CN112699283A - Test paper generation method and device - Google Patents

Test paper generation method and device Download PDF

Info

Publication number
CN112699283A
CN112699283A CN202011606340.0A CN202011606340A CN112699283A CN 112699283 A CN112699283 A CN 112699283A CN 202011606340 A CN202011606340 A CN 202011606340A CN 112699283 A CN112699283 A CN 112699283A
Authority
CN
China
Prior art keywords
paper
test
bidirectional
question
examination
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.)
Granted
Application number
CN202011606340.0A
Other languages
Chinese (zh)
Other versions
CN112699283B (en
Inventor
郝龙飞
沙晶
付瑞吉
王士进
魏思
胡国平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
iFlytek Co Ltd
Original Assignee
iFlytek Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by iFlytek Co Ltd filed Critical iFlytek Co Ltd
Priority to CN202011606340.0A priority Critical patent/CN112699283B/en
Publication of CN112699283A publication Critical patent/CN112699283A/en
Application granted granted Critical
Publication of CN112699283B publication Critical patent/CN112699283B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/90335—Query processing
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The application relates to the technical field of data processing, in particular to a test paper generation method and a test paper generation device, wherein the method comprises the following steps: acquiring volume group information; searching candidate volumes matched with the volume group information from the master volume library; acquiring a bidirectional item list of the candidate volume, wherein the bidirectional item list comprises a plurality of bidirectional item entries; adjusting the bidirectional detailed list according to the group volume information; and adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper. According to the method and the device, matched test paper is searched out from an existing mother paper library through the paper forming information to serve as the candidate paper, the candidate paper is abstracted to be a bidirectional detailed list describing key characteristics of the test paper, and the bidirectional detailed list is adjusted according to the paper forming information, so that a user can automatically generate the test paper only by setting the paper forming information, the test paper generation efficiency is improved, and meanwhile the problems that the quality of formed products is not high and the positioning is not accurate due to manual test paper forming are avoided.

Description

Test paper generation method and device
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a test paper generation method and apparatus.
Background
With the continuous development of the research in the intelligent education field, the intelligent education field plays more and more roles in teaching and examination. In the teaching process, the examination is a very effective mode in order to know the mastery condition of the knowledge of each student and the teaching quality of teachers. The teacher can judge the learning state of each student at the stage through the examination score of each student, and timely correct the students with abnormal learning states. Therefore, it is very important to check the learning effect of the student by using the examination and to feed back the learning process of the student.
When generating a test paper, a problem setting teacher usually searches related test questions from resources such as review data, a problem set, a test paper of a past year and the like according to the current test requirements, and then selects the test questions meeting the test requirements according to personal experience to generate a test paper. However, the above method needs to manually select questions from a huge number of question banks, which consumes a lot of time and effort, is inefficient, and is difficult to fully utilize the huge number of question bank resources. Moreover, because the quantity of the test questions in the test question bank is huge, the screening of the test questions meeting the conditions from the test question bank needs to depend on the personal intuition and experience of teachers, and a high-quality test paper generally needs some education experts with higher levels to complete the test paper after a long time of research. Therefore, how to improve the production efficiency of the test paper is an urgent problem to be solved on the premise of ensuring that the produced test paper has higher quality.
Disclosure of Invention
The embodiment of the application provides a test paper generation method and device, which can improve the generation efficiency of test paper on the premise of ensuring that the generated test paper has higher quality.
In a first aspect, an embodiment of the present application provides a test paper generation method, where the method includes:
acquiring volume group information;
searching a candidate volume matched with the volume group information from a parent volume library;
acquiring a bidirectional item list of the candidate paper, wherein the bidirectional item list comprises a plurality of bidirectional item items, and the bidirectional item items comprise attribute information of a certain test question in the candidate paper;
adjusting the bidirectional detailed list according to the group volume information;
and adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper.
Optionally, the method further includes: constructing the master paper library, wherein the master paper library comprises a plurality of examination papers, and each examination paper comprises a plurality of examination questions; and sequencing the examination schools of each examination paper according to historical examination data, and establishing a mapping relation for the horizontal capacity of any two examination schools.
Optionally, searching for a candidate volume matched with the group volume information from a parent volume library according to the group volume information includes: calculating the matching degree of the attribute information of each test paper in the master paper library and the paper group information; and determining the examination paper corresponding to the maximum matching degree as the candidate paper.
Optionally, the group volume information includes: target examination type, target examination paper difficulty, target question type quantity and target knowledge point;
the calculating the matching degree of the attribute information of each test paper in the master paper library and the paper group information comprises the following steps: calculating the type consistency of the attribute information of each test paper and the test paper information, wherein the type consistency comprises the consistency of the target examination type quantity and the examination type quantity of the test paper and the consistency of the target examination type and the examination type of the examination paper; calculating the target similarity of the attribute information of each test paper and the group paper information, wherein the target similarity comprises the similarity of the target test paper difficulty and the test paper difficulty of the test paper and the similarity of the target knowledge point and the test paper knowledge point of the test paper; determining the test paper priority of each test paper; and calculating the matching degree of each test paper according to the type consistency, the target similarity and the test paper priority of each test paper.
Optionally, the examination paper information further includes a target examination school;
calculating the test paper difficulty of the test paper, and specifically comprises the following steps: acquiring the average score of each test school corresponding to the test paper; determining the horizontal capability of each test school according to the mapping relationship between the horizontal capability of each test school and the horizontal capability of the target test school; and calculating the test paper difficulty of the test paper according to the horizontal capacity of each test school and the average score of each test school.
Optionally, the method further includes: constructing a topological sequence of the knowledge points according to the learning sequence of the knowledge points; and counting the examination question knowledge points in each examination paper according to the historical examination data to obtain at least one of high-frequency examination points, key points and difficulties in the knowledge points.
Optionally, the adjusting the bidirectional breakdown list according to the group volume information includes: traversing the bidirectional item entries, comparing the test question knowledge points in the bidirectional item entries with the target knowledge point, if the test question knowledge points of the first bidirectional item entries are behind the topological sequence of the target knowledge point, adjusting the first bidirectional item entries into second bidirectional item entries, wherein the second bidirectional item entries are bidirectional item entries with the test question knowledge points as second test question knowledge points, and the second test question knowledge points are any one of test question knowledge points, the high-frequency test points, the key points and the difficulties which are not included in the bidirectional item table.
Optionally, the method further includes: if the quantity of the first test question type in the plurality of bidirectional item items is more than that of the first test question type in the target quantity of the test questions, deleting a third bidirectional item, wherein the third bidirectional item is a third test question knowledge point with the test question type being the first test question type or a first test question difficulty, the third test question knowledge point is a test question knowledge point behind the topological order of the target knowledge point, and the first test question difficulty is a test question difficulty which is greater than the upper limit of a preset test question difficulty range or smaller than the lower line of the preset test question difficulty range; and if the quantity of the first test question type in the bidirectional item items is less than that of the first test question type in the target question type quantity, increasing the second bidirectional item items.
Optionally, the adjusting the test questions in the candidate paper according to the adjusted bidirectional breakdown list to obtain a target paper includes:
selecting at least one candidate test question from the master paper library according to the second bidirectional item; calculating the test question matching degree of each candidate test question in the at least one candidate test question; and replacing the candidate test question with the maximum test question matching degree in the at least one candidate test question with the test question corresponding to the second bidirectional item to obtain the target paper.
Optionally, the calculating the test question matching degree of each candidate test question in the at least one candidate test question includes: and calculating the test question matching degree of each candidate test question according to the test question knowledge point similarity, the test question number similarity, the test question difficulty similarity, the test question standard score similarity and the test question scene similarity of each candidate test question.
In a second aspect, an embodiment of the present application provides a test paper generating apparatus, where the apparatus includes:
a first acquisition unit configured to acquire group volume information;
the searching unit is used for searching the candidate volume matched with the volume group information from the parent volume library;
a second obtaining unit, configured to obtain a bidirectional breakdown list of the candidate paper, where the bidirectional breakdown list includes multiple bidirectional breakdown lists, and the bidirectional breakdown list entry includes attribute information of a certain test question in the candidate paper;
a first adjusting unit, configured to adjust the bidirectional breakdown list according to the group volume information;
and the second adjusting unit is used for adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper.
Optionally, the apparatus further comprises a processing unit, wherein,
the processing unit is configured to: constructing the master paper library, wherein the master paper library comprises a plurality of examination papers, and each examination paper comprises a plurality of examination questions; and sequencing the examination schools of each examination paper according to historical examination data, and establishing a mapping relation for the horizontal capacity of any two examination schools.
Optionally, the search unit is specifically configured to: calculating the matching degree of the attribute information of each test paper in the master paper library and the paper group information; and determining the examination paper corresponding to the maximum matching degree as the candidate paper.
Optionally, the group volume information includes: target examination type, target examination paper difficulty, target question type quantity and target knowledge point;
in terms of calculating the matching degree between the attribute information of each test paper in the master paper library and the paper group information, the search unit is specifically configured to: calculating the type consistency of the attribute information of each test paper and the test paper information, wherein the type consistency comprises the consistency of the target examination type quantity and the examination type quantity of the test paper and the consistency of the target examination type and the examination type of the examination paper; calculating the target similarity of the attribute information of each test paper and the group paper information, wherein the target similarity comprises the similarity of the target test paper difficulty and the test paper difficulty of the test paper and the similarity of the target knowledge point and the test paper knowledge point of the test paper; determining the test paper priority of each test paper; and calculating the matching degree of each test paper according to the type consistency, the target similarity and the test paper priority of each test paper.
Optionally, the examination paper information further includes a target examination school; in terms of calculating the test paper difficulty of the test paper, the search unit is specifically configured to: acquiring the average score of each test school corresponding to the test paper; determining the horizontal capability of each test school according to the mapping relationship between the horizontal capability of each test school and the horizontal capability of the target test school; and calculating the test paper difficulty of the test paper according to the horizontal capacity of each test school and the average score of each test school.
Optionally, the processing unit is further configured to: constructing a topological sequence of the knowledge points according to the learning sequence of the knowledge points; and counting the examination question knowledge points in each examination paper according to the historical examination data to obtain at least one of high-frequency examination points, key points and difficulties in the knowledge points.
Optionally, the first adjusting unit is specifically configured to: traversing the bidirectional item entries, comparing the test question knowledge points in the bidirectional item entries with the target knowledge point, if the test question knowledge points of the first bidirectional item entries are behind the topological sequence of the target knowledge point, adjusting the first bidirectional item entries into second bidirectional item entries, wherein the second bidirectional item entries are bidirectional item entries with the test question knowledge points as second test question knowledge points, and the second test question knowledge points are any one of test question knowledge points, the high-frequency test points, the key points and the difficulties which are not included in the bidirectional item table.
Optionally, the processing unit is further configured to: if the quantity of the first test question type in the plurality of bidirectional item items is more than that of the first test question type in the target quantity of the test questions, deleting a third bidirectional item, wherein the third bidirectional item is a third test question knowledge point with the test question type being the first test question type or a first test question difficulty, the third test question knowledge point is a test question knowledge point behind the topological order of the target knowledge point, and the first test question difficulty is a test question difficulty which is greater than the upper limit of a preset test question difficulty range or smaller than the lower line of the preset test question difficulty range; and if the quantity of the first test question type in the bidirectional item items is less than that of the first test question type in the target question type quantity, increasing the second bidirectional item items.
Optionally, the second adjusting unit is specifically configured to: selecting at least one candidate test question from the master paper library according to the second bidirectional item; calculating the test question matching degree of each candidate test question in the at least one candidate test question; and replacing the candidate test question with the maximum test question matching degree in the at least one candidate test question with the test question corresponding to the second bidirectional item to obtain the target paper.
Optionally, in calculating the test question matching degree of each candidate test question in the at least one candidate test question, the second adjusting unit is specifically configured to: and calculating the test question matching degree of each candidate test question according to the test question knowledge point similarity, the test question number similarity, the test question difficulty similarity, the test question standard score similarity and the test question scene similarity of each candidate test question.
In a third aspect, an embodiment of the present application provides a terminal device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing steps in any method of the first aspect of the embodiment of the present application.
In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program makes a computer perform part or all of the steps described in any one of the methods of the first aspect of the present application.
In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps as described in any one of the methods of the first aspect of the embodiments of the present application. The computer program product may be a software installation package.
In the embodiment of the application, volume group information is acquired; searching a candidate volume matched with the volume group information from a parent volume library; acquiring a bidirectional item list of the candidate paper, wherein the bidirectional item list comprises a plurality of bidirectional item items, and the bidirectional item items comprise attribute information of a certain test question in the candidate paper; adjusting the bidirectional detailed list according to the group volume information; and adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper. The matched test paper is searched out from the existing mother paper library through the paper grouping information to serve as the candidate paper, the candidate paper is abstracted to be the bidirectional item list describing the key characteristics of the test paper, the bidirectional item list is adjusted according to the paper grouping information, when a user needs to generate the test paper, the matched candidate paper can be automatically searched only by setting the paper grouping information, the test paper is generated after the test paper is adjusted according to the paper grouping information, the test paper generation efficiency is improved, and meanwhile, the problems that the quality of the product formed due to manual paper grouping is not high and the positioning is not accurate are avoided.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a test paper generation method provided in an embodiment of the present application;
fig. 2 is a schematic flowchart of calculating a matching degree according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of an application scenario for acquiring test questions provided in an embodiment of the present application;
FIG. 4a is a block diagram illustrating functional units of a test paper generation apparatus according to an embodiment of the present disclosure;
FIG. 4b is a block diagram illustrating functional units of a test paper generating apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
The technical solution in the present application will be described below with reference to the accompanying drawings.
It is to be understood that reference to "at least one" in the embodiments of the present application means one or more, and "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.
And, unless stated to the contrary, the embodiments of the present application refer to the ordinal numbers "first", "second", etc., for distinguishing a plurality of objects, and do not limit the sequence, timing, priority, or importance of the plurality of objects. For example, the first information and the second information are different information only for distinguishing them from each other, and do not indicate a difference in the contents, priority, transmission order, importance, or the like of the two kinds of information.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flow chart of a test paper generation method according to an embodiment of the present application. As shown in fig. 1, the method includes the following steps.
And S110, acquiring the volume group information.
The examination paper forming information may include information such as a target examination type, a target examination paper difficulty, a target question quantity, a target knowledge point, and the like.
In a specific implementation, when a test paper is created, the test type corresponding to the test paper of the test paper needs to be known first, and the test types include but are not limited to: weekly examinations, monthly examinations, interim examinations, end examinations, simulated examinations, etc. The question types contained in the test paper and the quantity of each type of question can also be different according to different test types, wherein the question types can comprise single-choice questions, multiple-choice questions, blank filling questions, solution questions and the like, for example, the weekly test is mainly used for inspecting the understanding degree of students on the contents learned in the week and the mastering degree of key contents, so that the quantity of the selected questions in the weekly test is large. After the examination type and the subject amount of the test paper are determined, the scope of the book section related to the test paper, namely the knowledge point considered by the test paper, is also needed, for example, for weekly examinations facing the same group of students, the learning content of the students in each week is different, so the knowledge point related to each weekly examination is also different. Further, the mastery degree of the knowledge points of different students is different, so that the difficulty of the test paper needs to be obtained when the test paper is generated, so that the generated test paper can better reflect the learning state of the students at the stage.
Illustratively, the test paper information may further include a target test school and a target test grade. Because the question points examined by different areas for the same knowledge point are possibly different, the test paper of the test school closer to the question points of the target test school can be found through the target test school and the target test grade, and the quality of the generated test paper is improved.
And S120, searching the candidate volume matched with the volume group information from the master volume library.
After each examination of the student, the examination paper of the examination can be imported into the database according to the requirement, so that the master paper database data is formed. If the examination papers of the student examination are paper, the examination papers of the paper edition can be obtained through scanning; if the examination paper of the student examination is an electronic version, the examination paper of the electronic version can be directly imported into the master paper library.
Further, when the examination paper is imported into the master paper library, the following attribute information of each set of examination paper needs to be filled or identified: the title of the examination paper, the examination time, the examination type, the knowledge points contained in the examination paper, the average scores of the schools participating in the examination and the students corresponding to the schools in the examination, and the information of the question number, the examination type, the examination question knowledge points, the standard scores of the examination questions, the average score of the schools participating in the examination in the question and the like contained in the examination paper.
Optionally, the method further includes: constructing the master paper library, wherein the master paper library comprises a plurality of examination papers, and each examination paper comprises a plurality of examination questions; and sequencing the examination schools of each examination paper according to historical examination data, and establishing a mapping relation for the horizontal capacity of any two examination schools.
The teaching level capability and the birth source of each school are different, so that the overall levels of students in different schools are different, and in order to reduce the difference among the schools, all schools can be sorted according to the historical examination data and the level capability of any two schools can be mapped. Specifically, the average score of students in an examination school related to the same examination paper is used as the horizontal capacity of the corresponding school, for example, one examination paper is adopted by a school A and a school B, the average score of the students in the school A is 72, and the horizontal capacity is 72; the students in school B are divided equally into 80 points, their horizontal competence is 80, and the mapping relationship between the horizontal competencies between school a and school B is 0.9.
Optionally, the method further includes: constructing a topological sequence of the knowledge points according to the learning sequence of the knowledge points; and counting the examination question knowledge points in each examination paper according to the historical examination data to obtain at least one of high-frequency examination points, key points and difficulties in the knowledge points.
In practical applications, a test question may involve multiple knowledge points with correlation between the multiple knowledge points. If the knowledge points related to the test question are directly input and the relevance between the knowledge points is ignored, the question intention of the test question may not be accurately understood. The students learn according to the compiling sequence of the teaching materials learned by the students, and in order to enable the students to master knowledge points more easily, the teaching materials are compiled successively according to the relevance and difficulty of the knowledge points. Therefore, the topological sequence of the knowledge points can be constructed according to the learning sequence of the knowledge points, and the knowledge points related to the test question can be better reflected.
Further, the degree of importance, ease, and degree of investigation of each knowledge point are different. The expert group also considers whether each knowledge point is a critical point or a high-frequency examination point, whether the examination questions comprise superbasic knowledge points, whether the examination questions are old and the like when the examination paper is made, so that in the embodiment of the application, after the students complete each examination, the examination question knowledge points in each examination paper can be counted according to the examination results of the students. The method specifically comprises the steps of counting the number of times of investigation of each knowledge point and the average score of each school participating in the examination at the knowledge point, determining high-frequency examination points according to the number of times of investigation of the knowledge points, and determining key points and difficulty points according to the number of times of investigation and the average score of the knowledge points.
Optionally, the searching for the candidate volume matched with the group volume information from the parent volume library according to the group volume information includes: calculating the matching degree of the attribute information of each test paper in the master paper library and the paper group information; and determining the examination paper corresponding to the maximum matching degree as the candidate paper.
The existing automatic paper grouping method simply defines paper grouping as an optimization problem of test question granularity and test paper granularity, the combined optimization is a Non-deterministic (NP) problem of Polynomial complexity, and it is difficult to search out an optimal solution from a massive test question library. Therefore, in the embodiment of the application, the high-quality examination paper in the past year is directly used as the master paper library according to the natural integrity of the existing test paper, and the test paper which best meets the requirements of the group paper is searched from the master paper library according to the requirements of the group paper, so that the complex problem of combination optimization is avoided.
Because general examination paper requirements include examination schools, examination grades, examination paper difficulty, examination type subject distribution and examination type, and examination relates to knowledge points. Therefore, the key factors for matching the test paper are: examination type, test paper difficulty, question type, question amount, chapter containing knowledge point range, and the like. When searching for the candidate paper, each test paper in the mother paper library is firstly traversed. For example, when the examination paper information includes a target examination school, examination papers of an examination school closer to the target examination school may be preferentially traversed. And then, according to the examination paper information, calculating the matching degree of each examination paper, and taking the examination paper with the maximum matching degree as a candidate paper.
Optionally, the calculating the matching degree between the attribute information of each test paper in the master paper library and the paper combination information includes:
calculating the type consistency of the attribute information of each test paper and the test paper information, wherein the type consistency comprises the consistency of the target examination type quantity and the examination type quantity of the test paper and the consistency of the target examination type and the examination type of the examination paper; calculating the target similarity of the attribute information of each test paper and the group paper information, wherein the target similarity comprises the similarity of the target test paper difficulty and the test paper difficulty of the test paper and the similarity of the target knowledge point and the test paper knowledge point of the test paper; determining the test paper priority of each test paper; and calculating the matching degree of each test paper according to the type consistency, the target similarity and the test paper priority of each test paper.
In the embodiment of the present application, as shown in fig. 2, when candidate papers are matched from the master paper library, the type consistency and the target similarity of each test paper are calculated respectively. The type consistency is used for measuring the question type quantity of the examination paper in the master paper and the target question type quantity in the group paper information, and the matching degree of the examination type of the examination paper in the master paper and the target examination type in the group paper information. The target similarity is used for measuring the matching degree of the knowledge point of the examination paper in the mother paper and the target knowledge point in the group paper information, and the test paper difficulty of the examination paper in the mother paper and the target test paper difficulty in the group paper information. Meanwhile, in order to embody the individuation of the test paper and fuse more expert knowledge, the test paper priority of each test paper is determined, and the determination of the test paper priority can be set according to specific application scenes and requirements. For example, for a simulated test of the reformed high third, the test paper priority of a newer test paper can be set to be higher in order to be more matched with the subject quantity of the reformed subject; for the weekly examination of a course, in order to reduce the difference of the questions in different regions, the test paper priority of the test papers of the similar school regions can be set to be higher; for the monthly exam of a course, in order to detect the mastery degree of the students on the knowledge points, the higher priority of the test paper of the famous school test paper can be set; for the end-of-term examination of a course, the priority of the examination paper of the joint examination paper can be set to be higher in order to better understand the learning effect of the detection students. According to different scenes and different requirements, the weighting can be used as the test paper priority measurement basis for different examination test papers.
Specifically, the calculation formula of the matching degree may be represented as: match ═ α ×, type identity + β ×, target similarity + γ ×, paper priority. The α, the β, and the γ are weight coefficients of the matching degree, the α, the β, and the γ are all positive numbers, and the sum thereof is 1. Illustratively, under unknown scenarios, three weighting coefficients are typically set a priori to 1/3. The actual effect may be influenced by the mother paper library and different for the user population, the three weight coefficients may be adjusted according to the actual scene, for example, the similarity of the test questions may be particularly emphasized in the weekly examination scene, and β may be set to be larger to ensure the targeted training effect; the end-of-term examination scene is more likely to be a new test question and a good test question, and therefore gamma can be set to be larger.
The type consistency comprises the question type quantity consistency and the test type consistency, and the consistency aims to utilize the overall information of the time of the master volume library as much as possible. The type consistency may be expressed as: type consistency (r) question volume consistency + (1-r) test type consistency. And r is a threshold value and is used for adjusting the question quantity of the question type and the importance degree of the test type, and the r is a positive number. And when the examination type of the examination paper in the examination paper library is the same as the target examination type, the r is 1, and otherwise, the r is 0. The topic theme consistency can be expressed as:
Figure BDA0002865987560000071
wherein m is the number of question types in the target question type question amount in the group volume information, and p isiThe question amount of question type i in the question amount of the target question type, the pi' is the quantity of the question type i in the examination paper in the master paper library.
Optionally, in the case that the test paper information further includes a target test school; calculating the test paper difficulty of the test paper, and specifically comprises the following steps:
acquiring the average score of each test school corresponding to the test paper; determining the horizontal capability of each test school according to the mapping relationship between the horizontal capability of each test school and the horizontal capability of the target test school; and calculating the test paper difficulty of the test paper according to the horizontal capacity of each test school and the average score of each test school.
Specifically, the target similarity includes a similarity between the target test paper difficulty and the test paper difficulty of the test paper in the master paper library, and a similarity between the target knowledge point and the test paper knowledge point of the test paper in the master paper library. In order to more accurately depict the difficulty of the test paper, the embodiment of the application measures according to the average score of students of the test paper. For example, a master batch is taken by N schools, each school can calculate the average score of the students according to the examination conditions to obtain [ (school 1, average score 1), (school 2, average score 2), … …, (school N, average score N)]. In the concrete implementation, the horizontal abilities of schools have certain difference, and in order to construct test paper with personalized difficulty for a target examination school, the abilities of any two schools can be mapped, namely the test paper difficulty of the test paper in the master paper library is determined according to the mapping relation of the horizontal abilities between the two schools. Specifically, it is known that the test paper of school A is equally divided into SAThen the average score of the test paper of school B can be SB＝RAB*SA，RABIs the ratio of the horizontal capacity of school A and school B. Therefore, the examination difficulty of the examination paper relative to the target examination school can be estimated according to the examination condition of the examination paper in the master paper library. The difficulty of the target test paper and the test paper of the examination paper in the master paper library are difficultThe similarity of the degrees can be determined by the ratio of the target test paper difficulty to the test paper difficulty of the test papers in the master paper library.
Further, the distribution of each knowledge point in different examination types and different question types is different, and whether the knowledge point is a high-frequency examination point or not is a factor of difficulty. Therefore, the embodiment of the application performs biased weighting on different knowledge points to calculate the similarity between the target knowledge point and the test paper knowledge point of the test paper in the master paper library. The similarity between the target knowledge point and the examination paper knowledge point of the examination paper in the master paper library can be expressed as follows:
SK＝(a1*c1*K1+a2*c2*K2+…+aN*cN*KN)/(a1*K1+a2*K2+？+N*KN)
wherein (a)1,a2,…，aN) Is a set of weights assigned to N target knowledge points according to the degree of importance of the knowledge points, (c)1,c2,…，cN) The knowledge points of the examination paper in the master paper library comprise the set of the N target knowledge points, cjThe value 1 represents that the examination paper in the master paper library comprises the corresponding target knowledge point j, and cjAnd the value 0 represents that the examination paper in the master paper library does not comprise the corresponding target knowledge point j, and j is a positive integer less than or equal to N.
S130, a bidirectional item list of the candidate paper is obtained, wherein the bidirectional item list comprises a plurality of bidirectional item entries, and the bidirectional item entries comprise attribute information of a certain test question in the candidate paper.
And abstracting the obtained candidate volume to obtain a universal bidirectional detailed list. The bidirectional detailed table comprises bidirectional detailed items of each test question, and the bidirectional detailed items comprise important information such as serial numbers, difficulty degrees, knowledge points and average values of the test questions.
In practical application, the matched candidate volume may not completely meet the requirements of the group volume, such as the mismatch of topic type and quantity or the existence of a super knowledge point. Therefore, after the candidate paper is obtained, the test questions in the candidate paper are adjusted according to the paper grouping information so as to meet the paper grouping requirement.
Optionally, the adjusting the bidirectional breakdown list according to the group volume information includes: traversing the bidirectional item entries, comparing the test question knowledge points in the bidirectional item entries with the target knowledge point, if the test question knowledge points of the first bidirectional item entries are behind the topological sequence of the target knowledge point, adjusting the first bidirectional item entries into second bidirectional item entries, wherein the second bidirectional item entries are bidirectional item entries with the test question knowledge points as second test question knowledge points, and the second test question knowledge points are any one of test question knowledge points, the high-frequency test points, the key points and the difficulties which are not included in the bidirectional item table.
Specifically, each bidirectional item table entry is traversed, the knowledge points contained in each bidirectional item entry are compared with the target knowledge points, and if the knowledge points in the bidirectional item entries have the super-principle knowledge points, the bidirectional item entries are replaced. The judgment condition of the knowledge point super-dimension of the bidirectional item entry can be as follows: and if the knowledge point exists after the topological sequence of all the target knowledge points, judging that the bidirectional item has the super-class knowledge point.
Optionally, the method further includes: if the quantity of the first test question type in the plurality of bidirectional item items is more than that of the first test question type in the target quantity of the test questions, deleting a third bidirectional item, wherein the third bidirectional item is a third test question knowledge point with the test question type being the first test question type or a first test question difficulty, the third test question knowledge point is a test question knowledge point behind the topological order of the target knowledge point, and the first test question difficulty is a test question difficulty which is greater than the upper limit of a preset test question difficulty range or smaller than the lower line of the preset test question difficulty range;
and if the quantity of the first test question type in the bidirectional item items is less than that of the first test question type in the target question type quantity, increasing the second bidirectional item items.
And traversing each bidirectional item table entry, and counting the question types contained in each bidirectional item entry to obtain the question type question amount of the bidirectional item entry. Then, the question type quantity of the bidirectional item entry is compared with the target question type quantity, and if the question type quantity of the bidirectional item entry does not meet the requirement of the target question type quantity, namely, if a certain type of test question is lack or a certain type of test question is excessive, the bidirectional item entry with the lack of the question type needs to be added or the bidirectional item entry with the excessive question type needs to be deleted.
S140, adjusting the bidirectional detailed list according to the group volume information.
In the embodiment of the application, in order to cover more complete knowledge points as much as possible and to bias toward difficulty points and high-frequency examination points, bidirectional item items with super-class knowledge points can be replaced by bidirectional item items of test questions corresponding to uncovered knowledge points, difficulty points, high-frequency examination points and the like preferentially.
It should be noted that the weight occupied by each knowledge point in the candidate volume may be adjusted according to the actual situation, which is not limited in the embodiment of the present application.
If the quantity of the first test question type in the bidirectional detailed list is larger than that of the first test question type in the target quantity of the test questions, the knowledge points with knowledge points not in the range of the target knowledge points, the bidirectional detailed items with too large difficult test questions or too small difficult test questions are preferentially deleted. If the quantity of the first test question type in the bidirectional item list is less than that of the first test question type in the target quantity of the test questions, in order to ensure that the difficulty of the test paper does not deviate too much from the difficulty of the target test paper, the bidirectional item items which are similar to the difficulty of the target test paper and contain knowledge points which are not covered, difficulty points and high-frequency examination points are preferentially added.
In the embodiment of the application, the test paper is abstracted into the bidirectional breakdown list describing the key characteristics of the test paper, and then the bidirectional breakdown list is adjusted according to the paper combination requirements of the test paper and the layout of the knowledge points. The search based on the test paper and the abstract bidirectional detailed list can effectively avoid the problem of combination optimization of the test question granularity.
S150, adjusting the test questions in the candidate paper according to the adjusted bidirectional fine list to obtain the target paper.
Optionally, the adjusting the test questions in the candidate paper according to the adjusted bidirectional breakdown list to obtain a target paper includes: selecting at least one candidate test question from the master paper library according to the second bidirectional item; calculating the test question matching degree of each candidate test question in the at least one candidate test question; and replacing the candidate test question with the maximum test question matching degree in the at least one candidate test question with the test question corresponding to the second bidirectional item to obtain the target paper.
And aiming at the replaced or added bidirectional breakdown list entries, traversing all the test questions of the same type from the master paper library, calculating the similarity of the test questions one by one, and selecting the test questions which best meet the requirements. And finally, forming the target paper by the selected test questions according to the question numbers.
Optionally, the calculating the test question matching degree of each candidate test question in the at least one candidate test question includes: and calculating the test question matching degree of each candidate test question according to the test question knowledge point similarity, the test question number similarity, the test question difficulty similarity, the test question standard score similarity and the test question scene similarity of each candidate test question.
Illustratively, the test question matching degree can be expressed as test question matching degree, a test question knowledge point similarity, b test question number similarity, c test question difficulty similarity, d test question standard score similarity and e test question scene similarity. The a, the b, the c, the d and the e are weights of the matching degree of the test questions, the a, the b, the c, the d and the e are positive numbers, the sum of the positive numbers is 1, and the importance degrees of different similarity degrees are represented respectively.
Wherein, a, b, c, d and e can be adjusted according to actual conditions. The similarity matching capability of the test questions can be fully considered by the different similarity weights, and the knowledge point layout is integrated, for example, under the condition that the student score discrimination is emphasized, the difficulty similarity weight can be increased, so that the test questions with proper difficulty can be matched more accurately; under the condition of a test scene that the ordering problem of different test questions is emphasized, the weight of the question number similarity can be increased under the condition that the test question difficulty is reached or the knowledge points are layered.
Furthermore, the similarity of the knowledge points can be measured according to the average score of students taking the test questions, and can be determined by the ratio of the difficulty of the target test question to the difficulty of the test questions in the master paper library. The specific calculation of the difficulty similarity can refer to a calculation mode of the similarity between the target test paper difficulty and the test paper difficulty of the test paper in the master paper library, and the specific calculation of the knowledge point similarity and the standard score similarity can refer to a calculation mode of the similarity between the target knowledge point and the test paper knowledge point of the test paper in the master paper library, which is not repeated in the embodiment of the present application.
In the embodiment of the present application, in order to maintain the context of the test paper as much as possible, the question number is considered to be very important information, and therefore, the question number similarity of the test questions is calculated in the question matching degree. The similarity of the test question numbers is the approximate degree of the serial numbers of the target bidirectional item items and the test question serial numbers in the master paper library. The similarity of the test question numbers can be measured by calculating the difference between the serial numbers of the target bidirectional item items and the test question serial numbers in the master paper library.
In practical application, the generated test paper often has some results which do not meet the requirements of the group paper. For example, the test paper is more desirable that some test questions are more biased to calculation, more biased to problem solving skills or more biased to application scenarios, etc. Illustratively, the application scenario of each test question in the test paper in the master paper library may be manually labeled, specifically, the application scenario of each test question is manually labeled when the test paper is imported into the master paper library.
Illustratively, the natural language understanding method can also be used for understanding the topic information of the test questions, and further automatically labeling the application scene of each test question. For example, as shown in fig. 3, feature processing is performed on each test question in each test paper, specifically, features are extracted by using a natural language processing technique, such as a Chinese segmentation technique, a test question formula expression technique, and the like. And then inputting the extracted features into a pre-trained prediction model, wherein the prediction model can be a Deep Neural Network (DNN) model, such as a Text Convolutional Neural network (Text Convolutional Neural network, Text CNN, Long Short-Term Memory (LSTM), and a Transformer and variant model thereof.
It can be seen that the test paper generation method provided in the embodiment of the present application obtains the group paper information; searching a candidate volume matched with the volume group information from a parent volume library; acquiring a bidirectional item list of the candidate paper, wherein the bidirectional item list comprises a plurality of bidirectional item items, and the bidirectional item items comprise attribute information of a certain test question in the candidate paper; adjusting the bidirectional detailed list according to the group volume information; and adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper. The matched test paper is searched out from the existing mother paper library through the paper grouping information to serve as the candidate paper, the candidate paper is abstracted to be the bidirectional item list describing the key characteristics of the test paper, the bidirectional item list is adjusted according to the paper grouping information, when a user needs to generate the test paper, the matched candidate paper can be automatically searched only by setting the paper grouping information, the test paper is generated after the test paper is adjusted according to the paper grouping information, the test paper generation efficiency is improved, and meanwhile, the problems that the quality of the product formed due to manual paper grouping is not high and the positioning is not accurate are avoided.
The above description has introduced the solution of the embodiment of the present application mainly from the perspective of the method-side implementation process. It is understood that the terminal device includes hardware structures and/or software modules for performing the respective functions in order to implement the functions. Those of skill in the art will readily appreciate that the present application is capable of hardware or a combination of hardware and computer software implementing the various illustrative elements and algorithm steps described in connection with the embodiments provided herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiment of the present application, the terminal device may be divided into the functional units according to the above method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.
Referring to fig. 4a, fig. 4a is a block diagram of functional units of a test paper generating apparatus according to an embodiment of the present application, where the apparatus 400 includes: a first obtaining unit 410, a searching unit 420, a second obtaining unit 430, a first adjusting unit 440 and a second adjusting unit 450, wherein,
the first obtaining unit 410 is configured to obtain group volume information;
the searching unit 420 is configured to search a candidate volume matching the group volume information from a parent volume library;
the second obtaining unit 430 is configured to obtain a bidirectional breakdown list of the candidate paper, where the bidirectional breakdown list includes a plurality of bidirectional breakdown lists, and the bidirectional breakdown list entry includes attribute information of a certain test question in the candidate paper;
the first adjusting unit 440 is configured to adjust the bidirectional breakdown list according to the group volume information;
the second adjusting unit 450 is configured to adjust the test questions in the candidate paper according to the adjusted bidirectional breakdown list to obtain a target paper.
Optionally, as shown in fig. 4b, the functional units of another test paper generating apparatus 400 provided in the embodiment of the present application form a block diagram, where the apparatus 400 further includes a processing unit 460, where,
the processing unit 460 is configured to: constructing the master paper library, wherein the master paper library comprises a plurality of examination papers, and each examination paper comprises a plurality of examination questions; and sequencing the examination schools of each examination paper according to historical examination data, and establishing a mapping relation for the horizontal capacity of any two examination schools.
Optionally, the search unit 420 is specifically configured to: calculating the matching degree of the attribute information of each test paper in the master paper library and the paper group information; and determining the examination paper corresponding to the maximum matching degree as the candidate paper.
Optionally, the group volume information includes: target examination type, target examination paper difficulty, target question type quantity and target knowledge point;
in calculating the matching degree between the attribute information of each test paper in the master paper library and the paper group information, the searching unit 420 is specifically configured to: calculating the type consistency of the attribute information of each test paper and the test paper information, wherein the type consistency comprises the consistency of the target examination type quantity and the examination type quantity of the test paper and the consistency of the target examination type and the examination type of the examination paper; calculating the target similarity of the attribute information of each test paper and the group paper information, wherein the target similarity comprises the similarity of the target test paper difficulty and the test paper difficulty of the test paper and the similarity of the target knowledge point and the test paper knowledge point of the test paper; determining the test paper priority of each test paper; and calculating the matching degree of each test paper according to the type consistency, the target similarity and the test paper priority of each test paper.
Optionally, the examination paper information further includes a target examination school; in terms of calculating the test paper difficulty of the test paper, the search unit 420 is specifically configured to: acquiring the average score of each test school corresponding to the test paper; determining the horizontal capability of each test school according to the mapping relationship between the horizontal capability of each test school and the horizontal capability of the target test school; and calculating the test paper difficulty of the test paper according to the horizontal capacity of each test school and the average score of each test school.
Optionally, the processing unit 460 is further configured to: constructing a topological sequence of the knowledge points according to the learning sequence of the knowledge points; and counting the examination question knowledge points in each examination paper according to the historical examination data to obtain at least one of high-frequency examination points, key points and difficulties in the knowledge points.
Optionally, the first adjusting unit 440 is specifically configured to: traversing the bidirectional item entries, comparing the test question knowledge points in the bidirectional item entries with the target knowledge point, if the test question knowledge points of the first bidirectional item entries are behind the topological sequence of the target knowledge point, adjusting the first bidirectional item entries into second bidirectional item entries, wherein the second bidirectional item entries are bidirectional item entries with the test question knowledge points as second test question knowledge points, and the second test question knowledge points are any one of test question knowledge points, the high-frequency test points, the key points and the difficulties which are not included in the bidirectional item table.
Optionally, the processing unit 460 is further configured to: if the quantity of the first test question type in the plurality of bidirectional item items is more than that of the first test question type in the target quantity of the test questions, deleting a third bidirectional item, wherein the third bidirectional item is a third test question knowledge point with the test question type being the first test question type or a first test question difficulty, the third test question knowledge point is a test question knowledge point behind the topological order of the target knowledge point, and the first test question difficulty is a test question difficulty which is greater than the upper limit of a preset test question difficulty range or smaller than the lower line of the preset test question difficulty range; and if the quantity of the first test question type in the bidirectional item items is less than that of the first test question type in the target question type quantity, increasing the second bidirectional item items.
Optionally, the second adjusting unit 450 is specifically configured to: selecting at least one candidate test question from the master paper library according to the second bidirectional item; calculating the test question matching degree of each candidate test question in the at least one candidate test question; and replacing the candidate test question with the maximum test question matching degree in the at least one candidate test question with the test question corresponding to the second bidirectional item to obtain the target paper.
Optionally, in terms of calculating the test question matching degree of each candidate test question in the at least one candidate test question, the second adjusting unit 450 is specifically configured to: and calculating the test question matching degree of each candidate test question according to the test question knowledge point similarity, the test question number similarity, the test question difficulty similarity, the test question standard score similarity and the test question scene similarity of each candidate test question.
It can be seen that the test paper generation apparatus provided in the embodiment of the present application obtains the group paper information through the first obtaining unit; the searching unit searches the candidate volume matched with the volume group information from the master volume library; a second obtaining unit obtains a bidirectional item list of the candidate paper, wherein the bidirectional item list comprises a plurality of bidirectional item entries, and the bidirectional item entries comprise attribute information of a certain test question in the candidate paper; the first adjusting unit adjusts the bidirectional detailed list according to the group volume information; and the second adjusting unit adjusts the test questions in the candidate paper according to the adjusted bidirectional fine list to obtain the target paper. When a user needs to generate a test paper, the matched candidate paper can be automatically searched only by setting the group paper information, and the test paper is generated after the test questions in the candidate paper are adjusted according to the group paper information, so that the test paper generation efficiency is improved, and the problems of low quality of the constructed product and inaccurate positioning caused by manual test paper construction are solved.
Referring to fig. 5, fig. 5 is a terminal device according to an embodiment of the present application, where the terminal device includes: a processor, a memory, a transceiver, and one or more programs. The processor, memory and transceiver are interconnected by a communication bus.
The memory includes, but is not limited to, Random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or portable read-only memory (CD-ROM), which is used for storing computer programs and data. The communication interface is used for receiving and transmitting data.
The processor may be one or more Central Processing Units (CPUs), and in the case of one CPU, the CPU may be a single-core CPU or a multi-core CPU.
The one or more programs are stored in the memory and configured to be executed by the processor; the program includes instructions for performing the steps of:
acquiring volume group information;
searching a candidate volume matched with the volume group information from a parent volume library;
acquiring a bidirectional item list of the candidate paper, wherein the bidirectional item list comprises a plurality of bidirectional item items, and the bidirectional item items comprise attribute information of a certain test question in the candidate paper;
adjusting the bidirectional detailed list according to the group volume information;
and adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper.
It should be noted that, for a specific implementation process in the embodiment of the present application, reference may be made to the specific implementation process described in the foregoing method embodiment, and details are not described herein again.
Embodiments of the present application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the methods as described in the above method embodiments.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods as described in the above method embodiments. The computer program product may be a software installation package.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash disk, ROM, RAM, magnetic or optical disk, and the like.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (13)

1. A test paper generation method, characterized in that the method comprises:
acquiring volume group information;
searching a candidate volume matched with the volume group information from a parent volume library;
acquiring a bidirectional item list of the candidate paper, wherein the bidirectional item list comprises a plurality of bidirectional item items, and the bidirectional item items comprise attribute information of a certain test question in the candidate paper;
adjusting the bidirectional detailed list according to the group volume information;
and adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper.
2. The method of claim 1, further comprising:
constructing the master paper library, wherein the master paper library comprises a plurality of examination papers, and each examination paper comprises a plurality of examination questions;
and sequencing the examination schools of each examination paper according to historical examination data, and establishing a mapping relation for the horizontal capacity of any two examination schools.
3. The method according to claim 2, wherein the searching for the candidate volume matching the group volume information from the parent volume library according to the group volume information comprises:
calculating the matching degree of the attribute information of each test paper in the master paper library and the paper group information;
and determining the examination paper corresponding to the maximum matching degree as the candidate paper.
4. The method of claim 3, wherein the group volume information comprises: target examination type, target examination paper difficulty, target question type quantity and target knowledge point;
the calculating the matching degree of the attribute information of each test paper in the master paper library and the paper group information comprises the following steps:
calculating the type consistency of the attribute information of each test paper and the test paper information, wherein the type consistency comprises the consistency of the target examination type quantity and the examination type quantity of the test paper and the consistency of the target examination type and the examination type of the examination paper;
calculating the target similarity of the attribute information of each test paper and the group paper information, wherein the target similarity comprises the similarity of the target test paper difficulty and the test paper difficulty of the test paper and the similarity of the target knowledge point and the test paper knowledge point of the test paper;
determining the test paper priority of each test paper;
and calculating the matching degree of each test paper according to the type consistency, the target similarity and the test paper priority of each test paper.
5. The method of claim 4, wherein the group information further includes a target test school;
calculating the test paper difficulty of the test paper, and specifically comprises the following steps:
acquiring the average score of each test school corresponding to the test paper;
determining the horizontal capability of each test school according to the mapping relationship between the horizontal capability of each test school and the horizontal capability of the target test school;
and calculating the test paper difficulty of the test paper according to the horizontal capacity of each test school and the average score of each test school.
6. The method according to any one of claims 2-5, further comprising:
constructing a topological sequence of the knowledge points according to the learning sequence of the knowledge points;
and counting the examination question knowledge points in each examination paper according to the historical examination data to obtain at least one of high-frequency examination points, key points and difficulties in the knowledge points.
7. The method of claim 6, wherein said adjusting the bidirectional breadcrumbs table based on the group volume information comprises:
traversing the bidirectional item entries, comparing the test question knowledge points in the bidirectional item entries with the target knowledge point, if the test question knowledge points of the first bidirectional item entries are behind the topological sequence of the target knowledge point, adjusting the first bidirectional item entries into second bidirectional item entries, wherein the second bidirectional item entries are bidirectional item entries with the test question knowledge points as second test question knowledge points, and the second test question knowledge points are any one of test question knowledge points, the high-frequency test points, the key points and the difficulties which are not included in the bidirectional item table.
8. The method of claim 7, further comprising:
if the quantity of the first test question type in the plurality of bidirectional item items is more than that of the first test question type in the target quantity of the test questions, deleting a third bidirectional item, wherein the third bidirectional item is a third test question knowledge point with the test question type being the first test question type or a first test question difficulty, the third test question knowledge point is a test question knowledge point behind the topological order of the target knowledge point, and the first test question difficulty is a test question difficulty which is greater than the upper limit of a preset test question difficulty range or smaller than the lower line of the preset test question difficulty range;
and if the quantity of the first test question type in the bidirectional item items is less than that of the first test question type in the target question type quantity, increasing the second bidirectional item items.
9. The method according to claim 7 or 8, wherein the adjusting the test questions in the candidate paper according to the adjusted bidirectional breakdown list to obtain a target paper comprises:
selecting at least one candidate test question from the master paper library according to the second bidirectional item;
calculating the test question matching degree of each candidate test question in the at least one candidate test question;
and replacing the candidate test question with the maximum test question matching degree in the at least one candidate test question with the test question corresponding to the second bidirectional item to obtain the target paper.
10. The method according to claim 9, wherein said calculating the question matching degree of each of the at least one candidate question comprises:
and calculating the test question matching degree of each candidate test question according to the test question knowledge point similarity, the test question number similarity, the test question difficulty similarity, the test question standard score similarity and the test question scene similarity of each candidate test question.
11. A test paper generation apparatus, characterized in that the apparatus comprises:
a first acquisition unit configured to acquire group volume information;
the searching unit is used for searching the candidate volume matched with the volume group information from the parent volume library;
a second obtaining unit, configured to obtain a bidirectional breakdown list of the candidate paper, where the bidirectional breakdown list includes multiple bidirectional breakdown lists, and the bidirectional breakdown list entry includes attribute information of a certain test question in the candidate paper;
a first adjusting unit, configured to adjust the bidirectional breakdown list according to the group volume information;
and the second adjusting unit is used for adjusting the test questions in the candidate paper according to the adjusted bidirectional detailed list to obtain the target paper.
12. An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-10.
13. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-10.
CN202011606340.0A 2020-12-28 2020-12-28 Test paper generation method and device Active CN112699283B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011606340.0A CN112699283B (en) 2020-12-28 2020-12-28 Test paper generation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011606340.0A CN112699283B (en) 2020-12-28 2020-12-28 Test paper generation method and device

Publications (2)

Publication Number Publication Date
CN112699283A true CN112699283A (en) 2021-04-23
CN112699283B CN112699283B (en) 2023-12-01

Family

ID=75512396

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011606340.0A Active CN112699283B (en) 2020-12-28 2020-12-28 Test paper generation method and device

Country Status (1)

Country Link
CN (1) CN112699283B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113538188A (en) * 2021-07-27 2021-10-22 北京世纪好未来教育科技有限公司 Test paper generation method and device, electronic equipment and computer readable storage medium
CN113656536A (en) * 2021-10-19 2021-11-16 深圳市菁优智慧教育股份有限公司 Method and system for automatically and parallelly grouping rolls based on machine learning
CN116431691A (en) * 2023-04-13 2023-07-14 陇东学院 Method for acquiring test paper questions, readable storage medium and computer device
CN116542829A (en) * 2023-07-03 2023-08-04 江西师范大学 Personalized intelligent group scroll and on-line examination method
CN117151070A (en) * 2023-10-31 2023-12-01 联城科技(河北)股份有限公司 Test paper question-setting method, device, equipment and computer readable storage medium
CN117216081A (en) * 2023-11-08 2023-12-12 联城科技(河北)股份有限公司 Automatic question bank updating method and device, electronic equipment and storage medium

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060125234A (en) * 2005-06-02 2006-12-06 헌 김 Method and apparatus for creating exam sheets to prevent cheating on the exam
CN101866561A (en) * 2010-06-11 2010-10-20 哈尔滨工程大学 Device and method for intellectually composing test paper by adjustable multi-variable asymptotic optimizing algorithm
KR101493490B1 (en) * 2014-05-08 2015-02-24 학교법인 한양학원 Method for setting examination sheets and apparatus using the method
CN106781865A (en) * 2016-12-27 2017-05-31 华南师范大学 A kind of intelligent Auto-generating Test Paper method and system based on two-way detail table pattern-recognition
CN106777223A (en) * 2016-12-26 2017-05-31 广州迅云教育科技有限公司 A kind of micro- class resource base construction method of association's type and system
JP2019016355A (en) * 2017-07-10 2019-01-31 勝俣　和彦 Test question supply and test result determination system and test management system
CN110413973A (en) * 2019-07-26 2019-11-05 浙江蓝鸽科技有限公司 Computer automatically generates the method and its system of set volume
CN111339740A (en) * 2020-02-14 2020-06-26 腾讯云计算（北京）有限责任公司 Test paper generation method and device, electronic equipment and readable storage medium
CN111737450A (en) * 2020-08-05 2020-10-02 江西风向标教育科技有限公司 Test paper grouping method and device, storage medium and computer equipment
CN112131407A (en) * 2020-09-29 2020-12-25 四川宇德中创信息科技有限公司 Intelligent paper making system and method based on knowledge graph

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060125234A (en) * 2005-06-02 2006-12-06 헌 김 Method and apparatus for creating exam sheets to prevent cheating on the exam
CN101866561A (en) * 2010-06-11 2010-10-20 哈尔滨工程大学 Device and method for intellectually composing test paper by adjustable multi-variable asymptotic optimizing algorithm
KR101493490B1 (en) * 2014-05-08 2015-02-24 학교법인 한양학원 Method for setting examination sheets and apparatus using the method
CN106777223A (en) * 2016-12-26 2017-05-31 广州迅云教育科技有限公司 A kind of micro- class resource base construction method of association's type and system
CN106781865A (en) * 2016-12-27 2017-05-31 华南师范大学 A kind of intelligent Auto-generating Test Paper method and system based on two-way detail table pattern-recognition
JP2019016355A (en) * 2017-07-10 2019-01-31 勝俣　和彦 Test question supply and test result determination system and test management system
CN110413973A (en) * 2019-07-26 2019-11-05 浙江蓝鸽科技有限公司 Computer automatically generates the method and its system of set volume
CN111339740A (en) * 2020-02-14 2020-06-26 腾讯云计算（北京）有限责任公司 Test paper generation method and device, electronic equipment and readable storage medium
CN111737450A (en) * 2020-08-05 2020-10-02 江西风向标教育科技有限公司 Test paper grouping method and device, storage medium and computer equipment
CN112131407A (en) * 2020-09-29 2020-12-25 四川宇德中创信息科技有限公司 Intelligent paper making system and method based on knowledge graph

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
WANG HAIRUI; WANG HUA: "Research and Implementation of Multi-agent Based Test Paper Generation Algorithm", IEEE, pages 493 - 496 *
黄超叶;卢光云;覃仲欣;: "智能组卷试题库系统的设计与开发探讨", 信息通信, no. 09, pages 76 - 78 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113538188A (en) * 2021-07-27 2021-10-22 北京世纪好未来教育科技有限公司 Test paper generation method and device, electronic equipment and computer readable storage medium
CN113538188B (en) * 2021-07-27 2024-03-01 北京世纪好未来教育科技有限公司 Test paper generation method and device, electronic equipment and computer readable storage medium
CN113656536A (en) * 2021-10-19 2021-11-16 深圳市菁优智慧教育股份有限公司 Method and system for automatically and parallelly grouping rolls based on machine learning
CN113656536B (en) * 2021-10-19 2022-02-08 深圳市菁优智慧教育股份有限公司 Method and system for automatically and parallelly grouping rolls based on machine learning
CN116431691A (en) * 2023-04-13 2023-07-14 陇东学院 Method for acquiring test paper questions, readable storage medium and computer device
CN116542829A (en) * 2023-07-03 2023-08-04 江西师范大学 Personalized intelligent group scroll and on-line examination method
CN117151070A (en) * 2023-10-31 2023-12-01 联城科技(河北)股份有限公司 Test paper question-setting method, device, equipment and computer readable storage medium
CN117151070B (en) * 2023-10-31 2024-01-23 联城科技(河北)股份有限公司 Test paper question-setting method, device, equipment and computer readable storage medium
CN117216081A (en) * 2023-11-08 2023-12-12 联城科技(河北)股份有限公司 Automatic question bank updating method and device, electronic equipment and storage medium
CN117216081B (en) * 2023-11-08 2024-02-06 联城科技(河北)股份有限公司 Automatic question bank updating method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN112699283B (en) 2023-12-01

Similar Documents

Publication Publication Date Title
CN112699283B (en) Test paper generation method and device
CN107230174B (en) Online interactive learning system and method based on network
CN111753098A (en) Teaching method and system based on cross-media dynamic knowledge graph
CN111274411A (en) Course recommendation method and device, electronic equipment and readable storage medium
CN111179675B (en) Personalized exercise recommendation method and system, computer device and storage medium
CN111651676B (en) Method, device, equipment and medium for performing occupation recommendation based on capability model
CN112784608B (en) Test question recommending method and device, electronic equipment and storage medium
CN109754349B (en) Intelligent teacher-student matching system for online education
CN111310463B (en) Test question difficulty estimation method and device, electronic equipment and storage medium
CN116263782A (en) Intelligent winding method, system and storage medium based on question bank
CN114254208A (en) Identification method of weak knowledge points and planning method and device of learning path
CN114913729B (en) Question selecting method, device, computer equipment and storage medium
CN111079018A (en) Exercise personalized recommendation method, exercise personalized recommendation device, exercise personalized recommendation equipment and computer readable storage medium
CN115577185A (en) Muting course recommendation method and device based on mixed reasoning and mesopic group decision
CN113836894B (en) Multi-dimensional English composition scoring method and device and readable storage medium
CN116862166A (en) Post matching method, device, equipment and computer storage medium
CN114416929A (en) Sample generation method, device, equipment and storage medium of entity recall model
Luchoomun et al. A knowledge based system for automated assessment of short structured questions
CN111930908A (en) Answer recognition method and device based on artificial intelligence, medium and electronic equipment
CN109800880B (en) Self-adaptive learning feature extraction system based on dynamic learning style information and application
CN111639485A (en) Course recommendation method based on text similarity and related equipment
CN112598202B (en) Test question difficulty evaluation method and device, storage medium and computing equipment
CN114818678A (en) Scientific and technological achievement management method and platform and electronic equipment
CN113919983A (en) Test question portrait method, device, electronic equipment and storage medium
CN110069783B (en) Answer content evaluation method and device

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
GR01 Patent grant
GR01 Patent grant