CN112016767A - Dynamic planning method and device for learning route - Google Patents
Dynamic planning method and device for learning route Download PDFInfo
- Publication number
- CN112016767A CN112016767A CN202011073828.1A CN202011073828A CN112016767A CN 112016767 A CN112016767 A CN 112016767A CN 202011073828 A CN202011073828 A CN 202011073828A CN 112016767 A CN112016767 A CN 112016767A
- Authority
- CN
- China
- Prior art keywords
- learning
- students
- student
- questions
- knowledge
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 14
- 238000013135 deep learning Methods 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000007786 learning performance Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 2
- 239000000463 material Substances 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003306 harvesting Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000692 anti-sense effect Effects 0.000 description 1
- 239000000872 buffer Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a dynamic planning method and device for a learning route. The method comprises the following steps: comprehensively evaluating the historical learning process, knowledge point mastering degree and learning ability of the student; recommending an optimal learning path to the student according to the knowledge graph and the comprehensive evaluation result; the forecast of probability distribution of mastering conditions of examination questions by students is given by an AI teacher module trained in advance; and recommending appropriate post-class practice questions to the students according to the prediction results. The dynamic planning method and the dynamic planning device for the learning route plan the optimal learning route from huge teaching resources according to the abilities of students and push reasonable questions to complete the learning of related knowledge points.
Description
Technical Field
The invention relates to the technical field of internet education, in particular to a dynamic planning method and device for a learning route.
Background
In education and teaching, we always advocate 'teaching according to the material'. The reason for education according to the situation is 'education is performed according to the specific conditions of the ability, character, aspiration and the like of the learners'. The core of the teaching aid is 'timber', namely 'students', education of an educator is required to be performed according to different conditions of the 'students', and the 'students' are objects for implementing education and are often the only basis for implementing education and teaching of the educator. Under the background of the internet + era, the appeal of parents and students is that comprehensive teaching is carried out by requiring multiple course resources. The teaching method is characterized in that different education is performed according to the learning conditions of students, the factors of teaching materials, the conditions in the learning process and the conditions of teachers (which are relatively diluted in the prior teaching), namely, the teaching according to the conditions aims at the abilities, the characters and the interests of the learners and the teachers, the characteristics of the teaching materials and the situation during teaching.
Along with the rapid development of the internet, the internet adds a plurality of element colors to the traditional education mode and also prompts the rapid development of the online education industry. Many education and teaching modes are moved from off-line to on-line, which brings great opportunity and challenge to on-line education. The opportunity is that a lot of teaching resources and data are accumulated, and the speed and the range of knowledge propagation are improved; the challenge is how to learn a large amount of teaching resources and data knowledge in a short time. Meanwhile, from the perspective of students, how to learn in numerous learning resources according to individual abilities and interests and according to a reasonable learning route, the core of knowledge is mastered.
Under the current situation, when many self-adaptive education companies are used for teaching related products according to the factors, the data analysis dimension is extremely single, and comprehensive data such as student capacity, knowledge point difficulty, teaching resources and the like are not utilized. At present, most products are based on a simple question-pushing function of traditional deep learning such as Knowledge Tracking (KT) or a Knowledge point recommendation based on a Knowledge graph. The method neglects thinking about student abilities and matching analysis of difficulty of the students, only recommends simple questions for the students, does not comprehensively consider the abilities of the students, the difficulty of the questions and the complexity of knowledge points to carry out complex comprehensive recommendation, then timely pushes related teaching resources according to the learning states of the students to answer questions for the students in time, and lacks the ability of integrating huge teaching resources. The students cannot be provided with positive guidance, which leads to difficult execution of the education according to the material.
Disclosure of Invention
The invention aims to provide a dynamic planning method and a dynamic planning device for a learning route, which plan an optimal learning route and push reasonable questions from huge teaching resources according to the abilities of students to complete the learning of related knowledge points.
In order to solve the technical problem, the invention provides a dynamic planning method for a learning route, which comprises the following steps: comprehensively evaluating the historical learning process, knowledge point mastering degree and learning ability of the student; recommending an optimal learning path to the student according to the knowledge graph and the comprehensive evaluation result; the forecast of probability distribution of mastering conditions of examination questions by students is given by an AI teacher module trained in advance; and recommending appropriate post-class practice questions to the students according to the prediction results.
In some embodiments, the comprehensive evaluation of the student's historical learning history includes: collecting and structuring learning behavior data of a single student; and correcting abnormal data appearing in the learning process of the students.
In some embodiments, the comprehensive assessment of the knowledge point mastery degree of the student comprises: constructing a deep learning multilayer network by utilizing a deep learning theory; according to the historical learning behaviors of students, the mastery degree and proficiency degree of the students on each knowledge point are mined by utilizing the deep learning multi-layer network.
In some embodiments, the comprehensive assessment of the learning abilities of the students includes: the method comprehensively evaluates the mastering degree of the students on the knowledge points, the subject content of the after-class exercises, the hobbies of the students, the living habits of the students and the interest degree of the English theme.
In some embodiments, recommending an optimal learning path to the student according to the knowledge graph and the comprehensive evaluation result comprises: and making a decision according to the comprehensive evaluation result of the historical learning process, the knowledge point mastering degree and the learning ability to obtain the recommended optimal learning path.
In some embodiments, the pre-training operation on the AI instructor module includes: taking the question making records of students and the question stem text contents of the questions as a basis, coding the question stem by adopting a natural language technology, and understanding the question stem text contents as a model; coding the knowledge points related to the questions, and analyzing the understanding degree of different knowledge points as an algorithm model; the learning state of each student and the mastery degree of different knowledge points are coded, and basic conditions are provided for the students to learn the personalized optimal learning path.
In some embodiments, recommending appropriate post-session exercise questions to the student based on the prediction results includes: predicting the future mastering conditions of the students on different questions under different knowledge points based on the learning performance of the students, and then performing difficulty grade division by using a hierarchical clustering algorithm and a decision algorithm based on a probability prediction result of the questions; the teacher blends the knowledge point range of each class teaching, teaching contents and other contents, integrates the capability evaluation and the optimal path customization results of the students in the prior art, and rejects part of questions; making a question decision of the last link by adopting a decision tree algorithm and according to the specification of the after-class exercises; and giving out the exercise after the class according to the question decision result.
In some embodiments, the difficulty ranking comprises: super simple, medium, difficult, super difficult.
In some embodiments, the proposed topics include: super simple and super difficult topics.
In addition, the present invention also provides a dynamic planning apparatus for learning a route, the apparatus comprising: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for dynamic planning of a learned route according to the foregoing.
After adopting such design, the invention has at least the following advantages:
the invention can track the learning state of students, dynamically plan the optimal learning route for the students, automatically analyze the mastering conditions of the students on different knowledge points without the supervision of teachers, then recommend teaching resources suitable for the abilities of the students, help the students to improve the learning interest and simultaneously harvest the growth of scores, and obtain the consistent recognition of a plurality of experienced and highly qualified teachers.
Drawings
The foregoing is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and the detailed description.
FIG. 1 is a flow chart of a method for dynamically planning a learned route according to an embodiment of the present invention;
fig. 2 is a structural diagram of a dynamic planning apparatus for learning a route according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
In order to solve the problem of extremely demanding 'teaching by factors' products, the invention integrates huge teaching resources and student data, realizes the first combination of deep learning and knowledge maps, and simultaneously realizes the recommendation scheme of deeply mining the teaching resources and the data and planning the learning route by utilizing the technology. The invention deeply excavates and tracks the learning state of students, constructs a knowledge point mastering matrix and a learning path for each student, dynamically tracks and analyzes the learning ability and the mastering degree of the knowledge points of the students, and then directionally pushes related learning materials to the students, so that the students can master new knowledge in a huge knowledge system in the shortest time according to the optimal learning path. Therefore, the invention enables the students to own a private AI teacher in the Internet era, and the AI teacher can supervise in real time every day according to the learning conditions of different students and check the omission of knowledge points in time, thereby realizing a real product of 'teaching according to the material'.
Deep learning is combined with a knowledge map, and the student ability, the subject difficulty, the knowledge point complexity and other dimensions are analyzed to construct a knowledge point mastering matrix and a learning path for the student. On each learning path, recommending related learning contents for the students from massive learning resources according to the abilities of the students, and enabling the AI teachers to ask and answer questions for the students in time to improve the learning abilities of the students.
2.1 core of practice and education according to the specific
2.1.1 educational database
Referring to fig. 1, the education database includes a material repository, an education repository, a question repository, and student answer records. The main content of the material resource library comprises video, pictures, texts and the like; the education resource library mainly comprises an outline, a course system, teaching targets, teaching courseware and the like; the question bank is mainly used for post-class exercises; the student answering records refer to the scoring conditions of the examination and the after-class exercises of the students. The data are all cleaned and put in storage according to a strict format, so that the AI algorithm can reasonably and efficiently utilize related data, the learning behaviors of students can be tracked in real time, and important data basic guarantee is provided for analyzing the learning states and abilities of the students and individually customizing the learning path.
2.1.2AI Algorithm
The invention analyzes and mines huge data based on the deep learning theory and analyzes potential student learning information, knowledge point information and question stem information.
The AI algorithm fuses deep learning, clustering and decision-making algorithms, firstly encodes the subject text content in the subject database, and provides first-step encoding information for AI reading and understanding of the subject stem. Meanwhile, the AI algorithm encodes the content of the knowledge points considered by the question stem and is responsible for analyzing the difficulty and complexity information of the knowledge points. The algorithm simultaneously judges the ability of students, tracks the learning state and diagnoses and analyzes knowledge points. Meanwhile, the teaching target of the teacher is added into the model by the algorithm, and basic information data and planning are provided for the personalized learning path customization of the students.
2.1.3 knowledge map
The knowledge graph subdivides different grades, different units, different teaching contents and the like of the courses, wherein the teaching contents comprise contents such as teaching contents, grammar, words, test questions, student information and the like. Taking junior middle school english as an example, the teaching content includes the learning subjects of each lesson of each unit, and the learning subjects are contents such as english conversation, words, phrases and the like aiming at common topics in daily life. The grammar includes verb tenses such as past time, proceeding time, and completion time; simple sentence, compound sentence, definite phrase clause and other sentence pattern structures; active and passive languages, etc. The words comprise roots, affixes, parts of speech, phonetic symbols and homophonic different words and phrases, and each word is related to each other, such as the association of parts of speech of the same root affixes, the same phonetic symbols, sense words or antisense words. The test questions are stored by taking the unique item identifier, knowledge point, question stem, analysis and other contents of the question bank as entities. The students construct the knowledge maps according to the grade of the students, the learning knowledge points, the chapters and other information. Based on the construction of all the entities, the knowledge graph carries out multi-dimensional relation construction on each test question, words, grammar, lecture contents, students and the like, so that a complete relation is established between each entity as far as possible, and each entity in the knowledge graph is guaranteed to have higher association degree.
2.2 historical behavior analysis of students educated by the factors
2.2.1 student's learning course
The module realizes supervision on historical learning behaviors of students. Taking English subjects as an example, the module comprises data of units, subjects, grammars, knowledge points, manufactured subjects and the like which are learned by students, collects and structures learning behavior data of a single student, corrects abnormal data appearing in the learning process of the student, improves data quality and sensitivity, tracks details of each student for a whole product, and achieves vital preparation for real factor education.
2.2.2 degree of mastery of knowledge points
The module has the importance that a deep learning multilayer network is constructed by utilizing a deep learning theory, and the mastery degree and proficiency of students on each knowledge point are mined according to the historical learning behaviors of the students. And predicting the mastery degree of the future knowledge points according to the analysis result of the mastery degree of the historical knowledge points, judging the learning state of the student in an all-around manner, and preparing for the capability evaluation of the student and the planning of the learning path.
2.2.3 student Capacity assessment
The module integrates historical learning data of students and mastery degree of knowledge points, and evaluates and predicts the abilities of the students. The part can use deep learning, an integrated model and a clustering algorithm to predict, the evaluation result of the student ability is evaluated in all aspects from the learning degree of the student to the knowledge points, the subject content of the after-class exercises and other dimensions, the hobbies of the student, the living habits of the student, the interest degree of certain English subjects and other aspects, and the evaluation result is a one-dimensional vector.
2.2.4 optimal learning Path
The module utilizes knowledge map and deep learning technology to provide the best learning path for students according to student capability assessment results and mastery degree results of knowledge points, then obtains relevant teaching materials and courses from a huge teaching database according to the learning path to enable the students to learn, ensures that the students learn in time and consolidates the relevant knowledge points, and achieves the capability of timely missing and filling in defects in the process of teaching according to the factors.
2.3AI teacher
The module is based on deep learning and knowledge map theory, reads all questions, knowledge point contents and teaching targets in a question bank, learns about millions of historical learning behavior data of 10 ten thousand students, is equivalent to teachers with abundant human experiences, and can predict the mastering condition of each knowledge point of the students through the learning conditions of the students. Firstly, in training, the question stem text content of the question and the question making records of students are used as a basis, the question stem is coded by adopting a natural language technology and used as a model to understand the text content of the question stem. Then, the knowledge points related to the topics are coded and used as an algorithm model to analyze the understanding degree of different knowledge points. And finally, coding the learning state of each student and the mastery degree of different knowledge points, and providing basic conditions for the students to learn the personalized optimal learning path. And finally, the AI teacher predicts the probability distribution of the mastering condition of the student on the examination questions.
2.4 topic difficulty clustering
2.4.1 topic difficulty clustering
The module performs difficulty rating based mainly on the probability distribution of each topic predicted by an AI teacher for a particular student. The invention considers that the learning of students aims at improving the learning ability of learning unfamiliar knowledge points, wherein the students with extremely simple knowledge points can continue to learn without wasting time; and the extremely difficult knowledge point is separated from the value recognition ability of students, and the improvement of the ability is not necessarily assisted. The invention predicts the future mastering conditions of different subjects under different knowledge points of a student based on the learning performance of the student, and then performs difficulty grade division by using a hierarchical clustering algorithm and a decision algorithm based on the probability prediction result of the subjects, wherein the difficulty grade division is divided into five grades: super simple, medium, difficult, super difficult.
2.4.2 teaching objects
The teaching target in the invention is the fusion of the knowledge point range and teaching contents of each section of teaching of the teacher. The module is mainly used for eliminating super-simple questions with super-difficulty by integrating the ability evaluation and the optimal path customization result of students based on the test question prediction probability and the question difficulty clustering result.
2.4.3 Integrated decision
The module mainly adopts a decision tree algorithm and makes a question decision of the last link according to the specification of the after-class exercises so as to ensure the best question quality. The module finally realizes that the student selects the most suitable subject from the massive subject database to ensure the effectiveness of the student in practicing the knowledge points in the process of tamping the knowledge points, so that the student can effectively consolidate the learned knowledge points in the shortest time.
2.4.4 recommendation of post-session problems
The module can be used for engineering the questions after comprehensive decision making by adopting an internet technology and pushing the questions to students, so that the students can practice the questions after learning the knowledge points, and the closed loop of the whole learning link is completed. Meanwhile, according to the process of the student exercise problem, the database and the knowledge map are updated according to certain rules according to the relevant data, so that an AI teacher is ensured to capture the learning condition of the student in real time, the latest learning path is timely updated for the student, and the student is ensured to learn enough knowledge in a short time, thereby helping the student to improve the learning ability quickly and efficiently.
The invention can track the learning state of students, dynamically plan the optimal learning route for the students, automatically analyze the mastering conditions of the students on different knowledge points without the supervision of teachers, then recommend teaching resources suitable for the abilities of the students, help the students to improve the learning interest and simultaneously harvest the growth of scores, and obtain the consistent recognition of a plurality of experienced and highly qualified teachers.
Fig. 2 shows the structure of a dynamic planning apparatus for learning a route. Referring to fig. 2, for example, the dynamic planning apparatus 200 for learning a route may be used to serve as a learning path planning apparatus in an online education system. As described herein, the dynamic planning device for learning a route 200 can be used to implement a planning function for a student's learning path in an online education system. The dynamic planner 200 of the learned route may be implemented in a single node, or the functionality of the dynamic planner 200 of the learned route may be implemented in multiple nodes in the network. Those skilled in the art will appreciate that the term dynamic planning of a learned route includes devices in a broad sense, of which the dynamic planning of a learned route 200 shown in fig. 2 is only one example. The dynamic planning apparatus 200 including a learned route is for clarity and is not intended to limit the application of the present invention to a specific embodiment of a dynamic planning apparatus for a learned route or to a certain type of embodiment of a dynamic planning apparatus for a learned route. At least some of the features/methods described herein may be implemented in a network device or component, such as the dynamic planning device 200 for learning a route. For example, the features/methods of the present invention may be implemented in hardware, firmware, and/or software running installed on hardware. The dynamic planning device 200 for learning a route may be any device that processes, stores, and/or forwards data frames through a network, such as a server, a client, a data source, and the like. As shown in fig. 2, the dynamic route planner 200 may include a transceiver (Tx/Rx)210, which may be a transmitter, a receiver, or a combination thereof. Tx/Rx 210 may be coupled to a plurality of ports 250 (e.g., an uplink interface and/or a downlink interface) for transmitting and/or receiving frames from other nodes. Processor 230 may be coupled to Tx/Rx 210 to process frames and/or determine to which nodes to send frames. Processor 230 may include one or more multi-core processors and/or memory devices 232, which may serve as data stores, buffers, and the like. Processor 230 may be implemented as a general-purpose processor or may be part of one or more Application Specific Integrated Circuits (ASICs) and/or Digital Signal Processors (DSPs).
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the present invention in any way, and it will be apparent to those skilled in the art that the above description of the present invention can be applied to various modifications, equivalent variations or modifications without departing from the spirit and scope of the present invention.
Claims (10)
1. A method for dynamically planning a learned route, comprising:
comprehensively evaluating the historical learning process, knowledge point mastering degree and learning ability of the student;
recommending an optimal learning path to the student according to the knowledge graph and the comprehensive evaluation result;
the forecast of probability distribution of mastering conditions of examination questions by students is given by an AI teacher module trained in advance;
and recommending appropriate post-class practice questions to the students according to the prediction results.
2. The dynamic planning method for learning route according to claim 1, wherein the comprehensive evaluation of the historical learning history of the student comprises:
collecting and structuring learning behavior data of a single student; and
and correcting abnormal data occurring in the learning process of the students.
3. The dynamic planning method for learning route according to claim 1, wherein the comprehensive evaluation of the knowledge point mastery degree of the student comprises:
constructing a deep learning multilayer network by utilizing a deep learning theory;
according to the historical learning behaviors of students, the mastery degree and proficiency degree of the students on each knowledge point are mined by utilizing the deep learning multi-layer network.
4. The dynamic planning method for learning route according to claim 1, wherein the comprehensive evaluation of the learning ability of the student comprises:
the method comprehensively evaluates the mastering degree of the students on the knowledge points, the subject content of the after-class exercises, the hobbies of the students, the living habits of the students and the interest degree of the English theme.
5. The dynamic planning method for learning route according to claim 1, wherein the recommending an optimal learning path to the student according to the knowledge map and the comprehensive evaluation result comprises:
and making a decision according to the comprehensive evaluation result of the historical learning process, the knowledge point mastering degree and the learning ability to obtain the recommended optimal learning path.
6. The method for dynamically planning a learning route according to claim 1, wherein the pre-training operation of the AI instructor module comprises:
taking the question making records of students and the question stem text contents of the questions as a basis, coding the question stem by adopting a natural language technology, and understanding the question stem text contents as a model;
coding the knowledge points related to the questions, and analyzing the understanding degree of different knowledge points as an algorithm model;
the learning state of each student and the mastery degree of different knowledge points are coded, and basic conditions are provided for the students to learn the personalized optimal learning path.
7. The dynamic planning method for learning route according to claim 1, wherein recommending appropriate post-session exercise questions to students according to the prediction result comprises:
predicting the future mastering conditions of the students on different questions under different knowledge points based on the learning performance of the students, and then performing difficulty grade division by using a hierarchical clustering algorithm and a decision algorithm based on a probability prediction result of the questions;
the teacher blends the knowledge point range of each class teaching, teaching contents and other contents, integrates the capability evaluation and the optimal path customization results of the students in the prior art, and rejects part of questions;
making a question decision of the last link by adopting a decision tree algorithm and according to the specification of the after-class exercises;
and giving out the exercise after the class according to the question decision result.
8. The method for dynamically planning a learned route according to claim 7, wherein the difficulty ranking comprises: super simple, medium, difficult, super difficult.
9. The method for dynamic planning of a learned route according to claim 8, wherein the proposed topics include: super simple and super difficult topics.
10. A dynamic planning apparatus for learning a route, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of learning the dynamic planning of a route according to any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011073828.1A CN112016767A (en) | 2020-10-09 | 2020-10-09 | Dynamic planning method and device for learning route |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011073828.1A CN112016767A (en) | 2020-10-09 | 2020-10-09 | Dynamic planning method and device for learning route |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112016767A true CN112016767A (en) | 2020-12-01 |
Family
ID=73527199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011073828.1A Pending CN112016767A (en) | 2020-10-09 | 2020-10-09 | Dynamic planning method and device for learning route |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112016767A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632295A (en) * | 2020-12-31 | 2021-04-09 | 郑雁 | Learning resource dynamic planning method and device based on knowledge graph |
| CN112734142A (en) * | 2021-04-02 | 2021-04-30 | 平安科技（深圳）有限公司 | Resource learning path planning method and device based on deep learning |
| CN112784154A (en) * | 2020-12-31 | 2021-05-11 | 电子科技大学 | Online teaching recommendation system with data enhancement |
| CN112950425A (en) * | 2021-03-09 | 2021-06-11 | 浙江创课网络科技有限公司 | Personalized learning plan dynamic generation method based on multiple dimensions |
| CN113256252A (en) * | 2021-05-25 | 2021-08-13 | 上海金程教育培训有限公司 | B/S architecture-based test system |
| CN113516574A (en) * | 2021-07-27 | 2021-10-19 | 北京爱学习博乐教育科技有限公司 | Self-adaptive learning system based on big data and deep learning and construction method thereof |
| CN114155124A (en) * | 2022-02-07 | 2022-03-08 | 山东建筑大学 | Test question resource recommendation method and system |
| CN114492848A (en) * | 2022-01-13 | 2022-05-13 | 成都合源美智教育科技有限公司 | Self-adaptive learning system compatible with multiple learning models, method and application |
| CN115129895A (en) * | 2022-07-05 | 2022-09-30 | 武汉达芬奇教育科技有限公司 | Self-adaptive learning system |
| CN116450801A (en) * | 2023-03-29 | 2023-07-18 | 北京思明启创科技有限公司 | Program learning method, apparatus, device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108573628A (en) * | 2018-04-23 | 2018-09-25 | 中山大学 | The method that H-NTLA based on study track is recommended with extension knowledge point set |
| CN108806341A (en) * | 2018-03-29 | 2018-11-13 | 上海乂学教育科技有限公司 | A kind of optimal individualized learning paths planning method |
| CN109903617A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Individualized exercise method and system |
| CN110543572A (en) * | 2019-08-26 | 2019-12-06 | 杭州奇迹在线科技有限公司 | learning cognitive path generation method based on cognitive map |
| CN111274411A (en) * | 2020-01-22 | 2020-06-12 | 文思海辉智科科技有限公司 | Course recommendation method and device, electronic equipment and readable storage medium |
| CN111368182A (en) * | 2020-02-17 | 2020-07-03 | 浙江创课网络科技有限公司 | Individualized self-adaptive learning recommendation method based on big data analysis of education platform |
-
2020
- 2020-10-09 CN CN202011073828.1A patent/CN112016767A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109903617A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Individualized exercise method and system |
| CN108806341A (en) * | 2018-03-29 | 2018-11-13 | 上海乂学教育科技有限公司 | A kind of optimal individualized learning paths planning method |
| CN108573628A (en) * | 2018-04-23 | 2018-09-25 | 中山大学 | The method that H-NTLA based on study track is recommended with extension knowledge point set |
| CN110543572A (en) * | 2019-08-26 | 2019-12-06 | 杭州奇迹在线科技有限公司 | learning cognitive path generation method based on cognitive map |
| CN111274411A (en) * | 2020-01-22 | 2020-06-12 | 文思海辉智科科技有限公司 | Course recommendation method and device, electronic equipment and readable storage medium |
| CN111368182A (en) * | 2020-02-17 | 2020-07-03 | 浙江创课网络科技有限公司 | Individualized self-adaptive learning recommendation method based on big data analysis of education platform |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112784154B (en) * | 2020-12-31 | 2022-03-15 | 电子科技大学 | Online teaching recommendation system with data enhancement |
| CN112784154A (en) * | 2020-12-31 | 2021-05-11 | 电子科技大学 | Online teaching recommendation system with data enhancement |
| CN112632295A (en) * | 2020-12-31 | 2021-04-09 | 郑雁 | Learning resource dynamic planning method and device based on knowledge graph |
| CN112950425A (en) * | 2021-03-09 | 2021-06-11 | 浙江创课网络科技有限公司 | Personalized learning plan dynamic generation method based on multiple dimensions |
| CN112950425B (en) * | 2021-03-09 | 2024-02-06 | 浙江创课网络科技有限公司 | Multi-dimension-based personalized learning plan dynamic generation method |
| CN112734142A (en) * | 2021-04-02 | 2021-04-30 | 平安科技（深圳）有限公司 | Resource learning path planning method and device based on deep learning |
| CN112734142B (en) * | 2021-04-02 | 2021-07-02 | 平安科技（深圳）有限公司 | Resource learning path planning method and device based on deep learning |
| CN113256252A (en) * | 2021-05-25 | 2021-08-13 | 上海金程教育培训有限公司 | B/S architecture-based test system |
| CN113516574A (en) * | 2021-07-27 | 2021-10-19 | 北京爱学习博乐教育科技有限公司 | Self-adaptive learning system based on big data and deep learning and construction method thereof |
| CN114492848A (en) * | 2022-01-13 | 2022-05-13 | 成都合源美智教育科技有限公司 | Self-adaptive learning system compatible with multiple learning models, method and application |
| CN114155124A (en) * | 2022-02-07 | 2022-03-08 | 山东建筑大学 | Test question resource recommendation method and system |
| CN115129895A (en) * | 2022-07-05 | 2022-09-30 | 武汉达芬奇教育科技有限公司 | Self-adaptive learning system |
| CN116450801A (en) * | 2023-03-29 | 2023-07-18 | 北京思明启创科技有限公司 | Program learning method, apparatus, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112016767A (en) | Dynamic planning method and device for learning route | |
| Marques et al. | Teaching machine learning in school: A systematic mapping of the state of the art | |
| US20060166174A1 (en) | Predictive artificial intelligence and pedagogical agent modeling in the cognitive imprinting of knowledge and skill domains | |
| CN113516574A (en) | Self-adaptive learning system based on big data and deep learning and construction method thereof | |
| CN111445362A (en) | Learner-centered adaptive learning system | |
| Ullah et al. | A rule-based method for cognitive competency assessment in computer programming using Bloom’s taxonomy | |
| Singh et al. | Implementation and evaluation of intelligence incorporated tutoring system | |
| Kwon et al. | A study on the design and effect of computational thinking and software education | |
| CN113378581B (en) | Knowledge tracking method and system based on multivariate concept attention model | |
| Mamcenko et al. | On using learning analytics to personalise learning in virtual learning environments | |
| CN113327468A (en) | Open-development type online vocational education course system | |
| CN113434563A (en) | Reinforced learning method and system in adaptive learning path recommendation | |
| Qiao et al. | Study on obe teaching concept in the context of deep learning for the construction of university mathematics microcourses | |
| Zulueta et al. | Scenario-based microlearning strategy for improved basic science process skills in self-directed learning | |
| Shaffer et al. | Using a quantitative model of participation in a community of practice to direct automated mentoring in an ill-formed domain | |
| Juric et al. | Implementing M-Learning System for Learning Mathematics Through Computer Games and Applying Neural Networks for Content Similarity Analysis of an Integrated Social Network. | |
| CN114155124B (en) | Test question resource recommendation method and system | |
| Spain et al. | Automated Assessment of Teamwork Competencies using Evidence-Centered Design-Based Natural Language Processing Approach | |
| Zou et al. | A novel learning early-warning model based on knowledge points and question types | |
| Sun et al. | Data Model Building for Online Teachers' Professional Development | |
| Wijayawardena et al. | AI and Machine Learning Based E–Learning System For Secondary Education | |
| CN117540108B (en) | Intelligent recommendation answering system based on examination point data distributed summary | |
| Karthik Ganesh | The Influence of AI-Assisted Learning on CAL: A Blueprint | |
| Blueprint | The Influence of AI-Assisted Learning on CAL | |
| Wang et al. | The Evaluation Model of College English Diagnostic Exercises Based on Machine Learning |
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 |