380000033
step 2.2, learner groups of similar knowledge levels obtained in step 2.1
Figure FDA0003250442380000034
Determining a group L of adjacent learners of a target learner according to a learning style of the learnero,similarThe method specifically comprises the following steps:
by using
Figure FDA0003250442380000035
Represents a learning style vector of a target learner,
Figure FDA0003250442380000036
respectively indicate the degree of the target learner belonging to convergent type, divergent type, assimilation type and accommodation type, and have
Figure FDA0003250442380000037
Figure FDA0003250442380000038
Representation collection
Figure FDA0003250442380000039
The learning style vector of the middle learner,
Figure FDA00032504423800000310
let r be2Representing a proximity parameter between learning styles, 0 ≦ r2≤1，|so-skI denotes the vector soAnd skThe euclidean distance between them, the adjacent learner group of the target learner is determined as:
Figure FDA00032504423800000311
5. the method according to claim 4, wherein the knowledge point feature model in the step 3 includes degrees of the knowledge points in various expression modes and a difficulty coefficient d of the knowledge points, wherein the degrees of the knowledge points in various expression modes are represented by a vector C, and C ═ C1,c2,c3,c4) Wherein c is1,c2,c3,c4Respectively representing the proportion of the knowledge content of one knowledge point expressed by courseware PPT, video, audio and document to the total knowledge content of the knowledge point, and c is more than or equal to 0i≤1(i＝1,2,3,4),c1+c2+c3+c41 is ═ 1; d is more than or equal to 0 and less than or equal to 1, the closer d is to 0, the smaller the difficulty of the knowledge point is, and the closer d is to 1, the greater the difficulty of the knowledge point is.
6. The method for recommending an individualized learning path based on an ant colony algorithm according to claim 5, wherein the step 4 specifically comprises:
step 4.1, classifying the electronic textbooks of the corresponding fields according to a three-layer knowledge frame, wherein the first layer is an outline of knowledge of the corresponding fields, namely chapters, the second layer is each section corresponding to the lower part of the chapter, and the third layer is meta-knowledge, wherein fields contained in the chapter comprise chapter id, chapter name, description of the chapter and section id contained under the chapter; the fields contained in the sections comprise section id, section name, section description and the affiliated chapter id; the meta knowledge is not subdivided, and the fields comprise meta knowledge id, meta knowledge name, precursor knowledge point id, successor knowledge point id, other relation knowledge point id and belonging node id, so that the construction of the corresponding knowledge field body structure is completed;
step 4.2, manually extracting entities, relations and attributes in the body structure, wherein the entities are the chapter, section and meta knowledge, the relations refer to the connection of the two entities through edges, and the attributes refer to the characteristics of entity objects, so that the primary construction of a knowledge graph is realized;
step 4.3, using an octopus data collector to crawl Baidu encyclopedia data: firstly, importing the network addresses of the collected corresponding domain knowledge points, then customizing keywords, abstracts, English names, brief descriptions and fields required to be crawled by a directory, and processing the imported corresponding domain knowledge points in batches to obtain crawled data;
step 4.4, manually labeling the data crawled in the step 4.3, namely partial corpus sentence data, extracting entities from the labeled data, performing non-repeated pairwise team formation on a plurality of entities contained in one corpus, storing the extracted result into a Mysql database, and removing duplication of the data with two entities in the same extracted result;
and 4.5, extracting the relation, manually judging the relation among the entities of a part of the data after the duplication removal obtained in the step 3.4 to generate data in the format of the entity, the relation and the corpus sentence, and fusing the extracted triple entity, the relation and the corpus sentence with the manually and preliminarily established knowledge map to realize the construction of the domain knowledge map.
7. The method for recommending an individualized learning path based on an ant colony algorithm according to claim 6, wherein the step 5 specifically comprises:
step 5.1, extracting the relation of the knowledge graph established in the step 4 to obtain the semantic relation existing among the knowledge points, wherein the semantic relation comprises seven relations of dependence, inclusion, belonging, near sense, antisense and same position;
step 5.2, positioning the learning targets of similar learners into the constructed hierarchical knowledge map, if the target knowledge points are first-layer knowledge points, inquiring all second-layer sub-knowledge points of the knowledge points through parent-child relationship, then respectively inquiring third-layer sub-knowledge points of the knowledge points through all second-layer knowledge points, and randomly distributing the third-layer knowledge points to each similar learner as learning starting points;
if the target knowledge point is a knowledge point of the second layer, inquiring all sub knowledge points of the third layer of the knowledge point through a parent-child relationship, and randomly distributing the knowledge points of the third layer to each similar learner as learning starting points; and if the target knowledge point is the third-layer meta knowledge, randomly distributing the third-layer knowledge point as a learning starting point to each similar learner.
8. The method for recommending an ant colony algorithm-based personalized learning path according to claim 7, wherein the personalized knowledge subgraph in step 6 is: and one or more learning paths connected by the knowledge points between the learning starting point and the learning target form an individual knowledge subgraph of the learner.
9. The method for recommending an individualized learning path based on an ant colony algorithm according to claim 8, wherein the step 7 specifically comprises:
step 7.1, initializing each parameter in the ant colony algorithm: setting of an influencing parameter alpha1，α2Beta and information volatility, initializing pheromone tau for each road segmentij(t), initializing the target learner LoKnowledge level of loAnd learning style So；
7.2, determining the adjacent learner group L in the step 2o,similarEach learner of (1) is used as an ant, and a learning start point o is randomly allocated to each adjacent learner according to the learning target of the target learner and the allocation method of the learning start points in the step 5iNamely, each ant is allocated with a learning starting point;
step 7.3, if the ant has already learned and finished the distributed learning starting point knowledge point oiTraversing all the next-level knowledge points o corresponding to the learning starting points according to the arrangement sequence of the knowledge points in the personalized knowledge subgraphjCalculating ant to select next knowledge point ojThe probability of learning as the next knowledge point is:
Figure FDA0003250442380000061
wherein the content of the first and second substances,
Figure FDA0003250442380000062
from knowledge point o for antsiTo the knowledge point ojIs selected probability of, τij(t) denotes the path o at the point in time ti→ojThe number of pheromones retained on the surface,
Figure FDA0003250442380000063
representing the learner's knowledge level and point of knowledge ojThe degree of match between the difficulties of the two,
Figure FDA0003250442380000064
representing the target learner LoLearning style and knowledge points ojDegree of match between expression patterns of, alpha1And alpha2Respectively represent
Figure FDA0003250442380000065
And
Figure FDA0003250442380000066
for the impact parameter of the decision, β represents the pheromone τij(t) impact parameters on the decision;
the above-mentioned
Figure FDA0003250442380000067
Calculated according to the following formula:
Figure FDA0003250442380000068
wherein loShows the learner LoKnowledge level of djRepresenting a knowledge point ojThe difficulty factor of (c);
the above-mentioned
Figure FDA0003250442380000069
Calculated according to the following formula:
Figure FDA00032504423800000610
wherein is made of
Figure FDA00032504423800000611
Represents a learning style vector of a target learner,
Figure FDA00032504423800000612
respectively representing the degrees of the target learners belonging to convergent type, divergent type, assimilation type and regulation type,
Figure FDA00032504423800000613
representing a knowledge point ojFeature vectors of knowledge expression, wherein
Figure FDA00032504423800000614
Respectively representing a knowledge point ojThe proportion of the knowledge content expressed by the courseware PPT, the video, the audio and the document to the total knowledge content of the knowledge point is adopted;
j (i) at the knowledge point oiThe ant of (1) the set of all selectable paths next;
step 7.4, selecting the knowledge point o with the maximum probabilityjLearning as the next knowledge point, and proceeding from the knowledge point o after the learner finishes learningiTo the knowledge point ojUpdating pheromones on the road section, wherein the updated pheromones are as follows:
Figure FDA0003250442380000071
wherein rho is an information volatility factor, rho is more than or equal to 0 and less than or equal to 1,
Figure FDA0003250442380000072
for learners to the knowledge point oiTo the knowledge point ojScoring of road sections, i.e. learner on road section oi→ojThe pheromone produced above;
step 7.5, then the knowledge point ojRepeatedly executing the steps 7.3-7.4 as a starting point to select the next knowledge point until reaching the end point, and generating a learning path J (i), namely generating a learning path J (i) for each adjacent learner;
step 7.6, for all sections o on the generated learned path J (i)i→ojUpdating pheromone intensity, and the formula is as follows:
Figure FDA0003250442380000073
step 7.7, calculate the overall probability of each adjacent learner finally selecting and generating learning path J (i)
Figure FDA0003250442380000074
Figure FDA0003250442380000075
That is, the product of the probabilities of selecting each segment of the path on path J (i) will be learned;
7.8, sequencing the overall probability of all adjacent learners generating the learning path J (i), and sequencing the probabilities
Figure FDA0003250442380000076
The maximum learning path is recommended to the learner.
CN202111043932.0A 2021-09-07 2021-09-07 Self-adaptive learning path recommendation method based on ant colony algorithm Active CN113868515B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111043932.0A CN113868515B (en) 2021-09-07 2021-09-07 Self-adaptive learning path recommendation method based on ant colony algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111043932.0A CN113868515B (en) 2021-09-07 2021-09-07 Self-adaptive learning path recommendation method based on ant colony algorithm

Publications (2)

Publication Number Publication Date
CN113868515A true CN113868515A (en) 2021-12-31
CN113868515B CN113868515B (en) 2024-02-09

Family

ID=78994637

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111043932.0A Active CN113868515B (en) 2021-09-07 2021-09-07 Self-adaptive learning path recommendation method based on ant colony algorithm

Country Status (1)

Country Link
CN (1) CN113868515B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160005323A1 (en) * 2014-07-03 2016-01-07 Mentorum Solutions Inc. Adaptive e-learning system and method
CN113127731A (en) * 2021-03-16 2021-07-16 西安理工大学 Knowledge graph-based personalized test question recommendation method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160005323A1 (en) * 2014-07-03 2016-01-07 Mentorum Solutions Inc. Adaptive e-learning system and method
CN113127731A (en) * 2021-03-16 2021-07-16 西安理工大学 Knowledge graph-based personalized test question recommendation method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
程岩;: "在线学习中基于群体智能的学习路径推荐方法", 系统管理学报, no. 02 *

Also Published As

Publication number Publication date
CN113868515B (en) 2024-02-09

Similar Documents

Publication Publication Date Title
CN111753098A (en) Teaching method and system based on cross-media dynamic knowledge graph
CN110399565A (en) Based on when null cycle attention mechanism recurrent neural network point of interest recommended method
CN113127731A (en) Knowledge graph-based personalized test question recommendation method
CN111428051B (en) Multi-intelligence fused self-adaptive learning knowledge graph construction method and system
CN108172047B (en) A kind of network on-line study individualized resource real-time recommendation method
CN112667877A (en) Scenic spot recommendation method and equipment based on tourist knowledge map
CN111914162B (en) Method for guiding personalized learning scheme based on knowledge graph
CN113344053B (en) Knowledge tracking method based on examination question different composition representation and learner embedding
CN114065040A (en) Individual learning path and learning resource recommendation method based on discipline knowledge graph
Zhang et al. Research on the influencing factors of kite culture inheritance based on an adversarial interpretive structure modeling method
CN116263782A (en) Intelligent winding method, system and storage medium based on question bank
CN112784608A (en) Test question recommendation method and device, electronic equipment and storage medium
CN110309300A (en) A method of identification natural sciences knowledge-ID
Tam et al. Toward a complete e-learning system framework for semantic analysis, concept clustering and learning path optimization
CN113851020A (en) Self-adaptive learning platform based on knowledge graph
CN114201684A (en) Knowledge graph-based adaptive learning resource recommendation method and system
CN113239209A (en) Knowledge graph personalized learning path recommendation method based on RankNet-transformer
CN112966092A (en) Knowledge graph personalized semantic recommendation method based on basic education
CN112380429A (en) Exercise recommendation method and device
CN113868515B (en) Self-adaptive learning path recommendation method based on ant colony algorithm
CN115438871A (en) Ice and snow scenic spot recommendation method and system integrating preference and eliminating popularity deviation
Yan et al. Personalization exercise recommendation framework based on knowledge concept graph
CN114547481A (en) MOOC course hybrid recommendation method based on fuzzy logic and teaching plan
Wu et al. Contrastive Personalized Exercise Recommendation With Reinforcement Learning
He et al. Research of scratch programming recommendation system based on med and knowledge graph

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant