CN113851020A - Self-adaptive learning platform based on knowledge graph - Google Patents
Self-adaptive learning platform based on knowledge graph Download PDFInfo
- Publication number
- CN113851020A CN113851020A CN202111297763.3A CN202111297763A CN113851020A CN 113851020 A CN113851020 A CN 113851020A CN 202111297763 A CN202111297763 A CN 202111297763A CN 113851020 A CN113851020 A CN 113851020A
- Authority
- CN
- China
- Prior art keywords
- learning
- knowledge
- student
- students
- style
- 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.)
- Pending
Links
- 230000013016 learning Effects 0.000 title claims abstract description 471
- 230000003044 adaptive effect Effects 0.000 claims abstract description 36
- 230000006399 behavior Effects 0.000 claims abstract description 28
- 238000007726 management method Methods 0.000 claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims description 54
- 238000000034 method Methods 0.000 claims description 40
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 15
- 230000000007 visual effect Effects 0.000 claims description 14
- 230000003993 interaction Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 230000008676 import Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000010365 information processing Effects 0.000 claims description 4
- 230000008447 perception Effects 0.000 claims description 4
- 238000013101 initial test Methods 0.000 claims description 3
- 238000012552 review Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 claims 1
- 230000001755 vocal effect Effects 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract description 5
- 230000002452 interceptive effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 12
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 239000000243 solution Substances 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000010790 dilution Methods 0.000 description 2
- 239000012895 dilution Substances 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000031836 visual learning Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
本发明提供了一种基于知识图谱的自适应学习平台。该方案包括学生用户端和学习管理端；其中，所述学生用户端，为所述学生用户提供交互信息，包括查看学习历史、查看个人评价；分析所述学生用户学习风格，进行学生学习行为学习，推荐适宜风格的学习资源；收集所述学生用户学习行为，进行知识重难点内容推荐和动态学习路径规划；其中，所述学习管理端，定向调整学习资源，所述定向调整学习资源为学习管理者根据学生个体的学习情况为单个学生提供学习建议，进行动态学习路径规划。该方案通过对于学习风格学习的基础上，结合对于重点掌握程度的提取，实现随着个体的不同进行针对性学习。
The present invention provides an adaptive learning platform based on knowledge graph. The solution includes a student user terminal and a learning management terminal; wherein, the student user terminal provides interactive information for the student user, including viewing learning history and personal evaluation; analyzes the student user's learning style, and conducts student learning behavior learning , recommend learning resources of suitable style; collect the learning behaviors of the students and users, carry out the content recommendation of knowledge and difficult points and dynamic learning path planning; wherein, the learning management terminal, directional adjustment learning resources, and the directional adjustment learning resources are learning management According to the individual learning situation of students, the author provides learning suggestions for individual students and carries out dynamic learning path planning. Based on the learning of learning styles, the scheme realizes targeted learning with individual differences by combining the extraction of key mastery degrees.
Description
Technical Field
The invention relates to the technical field of online education, in particular to a self-adaptive learning platform based on a knowledge graph.
Background
Today's online education is well-motivated, the learning mode of ' internet + education ' really has many advantages that the traditional offline education is incomparable with, such as abundant and extensive learning resources, learning mode which is not limited by time and space, personalized learning method, etc. The online education is still imperfect, and there are many problems to be improved, especially in the setting of teaching contents.
Before the technology of the invention, on-line education usually adopts on-line education and a content dilution mode is carried out on the basis of the on-line education. Therefore, the last online education piles up a huge amount of teaching resources in front of the learner. In this way, in the actual use process, the learner gets lost, and it is difficult to complete the personalized learning according to the learning habit of the learner in the face of the resource failure. In addition, as the association relation between the traditional off-line teaching knowledge is controlled by a teacher under the control of the sound color of the real estate, and the knowledge lacks obvious association in on-line learning, students are difficult to form a systematic knowledge structure in learning, and knowledge leaks are easy to occur. These have resulted in on-line learning that is unsatisfactory.
Aiming at the defects of the online education, the current better solution is to use a self-adaptive learning system to perform online learning. The adaptive learning system is used for establishing a learner model by collecting and analyzing interaction data of students and an online system during learning activities, and dynamically adapting to the learning requirements of learners. The learner changes the object into the subject, changes passive learning into active learning, and realizes personalized learning; meanwhile, the self-adaptive learning system can effectively solve the contradiction between 'infinite overall resources' and 'limited individual resource demand' inherent in online education, so that the utilization of online education resources is maximized. The self-adaptive learning system generally comprises a knowledge model, a student model, a structure model and a self-adaptive engine, wherein the knowledge model is used for describing a knowledge structure and expressing the relation between knowledge concepts, and is an important basis for the self-adaptive learning system to carry out learning adaptation and resource recommendation. Thus, the quality of the knowledge model directly determines the effectiveness of the adaptive learning system. However, the knowledge in the traditional teaching is often in the form of semi-structured or unstructured data, and the data is difficult to be directly applied to model building. Most of the existing knowledge models are directly built based on teaching catalogues or only simply classified, and the association between knowledge concepts is neglected, so that the models have the problems of discrete knowledge performance, low systematicness and the like.
Disclosure of Invention
In view of the above problems, the present invention provides an adaptive learning platform based on knowledge maps, which realizes targeted learning according to different individuals by combining with the extraction of important mastery degree on the basis of learning style.
According to a first aspect of the embodiments of the present invention, an adaptive learning platform based on knowledge graph is provided.
In one or more embodiments, preferably, the knowledge-graph-based adaptive learning platform comprises:
the platform comprises a student user side and a learning management side;
wherein, student user side specifically implements as:
acquiring learning conditions required by online learning for student users, wherein the learning conditions comprise a learning platform, learning resources, examination evaluation and forum discussion;
providing interaction information with the knowledge-graph-based adaptive learning platform for the student user, wherein the interaction information comprises learning history checking and personal evaluation checking;
analyzing the learning style of the student user, learning the learning behavior of the student, and recommending the learning resources with the proper style;
collecting the learning behaviors of the student users, and carrying out content recommendation of hard points of knowledge and dynamic learning path planning;
the learning management terminal is specifically implemented as follows:
executing the student user management function, wherein the student user management function comprises student basic information checking and student learning condition checking;
modifying the knowledge graph, wherein the modifying knowledge graph is specifically used for adding, deleting, modifying, inquiring and batch importing the subject knowledge graph by a learning manager according to the whole learning condition of the student;
directionally adjusting learning resources, wherein the directionally adjusting learning resources provide learning suggestions for a learning manager to a single student according to the individual learning condition of the student, directionally add or adjust the learning resources, provide batch import of the learning resources, and perform dynamic learning path planning during the process of directionally adjusting the learning resources, wherein the learning manager adds or adjusts the learning resources to the students in bulk;
the directed adjustment learning resources are realized by recommending the content of the difficulty in knowledge.
In one or more embodiments, preferably, the workflow specific function of the student user side includes:
step one, after logging in, the student user judges whether a learning style test is carried out or not, if the learning style test is carried out, the step two is directly executed, if the learning style test is not carried out, an initial test result of the learning style of the student user is obtained by using a scale, and then the step two is carried out;
step two, judging whether the student user has a learning history, and if so, directly executing step three; if the learning history does not exist, setting a first knowledge point of the course as a current knowledge point, pushing learning resources of a corresponding style of the current knowledge point according to the learning style of the student user, collecting the learning data of the student user, and correcting the learning style of the student user;
step three, judging whether the student user is in a learning chapter completion state, if so, calling corresponding exercise resources, testing the learning result of the student, and then planning a learning path for the student according to the learning effect condition of the student and combining the subject knowledge map to check the omission of knowledge; if the learning chapter is not in the learning chapter completion state, executing a step four;
step four, judging whether the student user meets the knowledge difficulty point recommendation condition and whether learning exceeding a certain amount is performed, if the knowledge difficulty point recommendation condition is met, performing personalized difficulty point labeling knowledge on the student user according to a collaborative recommendation algorithm, and recommending the important learning to the student user; and if the conditions for recommending the difficulty and the difficulty of knowledge are not met, continuing to perform the current unfinished learning task.
In one or more embodiments, preferably, the workflow of the learning management end specifically includes:
checking the current learning progress and learning effect of the student user;
according to the learning progress and the learning effect of the whole student, adaptively modifying the subject knowledge graph, and adding or adjusting the current learning resources;
and aiming at the individual learning condition of the student user, providing a targeted suggestion according to weak and unowned knowledge points, and adding targeted exercises or learning resources to help the student user improve the knowledge mastering degree.
In one or more embodiments, preferably, the analyzing the learning style of the student user includes: measuring learning styles, generating a scale, learning the learning styles of students from four dimensions through the scale, and generating the learning styles corresponding to the student users, wherein the learning styles are eight types;
wherein the four dimensions are respectively: information processing, perception, information input and content understanding;
wherein the eight types are respectively: active type, meditation type, comprehension type, intuition type, visual type, speech type, sequence type and comprehensive type;
the scale comprises 44 questionnaire test questions, wherein each dimension of the four dimensions corresponds to 11 questionnaire test questions, the questionnaire test questions are only provided with two options, namely a option and b option, after the student user finishes answering, the number of the options a and b corresponding to each dimension is counted, and the absolute value of the difference value of the number is used as the calculation value of the scale of the student learning style.
In one or more embodiments, preferably, the learning of the learning behaviors of the students includes mining learning behaviors of the students by using a bayesian network, determining a score influence index corresponding to the student user according to a calculation formula of the index, and dynamically adjusting the learning style of the students, and specifically includes:
determining the student learning behaviors related to the learning style which can be recorded as process learning behaviors; substituting the process learning behavior into a Bayesian network calculation formula by taking the process learning behavior as a parameter to deduce the type of the learning style of the student user in the corresponding dimension;
setting a result influence index, wherein the result influence index is 100% if the test result is a good result, the result influence index is 70% if the test result is a good result, and the result influence index is 30% if the test result is a bad result;
dynamically adjusting the learning style of the student according to the analyzed learning style of the student user by utilizing the score influence index;
wherein, the Bayesian network calculation formula is as follows:
wherein, P (X)1,X2,...,Xn) Is the joint probability of a series of associated nodes, N is the total number of associated nodes, j is the number of associated nodes, places (Y)j) Is an associated node XjCorresponding upper node set, P (X)j|Parents(Yj) Is associated node X)jThe conditional probability of (a);
the formula for calculating the student learning style judgment index is as follows:
wherein P is the student learning style judgment index，
As said score impact index, scores (Y)1,Y2) Is an associated node X1And X2And the corresponding upper-layer node set.
In one or more embodiments, preferably, the dynamically learned path planning specifically includes:
acquiring a preset discipline knowledge graph, wherein the discipline knowledge graph is a structured semantic network, and specifically is a collection of interconnection relations among knowledge recorded in a text mode and association relations among all knowledge texts;
extracting key words from all subject courses, condensing the key words into knowledge points, determining the relationship between children and parents and the relationship between front and back of knowledge points,
acquiring the relationship between the child level and the parent level and the relationship between the front level and the rear level, and setting the relationship as a discipline knowledge graph, wherein the discipline knowledge graph is a structured semantic network, and specifically is a collection of interconnection relationships among knowledge recorded in a text mode and association relationships among all knowledge texts;
storing the discipline knowledge graph in a neo4j graphical database through cypher;
cypher is a descriptive graph query language, and allows a query of expressiveness and efficiency of graph storage without writing graph-structured traversal code. Cypher is also continuing to develop and mature, which means that grammatical changes are likely to occur. It also means that the assembly has not undergone stringent performance testing. The goal of Cypher design is suitable for developers and professional operators who do point-to-point schema queries on databases.
The neo4j graph database is a high performance graph database, storing structured data on the network instead of in tables, is an embedded, disk-based, Java persistence engine with full transactional features, but stores structured data on the network.
Establishing a link of the discipline knowledge graph, and waiting for directly operating the neo4j graphical database through the link;
setting at least ten corresponding exercise questions according to each knowledge point in the discipline knowledge graph and storing the exercise questions into the neo4j graphical database;
enabling the student user to test ten questions of the same knowledge point to obtain the number of correct questions;
when the number of the correct questions is more than 8, the correct questions are regarded as a mastery state, when the number of the correct questions is not more than 8 and not less than 5, the correct questions are regarded as an understanding state, and when the number of the correct questions is less than 5, the correct questions are regarded as an unsophisticated state;
classifying the knowledge points of the student users in the understanding state as weak knowledge points, and presenting and recommending students to review the corresponding knowledge point contents on a knowledge point list;
and classifying the knowledge points of the student user in the unowned state as unknown knowledge points, presenting and recommending the student to study the knowledge point contents in a key point mode by using special colors on a knowledge point list, simultaneously investigating the front knowledge point mastering condition of the student user on the knowledge points, and if the knowledge points are still unknown knowledge points, continuously investigating the previous knowledge points, so that an individualized knowledge point learning path can be connected in a knowledge map, and the learning path can be dynamically changed along with the knowledge point mastering condition of the student.
In one or more embodiments, preferably, the recommending of the content knowing the difficulty of identification specifically includes:
acquiring a learning unit as a learning unit;
setting target students, wherein the target students refer to students who finish one third of learning content of the learning units and finish all corresponding systems of the content;
setting a contrast student, wherein the contrast student is a student who completes all learning contents of the learning unit and completes unit testing;
setting ten testing questions for each knowledge point;
testing ten questions of each knowledge point of the target student and the comparison student to obtain the number of correct answer questions as the mastery degree of the target student on the corresponding knowledge points;
performing similarity calculation by using a collaborative filtering recommendation method according to the mastery degrees of the target student and the comparison student;
after the similarity between all the target students and all the comparison students is calculated, the target students corresponding to the comparison students with the similarity larger than 0.95 are determined to be similar classmates, and the difficult and difficult point problems encountered by the similar classmates in the later learned contents are recommended to the target students corresponding to the similar classmates to serve as the important learning contents.
In one or more embodiments, preferably, the collaborative filtering recommendation method specifically includes:
calculating the grasping similarity of the students according to the key grasping degrees of the target student and the contrast student by using a first calculation formula;
wherein the first calculation formula is:
wherein sim is the student mastery similarity, xiFor the mastery degree, y, of the i-th knowledge point of the target studentiAnd n is the number of the knowledge points which have been learned by the target student for contrasting the mastery degree of the student on the ith knowledge point.
According to a second aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method according to any one of the first aspect of embodiments of the present invention.
According to a third aspect of embodiments of the present invention, there is provided an electronic device, comprising a memory and a processor, the memory being configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the steps of any one of the first aspects of embodiments of the present invention.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects:
1) the embodiment of the invention provides a self-adaptive learning method based on learning style, which completes dynamic update of student states by adjusting the learning content of students; meanwhile, in the process of determining the learning style, the test result influence index is innovatively added, so that the determination of the learning style is more accurate compared with the existing method;
2) the embodiment of the invention provides an extraction method of key mastery degree, which realizes the self-adaptive adjustment of the learning route of students according to the learning experiences of similar students and the targeted learning of different individuals.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a block diagram of an adaptive learning platform based on knowledge-graphs, in accordance with an embodiment of the present invention.
Fig. 2 is a flow chart of the work of the student user side in the knowledge-graph based adaptive learning platform according to an embodiment of the invention.
Fig. 3 is a flowchart of the work of the learning management side in the adaptive learning platform based on knowledge-graph according to an embodiment of the present invention.
Fig. 4 is a questionnaire test chart of the learning style of students in the knowledge-graph-based adaptive learning platform according to an embodiment of the invention.
Fig. 5 is a flow chart of learning student learning behavior in an adaptive learning platform based on knowledge-graph according to an embodiment of the invention.
Fig. 6 is a flow chart of dynamic learning path planning in an adaptive learning platform based on knowledge-graph according to an embodiment of the present invention.
Fig. 7 is a flowchart of content recommendation of difficulty of knowledge in adaptive learning platform based on knowledge-graph according to an embodiment of the present invention.
Fig. 8 is a block diagram of an electronic device in one embodiment of the invention.
Detailed Description
In some of the flows described in the present specification and claims and in the above figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, with the order of the operations being indicated as 101, 102, etc. merely to distinguish between the various operations, and the order of the operations by themselves does not represent any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Today's online education is well-motivated, the learning mode of ' internet + education ' really has many advantages that the traditional offline education is incomparable with, such as abundant and extensive learning resources, learning mode which is not limited by time and space, personalized learning method, etc. The online education is still imperfect, and there are many problems to be improved, especially in the setting of teaching contents.
Before the technology of the invention, on-line education usually adopts on-line education and a content dilution mode is carried out on the basis of the on-line education. Therefore, the last online education piles up a huge amount of teaching resources in front of the learner. In this way, in the actual use process, the learner gets lost, and it is difficult to complete the personalized learning according to the learning habit of the learner in the face of the resource failure. In addition, as the association relation between the traditional off-line teaching knowledge is controlled by a teacher under the control of the sound color of the real estate, and the knowledge lacks obvious association in on-line learning, students are difficult to form a systematic knowledge structure in learning, and knowledge leaks are easy to occur. These have resulted in on-line learning that is unsatisfactory.
Aiming at the defects of the online education, the current better solution is to use a self-adaptive learning system to perform online learning. The adaptive learning system is used for establishing a learner model by collecting and analyzing interaction data of students and an online system during learning activities, and dynamically adapting to the learning requirements of learners. The learner changes the object into the subject, changes passive learning into active learning, and realizes personalized learning; meanwhile, the self-adaptive learning system can effectively solve the contradiction between 'infinite overall resources' and 'limited individual resource demand' inherent in online education, so that the utilization of online education resources is maximized. The self-adaptive learning system generally comprises a knowledge model, a student model, a structure model and a self-adaptive engine, wherein the knowledge model is used for describing a knowledge structure and expressing the relation between knowledge concepts, and is an important basis for the self-adaptive learning system to carry out learning adaptation and resource recommendation. Thus, the quality of the knowledge model directly determines the effectiveness of the adaptive learning system. However, the knowledge in the traditional teaching is often in the form of semi-structured or unstructured data, and the data is difficult to be directly applied to model building. Most of the existing knowledge models are directly built based on teaching catalogues or only simply classified, and the association between knowledge concepts is neglected, so that the models have the problems of discrete knowledge performance, low systematicness and the like.
The adaptive learning platform is a typical application of the adaptive learning system technology, and due to the reasons, the adaptive learning system models at the present stage all have certain defects, so that the current adaptive learning platform has the problem of poor practicability.
The embodiment of the invention provides a self-adaptive learning platform based on a knowledge graph. According to the scheme, on the basis of learning of the learning style, the extraction of key mastery degree is combined, and the purpose of performing targeted learning along with different individuals is achieved.
According to a first aspect of the embodiments of the present invention, an adaptive learning platform based on knowledge graph is provided.
FIG. 1 is a block diagram of an adaptive learning platform based on knowledge-graphs, in accordance with an embodiment of the present invention.
In one or more embodiments, as shown in fig. 1, preferably, the knowledge-graph-based adaptive learning platform comprises:
the platform comprises a student user terminal 101 and a learning management terminal 102;
wherein, student user side specifically implements as:
s101, acquiring learning conditions required by online learning for student users, wherein the learning conditions comprise a learning platform, learning resources, examination evaluation and forum discussion;
s102, providing interaction information of the self-adaptive learning platform based on the knowledge graph for the student user, wherein the interaction information comprises learning history checking and personal evaluation checking;
s103, analyzing the learning style of the student user, learning the learning behavior of the student, and recommending the learning resources with the proper style;
s104, collecting the learning behaviors of the student users, and carrying out content recommendation of difficult and hard points of knowledge and dynamic learning path planning;
the learning management terminal is specifically implemented as follows:
s105, executing the student user management function, wherein the student user management function comprises student basic information checking and student learning condition checking;
s106, modifying the knowledge graph, wherein the modified knowledge graph is formed by adding, deleting, modifying, inquiring and importing the subject knowledge graph in batch by a learning manager according to the integral learning condition of the student;
s107, directionally adjusting learning resources, wherein the directionally adjusting learning resources provide learning suggestions for a learning manager to a single student according to the individual learning condition of the student, directionally add or adjust the learning resources, provide batch import of the learning resources, and perform dynamic learning path planning during the process of directionally adjusting the learning resources, wherein the learning manager adds or adjusts the learning resources to the student in large batch;
the directed adjustment learning resources are realized by recommending the content of the difficulty in knowledge.
In the embodiment of the invention, the student user side provides an online learning environment, an adaptive learning path and a timely fed back learning result for students, helps the students to construct a complete knowledge system of the system, simultaneously accurately positions knowledge holes of the students, quickly checks missing and filling up, and improves learning efficiency; the learning management terminal provides a digitalized management method for learning managers such as class teachers and the like, so that the managers can timely acquire the learning conditions of class students and give feedback, dynamically adjust learning resources and subject knowledge maps, and better realize personalized education for the students. The directional adjustment of the learning resources is exemplified, the training questions are adjusted in a targeted manner, the platform also provides batch import of the learning resources, and a learning manager can add or adjust the learning resources in a large batch for the whole student.
The self-adaptive learning platform based on the knowledge graph builds a webpage front-end application in a contact mode and builds a webpage back-end service in a django mode; meanwhile, the webpage stores the collected user information and user data in the mysql database through the back end, and comparison and calling at any time are facilitated.
Fig. 2 is a flow chart of the work of the student user side in the knowledge-graph based adaptive learning platform according to an embodiment of the invention.
As shown in fig. 2, in one or more embodiments, preferably, the workflow specific function of the student user side includes:
step one, after logging in, the student user judges whether a learning style test is carried out or not, if the learning style test is carried out, the step two is directly executed, if the learning style test is not carried out, an initial test result of the learning style of the student user is obtained by using a scale, and then the step two is carried out;
step two, judging whether the student user has a learning history, and if so, directly executing step three; if the learning history does not exist, setting a first knowledge point of the course as a current knowledge point, pushing learning resources of a corresponding style of the current knowledge point according to the learning style of the student user, collecting the learning data of the student user, and correcting the learning style of the student user;
step three, judging whether the student user is in a learning chapter completion state, if so, calling corresponding exercise resources, testing the learning result of the student, and then planning a learning path for the student according to the learning effect condition of the student and combining the subject knowledge map to check the omission of knowledge; if the learning chapter is not in the learning chapter completion state, executing a step four;
step four, judging whether the student user meets the knowledge difficulty point recommendation condition and whether learning exceeding a certain amount is performed, if the knowledge difficulty point recommendation condition is met, performing personalized difficulty point labeling knowledge on the student user according to a collaborative recommendation algorithm, and recommending the important learning to the student user; and if the conditions for recommending the difficulty and the difficulty of knowledge are not met, continuing to perform the current unfinished learning task.
In the embodiment of the invention, the student user side provides an online learning environment, an adaptive learning path and a timely feedback learning result for students, helps the students to construct a complete knowledge system of the system, simultaneously accurately positions knowledge holes of the students, quickly checks missing and fills up the missing, and improves the learning efficiency.
Fig. 3 is a flowchart of the work of the learning management side in the adaptive learning platform based on knowledge-graph according to an embodiment of the present invention.
As shown in fig. 3, in one or more embodiments, preferably, the work flow of the learning management end specifically includes:
s301, checking the current learning progress and learning effect of the student user;
s302, adaptively modifying the subject knowledge graph according to the learning progress and the learning effect of the whole student, and adding or adjusting the current learning resources;
s303, aiming at the individual learning condition of the student user, providing a targeted suggestion according to weak and unowned knowledge points, and adding targeted exercises or learning resources to help the student user improve the knowledge mastering degree.
In the embodiment of the invention, the learning management terminal provides a digital management method for learning managers such as class teachers and the like, so that the managers can timely acquire the learning conditions of class students and give feedback, dynamically adjust learning resources and subject knowledge maps and better realize the personalized education of the students.
Fig. 4 is a questionnaire test chart of the learning style of students in the knowledge-graph-based adaptive learning platform according to an embodiment of the invention.
As shown in fig. 4, in one or more embodiments, preferably, the analyzing the learning style of the student user includes: measuring learning styles, generating a scale, learning the learning styles of students from four dimensions through the scale, and generating the learning styles corresponding to the student users, wherein the learning styles are eight types;
wherein the four dimensions are respectively: information processing, perception, information input and content understanding;
wherein the eight types are respectively: active type, meditation type, comprehension type, intuition type, visual type, speech type, sequence type and comprehensive type;
the scale comprises 44 questionnaire test questions, wherein each dimension of the four dimensions corresponds to 11 questionnaire test questions, the questionnaire test questions are only provided with two options, namely a option and b option, after the student user finishes answering, the number of the options a and b corresponding to each dimension is counted, and the absolute value of the difference value of the number is used as the calculation value of the scale of the student learning style.
In the embodiment of the present invention, there may be 12 different values for the learning style of the student, that is, [11a,9a,7a,5a,3a, a, b,1b,3b,5b,7b,9b ], where [11a,9a,7a,5a ] is labeled as a-type style, [3a, a, b,3b ] is labeled as fuzzy-type style, and [5b,7b,9b,11b ] is labeled as b-type style. For example, when the subject selects 10a and 1b among 11 questions in the information processing dimension, the subject score is determined as an active learning style, and learning styles in the other three dimensions are determined similarly. Students with different learning style types are suitable for different learning resources, which is an important index when the self-adaptive learning platform carries out resource recommendation. However, the result of the learning style of the student presumed through a single style test is not reliable enough, and random errors such as errors caused by random filling of the student exist. Therefore, the learning style of the student needs to be further determined at a later stage.
Fig. 5 is a flow chart of learning student learning behavior in an adaptive learning platform based on knowledge-graph according to an embodiment of the invention.
As shown in fig. 5, in one or more embodiments, preferably, the learning of the student learning behaviors includes mining learning behaviors of students through a bayesian network, determining an index affecting an achievement corresponding to a student user according to a calculation formula of an index of a student learning style, and dynamically adjusting the student learning style, and specifically includes:
s501, determining the student learning behaviors which are related to the learning style and can be recorded as process learning behaviors; substituting the process learning behavior into a Bayesian network calculation formula by taking the process learning behavior as a parameter to deduce the type of the learning style of the student user in the corresponding dimension;
s502, setting a result influence index, wherein the result influence index is 100% if the test result is excellent, 70% if the test result is good, and 30% if the test result is poor;
s503, dynamically adjusting the learning style of the student according to the analysis of the learning style of the student user by utilizing the achievement influence index;
wherein, the Bayesian network calculation formula is as follows:
wherein, P (X)1,X2,...,Xn) Is the joint probability of a series of associated nodes, N is the total number of associated nodes, j is the number of associated nodes, places (Y)j) Is an associated node XjCorresponding upper node set, P (X)j|Parents(Yj) Is associated node X)jThe conditional probability of (a);
the formula for calculating the student learning style judgment index is as follows:
wherein P is the student learning style judgment index,
as said score impact index, scores (Y)1,Y2) Is an associated node X1And X2And the corresponding upper-layer node set.
In the embodiment of the invention, the probability relation between two types of a certain dimension is calculated by a formula,thereby inferring what type of learning style the student has in that dimension. For example, taking information input dimension as an example, establishing video-class resource learning as node X1The learning duration of the text resources is node X2The upper node learning mode and the test result are respectively node Y1、Y12. The percentage of the learning duration of a certain type of learning resources in the total learning duration is taken as a reference, the low-stage prediction threshold is less than 50%, the middle-stage prediction threshold is 50-75%, and the high-stage prediction threshold is more than 75%. The reference amount is added with the test scores of the students at the end of the chapters, and the score of the test is recorded as excellent 8 or more, good 8-5 and poor 5 or less.
In the embodiment of the invention, the reason for setting the performance influence index is that even if a student learns in a certain learning mode for a long time, if the student does not obtain a good learning effect finally, the time length cannot prove that the learning mode is a mode suitable for the learning style of the student
Specifically, for example, assuming that an existing student has a video learning duration of 70% in a learning time of a certain chapter, a text learning duration of 30%, and a chapter test of 8 points, which is a super grade, the probability that the learning style is a visual type can be calculated according to bayesian theorem as follows:
p (visual type) ═ P (visual type/video learning, preferably) × P (video learning) × P (optimum) + P (visual type/text learning, preferably) × P (text learning) × P (optimum) + P (visual type/video learning, good) × P (video learning) × P (good) + P (visual type/text learning, good) × P (text learning) × P (good) + P (visual type/video learning, difference) × P (video learning) × P (difference) + P (visual type/text learning, difference) × P (text learning) × P (difference);
wherein for this same theory, P (video learning) ═ 0.7, P (text learning) ═ 0.3, P (excellent) ═ 1, P (good) ═ 0, P (difference) ═ 0, and thus P (visual type) ═ 0.9 × 0.7 ═ 1+0.1 × 0.3 × (1 + 0.75) × (0.7) +0.25 × (0.3) + 0.3 ═ 0.5 ═ 0.7 × (0.5) × (0.3) × (0.66);
the probability that the learning style of the classmate is the language type can be obtained by the same method as follows: p (speech type) ═ 0.34, the difference between the two is P (visual type) — P (speech type) ═ 0.32, and at the same time, the test rating is excellent, the score contribution degree, so the learning style judgment index P is 0.32. According to the test of the learning style scale, the type of the two types can be judged only when the difference between the test values is more than 3. The class is deduced, namely when the difference of the probability indexes is more than 0.3, the type of the object can be judged, otherwise, the object is fuzzy. Here, since the determination index P is 0.32>0.3, it can be determined that the generation is a visual learning style. By analogy, the learning style types of other three dimensions of the learner can be calculated.
In the specific implementation process, after the learning style of the student is determined, the subsequent parts related to resource recommendation of the adaptive learning platform refer to the learning style of the student. For example, in the face of students whose information input is visual style, the platform will prefer the video and image learning resources of a knowledge point to the text learning resources when recommending that knowledge point.
Fig. 6 is a flow chart of dynamic learning path planning in an adaptive learning platform based on knowledge-graph according to an embodiment of the present invention.
As shown in fig. 6, in one or more embodiments, preferably, the dynamically learned path planning specifically includes:
s601, acquiring a preset discipline knowledge graph, wherein the discipline knowledge graph is a structured semantic network, and specifically is a collection of interconnection relations among knowledge recorded in a character mode and association relations among all knowledge characters;
s602, extracting keywords through all subject courses, refining the keywords into knowledge points, and determining the relationship between children and parents and the relationship between front and back of the knowledge points;
s603, acquiring the relationship between the child level and the parent level and the relationship between the front level and the rear level, and setting the relationship as a subject knowledge graph, wherein the subject knowledge graph is a structured semantic network, and specifically is a collection of an interconnection relationship among knowledge recorded in a text mode and an association relationship among all knowledge texts;
s604, storing the discipline knowledge graph in a neo4j graphical database through cypher;
s605, establishing a link of the discipline knowledge graph, and waiting for directly operating the neo4j graphical database through the link;
s606, setting at least ten corresponding exercise problems according to each knowledge point in the discipline knowledge graph and storing the exercise problems into the neo4j graphical database;
s607, enabling the student user to test ten questions of the same knowledge point to obtain the number of correct questions;
s608, when the number of the correct questions is larger than 8, the correct questions are regarded as a mastery state, when the number of the correct questions is not larger than 8 and not smaller than 5, the correct questions are regarded as an understanding state, and when the number of the correct questions is smaller than 5, the correct questions are regarded as an unsophisticated state;
s609, classifying the knowledge points of the student user in the understanding state as weak knowledge points, and presenting and recommending the students to review the corresponding knowledge point contents on a knowledge point list;
s610, classifying the knowledge points of the student user in the unowned state as unknown knowledge points, presenting and recommending the student to learn the knowledge point content in a key point mode by using special colors on a knowledge point list, simultaneously inspecting the mastering condition of the student user on the front knowledge points of the knowledge points, and if the knowledge points are still unknown knowledge points, continuously inspecting the knowledge points at the upper level, so that a personalized knowledge point learning path can be connected in a knowledge map, and the learning path can be dynamically changed along with the condition that the student grasps the knowledge points.
In the embodiment of the invention, after the knowledge graph is constructed, a plurality of corresponding exercises are set for each knowledge point in the knowledge graph, and the exercises are stored in the mysql database. The learning path planning and the knowledge difficulty and difficulty point content recommendation functions of the self-adaptive learning platform are respectively specific to learned knowledge and unlearned knowledge of the student. For the learned knowledge, the self-adaptive learning platform dynamically plans a more targeted learning route for the students according to the answering conditions of the students, and the gap filling is efficiently checked; for the knowledge which is not learned yet, the adaptive learning platform can make similar recommendation according to the learning condition data of other students and tell the students which knowledge points need to be studied seriously in the future.
Fig. 7 is a flowchart of content recommendation of difficulty of knowledge in adaptive learning platform based on knowledge-graph according to an embodiment of the present invention.
As shown in fig. 7, in one or more embodiments, preferably, the recommending of the content knowing the difficulty of knowing includes:
s701, acquiring a learning unit as a learning unit;
s702, target students are set, wherein the target students refer to students who finish one third of learning content of the learning units and finish all corresponding systems of the content;
s703, setting a comparison student, wherein the comparison student is the student who completes all learning contents of the learning unit and completes the unit test;
s704, setting ten test questions for each knowledge point;
s705, testing ten questions of each knowledge point of the target student and the comparison student to obtain the number of correct answer questions as the mastery degree of the target student on the corresponding knowledge point;
s706, calculating the similarity by using a collaborative filtering recommendation method according to the mastery degrees of the target student and the comparison student;
s707, after calculating the similarity between all the target students and all the comparison students, determining that the target students corresponding to the comparison students with the similarity larger than 0.95 are similar classmates, and recommending the difficult and difficult point problems encountered by the similar classmates in the later learned contents to the target students corresponding to the similar classmates as the key learning contents.
In the embodiment of the present invention, for example, if the student a has learned the first three chapters of the first unit, the student B has completely learned the first unit, and the similarity of the learning grasping conditions of the first three chapters of the first units a and B is greater than 0.95, the student B is the similar classmate of the student a. If the student B encounters difficulty in learning the second section of the fifth chapter of the first unit and the mastering effect is poor, the second section of the fifth chapter of the first unit can be marked as the difficulty point to be recommended to the student A, and the student A is recommended to focus on learning when the student A learns the section. In any unit learning of the platform, all learners meeting the conditions of the target students perform similarity matching with students who finish the unit learning, and further important and difficult point recommendation information of the unlearned part of the unit is obtained.
In one or more embodiments, preferably, the collaborative filtering recommendation method specifically includes:
calculating the grasping similarity of the students according to the key grasping degrees of the target student and the contrast student by using a first calculation formula;
wherein the first calculation formula is:
wherein sim is the student mastery similarity, xiFor the mastery degree, y, of the i-th knowledge point of the target studentiAnd n is the number of the knowledge points which have been learned by the target student for contrasting the mastery degree of the student on the ith knowledge point.
The method is more targeted, so that the students can concentrate on the real important and difficult points for themselves, and the learning effect of the students is better under the condition of paying the same concentration. Meanwhile, the similarity calculation method is used as the similarity measurement, and the similarity of students on cognitive structures can be reflected better. Compared with the traditional Euclidean distance measurement method which emphasizes absolute differences, the similarity emphasizes the difference in direction, and is more suitable for knowledge recommendation in this point. For example, the mastery of three knowledge points of student a is evaluated as (8, 7, 8), the mastery of three knowledge points of student B is evaluated as (6, 5, 6), and the two knowledge points have a long euclidean distance but a similarity of 0.99. Macroscopically, two classmates are that the first knowledge point and the third knowledge point are better mastered than the second knowledge point, and the trends are similar, so that the trend of two people in later learning can be presumed to be similar. Therefore, the similarity is used for recommending the important difficulty, and the method is more suitable for the application scene than other methods.
In the embodiment of the invention, the self-adaptive learning platform realizes the function of recommending the content of the difficulty in learning and identifying mainly depends on the learning condition data of other similar students of the platform so as to predict the important difficult knowledge which the student may encounter in the future. In the traditional education mode, the knowledge points can be distinguished from the important and difficult points, but the distinction is uniform, namely the important and difficult points of the knowledge are the same for all students. However, students have various differences such as learning basis, cognitive level and the like, and the unified division of important and difficult points is not beneficial to realizing efficient personalized education, so that the platform adopts a collaborative filtering recommendation algorithm to recommend important and difficult point knowledge for the students in a personalized manner, and the learning effect of the students is improved.
Specifically, the single modification and batch import functions of the knowledge graph are realized by a py2neo toolkit, and the addition, deletion, modification and check of the knowledge graph are completed by a cypher statement and a python statement; the batch import function of the knowledge graph is realized by a python back end, target CSV files are put into a neo4j database designated folder, then the neo4j database analyzes the content in the CSV files, the nodes and the relations in the CSV files are identified, and the CSV files are imported into the knowledge graph.
According to a second aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method according to any one of the first aspect of embodiments of the present invention.
According to a third aspect of the embodiments of the present invention, there is provided an electronic apparatus. Fig. 8 is a block diagram of an electronic device in one embodiment of the invention. The electronic device shown in fig. 8 is a generic data sharing fusion device, which includes a generic computer hardware structure, which includes at least a processor 801 and a memory 802. The processor 801 and the memory 802 are connected by a bus 803. The memory 802 is adapted to store instructions or programs executable by the processor 801. The processor 801 may be a stand-alone microprocessor or a collection of one or more microprocessors. Thus, the processor 801 implements the processing of data and the control of other devices by executing instructions stored by the memory 802 to perform the method flows of embodiments of the present invention as described above. The bus 803 connects the above components together, and also connects the above components to a display controller 804 and a display device and an input/output (I/O) device 805. Input/output (I/O) devices 805 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, the input/output devices 805 are coupled to the system through input/output (I/O) controllers 806.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects:
1) the embodiment of the invention provides a self-adaptive learning method based on learning style, which completes dynamic update of student states by adjusting the learning content of students; meanwhile, in the process of determining the learning style, the test result influence index is innovatively added, so that the determination of the learning style is more accurate compared with the existing method;
2) the embodiment of the invention provides an extraction method of key mastery degree, which realizes the self-adaptive adjustment of the learning route of students according to the learning experiences of similar students and the targeted learning of different individuals.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111297763.3A CN113851020A (en) | 2021-11-04 | 2021-11-04 | Self-adaptive learning platform based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111297763.3A CN113851020A (en) | 2021-11-04 | 2021-11-04 | Self-adaptive learning platform based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113851020A true CN113851020A (en) | 2021-12-28 |
Family
ID=78983928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111297763.3A Pending CN113851020A (en) | 2021-11-04 | 2021-11-04 | Self-adaptive learning platform based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113851020A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114579760A (en) * | 2022-02-28 | 2022-06-03 | 深圳懂你教育科技有限公司 | Student wrong question knowledge point self-adaptive stage learning system |
| CN116226348A (en) * | 2023-03-01 | 2023-06-06 | 读书郎教育科技有限公司 | Knowledge graph-based learning method |
| CN116308920A (en) * | 2023-03-03 | 2023-06-23 | 深圳十方融海科技有限公司 | Control method, device, equipment and storage medium |
| CN116610945A (en) * | 2023-03-23 | 2023-08-18 | 读书郎教育科技有限公司 | Learning platform data recording system based on intelligent algorithm |
| CN116862727A (en) * | 2023-07-06 | 2023-10-10 | 杭州睿数科技有限公司 | Teaching management method based on dynamic planning |
| CN116861073A (en) * | 2023-06-09 | 2023-10-10 | 中国船舶集团有限公司第七〇九研究所 | Learning resource pushing method and system |
| CN117252047A (en) * | 2023-11-20 | 2023-12-19 | 深圳市联特微电脑信息技术开发有限公司 | Teaching information processing method and system based on digital twinning |
| CN117672027A (en) * | 2024-02-01 | 2024-03-08 | 青岛培诺教育科技股份有限公司 | VR teaching method, device, equipment and medium |
| CN117972074A (en) * | 2024-03-27 | 2024-05-03 | 山东蓝思教育科技(集团)有限公司 | Personalized learning recommendation method |
| CN118333810A (en) * | 2024-05-21 | 2024-07-12 | 广东保伦电子股份有限公司 | Course arrangement method, electronic device, storage medium, and program product |
| CN118628308A (en) * | 2024-06-03 | 2024-09-10 | 肇庆学院 | Learning content recommendation method and system based on knowledge tracking |
| CN119128233A (en) * | 2024-11-14 | 2024-12-13 | 辽宁蒲公英教育咨询有限公司 | A course recommendation method based on learning trajectory and knowledge graph |
| CN119273009A (en) * | 2024-12-06 | 2025-01-07 | 广州中长康达信息技术有限公司 | Student guidance data processing method and system based on multiple AI models |
| CN120182053A (en) * | 2025-01-16 | 2025-06-20 | 江苏旭禾教育科技有限公司 | A teaching information processing system and method based on electrical automation control |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6782396B2 (en) * | 2001-05-31 | 2004-08-24 | International Business Machines Corporation | Aligning learning capabilities with teaching capabilities |
| CN110765362A (en) * | 2019-09-04 | 2020-02-07 | 广东工业大学 | Collaborative filtering personalized learning recommendation method based on learning condition similarity |
| CN111831831A (en) * | 2020-07-17 | 2020-10-27 | 广东金融学院 | A Personalized Learning Platform Based on Knowledge Graph and Its Construction Method |
| CN112507140A (en) * | 2021-02-08 | 2021-03-16 | 深圳市阿卡索资讯股份有限公司 | Personalized intelligent learning recommendation method, device, equipment and storage medium |
| CN112632295A (en) * | 2020-12-31 | 2021-04-09 | 郑雁 | Learning resource dynamic planning method and device based on knowledge graph |
| CN113111242A (en) * | 2021-03-10 | 2021-07-13 | 西安理工大学 | Self-adaptive learning path recommendation method based on knowledge graph |
| CN113190747A (en) * | 2021-04-29 | 2021-07-30 | 西安理工大学 | Personalized resource recommendation method based on learning style and cognitive level |
-
2021
- 2021-11-04 CN CN202111297763.3A patent/CN113851020A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6782396B2 (en) * | 2001-05-31 | 2004-08-24 | International Business Machines Corporation | Aligning learning capabilities with teaching capabilities |
| CN110765362A (en) * | 2019-09-04 | 2020-02-07 | 广东工业大学 | Collaborative filtering personalized learning recommendation method based on learning condition similarity |
| CN111831831A (en) * | 2020-07-17 | 2020-10-27 | 广东金融学院 | A Personalized Learning Platform Based on Knowledge Graph and Its Construction Method |
| CN112632295A (en) * | 2020-12-31 | 2021-04-09 | 郑雁 | Learning resource dynamic planning method and device based on knowledge graph |
| CN112507140A (en) * | 2021-02-08 | 2021-03-16 | 深圳市阿卡索资讯股份有限公司 | Personalized intelligent learning recommendation method, device, equipment and storage medium |
| CN113111242A (en) * | 2021-03-10 | 2021-07-13 | 西安理工大学 | Self-adaptive learning path recommendation method based on knowledge graph |
| CN113190747A (en) * | 2021-04-29 | 2021-07-30 | 西安理工大学 | Personalized resource recommendation method based on learning style and cognitive level |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114579760A (en) * | 2022-02-28 | 2022-06-03 | 深圳懂你教育科技有限公司 | Student wrong question knowledge point self-adaptive stage learning system |
| CN116226348A (en) * | 2023-03-01 | 2023-06-06 | 读书郎教育科技有限公司 | Knowledge graph-based learning method |
| CN116226348B (en) * | 2023-03-01 | 2023-09-26 | 读书郎教育科技有限公司 | A learning method based on knowledge graph |
| CN116308920A (en) * | 2023-03-03 | 2023-06-23 | 深圳十方融海科技有限公司 | Control method, device, equipment and storage medium |
| CN116610945A (en) * | 2023-03-23 | 2023-08-18 | 读书郎教育科技有限公司 | Learning platform data recording system based on intelligent algorithm |
| CN116610945B (en) * | 2023-03-23 | 2023-11-14 | 读书郎教育科技有限公司 | Learning platform data recording system based on intelligent algorithm |
| CN116861073A (en) * | 2023-06-09 | 2023-10-10 | 中国船舶集团有限公司第七〇九研究所 | Learning resource pushing method and system |
| CN116862727A (en) * | 2023-07-06 | 2023-10-10 | 杭州睿数科技有限公司 | Teaching management method based on dynamic planning |
| CN117252047A (en) * | 2023-11-20 | 2023-12-19 | 深圳市联特微电脑信息技术开发有限公司 | Teaching information processing method and system based on digital twinning |
| CN117252047B (en) * | 2023-11-20 | 2024-03-19 | 深圳市联特微电脑信息技术开发有限公司 | Teaching information processing method and system based on digital twinning |
| CN117672027A (en) * | 2024-02-01 | 2024-03-08 | 青岛培诺教育科技股份有限公司 | VR teaching method, device, equipment and medium |
| CN117672027B (en) * | 2024-02-01 | 2024-04-30 | 青岛培诺教育科技股份有限公司 | VR teaching method, device, equipment and medium |
| CN117972074A (en) * | 2024-03-27 | 2024-05-03 | 山东蓝思教育科技(集团)有限公司 | Personalized learning recommendation method |
| CN118333810A (en) * | 2024-05-21 | 2024-07-12 | 广东保伦电子股份有限公司 | Course arrangement method, electronic device, storage medium, and program product |
| CN118628308A (en) * | 2024-06-03 | 2024-09-10 | 肇庆学院 | Learning content recommendation method and system based on knowledge tracking |
| CN119128233A (en) * | 2024-11-14 | 2024-12-13 | 辽宁蒲公英教育咨询有限公司 | A course recommendation method based on learning trajectory and knowledge graph |
| CN119128233B (en) * | 2024-11-14 | 2025-01-24 | 辽宁蒲公英教育咨询有限公司 | Course recommendation method based on learning track and knowledge graph |
| CN119273009A (en) * | 2024-12-06 | 2025-01-07 | 广州中长康达信息技术有限公司 | Student guidance data processing method and system based on multiple AI models |
| CN120182053A (en) * | 2025-01-16 | 2025-06-20 | 江苏旭禾教育科技有限公司 | A teaching information processing system and method based on electrical automation control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113851020A (en) | Self-adaptive learning platform based on knowledge graph | |
| Akçapınar et al. | Using learning analytics to develop early-warning system for at-risk students | |
| Ilić et al. | Intelligent techniques in e-learning: a literature review | |
| Cho et al. | Exploring online students’ self-regulated learning with self-reported surveys and log files: a data mining approach | |
| Romero et al. | Educational data mining: a review of the state of the art | |
| Blikstein et al. | Programming pluralism: Using learning analytics to detect patterns in the learning of computer programming | |
| Scheuer et al. | Educational data mining | |
| CN111274411A (en) | Course recommendation method and device, electronic equipment and readable storage medium | |
| CN112184500A (en) | Extraclass learning tutoring system based on deep learning and knowledge graph and implementation method | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| Hwang et al. | Diagnosing student learning problems based on historical assessment records | |
| Yuan et al. | Assessment of collaborative problem solving based on process stream data: A new paradigm for extracting indicators and modeling dyad data | |
| Goggins et al. | Learning Analytics at" Small" Scale: Exploring a Complexity-Grounded Model for Assessment Automation. | |
| Durak et al. | Classification and prediction‐based machine learning algorithms to predict students’ low and high programming performance | |
| Sandiwarno et al. | A novel hybrid machine learning model for analyzing e-learning users’ satisfaction | |
| Hidayat et al. | Usability evaluation on educational chatbot using the system usability scale (SUS) | |
| Kang et al. | Investigating navigational behavior patterns of students across at-risk categories within an open-ended serious game | |
| Akhuseyinoglu et al. | Exploring behavioral patterns for data-driven modeling of learners' individual differences | |
| Huang et al. | Uncovering emotion sequence patterns in different interaction groups using deep learning and sequential pattern mining | |
| Kahraman et al. | A novel model for web‐based adaptive educational hypermedia systems: SAHM (supervised adaptive hypermedia model) | |
| CN118822696A (en) | Personalized exercise resource recommendation method and system based on solution strategy | |
| Mendjoge et al. | Review of knowledge representation techniques for Intelligent Tutoring System | |
| Bendjebar et al. | An improvement of a data mining technique for early detection of at-risk learners in distance learning environments | |
| de Morais et al. | Improving sensor-free affect detection by considering students' personality traits | |
| Pokharel | Determining learning style preferences of learners |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211228 |
|
| RJ01 | Rejection of invention patent application after publication |