CN114529432A - Knowledge point difficulty grading method based on big data - Google Patents
Knowledge point difficulty grading method based on big data Download PDFInfo
- Publication number
- CN114529432A CN114529432A CN202210074220.3A CN202210074220A CN114529432A CN 114529432 A CN114529432 A CN 114529432A CN 202210074220 A CN202210074220 A CN 202210074220A CN 114529432 A CN114529432 A CN 114529432A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- difficulty
- data
- target knowledge
- test question
- 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 31
- 238000012360 testing method Methods 0.000 claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Abstract
The invention relates to a knowledge point difficulty grading method based on big data, which firstly determines a target knowledge point, acquires all corresponding test question information and answer data under the target knowledge point, then calculates the difficulty index of the target knowledge point according to the test question information and the answer data, then carries out difficulty grading on the target knowledge point according to the obtained difficulty index, periodically updates the test question information and the answer data of the target knowledge point, and dynamically adjusts the difficulty grading of the target knowledge point. The defects that the system becomes backward due to lack of data updating, the data validity is not enough and the like can be overcome.
Description
[ technical field ] A
The invention relates to the technical field of intelligent education, in particular to a knowledge point difficulty grading method based on big data.
[ background ] A method for producing a semiconductor device
Currently, the difficulty level of the knowledge points learned by students is usually manually grasped and judged by a question taker or a question teacher. Meanwhile, with the continuous development and progress of computer technology, more and more teachers adopt an automatic question setting mode, for example, a computer is used for randomly selecting corresponding questions from a question bank according to corresponding question types to generate test papers. The problem setting mode is difficult to master the difficulty of knowledge points, the difficulty of the knowledge points of related test problems can not be automatically calculated according to the collected big data, the condition that the problem difficulty is too high or the problem difficulty is too low can be easily caused, and the problem setting mode is not beneficial to the study of students and the teaching of teachers according to the material.
The patent CN112348725A discloses a big data-based knowledge point difficulty ranking method, and the knowledge point mastery degree formula disclosed by the method has obvious disadvantages, and when the same user is completely paired or completely paired, the mastery degree calculation results are consistent, and are not in accordance with objective practice, and the formula is not normalized, and the mastery degree trend is that the more knowledge points are, the more the mastery degree is accumulated correspondingly, which results in a higher mastery degree than the knowledge points with fewer other problems, and is unreasonable. And the subsequent calculation formula of the complexity of the target knowledge point is not reasonable, and the difficulty of the knowledge point does not have an obvious positive correlation with the quantity of the questions of the knowledge point, so that the method disclosed by the patent has obvious defects and is not enough to achieve the effect of the early design.
[ summary of the invention ]
Aiming at the defects of the prior art, the invention aims to provide a knowledge point difficulty grading method based on big data.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
a big data-based knowledge point difficulty ranking method, the method comprising:
determining a target knowledge point, and acquiring all corresponding test question information and answering data under the target knowledge point;
calculating the difficulty index of the target knowledge point according to the test question information and the answering data;
grading the difficulty of the target knowledge point according to the index;
periodically updating the test question information and the answer data of the target knowledge points, and dynamically adjusting the difficulty level of the target knowledge points.
Further, the test question information at least comprises the total number of the test questions.
Further, the answering data includes, but is not limited to, total number of answering questions per track, number of correct answering questions per user.
Further, the difficulty index Kp of the target knowledge point may be calculated by the following formula:
w1+w2＝1
in the above formula, w1 and w2 represent weighting coefficients, the weighting coefficients can be adjusted as required, N represents the total number of test questions corresponding to the target knowledge point, i represents the ith topic in the target knowledge point, Ri represents the number of users for the ith topic pair, Wi represents the number of users who make a mistake for the ith topic, M represents the number of users who make questions contained in the target knowledge point, j represents the jth user, Qrj represents the number of topics for which the jth user makes a pair, and Qwj represents the number of questions for which the jth user makes a mistake. In the invention, the grasping indexes of the knowledge points are weighted and calculated in two dimensions of the user question answering accuracy of all questions of the target knowledge points and the overall question making accuracy of all users.
Further, the target knowledge point difficulty rating is a difficulty index distribution interval corresponding to different knowledge point difficulty ratings set by subject experts, and the difficulty rating of the target knowledge point can be determined according to the range (how this is calculated) of the calculated interval in the distribution interval.
Further, the step of periodically updating the test question information and the response data of the target knowledge point means that the latest test question information and the latest response data are obtained by setting a period threshold value, and then the knowledge point difficulty grading is updated.
Further, the period threshold may be set according to a periodic, monthly, quarterly, and/or term regularity.
Further, the latest test question information and answer data can be collected from the test question source data of each knowledge point through an operation system, an examination paper reading system, a smart classroom system, an error book system and/or a question recording system.
Further, the answer information of the corresponding topic under the target knowledge point can be verified, if and only the topic corresponding to the answer information after the verification is passed can participate in the calculation, for example, if and only if the number of answer users of each topic exceeds the number of the preset threshold, the topic can be regarded as the effective statistical topic of the knowledge point, so that only the effective statistical topic can participate in the calculation.
Further, updating the test question and answer information of the target knowledge point further comprises manual updating, and updating is automatically triggered when the increment of the new test question exceeds a preset threshold value.
The invention has the beneficial effects that: the invention is a knowledge point difficulty grading method based on big data, which firstly determines a target knowledge point, acquires all corresponding test question information and answer data under the target knowledge point, then calculates the difficulty index of the target knowledge point according to the test question information and the answer data, and then carries out difficulty grading to the target knowledge point according to the obtained difficulty index, in the process, the test question information and the answer data of the target knowledge point need to be periodically updated, the difficulty grading of the target knowledge point is dynamically adjusted, the invention calculates the difficulty index of the target knowledge point by weighting two dimensions of the user answer accuracy of all questions of the target knowledge point and the accuracy of the integral answer of all users, thereby carrying out the difficulty grading of the knowledge point according to the difficulty index, which is a scientific, objective and effective knowledge point grading method, the difficulty grading mode for updating the knowledge points can be used for dynamically adjusting by combining the latest question setting condition of the knowledge points, and the defects that the system is lagged due to lack of data updating, the data effectiveness is insufficient and the like can be overcome.
[ detailed description ] embodiments
The present invention will be further described below. It should be noted that the present embodiment is premised on the technical solution, and detailed description and specific implementation are given, but the scope of protection of the present invention is not limited to the present embodiment.
A big data-based knowledge point difficulty ranking method, the method comprising:
determining a target knowledge point, and acquiring all corresponding test question information and answering data under the target knowledge point;
calculating the difficulty index of the target knowledge point according to the test question information and the answering data;
grading the difficulty of the target knowledge point according to the index;
periodically updating the test question information and the answer data of the target knowledge points, and dynamically adjusting the difficulty level of the target knowledge points.
In one embodiment, the test question information includes at least a total number of test questions.
In one embodiment, the response data includes, but is not limited to, total number of answers per topic, correct number of answers per user, number of correct answers per user.
In one embodiment, the difficulty index Kp of the target knowledge point may be calculated by the following formula:
w1+w2＝1
in the above formula, W1 and W2 represent weighting coefficients, which can be adjusted as needed (adjustment as needed is generally set by a subject expert according to experience, and only needs to satisfy W1+ W2 being 1), N represents the total number of test questions corresponding to a target knowledge point, i represents the ith topic in the target knowledge point, Ri represents the number of users paired with the ith topic, Wi represents the number of users with the ith topic being wrong, M represents the number of users who have made topics included in the target knowledge point, j represents the jth user, Qrj represents the number of topics made pairs by the jth user, and Qwj represents the number of questions with the jth user being wrong. In the invention, the grasping indexes of the knowledge points are weighted and calculated in two dimensions of the user question answering accuracy of all questions of the target knowledge points and the overall question making accuracy of all users.
In this embodiment, w1 is 0.5, w2 is 0.5, the total number of the test questions corresponding to the target knowledge point is 2 (N is 2), the first question 2 is right, 2 is wrong, the second question 1 is right, 1 is wrong, and there are 4 user answers in total for the two knowledge points, the first user answers right 2, wrong 0, the second user answers right 0, wrong 0 for right 1, the third user answers right 1, wrong 0 for right 0, and the fourth user answers right 0, wrong 1, so the difficulty index Kp of the target knowledge point is as follows:
in one embodiment, the target knowledge point difficulty rating is a difficulty index distribution interval corresponding to different knowledge point difficulty ratings set by a subject expert according to experience, and the difficulty rating of the target knowledge point can be determined according to the range of the calculated interval in the distribution interval.
In this embodiment, the correspondence between the difficulty index of the target knowledge point and the difficulty level of the knowledge point is as follows:
kp is in the interval of 0.8-1, and the difficulty of knowledge points is simple;
kp is between 0.6 and 0.8, and the difficulty of knowledge points is general;
kp is between 0.4 and 0.6, and the difficulty of knowledge points is difficult;
kp is between 0 and 0.4, and the difficulty of knowledge points is very difficult.
In one embodiment, the periodically updating the test question information and the response data of the target knowledge point means that the latest test question information and the latest response data are obtained by setting a period threshold, so as to update the knowledge point difficulty rating.
In one embodiment, the period threshold may be set by the node according to a periodic, monthly, quarterly, and/or term regularity.
In one embodiment, the latest test question information and answer data can be collected from the test question source data of each knowledge point through a system including, but not limited to, an operating system, a paper reading system, a smart classroom system, a question error book system and/or a question recording system.
In one embodiment, the answer information of the corresponding topic under the target knowledge point can be checked, and if and only if the answer information corresponding to the checked answer information can participate in the calculation, for example, if and only if the number of answer users of each topic exceeds a preset threshold number, the topic can be regarded as a valid statistical topic of the knowledge point, so that only the valid statistical topic can participate in the calculation.
In one embodiment, the updating of the test question and answer information of the target knowledge point further comprises manual updating, and the updating is automatically triggered when the increment of the new test question exceeds a preset threshold value.
The invention is a knowledge point difficulty grading method based on big data, which firstly determines a target knowledge point, acquires all corresponding test question information and answer data under the target knowledge point, then calculates the difficulty index of the target knowledge point according to the test question information and the answer data, and then carries out difficulty grading to the target knowledge point according to the obtained difficulty index, in the process, the test question information and the answer data of the target knowledge point need to be periodically updated, the difficulty grading of the target knowledge point is dynamically adjusted, the invention calculates the difficulty index of the target knowledge point by weighting two dimensions of the user answer accuracy of all questions of the target knowledge point and the accuracy of the integral answer of all users, thereby carrying out the difficulty grading of the knowledge point according to the difficulty index, which is a scientific, objective and effective knowledge point grading method, the difficulty grading mode for updating the knowledge points can be used for dynamically adjusting by combining the latest question setting condition of the knowledge points, and the defects that the system is lagged due to lack of data updating, the data effectiveness is insufficient and the like can be overcome.
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.
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.
Although the present invention has been described in detail with reference to the above embodiments, it will be apparent to those skilled in the art from this disclosure that various changes or modifications can be made herein without departing from the principles and spirit of the invention as defined by the appended claims. Therefore, the detailed description of the embodiments of the present disclosure is to be construed as merely illustrative, and not limitative of the remainder of the disclosure, but rather to limit the scope of the disclosure to the full extent set forth in the appended claims.
Claims (10)
1. A knowledge point difficulty ranking method based on big data is characterized by comprising the following steps:
determining a target knowledge point, and acquiring all corresponding test question information and answering data under the target knowledge point;
calculating the difficulty index of the target knowledge point according to the test question information and the answering data;
grading the difficulty of the target knowledge point according to the index;
periodically updating the test question information and the answer data of the target knowledge points, and dynamically adjusting the difficulty level of the target knowledge points.
2. The big-data-based knowledge point difficulty ranking method according to claim 1, wherein the test question information at least includes a total number of test questions.
3. The big-data-based knowledge point difficulty rating method according to claim 1, wherein the answer data includes but is not limited to total number of answers per topic, correct number of answers per user, number of questions answered per user, and correct number of answers per user.
4. The big-data-based difficulty ranking method for knowledge points according to claim 1, wherein the difficulty index Kp of the target knowledge point is obtained by calculating according to the following formula:
w1+w2＝1
in the above formula, w1 and w2 represent weighting coefficients, the weighting coefficients can be adjusted as required, N represents the total number of test questions corresponding to the target knowledge point, i represents the ith topic in the target knowledge point, Ri represents the number of users for the ith topic pair, Wi represents the number of users who make a mistake for the ith topic, M represents the number of users who make questions contained in the target knowledge point, j represents the jth user, Qrj represents the number of topics for which the jth user makes a pair, and Qwj represents the number of questions for which the jth user makes a mistake.
5. The big-data-based difficulty rating method for knowledge points according to claim 1, wherein the target difficulty rating is a difficulty index distribution interval corresponding to different difficulty ratings of knowledge points set by subject experts, and the difficulty rating of the target knowledge point can be determined according to the range of the calculated interval in the distribution interval.
6. The big-data-based knowledge point difficulty grading method according to claim 1, wherein the periodically updating of the test question information and the response data of the target knowledge point means that the latest test question information and response data are obtained by setting a period threshold.
7. The big-data-based knowledge point difficulty rating method of claim 1, wherein the period threshold is set according to a periodic, monthly, quarterly and/or scholarly regularity.
8. The big data based knowledge point difficulty rating method as claimed in claim 6, wherein the latest test question information and answer data can be collected from the test question source data of each knowledge point by the operation system, examination paper system, intelligent classroom system, wrong-answer book system and/or question recording system.
9. The big-data-based knowledge point difficulty grading method according to claim 1, characterized in that answer information corresponding to a question under a target knowledge point can be verified, and if and only if the answer information corresponding to the verified answer information can participate in the calculation.
10. The big-data-based knowledge point difficulty grading method according to claim 6, wherein updating the test question and answer information of the target knowledge point further comprises manual updating, and updating is automatically triggered when the increment of a new test question exceeds a preset threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210074220.3A CN114529432A (en) | 2022-01-21 | 2022-01-21 | Knowledge point difficulty grading method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210074220.3A CN114529432A (en) | 2022-01-21 | 2022-01-21 | Knowledge point difficulty grading method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114529432A true CN114529432A (en) | 2022-05-24 |
Family
ID=81620974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210074220.3A Pending CN114529432A (en) | 2022-01-21 | 2022-01-21 | Knowledge point difficulty grading method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114529432A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115658928A (en) * | 2022-12-14 | 2023-01-31 | 成都泰盟软件有限公司 | Method and device for assembling test paper, computer equipment and storage medium |
| CN115936940A (en) * | 2022-12-26 | 2023-04-07 | 吉林农业科技学院 | Mathematical simulation teaching system and method based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184709A (en) * | 2015-08-20 | 2015-12-23 | 浙江通关教育科技有限公司 | Subject evaluation system and method based on knowledge point system |
| CN109949638A (en) * | 2019-04-22 | 2019-06-28 | 软通智慧科技有限公司 | Acquisition of knowledge degree determines method, apparatus, terminal and medium |
| CN110147428A (en) * | 2019-04-11 | 2019-08-20 | 北京任学教育科技有限公司 | Update method, device, equipment and the storage medium of knowledge point master degree |
| CN112348725A (en) * | 2020-11-30 | 2021-02-09 | 上海松鼠课堂人工智能科技有限公司 | Knowledge point difficulty grading method based on big data |
| CN113077184A (en) * | 2021-04-27 | 2021-07-06 | 上海松鼠课堂人工智能科技有限公司 | Data adjustment method, device, equipment and medium based on Bayesian knowledge tracking |
-
2022
- 2022-01-21 CN CN202210074220.3A patent/CN114529432A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184709A (en) * | 2015-08-20 | 2015-12-23 | 浙江通关教育科技有限公司 | Subject evaluation system and method based on knowledge point system |
| CN110147428A (en) * | 2019-04-11 | 2019-08-20 | 北京任学教育科技有限公司 | Update method, device, equipment and the storage medium of knowledge point master degree |
| CN109949638A (en) * | 2019-04-22 | 2019-06-28 | 软通智慧科技有限公司 | Acquisition of knowledge degree determines method, apparatus, terminal and medium |
| CN112348725A (en) * | 2020-11-30 | 2021-02-09 | 上海松鼠课堂人工智能科技有限公司 | Knowledge point difficulty grading method based on big data |
| CN113077184A (en) * | 2021-04-27 | 2021-07-06 | 上海松鼠课堂人工智能科技有限公司 | Data adjustment method, device, equipment and medium based on Bayesian knowledge tracking |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115658928A (en) * | 2022-12-14 | 2023-01-31 | 成都泰盟软件有限公司 | Method and device for assembling test paper, computer equipment and storage medium |
| CN115936940A (en) * | 2022-12-26 | 2023-04-07 | 吉林农业科技学院 | Mathematical simulation teaching system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114529432A (en) | Knowledge point difficulty grading method based on big data | |
| CN111062842A (en) | Method and device for dynamically generating personalized questions | |
| CN110246072B (en) | Review method executed by machine equipment | |
| CN112348725A (en) | Knowledge point difficulty grading method based on big data | |
| CN109254991A (en) | A kind of interactive learning methods and device | |
| Battistin et al. | Counting rotten apples: Student achievement and score manipulation in Italian elementary Schools | |
| CN110288878A (en) | Adaptive learning method and device | |
| CN107316256A (en) | A kind of physics exercise question-setting system | |
| US20120329028A1 (en) | Method for intelligent personalized learning service | |
| CN111428020A (en) | Personalized learning test question recommendation method based on artificial intelligence | |
| CN115935032B (en) | Method and device for issuing personalized operation based on intelligent recommendation problem | |
| CN111932160A (en) | Knowledge acquisition information processing method, knowledge acquisition information processing device, computer device, and storage medium | |
| CN115952299A (en) | Intelligent simulation examination recommendation system and method | |
| CN116092639A (en) | Aphasia rehabilitation training system and method based on course self-adaptive adjustment | |
| CN111179666B (en) | Self-adaptive education system based on artificial intelligence | |
| CN112883284B (en) | Online learning system based on network and data analysis and test question recommendation method | |
| CN112614034A (en) | Test question recommendation method and device, electronic equipment and readable storage medium | |
| Ozyurt et al. | An application of individualized assessment in educational Hypermedia: Design of computerized adaptive testing system and its integration into UZWEBMAT | |
| CN113409635A (en) | Interactive teaching method and system based on virtual reality scene | |
| CN113537746A (en) | Automatic course arrangement method and system | |
| CN112529746A (en) | Method for assisting teachers in real-time learning supervision, reminding and analysis | |
| CN111539588A (en) | Method for predicting learning result by correcting short answer question score | |
| CN110599840A (en) | Personalized self-adaptive online learning method based on big data | |
| CN118053548A (en) | Light cognitive impairment rehabilitation training method, device, equipment and medium | |
| CN111738886B (en) | Learning report analysis system based on neural network |
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 |