Unlock instant, AI-driven research and patent intelligence for your innovation.

A quality evaluation method for intelligent test papers based on knowledge graph

A knowledge map and quality evaluation technology, applied in the field of intelligent management of test questions, can solve problems such as unsatisfactory test results and unfavorable progress of test takers, and achieve the effect of improving the correct rate

Active Publication Date: 2022-06-07
杭州恒生数字设备科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, different teachers, different student qualifications, and different time spent on learning lead to different knowledge points for different students in different regions. If you ignore the differences and follow the traditional way of writing test papers, the results of the test will be unsatisfactory, which is not conducive to promoting test-taking Therefore, it is necessary to evaluate the knowledge points covered area and difficulty of the test paper

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A quality evaluation method for intelligent test papers based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] like figure 1 As shown, a method for evaluating the quality of an intelligent test paper based on a knowledge graph includes the steps of constructing a knowledge graph 011, constructing a keyword database step 012, constructing a phrase database step 013, keyword segmentation step 014, keyword determination step 015, and phrase determination step 016 and test paper quality assessment steps;

[0033] The step 011 of constructing a knowledge map is to acquire knowledge point data of a single subject and historical test paper topics, and arrange the knowledge point data into a tree diagram to form a knowledge map according to the correlation between the knowledge point data in the historical test paper topics, The knowledge map reflects the content of knowledge points, the difficulty of knowledge points, and the degree of association between knowledge points;

[0034] In the step 012 of constructing a keyword database, a number of word data groups are set, and preset key...

Embodiment 2

[0047] The difference from Embodiment 1 is: the phrase data group questions in the step 013 of constructing the phrase database are stored with different second difficulty values ​​corresponding to different question types, and the second difficulty values ​​replace the first difficulty values. value as the new first difficulty value.

Embodiment 3

[0049] The difference from Embodiment 1 is that the test paper quality evaluation method further includes a difficulty correction step, and in the difficulty correction step, the actual score rate of each question in the test paper is obtained as the actual difficulty of the question, and the construction is corrected according to the actual difficulty of the question. The first difficulty value in step 013 of the phrase database.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for evaluating the quality of intelligent test papers based on knowledge graphs, and at the same time, the first word segmentation algorithm (based on character string matching) and the second word segmentation algorithm (based on subject dictionary and statistics) are used to perform word segmentation and extract the first keyword for the topic respectively. and the second keyword to prevent word segmentation errors in the single word segmentation algorithm; get the first preset keyword and the second preset keyword from the keyword database to prevent the extracted keywords from being different due to the different word habits of different testers Words can not all correspond to the keywords in the phrase data group; according to the same words in some first preset keywords and some second preset keywords as the reference keyword, the phrase data in the phrase database is reduced according to the reference keyword The number of groups, and then determine the keywords in the title according to other keywords in several locked phrase data groups; several target phrases are matched with the knowledge map to obtain the quality information of the test paper.

Description

technical field [0001] The invention relates to the technical field of intelligent management of test questions, in particular to an intelligent test paper quality evaluation method based on a knowledge map. Background technique [0002] In the study or work stage, the examination is an important means to test the ability of students or employees. A good test paper, its content should cover most of the test sites, and its difficulty should be adapted to the test taker's ability. However, different teachers, different aptitudes of students, and different time spent on learning cause different students in different regions to master different knowledge points. If we ignore the differences and follow the traditional way of producing test papers, the results of the test will be unsatisfactory, which is not conducive to promoting test-taking. Therefore, it is necessary to evaluate the coverage area and difficulty of the knowledge points of the test paper. SUMMARY OF THE INVENT...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/36G06F40/242G06F40/289G06F40/30G09B19/00
CPCG06F16/367G06F40/30G06F40/289G06F40/242G09B19/00
Inventor 查敏中
Owner 杭州恒生数字设备科技有限公司