Online education curriculum optimization sorting method and system
By calculating the recommendation index, we recommend course units that meet the current learning status of learners, which solves the problem of failing to effectively rely on learning characteristics in the existing technology, and achieves targeted optimization of online education courses and improves learning efficiency.
Patent Information
- Application Number
- CN202411586878.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-08
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing online education course optimization methods have failed to effectively rely on the actual learning characteristics of learners, resulting in excessive investment but poor results.
By obtaining the current learning direction and status of the learners, calculating the recommendation index, recommending course units that meet the learning status, forming an optimized course set, and sorting the recommendation index from large to small.
It realizes targeted optimization of the course, avoids repeated learning, saves learning time, and improves learning efficiency.
Smart Images

Figure CN119090686A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to an online education course optimization sorting method and system. Background Art
[0002] Online education refers to a way of providing students with convenient and efficient educational services through Internet technology. The advantage of online education is that it breaks geographical restrictions, allowing learners to enjoy high-quality educational resources wherever they are as long as they have access to the Internet. In recent years, online education in my country has developed rapidly, and more and more students choose online learning. There are several main reasons: 1. Rich teaching resources: Online education platforms bring together famous teachers from famous schools across the country. Students can choose courses according to their interests and needs to broaden their knowledge. 2. Flexible learning time: Online education allows students to study at any time and any place, which is very suitable for the lifestyle of modern people. 3. Lower learning costs: Compared with traditional education, online education tuition fees are often lower, and some platforms are even free, so students can save a lot of transportation costs. 4. Strong interactivity: Online education provides a rich communication platform. Students can interact with other students through discussion areas, question-and-answer tools, and deepen their understanding of knowledge. 5. Personalized learning: Online education platforms will recommend learning content and progress suitable for students based on their learning behaviors and habits, which is conducive to personalized learning. In general, online education is an emerging educational model that not only meets the learning needs of students, but also brings new changes to the education industry.
[0003] In order to optimize online education courses, we need to consider the following aspects: 1. Course content: High-quality course content is the key to attracting and retaining students. Therefore, we need to continuously update and improve the course content to make it closer to the needs of the times and society, while focusing on the depth and breadth of knowledge to meet the learning needs of different students. 2. Teaching methods: We can use a variety of teaching methods, such as video explanations, live lectures, interactive discussions, etc., to improve the fun and interactivity of learning. In addition, we can also introduce some practical teaching methods, such as case analysis, role-playing, etc., so that students can better understand and master knowledge. 3. Technical support: One of the major advantages of online education is that learning can be carried out anytime and anywhere, so we need to ensure the stability and fluency of technology to ensure that students can learn smoothly. In addition, we also need to continuously upgrade and optimize the teaching platform to provide a better user experience. 4. Service quality: High-quality service quality can improve student satisfaction and retention. We need to establish a sound service system, respond to students' questions and problems in a timely manner, and provide personalized learning support and feedback. 5. Evaluation mechanism: Establishing a scientific and reasonable evaluation mechanism can help us better understand students’ learning outcomes, thereby adjusting teaching strategies and methods and improving teaching quality. In general, the optimization of online education courses is a continuous process that requires us to comprehensively consider and optimize from multiple aspects in order to truly improve the quality and value of online education.
[0004] Existing course optimization is based on the optimization of the course content itself, and does not rely on the actual learning characteristics of learners, which often results in excessive investment but poor results. Summary of the invention
[0005] In order to solve the above technical problems, the present invention provides an online education course optimization and sorting method, which is suitable for recommending learners to review the learned content, especially for optimizing and recommending courses for individual learners. The online education course optimization and sorting method comprises the following steps: S1. Obtain the current learning direction of the learner and determine the corresponding basic learning unit according to the learning direction.
[0006] S2. Obtain the current learning status of the learner, and calculate the learner's status keyword and its corresponding learning saturation value S.
[0007] S3. Extract the basic learning units of the current learning direction, and calculate the recommendation index R based on its learning keywords, the status keywords of the learners, and the learning saturation value.
[0008] S4. The recommended index R of the basic learning unit for the selected learning direction is greater than a preset The basic learning units are collected and organized into an optimized course set. They are sorted from large to small according to the recommendation index R, and then recommended in order.
[0009] Preferably: the learning direction division may include but is not limited to learning content, learning progress, learning mode, etc.
[0010] Preferably, the method for obtaining the learning status of a learner may include: obtaining the learning supplementary materials of the learner, binding and analyzing the learning supplementary materials with the learner, and obtaining the current learning status of the learner.
[0011] Preferably: the teaching supplementary materials may include exercises and test papers for learners.
[0012] Preferably, the method for obtaining the status keywords of the learner may include: dividing the content of the supplementary teaching materials to obtain various learning content units, then analyzing the learning content units to obtain the content tags of the corresponding learning basic units, then classifying the learning content units according to the content tags of the learning basic units, obtaining the learning direction corresponding to the learning content units, and then constructing the status keywords according to the learning direction and the content tags. Therefore, the status keywords at this time are learning direction-content tags.
[0013] Preferably, the method for obtaining the learning saturation value S may include: collecting the same state keywords within a preset reference time period to obtain a state keyword set, and then calculating the learning saturation value S of the state keyword set.
[0014] Preferred: Learn saturation value , where i is the ranking number of the state keyword in the state keyword set, I is the total number of state keywords in the state keyword set, i=1,2,…,I; j is the evaluation impact factor number of the state keyword, J is the total number of evaluation impact factors of the state keyword, j=1,2,…,J; It is the value of the status keyword numbered i and the evaluation impact factor numbered j.
[0015] Preferably: the evaluation influencing factors may include but are not limited to proportional value influencing factors , weight impact factor And the proportion of impact factors wait.
[0016] Preferred: The proportion influencing factor , where i is the ranking number of the state keyword, I is the total number of state keywords in the state keyword set, i=1,2,…,I; is the actual score of the status keyword. The full score corresponding to the status keyword.
[0017] Preferred: Recommended index for learning basic units , where n is the number of the evaluation factor of the relevant state keyword set of the current learning basic unit, N is the total number of evaluation factors of the state keyword set, n=1,2,…,N; is the overlap value between the state keyword set numbered n and the evaluation factors of the basic learning unit. The evaluation factors here include learning direction and content label. It is the weight value of the factor overlap evaluation of the state keyword set, which can be preset according to actual conditions, and its value is generally 1-10.
[0018] Preferably: the overlap value The calculation method may be the overlap ratio between the content of the learning keyword numbered n in the status keyword and the content of the corresponding learning keyword.
[0019] The present invention also provides an online education course optimization and sorting system, comprising: The learning direction selection module is used to obtain the current learning direction of the learner and determine the corresponding basic learning unit according to the learning direction.
[0020] The learning status acquisition module is used to obtain the current learning status of the learner, calculate the learner's status keyword and its corresponding learning saturation value S. The learning status acquisition module obtains the learner's supplementary teaching materials, binds the supplementary teaching materials with the learner and analyzes them, so as to obtain the learner's current learning status.
[0021] The recommendation calculation module is used to extract the basic learning units of the current learning direction and calculate the recommendation index R based on its learning keywords, the status keywords of the learners, and the learning saturation value.
[0022] The course optimization module is used to recommend the learning basic unit index R of the selected learning direction to be greater than a preset The basic learning units are collected and organized into an optimized course set. They are sorted from large to small according to the recommendation index R, and then recommended in order.
[0023] The display module is used to display the optimized course set.
[0024] Preferably: the online education course optimization and sorting system also includes a course segmentation module, which is used to segment the education course to obtain learning basic units. The learning basic units can be based on knowledge points, and each learning basic unit corresponds to a knowledge point. Of course, the education course can also be manually segmented to obtain learning basic units, or it can be directly produced according to knowledge points. The details are not repeated here.
[0025] The technical effects and advantages of the present invention are as follows: the present invention evaluates by calculating the recommendation index, and the learning basic unit with a large recommendation index is more consistent with the current learning status of the learner. The online course is optimized by forming an optimized course set, so that the course is more targeted and convenient for the learner to learn in a targeted manner. It avoids a large amount of repeated learning by the learner, thereby saving learning time and improving learning efficiency. The threshold can be set artificially, so that it has strong applicability. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 A flowchart of an online education course optimization sorting method proposed by the present invention.
[0027] Figure 2 The present invention provides a flowchart of status keywords in an online education course optimization sorting method.
[0028] Figure 3 This is a structural block diagram of an online education course optimization and sorting system proposed by the present invention. DETAILED DESCRIPTION
[0029] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.
[0030] Example 1 refer to Figure 1 In this embodiment, an online education course optimization and sorting method is proposed, which is suitable for recommending learners to review the learned content, especially for optimizing and recommending courses for individual learners. The online education course optimization and sorting method includes the following steps: S1. Obtain the current learning direction of the learner, and determine the corresponding learning basic unit according to the learning direction. The learner is a learning unit subject, and a learning unit subject is required to have a learning characteristic, so as to facilitate the targeted evaluation of the learning unit subject, which is convenient for the later course optimization and recommendation. The learning unit subject can be a person, of course, it can also be a class, a group, etc. The learning characteristic can be learning progress, learning bias, etc., which will not be described in detail here. For a person, the learning characteristic is the characteristic of this person in this learning direction. As an individual, his learning characteristics are more obvious and prominent, the characteristics are concentrated and easy to evaluate, and the evaluation results are also more accurate. However, for groups and classes of multiple people, their learning characteristics will be scattered among each member, and everyone has their own learning characteristics. For a group or class, everyone's learning characteristics will be different from person to person, which will cause everyone's learning characteristics to be more scattered. In this case, it is necessary to evaluate the characteristics of the largest number of people, which can meet most of the learning characteristics, so it will not be very accurate. Therefore, the present invention is more suitable for single learners, but does not represent a learning unit subject that is not suitable for multiple people. The current learning direction is the direction of the content that the learner is currently learning. We can classify the content that the learner is going to learn in advance to obtain various learning directions. The learning direction division may include but is not limited to learning content, learning progress, learning mode, etc. For example, the learning content division may be Chinese, mathematics, English, etc., the learning progress may include the first semester, the first unit, etc., and the learning mode may include a question-solving mode, a text review mode, a scenario simulation mode, etc., which will not be described in detail here. We can pre-divide the educational course content, and can be divided into multiple learning basic units according to knowledge points, and each learning basic unit can correspond to a knowledge point. When we obtain each learning basic unit, we will calibrate it to obtain a label, and obtain the corresponding learning keywords. The learning keywords may include the corresponding learning direction and label, so as to facilitate selection and analysis. This method can greatly reduce the difficulty of later learning analysis and improve the accuracy of analysis. By dividing it into multiple learning basic units, it can be based on knowledge points and carry out targeted extraction, which is convenient for targeted optimization. In this application, each learning direction is not completely divided, but can be selected crosswise. For example, Chinese can be divided into the first unit and the second unit, etc., which will not be described in detail here. The current learning direction of the learner can be obtained by inputting and selecting the learning direction when using it. Based on the convenience of current voice control, it can also be operated by voice. The display screen is used to display various learning directions and learning contents, so that learners can choose and learn. The existing educational courses are basically classified and constructed according to various directions, so designing by learning direction is closer to the existing educational course system.The learning direction is not selected only once, but can be selected in multiple levels, where each learning direction can overlap with each other, so as to achieve comprehensive classification. For example, the first learning direction selected is Chinese, and then the second learning direction is selected, and the learner selects the second unit, and then the third learning direction is selected, and the learner selects classroom content explanation, etc. Of course, this is just a simple example and is not universal, and other situations will not be repeated here.
[0031] S2. Obtain the current learning status of the learner, calculate and obtain the learner's status keywords and their corresponding learning saturation value S. The learning status of the learner can be obtained by identifying the learner's identity. There are many ways to identify the identity. You can register an account, complete the account name and corresponding identity information when registering the account, and then confirm the identity information by logging into the account. The way to log into the account can be manual input, mobile phone code scanning input, voice timbre recognition or face recognition, etc., which can be designed according to the device requirements, and the details are not repeated here. The method for obtaining the learning status of the learner may include: uploading the learner's teaching materials to this system, the system extracts the teaching materials, binds the teaching materials to the learner and analyzes them, so as to obtain the learner's current learning status. The teaching materials may include exercises and test papers of the learner. Exercises and test papers can be online or paper-based. The content of online teaching materials is more convenient and accurate. If it is paper content, it is necessary to take a photo and upload it, and then identify it. Photo recognition is already an existing technology, and the details are not repeated here. Reference Figure 2, the method for obtaining the status keywords of the learner may include: segmenting the content of the supplementary teaching materials to obtain each learning content unit, then analyzing the learning content unit to obtain the content label of the corresponding basic learning unit, then classifying the learning content unit according to the content label of the basic learning unit, obtaining the learning direction corresponding to the learning content unit, and then constructing the status keyword according to the learning direction and the content label. So the status keyword at this time is learning direction-content label. For example, the status keyword analysis is performed on the mathematics supplementary teaching materials for the first grade of primary school. At this time, the supplementary teaching materials are students' after-class quiz papers. The after-class quiz papers are segmented to obtain each learning content unit. At this time, the learning content unit is each calculation question. Then the calculation question is analyzed to obtain a content label of addition and subtraction within ten, and then the learning content unit is classified according to the content label of the basic learning unit, and the learning direction corresponding to this question is the content of the first unit of first-grade mathematics, and then the status keyword is constructed according to the learning direction and the content label as first-grade mathematics, first unit-addition and subtraction within ten. For each question, we can pre-set its content label. Of course, this is just a simple example and is not necessarily universal. Other specific cases will not be described here. For a comprehensive learning content unit, there may be more than one content tag involved, and each content tag may involve different learning directions. Specifically, we can analyze its content tags, and then obtain the proportion of each content tag in this learning content unit, and then construct the status keywords. So the status keywords at this time are learning direction-content tag-percentage, and the specific process will not be described here.
[0032] The method for obtaining the learning saturation value S may include: collecting the same state keywords within a preset reference time period to obtain a state keyword set, and then calculating the learning saturation value of the state keyword set. , where i is the ranking number of the state keyword in the state keyword set, I is the total number of state keywords in the state keyword set, i=1,2,…,I; j is the evaluation impact factor number of the state keyword, J is the total number of evaluation impact factors of the state keyword, j=1,2,…,J; is the state keyword numbered i and the value of the evaluation impact factor numbered j. The evaluation impact factor may include but is not limited to a proportional value impact factor , weight impact factor , Proportion Impact Factor Etc., specific design and real-time optimization need to be carried out according to actual conditions, and the specific situation will not be elaborated here.
[0033] The ratio value influences the factor It can be the same as the percentage value in the status keyword. If there is no corresponding content tag, its value is 1. The specific details are not described here. The acquisition of can be set according to the situation, of course, it can also be obtained by calculation. Specifically, it can be the weight of the learning content unit in the assessment content. The specific value can be the proportion of the learning content unit content score to the total assessment content score during the assessment. The assessment can be a final exam, a high school entrance exam, a college entrance exam, or other exams. Of course, it can also be marked when we construct the course. The details are not repeated here. Proportion influencing factor The percentage of correct answers in the supplementary materials is generally related to the score of the question. For objective questions, the correct answer is 1 and the wrong answer is 0. Of course, not all questions in normal assessments are objective questions. , where i is the ranking number of the state keyword, I is the total number of state keywords in the state keyword set, i=1,2,…,I; is the actual score of the status keyword. is the full score corresponding to the status keyword. For example, there are two questions in the status keyword set, A1 and A2, and the full scores of the two questions are 5 and 10 respectively. The actual scores of a student are 5 and 8 respectively. Then the calculated impact factor is 1+0.8=1.8. Of course, this is just a simple example and is not universal. Other values are not repeated here.
[0034] The learning saturation calculated by this method can be used to evaluate the learning status of each knowledge point in a targeted manner, and the evaluation of the learning status of learners is more objective and accurate, providing an accurate data basis for subsequent recommendations. A reference time period can be determined according to actual conditions, generally one semester, one month or one week, and can also be determined according to the assessment or learning frequency, which will not be elaborated here.
[0035] S3. Extract the basic learning units of the current learning direction, and calculate the recommendation index R based on its learning keywords, the status keywords of the learners, and the learning saturation value. When we construct educational courses, we will construct learning keywords for each course. When we extract the basic learning units that determine the learning direction, we will obtain their learning keywords. For example, in the first-grade mathematics, the first unit, the second lesson, the content label is addition within ten. At this time, the first-grade mathematics-first unit-second lesson-addition within ten is the learning keyword. Of course, this is just a simple example and is not necessarily universal. Other situations will not be elaborated here. Recommendation index of basic learning units , where n is the number of the evaluation factor of the relevant state keyword set of the current learning basic unit, N is the total number of evaluation factors of the state keyword set, n=1,2,…,N; is the overlap value between the state keyword set numbered n and the evaluation factors of the basic learning unit. The evaluation factors here include learning direction and content label. is the weight value of the overlap evaluation of the factors of the status keyword set, which can be pre-set according to actual conditions, and its value is generally 1-10. The recommendation index calculated by this method can take into account the current learning status of the learner, the deviation of the selected direction, and can highlight a high overlap, avoiding a high overlap being covered by the approximate overlap of other items, and the calculated recommendation index is more practical. For example, when the learning keywords are mathematics, first grade, and addition and subtraction operations, the status keywords are mathematics, first grade, and addition and subtraction within ten. When we perform the recommendation index calculation, we use the status keywords as the basis, and the selected learning direction does not need to consider the order. The status keyword overlap evaluation weight values of mathematics, first grade, and addition and subtraction within ten are 1, 2, and 10, respectively. By analyzing the overlap values, they are 1, 1, and 0.3, respectively. The learning saturation value S is calculated to be 0.3, and the recommendation index is calculated to be 77. Of course, this is just a simple example, and other values are not repeated here. The overlap value The calculation method may be the overlap ratio between the content of the learning keyword numbered n in the status keyword and the content of the corresponding learning keyword. Of course, it may also be obtained by other methods, which will not be elaborated here.
[0036] S4. The recommended index R of the basic learning unit for the selected learning direction is greater than a preset R 标 The learning basic units are collected and organized into optimized course sets, and are sorted from large to small according to the recommendation index R, and then recommended in order. The learning basic units with large recommendation indexes are more consistent with the current learning status of the learners. By forming an optimized course set, the online courses are optimized, making the courses more targeted and facilitating targeted learning for the learners. This avoids a large amount of repeated learning for the learners, thereby saving learning time and improving learning efficiency. You can set it according to your personal learning urgency. If you have enough time and experience, the preset The value can be set smaller. If time is tight, the value can be set larger. This can improve learning initiative. The details will not be elaborated here.
[0037] Example 2 refer to Figure 3 The present invention also provides an online education course optimization and sorting system, comprising: The course segmentation module is used to segment the educational courses to obtain basic learning units. The basic learning units can be based on knowledge points, and each basic learning unit corresponds to a knowledge point. Of course, the educational courses can also be manually segmented to obtain basic learning units, or they can be directly produced according to knowledge points. The details are not described here.
[0038] The learning direction selection module is used to obtain the current learning direction of the learner and determine the corresponding basic learning unit according to the learning direction.
[0039] The learning status acquisition module is used to obtain the current learning status of the learner, calculate the learner's status keyword and its corresponding learning saturation value S. The learning status acquisition module obtains the learner's supplementary teaching materials, binds the supplementary teaching materials with the learner and analyzes them, so as to obtain the learner's current learning status.
[0040] The recommendation calculation module is used to extract the basic learning units of the current learning direction and calculate the recommendation index R based on its learning keywords, the status keywords of the learners, and the learning saturation value.
[0041] The course optimization module is used to recommend the learning basic unit index R of the selected learning direction to be greater than a preset The basic learning units are collected and organized into an optimized course set. They are sorted from large to small according to the recommendation index R, and then recommended in order.
[0042] The display module is used to display the optimized course set.
[0043] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.
Claims
1. A method for optimizing and ranking online education courses, characterized in that: The online education course optimization sorting method comprises the following steps: S1. Obtain the current learning direction of the learner and determine the corresponding basic learning unit according to the learning direction; S2. Obtain the current learning status of the learner, calculate the learner's status keyword and its corresponding learning saturation value S; S3, extracting the basic learning unit of the current learning direction, and calculating the recommendation index R according to its learning keywords, the status keywords of the learners, and the learning saturation value; S4. The recommended index R for the selected learning direction is greater than a preset The basic learning units are collected and organized into an optimized course set. They are sorted from large to small according to the recommendation index R, and then recommended in order.
2. The online education course optimization sorting method according to claim 1, characterized in that: The learning direction division includes learning content, learning progress and learning mode.
3. The online education course optimization sorting method according to claim 1, characterized in that: The method for obtaining the learning status of the learner includes: obtaining the learning materials of the learner, binding and analyzing the learning materials with the learner, and obtaining the current learning status of the learner.
4. The online education course optimization sorting method according to claim 3 is characterized in that: The teaching materials include exercises and test papers for learners.
5. The online education course optimization sorting method according to claim 1, characterized in that: The method for obtaining the status keywords of learners includes: dividing the content of teaching materials to obtain various learning content units, analyzing the learning content units to obtain the content labels of the corresponding basic learning units, and then classifying the learning content units according to the content labels of the basic learning units to obtain the learning directions corresponding to the learning content units, and then constructing the status keywords based on the learning directions and content labels.
6. The online education course optimization sorting method according to claim 1, characterized in that: The method for obtaining the learning saturation value S includes: collecting the same state keywords within a preset reference time period to obtain a state keyword set, and then calculating the learning saturation value S of the state keyword set.
7. The online education course optimization sorting method according to claim 1 is characterized in that learning Saturation value , where i is the ranking number of the state keyword in the state keyword set, I is the total number of state keywords in the state keyword set, i=1,2,…,I; j is the evaluation impact factor number of the state keyword, J is the total number of evaluation impact factors of the state keyword, j=1,2,…,J; It is the value of the status keyword numbered i and the evaluation impact factor numbered j.
8. The online education course optimization and sorting method according to claim 7, characterized in that: The evaluation impact factors include: proportional value impact factor , weight impact factor And the proportion of impact factors .
9. An online education course optimization ranking system, characterized in that: include: A learning direction selection module is used to obtain the current learning direction of the learner and determine the corresponding learning basic unit according to the learning direction; A learning status acquisition module is used to obtain the current learning status of the learner, calculate the learner's status keyword and its corresponding learning saturation value S; The recommendation calculation module is used to extract the basic learning unit of the current learning direction and calculate the recommendation index R according to its learning keywords, the status keywords of the learners, and the learning saturation value; The course optimization module is used to recommend the learning basic unit index R of the selected learning direction to be greater than a preset Collect the basic learning units, form an optimized course set, sort them from large to small according to the recommendation index R, and then recommend them in order; The display module is used to display the optimized course set.
10. The online education course optimization and ranking system according to claim 9, characterized in that: The online education course optimization and ranking system also includes a course segmentation module, which is used to segment the education courses to obtain basic learning units, and the basic learning units are based on knowledge points.
Citation Information
Patent Citations
Question pushing method and device, computer equipment and storage medium
CN110472060A
Targeted reinforcement learning method and device, terminal and storage medium
CN112733029A
Music online intelligent course learning method, device and system based on big data
CN114493950A
Learning condition big data analysis system and learning condition server
CN115081965A
Education platform implementation method and system based on tablet computer
CN117454018A
