CN109471940A - A kind of generation method and computer readable storage medium of PK match exam pool - Google Patents
A kind of generation method and computer readable storage medium of PK match exam pool Download PDFInfo
- Publication number
- CN109471940A CN109471940A CN201811303495.XA CN201811303495A CN109471940A CN 109471940 A CN109471940 A CN 109471940A CN 201811303495 A CN201811303495 A CN 201811303495A CN 109471940 A CN109471940 A CN 109471940A
- Authority
- CN
- China
- Prior art keywords
- topic
- score
- evaluation
- exam pool
- test
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the generation method and computer readable storage medium of a kind of PK match exam pool, including total exam pool, evaluation and test library and PK match exam pool;Specifically comprise the following steps: step 10, extract all evaluation and tests record for selecting bibliography from evaluation and test library;Step 20 is directed to same topic, extracts the score value of the topic from total exam pool, and extracts from the evaluation and test library all scores that the topic was done;Whole differences of all scores Yu the topic score value are found out respectively, then all difference values, finally the result of difference value divided by the product of the score value of the topic and total answer number of the topic, obtain score and be averaged relative mistake;It is averaged relative mistake according to the score that the above method calculates all topics;The score of all topics relative mistake that is averaged is clustered into simple topic, medium topic and problem three classes with K mean cluster algorithm by step 30;Step 40 generates PK match exam pool as requested.
Description
Technical field
The present invention relates to a kind of education sectors, refer in particular to the generation method and computer-readable storage of a kind of PK match exam pool
Medium.
Background technique
The fashionable world of answer game is even more to sweep one trend in education sector because of the interest that it can cause student to learn
Wind.
The shortcomings that existing PK match exam pool, is as follows:
1, item difficulty is often determined by subjectivity, and ignores the evaluation result of history;
2, the difficulty of PK match exam pool is not objective enough, influences the fairness of evaluation result;
Item difficulty and the objective difficulty for holding PK match exam pool are how assessed, is an important problem.
Summary of the invention
In order to provide assessment item difficulty and the objective difficulty for holding PK match exam pool, the present invention proposes a kind of PK match topic
The generation method and computer readable storage medium in library.
The present invention is implemented as follows:
A kind of generation method of PK match exam pool, including total exam pool, evaluation and test library and PK match exam pool;Total exam pool includes multiple
Several original records, each original records include: bibliography, topic, answer and score value;The evaluation and test library includes plural number
A evaluation and test record, the evaluation and test are recorded as the record that topic in total exam pool be used to evaluate and test, and the evaluation and test record includes:
User, bibliography, topic, score and practical Reaction time;
The method specifically includes following steps:
Step 10, all evaluation and tests record that selected bibliography is extracted from the evaluation and test library;
Step 20 is directed to same topic, the score value of the topic is extracted from total exam pool, and mention from the evaluation and test library
The topic is taken to correspond to the score in N number of evaluation and test record;It is averaged phase by the score that the score value calculates the topic with the score
To difference;The score relative mistake specific formula for calculation that is averaged is as follows:
Wherein, score 1, score 2, score 3 and score N are respectively obtaining in the corresponding multiple evaluation and test records of the topic
Point;N is the natural number greater than zero;
Step 30, the score that all topics are calculated according to above-mentioned formula are averaged relative mistake, with K mean cluster algorithm by
Divide average relative mistake that all topics are clustered into simple topic, medium topic and problem three classes;
Step 40, the topic quantity that simple topic, medium topic and problem is respectively set, from the similar topic clustered with
Machine exports the topic of respective numbers, ultimately generates PK match exam pool.
Preferably, in the step 40, if certain a kind of total topic quantity is less than the derived topic of such needs after cluster
Quantity, then after all topics for exporting such, the topic for differing quantity randomly selects supplement from other two class, until meeting
Until such needs derived topic quantity.
Preferably, the step 20 further includes, for same topic, extracting the topic from the evaluation and test record in the evaluation and test library
All practical Reaction times of mesh average all practical Reaction times to obtain average Reaction time.
Preferably, in the step 40, every record in the PK match exam pool includes: topic, score value, average
Relative mistake and complexity.
A kind of computer readable storage medium, including total exam pool, evaluation and test library and PK match exam pool, and total exam pool includes multiple
Several original records, each original records include: bibliography, topic, answer and score value;The evaluation and test library includes plural number
A evaluation and test record, the evaluation and test are recorded as the record that topic in total exam pool be used to evaluate and test, and the evaluation and test record includes:
User, bibliography, topic, score and practical Reaction time;Computer program is stored on computer readable storage medium;
The program performs the steps of when being executed by processor
Step 10, all evaluation and tests record that selected bibliography is extracted from the evaluation and test library;
Step 20 is directed to same topic, the score value of the topic is extracted from total exam pool, and mention from the evaluation and test library
The topic is taken to correspond to the score in N number of evaluation and test record;It is averaged phase by the score that the score value calculates the topic with the score
To difference;The score relative mistake specific formula for calculation that is averaged is as follows:
Wherein, score 1, score 2, score 3 and score N are respectively obtaining in the corresponding multiple evaluation and test records of the topic
Point;N is the natural number greater than zero;
Step 30, the score that all topics are calculated according to above-mentioned formula are averaged relative mistake, with K mean cluster algorithm by
Divide average relative mistake that all topics are clustered into simple topic, medium topic and problem three classes;
Step 40, the topic quantity that simple topic, medium topic and problem is respectively set, from the similar topic clustered with
Machine exports the topic of respective numbers, ultimately generates PK match exam pool.
Preferably, in the step 40, if certain a kind of total topic quantity is less than the derived topic of such needs after cluster
Mesh number amount, then after all topics for exporting such, the topic for differing quantity randomly selects supplement from other two class, until full
Until the derived topic quantity of such needs of foot.
Preferably, the step 20 further includes, for same topic, extracting the topic from the evaluation and test record in the evaluation and test library
All practical Reaction times of mesh average all practical Reaction times to obtain average Reaction time.
Preferably, in the step 40, every record in the PK match exam pool includes: topic, score value, average
Relative mistake and complexity.
The present invention has the advantage that
1, it carries out score to per pass topic using existing evaluation and test library to be averaged the calculating of relative mistake, from the scoring event of topic
Assess the complexity of the topic.
2, it by the complexity of the objective determining topic of K mean cluster algorithm, is wanted further according to all kinds of difficulty topic quantity
PK match exam pool is sought survival into, with the difficulty of objective assurance PK match exam pool.
3, when recording enough in evaluation and test library, the difficulty for the PK match exam pool that the present invention generates will be more accurate;And
Evaluation and test library of the invention is real-time update, so the complexity of every problem is also real-time update, the present invention more can be objective
React the complexity of topic.
4, using Reaction time as a factor of evaluation, the fixation Reaction time that tradition is set manually, this hair are different from
The Reaction time of bright every topic is that the previous all practical Reaction times of the comprehensive topic are calculated, the Reaction time of every topic and the topic
Item difficulty it is related.
Specific embodiment
A kind of generation method of PK match exam pool, including total exam pool, evaluation and test library and PK match exam pool;Total exam pool includes multiple
Several original records, each original records include: bibliography, topic, answer and score value;The evaluation and test library includes plural number
A evaluation and test record, the evaluation and test are recorded as the record that topic was done in total exam pool, and the evaluation and test record includes: using
Family, bibliography, topic, score and practical Reaction time;
The method specifically includes following steps:
Step 10, all evaluation and tests record that selected bibliography is extracted from the evaluation and test library;
Step 20 is directed to same topic, the score value of the topic is extracted from total exam pool, and mention from the evaluation and test library
The topic is taken to correspond to the score in N number of evaluation and test record;It is averaged phase by the score that the score value calculates the topic with the score
To difference;The score relative mistake specific formula for calculation that is averaged is as follows:
Wherein, score 1, score 2, score 3 and score N are respectively obtaining in the corresponding multiple evaluation and test records of the topic
Point;N is the natural number greater than zero;
For same topic, all practical Reaction times of the topic are extracted from the evaluation and test record in the evaluation and test library, it is right
All practical Reaction times average to obtain average Reaction time;
It is averaged relative mistake and average Reaction time according to the score that the above method calculates all topics;Score is averaged relative mistake
For assessing the complexity of the topic;Average Reaction time is used to limit Reaction time and the auxiliary judgment students topics
Qualification.
Step 30, the score that all topics are calculated according to above-mentioned formula are averaged relative mistake, with K mean cluster algorithm by
Divide average relative mistake that all topics are clustered into simple topic, medium topic and problem three classes;
Step 40, the topic quantity that simple topic, medium topic and problem is respectively set, from the similar topic clustered with
Machine exports the topic of respective numbers, ultimately generates PK match exam pool;
If in the similar topic clustered, total topic quantity is less than such and needs derived topic quantity, then exporting
After such all topic, the topic of difference randomly selects supplement from other two class, until meeting such needs derived topic
Until mesh number amount.
A kind of computer readable storage medium, including total exam pool, evaluation and test library and PK match exam pool;Total exam pool includes multiple
Several original records, each original records include: bibliography, topic, answer and score value;The evaluation and test library includes plural number
A evaluation and test record, the evaluation and test are recorded as the record that topic was done in total exam pool, and the evaluation and test record includes: using
Family, bibliography, topic, score and practical Reaction time;It is stored with computer program on the computer readable storage medium, the journey
It is performed the steps of when sequence is executed by processor
Step 10, all evaluation and tests record that selected bibliography is extracted from the evaluation and test library;
Step 20 is directed to same topic, the score value of the topic is extracted from total exam pool, and mention from the evaluation and test library
The topic is taken to correspond to the score in N number of evaluation and test record;It is averaged phase by the score that the score value calculates the topic with the score
To difference;The score relative mistake specific formula for calculation that is averaged is as follows:
Wherein, score 1, score 2, score 3 and score N are respectively obtaining in the corresponding multiple evaluation and test records of the topic
Point;N is the natural number greater than zero;
For same topic, all practical Reaction times of the topic are extracted from the evaluation and test record in the evaluation and test library, it is right
All practical Reaction times average to obtain average Reaction time;
It is averaged relative mistake and average Reaction time according to the score that the above method calculates all topics;Score is averaged relative mistake
For assessing the complexity of the topic;Average Reaction time is used to limit Reaction time and the auxiliary judgment students topics
Qualification.
Step 30, the score that all topics are calculated according to above-mentioned formula are averaged relative mistake, with K mean cluster algorithm by
Divide average relative mistake that all topics are clustered into simple topic, medium topic and problem three classes;
Step 40, the topic quantity that simple topic, medium topic and problem is respectively set, from the similar topic clustered with
Machine exports the topic of respective numbers, ultimately generates PK match exam pool;
If in the similar topic clustered, total topic quantity is less than such and needs derived topic quantity, then exporting
After such all topic, the topic of difference randomly selects supplement from other two class, until meeting such needs derived topic
Until mesh number amount.
It is as shown in table 1 that PK matches exam pool pkQueLib generating algorithm.
1 PK of table matches exam pool pkQueLib generating algorithm
Although specific embodiments of the present invention have been described above, those familiar with the art should be managed
Solution, we are merely exemplary described specific embodiment, rather than for the restriction to the scope of the present invention, it is familiar with this
The technical staff in field should be covered of the invention according to modification and variation equivalent made by spirit of the invention
In scope of the claimed protection.
Claims (8)
1. a kind of generation method of PK match exam pool, it is characterised in that: match exam pool including total exam pool, evaluation and test library and PK;It is described total
Exam pool includes a plurality of original records, and each original records include: bibliography, topic, answer and score value;The evaluation and test
Library includes a plurality of evaluation and test records, and the evaluation and test is recorded as the record that topic in total exam pool be used to evaluate and test, the evaluation and test
Record includes: user, bibliography, topic, score and practical Reaction time;
The method specifically includes following steps:
Step 10, all evaluation and tests record that selected bibliography is extracted from the evaluation and test library;
Step 20 is directed to same topic, and the score value of the topic is extracted from total exam pool, and extracting from the evaluation and test library should
Topic corresponds to the score in N number of evaluation and test record;It is averaged relative mistake by the score that the score value and the score calculate the topic;
The score relative mistake specific formula for calculation that is averaged is as follows:
Wherein, score 1, score 2, score 3 and score N are respectively the score in the corresponding multiple evaluation and test records of the topic;N is
Natural number greater than zero;
Step 30, the score that all topics are calculated according to above-mentioned formula are averaged relative mistake, flat by score with K mean cluster algorithm
All topics are clustered into simple topic, medium topic and problem three classes by equal relative mistake;
Step 40, the topic quantity that simple topic, medium topic and problem is respectively set, lead at random from the similar topic clustered
The topic of respective numbers out ultimately generates PK match exam pool.
2. a kind of generation method of PK match exam pool according to claim 1, it is characterised in that: in the step 40, if poly-
Certain a kind of total topic quantity is less than the derived topic quantity of such needs, then after all topics for exporting such, phase after class
The topic of difference amount randomly selects supplement from other two class, until meeting such and needing derived topic quantity.
3. a kind of generation method of PK match exam pool according to claim 1, it is characterised in that: the step 20 further includes,
For same topic, all practical Reaction times of the topic are extracted from the evaluation and test record in the evaluation and test library, to all reality
Reaction time averages to obtain average Reaction time.
4. a kind of generation method of PK match exam pool according to claim 1, it is characterised in that: described in the step 40
Every record in PK match exam pool includes: topic, score value, average relative mistake and complexity.
5. a kind of computer readable storage medium, which is characterized in that match exam pool including total exam pool, evaluation and test library and PK;It is described total
Exam pool includes a plurality of original records, and each original records include: bibliography, topic, answer and score value;The evaluation and test
Library includes a plurality of evaluation and test records, and the evaluation and test is recorded as the record that topic in total exam pool be used to evaluate and test, the evaluation and test
Record includes: user, bibliography, topic, score and practical Reaction time;Calculating is stored on computer readable storage medium
Machine program,
The program performs the steps of when being executed by processor
Step 10, all evaluation and tests record that selected bibliography is extracted from the evaluation and test library;
Step 20 is directed to same topic, and the score value of the topic is extracted from total exam pool, and extracting from the evaluation and test library should
Topic corresponds to the score in N number of evaluation and test record;It is averaged relative mistake by the score that the score value and the score calculate the topic;
The score relative mistake specific formula for calculation that is averaged is as follows:
Wherein, score 1, score 2, score 3 and score N are respectively the score in the corresponding multiple evaluation and test records of the topic;N is
Natural number greater than zero;
Step 30, the score that all topics are calculated according to above-mentioned formula are averaged relative mistake, flat by score with K mean cluster algorithm
All topics are clustered into simple topic, medium topic and problem three classes by equal relative mistake;
Step 40, the topic quantity that simple topic, medium topic and problem is respectively set, lead at random from the similar topic clustered
The topic of respective numbers out ultimately generates PK match exam pool.
6. a kind of computer readable storage medium according to claim 5, it is characterised in that: in the step 40, if poly-
Certain a kind of total topic quantity is less than the derived topic quantity of such needs after class, then after all topics for exporting such,
The topic of difference quantity randomly selects supplement from other two class, until meeting such and needing derived topic quantity.
7. a kind of computer readable storage medium according to claim 5, it is characterised in that: the step 20 further includes,
For same topic, all practical Reaction times of the topic are extracted from the evaluation and test record in the evaluation and test library, to all reality
Reaction time averages to obtain average Reaction time.
8. a kind of computer readable storage medium according to claim 5, it is characterised in that: described in the step 40
Every record in PK match exam pool includes: topic, score value, average relative mistake and complexity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811303495.XA CN109471940A (en) | 2018-11-02 | 2018-11-02 | A kind of generation method and computer readable storage medium of PK match exam pool |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811303495.XA CN109471940A (en) | 2018-11-02 | 2018-11-02 | A kind of generation method and computer readable storage medium of PK match exam pool |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109471940A true CN109471940A (en) | 2019-03-15 |
Family
ID=65666607
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811303495.XA Pending CN109471940A (en) | 2018-11-02 | 2018-11-02 | A kind of generation method and computer readable storage medium of PK match exam pool |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109471940A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2575123A1 (en) * | 2011-09-30 | 2013-04-03 | Tata Consultancy Services Limited | Customized question paper generation |
CN104900101A (en) * | 2015-06-19 | 2015-09-09 | 北京天奇健教育科技有限公司 | Terminal examination evaluation system and evaluation method using the same |
CN106409039A (en) * | 2016-12-20 | 2017-02-15 | 国网山东省电力公司东明县供电公司 | Electric power safety training method and system |
CN106803123A (en) * | 2016-12-20 | 2017-06-06 | 广州中软信息技术有限公司 | A kind of automatic volume group method for online exam |
CN107316258A (en) * | 2017-06-26 | 2017-11-03 | 深圳市斯维尔科技股份有限公司 | With no paper contest method, device, terminal and computer-readable recording medium |
CN107895518A (en) * | 2017-09-08 | 2018-04-10 | 杭州伯仲信息科技有限公司 | Information-based nurse training method |
CN107918655A (en) * | 2017-11-16 | 2018-04-17 | 重庆三峡学院 | A kind of test paper generation management control system and control method |
-
2018
- 2018-11-02 CN CN201811303495.XA patent/CN109471940A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2575123A1 (en) * | 2011-09-30 | 2013-04-03 | Tata Consultancy Services Limited | Customized question paper generation |
CN104900101A (en) * | 2015-06-19 | 2015-09-09 | 北京天奇健教育科技有限公司 | Terminal examination evaluation system and evaluation method using the same |
CN106409039A (en) * | 2016-12-20 | 2017-02-15 | 国网山东省电力公司东明县供电公司 | Electric power safety training method and system |
CN106803123A (en) * | 2016-12-20 | 2017-06-06 | 广州中软信息技术有限公司 | A kind of automatic volume group method for online exam |
CN107316258A (en) * | 2017-06-26 | 2017-11-03 | 深圳市斯维尔科技股份有限公司 | With no paper contest method, device, terminal and computer-readable recording medium |
CN107895518A (en) * | 2017-09-08 | 2018-04-10 | 杭州伯仲信息科技有限公司 | Information-based nurse training method |
CN107918655A (en) * | 2017-11-16 | 2018-04-17 | 重庆三峡学院 | A kind of test paper generation management control system and control method |
Non-Patent Citations (1)
Title |
---|
范玉玲 等: "基于在线评测数据的题目等级分类模型研究", 《计算机与现代化》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103208211A (en) | Method and device for question selection of network education test | |
CN109783601A (en) | Computer intelligence group volume method and its system based on knowledge on testing point | |
Mariño et al. | An empirical evaluation of evaluation metrics of procedurally generated Mario levels | |
Chiesi et al. | Item response theory analysis and differential item functioning across age, gender and country of a short form of the advanced progressive matrices | |
CN109033262A (en) | Question and answer knowledge base update method and device | |
CN107292785A (en) | One kind is set a question method and system | |
CN111191935A (en) | Evaluation and assessment system and method | |
CN115952299A (en) | Intelligent simulation examination recommendation system and method | |
CN115798022A (en) | Artificial intelligence identification method based on feature extraction | |
Wainer | A primer | |
CN114119304A (en) | User management method, system and computer storage medium for online education platform | |
JP2005024635A (en) | Ability evaluation system, method and program for the same | |
CN112256576B (en) | Man-machine dialogue corpus testing method, device, equipment and storage medium | |
CN116542829A (en) | Personalized intelligent group scroll and on-line examination method | |
CN109471940A (en) | A kind of generation method and computer readable storage medium of PK match exam pool | |
Vidler et al. | Further validation of a scale of academic curiosity | |
CN114461786B (en) | Learning path generation method and system | |
Waller | A procedure for comparing logistic latent trait models | |
Lin | Evaluation of resources for question answering evaluation | |
CN109464799A (en) | A kind of competition method and computer readable storage medium of two people PK | |
CN108664842B (en) | Lip movement recognition model construction method and system | |
CN111967276B (en) | Translation quality evaluation method and device, electronic equipment and storage medium | |
CN113918471A (en) | Test case processing method and device and computer readable storage medium | |
Arikan | The Effect of Mini and Midi Anchor Tests on Test Equating. | |
Li | Examining the impact of drifted polytomous anchor items on test characteristic curve (TCC) linking and IRT true score equating |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190315 |