[go: up one dir, main page]

CN112035654B - Automatic derivation generation method for questions - Google Patents

Automatic derivation generation method for questions Download PDF

Info

Publication number
CN112035654B
CN112035654B CN202010905871.3A CN202010905871A CN112035654B CN 112035654 B CN112035654 B CN 112035654B CN 202010905871 A CN202010905871 A CN 202010905871A CN 112035654 B CN112035654 B CN 112035654B
Authority
CN
China
Prior art keywords
examined
student
knowledge points
information
target sub
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.)
Active
Application number
CN202010905871.3A
Other languages
Chinese (zh)
Other versions
CN112035654A (en
Inventor
王鑫
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.)
Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd
Original Assignee
Shanghai Squirrel Classroom Artificial Intelligence Technology 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 Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd filed Critical Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd
Priority to CN202010905871.3A priority Critical patent/CN112035654B/en
Publication of CN112035654A publication Critical patent/CN112035654A/en
Application granted granted Critical
Publication of CN112035654B publication Critical patent/CN112035654B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/335—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/34—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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—Information and communication technology [ICT] specially adapted for implementation of business processes of 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
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Strategic Management (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses an automatic deriving and generating method of questions, which comprises the steps of S10, obtaining student information and obtaining knowledge points to be examined corresponding to the student information, S20, determining questions matched with the student information and the knowledge points to be examined according to the student information and the knowledge points to be examined, and S30, generating the questions which correspond to the knowledge points to be examined and are consistent with the questions according to the questions and the knowledge points to be examined. According to the technical scheme, the problem can be automatically generated according to the knowledge points to be examined of the students, the repetition probability of the generated problem and the existing problem is low, the problem generation efficiency is improved, and the examination effect of the problem on the students is improved.

Description

Automatic derivation generation method for questions
Technical Field
The invention relates to the technical field of data processing, in particular to an automatic title derivative generation method.
Background
With the development and popularization of computer technology and the internet, the work, study and life style of people are changed greatly, for example, people acquire knowledge by increasingly using computers, the computers provide more and more convenient services for people, and in the education field, the computer technology provides convenience for teachers and students.
At present, aiming at practice problems or test problems contacted by teachers or students at ordinary times, the problems are basically searched from a test problem library according to the teaching requirements of the subject by the teachers, are easy to repeat with the existing problems, have high problem repetition rate and are not beneficial to the examination of the students.
Disclosure of Invention
The invention provides an automatic title derivation generation method.
The invention provides a method for automatically deriving and generating topics, which comprises the following steps of S10-S30:
Step S10, student information is obtained, and knowledge points to be examined corresponding to the student information are obtained;
Step S20, determining a question type matched with the student information and the knowledge point to be examined according to the student information and the knowledge point to be examined;
And step S30, generating a question corresponding to the knowledge point to be examined and consistent with the question according to the question type and the knowledge point to be examined.
Preferably, the step S10 of obtaining student information and obtaining knowledge points to be examined corresponding to the student information includes:
The method comprises the steps of obtaining student information, wherein the student information comprises student characteristic information, student grade information, student capability information and historical test information, and the student characteristic information comprises any one or more of student number, student name, student class and student age;
Obtaining subject information matched with the student grade information according to the student grade information;
extracting all subject knowledge points matched with the student information in the subject information according to the subject information;
acquiring mastered knowledge points corresponding to the student information according to the student capability information and the history test information;
And comparing the mastered knowledge points with the corresponding knowledge points of all subjects to obtain the non-mastered knowledge points corresponding to the student information, and taking the non-mastered knowledge points as the knowledge points to be examined corresponding to the student information.
Preferably, the determining, according to the student information and the knowledge point to be examined, a question type matched with the student information and the knowledge point to be examined includes:
acquiring a difficulty coefficient corresponding to the knowledge point to be examined;
acquiring a difficulty coefficient range of a question acceptable by a student corresponding to student information according to the student capability information;
judging whether the difficulty coefficient corresponding to the knowledge point to be examined exceeds the difficulty coefficient range;
if the difficulty coefficient range is not exceeded, determining a first question type as the question type matched with the student information and the knowledge point to be examined, wherein the first question type comprises any question type of a question and a gap-filling question;
If the difficulty coefficient range is exceeded, determining a second question type as the question type matched with the student information and the knowledge point to be examined, wherein the second question type comprises any one of a judgment question and a selection question.
Preferably, the method further comprises:
pushing the generated questions to student terminals corresponding to the student information, so that students can perform corresponding tests based on the generated questions;
and acquiring a test result obtained by testing the students corresponding to the student information based on the generated questions and feedback information of the students.
Preferably, the method further comprises:
Searching a system question bank according to the generated questions, and identifying whether the system question bank has the same existing questions as the questions;
if the existing topics which are the same as the topics do not exist, the topics are saved to the system topics;
if there is an existing topic identical to the topic, step S30 is re-executed to generate a new topic.
Preferably, when there are a plurality of knowledge points to be examined, generating a question corresponding to the knowledge point to be examined and consistent with the question according to the question type and the knowledge point to be examined, including steps A1-A6:
a1, acquiring a text from a preset text library, and splitting the text to obtain a text abstract and text main body content corresponding to the text;
Step A2, judging whether the text abstract comprises at least M1 knowledge points to be examined, if yes, continuing the step A3, otherwise, returning to the step A1, wherein M1 is a positive integer equal to or greater than 1;
Step A3, segmenting the text main body content to obtain a plurality of sub-contents, removing the sub-contents which do not comprise any knowledge point to be examined from the plurality of sub-contents, and leaving a plurality of first target sub-contents, wherein each first target sub-content comprises at least one knowledge point to be examined;
Step A4, calculating the weight ratio of the knowledge points to be examined in the text main body content, which are included in each first target sub-content;
Step A5, screening the plurality of first target sub-contents according to the weight ratio to obtain a left second target sub-content;
And A6, generating a question which contains the knowledge points to be examined and is consistent with the question type according to the second target sub-content.
Preferably, the step A4 of calculating a weight ratio of the knowledge point to be examined included in each first target sub-content in the text body content includes:
Calculating the degree of association between the plurality of first target sub-contents according to the following formula (1):
In the formula (1), g i represents the ratio of the knowledge points to be mastered included in the i-th first target sub-content to all the knowledge points to be mastered, g i+1 represents the ratio of the knowledge points to be mastered included in the i+1th first target sub-content to all the knowledge points to be mastered, g i-1 represents the ratio of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered, d i represents the ratio of the storage space occupied by the i-th first target sub-content to the storage space occupied by the text main content, d i+1 represents the ratio of the storage space occupied by the i+1th first target sub-content to the storage space occupied by the text main content, d i-1 represents the ratio of the storage space occupied by the i-1th first target sub-content to the storage space occupied by the text main content, and n represents the total number of the first target sub-content;
Using formula (2), calculating the space ratio s 1k of all the first target sub-contents including the kth point of knowledge to be examined in the text body contents, wherein the space ratio s 1k is as follows:
Wherein m represents the total number of paragraphs of the text main body content, H kj represents the number of lines occupied by the first target sub-content including the kth knowledge point to be examined in the jth segment, H j represents the total number of lines included in the jth segment, delta 1k represents the space duty correction value corresponding to s 1k, and the space duty correction value is a preset value, and the value range is [0.01,0.05];
calculating the frequency of occurrence ratio s 2k of all the first target sub-contents including the kth knowledge point to be examined in the text body content by using the formula (3), wherein the method comprises the following steps:
Wherein P kj represents the occurrence number of the kth knowledge point to be examined in the jth segment, G kj represents the total occurrence number of each knowledge point to be examined in the jth segment, delta 2k represents the corresponding occurrence frequency duty ratio correction value of s 2k, which is a preset value and has a value range of [0.01,0.02];
According to the F, the s 1k, the s 2k and the following formula (4), calculating a weight ratio w k of the kth knowledge point to be examined in the text body content, wherein the weight ratio comprises:
In the formula (4), a represents a constant related to s 1k, which is 0.7, and b represents a constant related to s 2k, which is 0.3.
Preferably, the step A5 of screening the plurality of first target sub-contents according to the weight ratio to obtain a remaining second target sub-content includes:
Determining a target knowledge point to be inspected, wherein the corresponding weight duty ratio of the target knowledge point is equal to or larger than a preset weight duty ratio threshold value;
acquiring each first target sub-content comprising the target knowledge point to be inspected, and taking each first target sub-content comprising the target knowledge point to be inspected as the second target sub-content;
And step A6, generating a question which contains the knowledge points to be inspected and is consistent with the question type according to the second target sub-content, wherein the step A6 comprises the following steps:
and according to the current second target sub-content and the extracted target knowledge points to be inspected, generating a question corresponding to the extracted target knowledge points to be inspected and consistent with the question type.
The automatic deriving and generating method of the questions can intelligently and automatically generate the questions according to the knowledge points to be examined of the students, avoids the repetition of the questions with the existing test questions, has low question repetition rate, can improve the examination effect of the students, has high question generation speed, improves the efficiency and accuracy of the question generation, and improves the intelligence and objectivity of the question generation.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical scheme of the invention is further described below through the attached drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic workflow diagram of one embodiment of the subject auto-derivatization method of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention provides an automatic deriving generation method of questions, which aims to automatically derive corresponding questions according to related knowledge points to replace the traditional question-setting mode of manual question setting.
FIG. 1 is a schematic workflow diagram of one embodiment of the subject automatic derivative generation method of the present invention, which can be implemented as steps S10-S30 described below:
And S10, acquiring student information and acquiring knowledge points to be examined corresponding to the student information.
And step S20, determining the question type matched with the student information and the knowledge point to be examined according to the student information and the knowledge point to be examined.
And step S30, generating a question corresponding to the knowledge point to be examined and consistent with the question according to the question type and the knowledge point to be examined.
In one embodiment, the step S10 of obtaining student information and obtaining knowledge points to be examined corresponding to the student information may be specifically implemented as:
The method comprises the steps of obtaining student information, wherein the student information comprises student characteristic information, student grade information, student capability information and historical test information, and the student characteristic information comprises any one or more of student number, student name, student class and student age;
Obtaining subject information matched with the student grade information according to the student grade information;
extracting all subject knowledge points matched with the student information in the subject information according to the subject information;
acquiring mastered knowledge points corresponding to the student information according to the student capability information and the history test information;
And comparing the mastered knowledge points with the corresponding knowledge points of all subjects to obtain the non-mastered knowledge points corresponding to the student information, and taking the non-mastered knowledge points as the knowledge points to be examined corresponding to the student information.
In one embodiment, the determining the question type matching with the student information and the knowledge point to be examined according to the student information and the knowledge point to be examined may be implemented as follows:
acquiring a difficulty coefficient corresponding to the knowledge point to be examined;
acquiring a difficulty coefficient range of a question acceptable by a student corresponding to student information according to the student capability information;
judging whether the difficulty coefficient corresponding to the knowledge point to be examined exceeds the difficulty coefficient range;
if the difficulty coefficient range is not exceeded, determining a first question type as the question type matched with the student information and the knowledge point to be examined, wherein the first question type comprises any question type of a question and a gap-filling question;
If the difficulty coefficient range is exceeded, determining a second question type as the question type matched with the student information and the knowledge point to be examined, wherein the second question type comprises any one of a judgment question and a selection question.
In one embodiment, the method may further comprise the steps of:
Pushing the questions generated in the step S30 to student terminals corresponding to the student information, so that students can perform corresponding tests based on the generated questions;
and acquiring a test result obtained by testing the students corresponding to the student information based on the generated questions and feedback information of the students.
In one embodiment, the method may further comprise the steps of:
Searching a system question bank according to the generated questions, and identifying whether the system question bank has the same existing questions as the questions;
if the existing topics which are the same as the topics do not exist, the topics are saved to the system topics;
if there is an existing topic identical to the topic, step S30 is re-executed to generate a new topic.
The technical scheme can conveniently and rapidly expand the topics in the system topics, and improves the topic expansion speed of the system topic database.
In one embodiment, when there are multiple knowledge points to be examined (for example, when the knowledge points to be examined are multiple english knowledge points, the english knowledge points may be vocabulary, idioms, grammar, fixed sentence patterns or structures, etc.), the generating, according to the question type and the knowledge points to be examined, a question corresponding to the knowledge points to be examined and consistent with the question type may include steps A1-A6:
A1, acquiring a text (such as English novels) from a preset text library, and splitting the text to obtain a text abstract and text main body content corresponding to the text;
Step A2, judging whether the text abstract comprises at least M1 knowledge points to be examined, if yes, continuing the step A3, otherwise, returning to the step A1, wherein M1 is a positive integer equal to or greater than 1;
Step A3, segmenting the text main body content to obtain a plurality of sub-contents, removing the sub-contents which do not comprise any knowledge point to be examined from the plurality of sub-contents, and leaving a plurality of first target sub-contents, wherein each first target sub-content comprises at least one knowledge point to be examined;
Step A4, calculating the weight ratio of the knowledge points to be examined in the text main body content, which are included in each first target sub-content;
Step A5, screening the plurality of first target sub-contents according to the weight ratio to obtain a left second target sub-content;
And A6, generating a question which contains the knowledge points to be examined and is consistent with the question type according to the second target sub-content.
In one embodiment, the step A4 of calculating the weight ratio of the knowledge point to be examined included in each first target sub-content in the text body content includes:
Calculating the degree of association between the plurality of first target sub-contents according to the following formula (1):
In the formula (1), g i represents the ratio of the knowledge points to be mastered included in the i-th first target sub-content to all the knowledge points to be mastered, g i+1 represents the ratio of the knowledge points to be mastered included in the i+1th first target sub-content to all the knowledge points to be mastered, g i-1 represents the ratio of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered, d i represents the ratio of the storage space occupied by the i-th first target sub-content to the storage space occupied by the text main content, d i+1 represents the ratio of the storage space occupied by the i+1th first target sub-content to the storage space occupied by the text main content, d i-1 represents the ratio of the storage space occupied by the i-1th first target sub-content to the storage space occupied by the text main content, and n represents the total number of the first target sub-content;
Using formula (2), calculating the space ratio s 1k of all the first target sub-contents including the kth point of knowledge to be examined in the text body contents, wherein the space ratio s 1k is as follows:
Wherein m represents the total number of paragraphs of the text main body content, H kj represents the number of lines occupied by the first target sub-content including the kth knowledge point to be examined in the jth segment, H j represents the total number of lines included in the jth segment, delta 1k represents the space duty correction value corresponding to s 1k, and the space duty correction value is a preset value, and the value range is [0.01,0.05];
calculating the frequency of occurrence ratio s 2k of all the first target sub-contents including the kth knowledge point to be examined in the text body content by using the formula (3), wherein the method comprises the following steps:
Wherein P kj represents the occurrence number of the kth knowledge point to be examined in the jth segment, G kj represents the total occurrence number of each knowledge point to be examined in the jth segment, delta 2k represents the corresponding occurrence frequency duty ratio correction value of s 2k, which is a preset value and has a value range of [0.01,0.02];
According to the F, the s 1k, the s 2k and the following formula (4), calculating a weight ratio w k of the kth knowledge point to be examined in the text body content, wherein the weight ratio comprises:
In the formula (4), a represents a constant related to s 1k, which is 0.7, and b represents a constant related to s 2k, which is 0.3.
In one embodiment, the step A5 of screening the plurality of first target sub-contents according to the weight ratio to obtain a remaining second target sub-content includes:
Determining a target knowledge point to be inspected, wherein the corresponding weight duty ratio of the target knowledge point is equal to or larger than a preset weight duty ratio threshold value;
acquiring each first target sub-content comprising the target knowledge point to be inspected, and taking each first target sub-content comprising the target knowledge point to be inspected as the second target sub-content;
And step A6, generating a question which contains the knowledge points to be inspected and is consistent with the question type according to the second target sub-content, wherein the step A6 comprises the following steps:
and according to the current second target sub-content and the extracted target knowledge points to be inspected, generating a question corresponding to the extracted target knowledge points to be inspected and consistent with the question type.
For example, when the question type is a selected question and the current second target sub-content is an English paragraph, the English paragraph includes three sentences, one English paragraph includes two knowledge points to be examined, one English sentence is an English vocabulary, and the other English paragraph is a fixed sentence structure, then the question corresponding to the extracted target knowledge point to be examined can be generated according to the current second target sub-content and the extracted target knowledge point to be examined, and the question corresponding to the question type can be implemented by eliminating the target knowledge point to be examined in the current second target sub-content and replacing the target knowledge point with brackets, and providing a plurality of corresponding selectable filling items for each bracket, thereby generating the question.
The automatic deriving and generating method of the questions can intelligently and automatically generate the questions according to the knowledge points to be examined of the students, avoids the repetition of the questions with the existing test questions, has low question repetition rate, can improve the examination effect of the students, has high question generation speed, improves the efficiency and accuracy of the question generation, and improves the intelligence and objectivity of the question generation.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (5)

1.一种题目自动衍生生成方法，其特征在于，所述方法包括步骤S10-S30：1. A method for automatically generating a topic, characterized in that the method comprises steps S10-S30: 步骤S10、获取学生信息，并获取所述学生信息所对应的待考察知识点；Step S10: obtaining student information, and obtaining the knowledge points to be examined corresponding to the student information; 步骤S20、根据所述学生信息和所述待考察知识点，确定与所述学生信息和所述待考察知识点相匹配的题型；Step S20: determining, according to the student information and the knowledge points to be tested, a question type that matches the student information and the knowledge points to be tested; 步骤S30、根据所述题型和所述待考察知识点，生成所述待考察知识点对应的、且与所述题型一致的题目；Step S30, generating questions corresponding to the knowledge points to be tested and consistent with the question type according to the question type and the knowledge points to be tested; 其中，当所述待考察知识点有多个时，所述根据所述题型和所述待考察知识点，生成所述待考察知识点对应的、且与所述题型一致的题目，包括步骤A1-A6：Wherein, when there are multiple knowledge points to be examined, generating questions corresponding to the knowledge points to be examined and consistent with the question type according to the question type and the knowledge points to be examined includes steps A1-A6: 步骤A1、从预设文本库中获取文本，并将所述文本进行拆分，得到所述文本对应的文本摘要和文本主体内容；Step A1: obtaining text from a preset text library, and splitting the text to obtain a text summary and a text body content corresponding to the text; 步骤A2、判断所述文本摘要中是否包括至少M1个待考察知识点，如果是，则继续步骤A3；如果否，则返回步骤A1；M1为等于或大于1的正整数；Step A2: determine whether the text summary includes at least M1 knowledge points to be examined. If yes, proceed to step A3; if no, return to step A1; M1 is a positive integer equal to or greater than 1; 步骤A3、对所述文本主体内容进行分割，获得多个子内容，将所述多个子内容中不包括任何一个待考察知识点的子内容剔除，留下多个第一目标子内容，每个第一目标子内容中均包括至少一个待考察知识点；Step A3, dividing the main body of the text to obtain a plurality of sub-contents, removing the sub-contents that do not include any knowledge point to be examined from the plurality of sub-contents, leaving a plurality of first target sub-contents, each of which includes at least one knowledge point to be examined; 步骤A4、计算每个第一目标子内容所包括的待考察知识点在所述文本主体内容中的权重占比；Step A4, calculating the weight ratio of the knowledge points to be examined included in each first target sub-content in the main body of the text; 步骤A5、根据所述权重占比对所述多个第一目标子内容进行筛选，得到留下的第二目标子内容；Step A5, screening the plurality of first target sub-contents according to the weight proportions to obtain remaining second target sub-contents; 步骤A6、根据第二目标子内容，生成包含待考察知识点的、且与所述题型一致的题目；Step A6: generating, according to the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type; 其中，所述步骤A4、计算每个第一目标子内容所包括的待考察知识点在所述文本主体内容中的权重占比，包括：The step A4 of calculating the weight ratio of the knowledge points to be examined included in each first target sub-content in the main body of the text includes: 根据如下公式(1)计算所述多个第一目标子内容之间的关联度：The association degree between the multiple first target sub-contents is calculated according to the following formula (1): 公式(1)中，gi表示第i个第一目标子内容中包括的待掌握知识点占所有待掌握知识点的占比；gi+1表示第i+1个第一目标子内容中包括的待掌握知识点占所有待掌握知识点的占比；gi-1表示第一目标子内容中包括的待掌握知识点占所有待掌握知识点的占比；di表示第i个第一目标子内容所占据的存储空间与所述文本主体内容所占据的存储空间之间的比值；di+1表示第i+1个第一目标子内容所占据的存储空间与所述文本主体内容所占据的存储空间之间的比值；di-1表示第i-1个第一目标子内容所占据的存储空间与所述文本主体内容所占据的存储空间之间的比值；n为第一目标子内容的总数目；In formula (1), gi represents the ratio of the knowledge points to be mastered included in the ith first target sub-content to all the knowledge points to be mastered; gi +1 represents the ratio of the knowledge points to be mastered included in the i+1th first target sub-content to all the knowledge points to be mastered; gi -1 represents the ratio of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered; di represents the ratio of the storage space occupied by the ith first target sub-content to the storage space occupied by the main body of the text; di +1 represents the ratio of the storage space occupied by the i+1th first target sub-content to the storage space occupied by the main body of the text; di -1 represents the ratio of the storage space occupied by the i-1th first target sub-content to the storage space occupied by the main body of the text; n is the total number of first target sub-contents; 利用公式(2)，计算包括第k个待考察知识点的所有第一目标子内容在所述文本主体内容中的篇幅占比s1k，则有：Using formula (2), the proportion s 1k of the length of all first target sub-contents including the kth knowledge point to be examined in the main body of the text is calculated, and then: 其中，m表示所述文本主体内容的段落总数；Hkj表示第j段中包括第k个待考察知识点的第一目标子内容所占据的行数；hj表示第j段包括的总行数；Δδ1k表示s1k对应的篇幅占比修正值，为预设值，其取值范围为[0.01，0.05]；Wherein, m represents the total number of paragraphs in the main body of the text; H kj represents the number of lines occupied by the first target sub-content including the kth knowledge point to be examined in the jth paragraph; h j represents the total number of lines included in the jth paragraph; Δδ 1k represents the correction value of the length proportion corresponding to s 1k , which is a preset value and its value range is [0.01, 0.05]; 利用公式(3)，计算包括第k个待考察知识点的所有第一目标子内容在所述文本主体内容中的出现频率占比s2k，则有：Using formula (3), the occurrence frequency ratio s 2k of all first target sub-contents including the kth knowledge point to be examined in the main body of the text is calculated, and then: 其中，Pkj表示第j段中第k个待考察知识点的出现次数；Gkj表示第j段中出现的每个待考察知识点的总出现次数；Δδ2k表示s2k对应的出现频率占比修正值，为预设值，其取值范围为[0.01，0.02]；Wherein, P kj represents the number of occurrences of the kth knowledge point to be examined in the jth segment; G kj represents the total number of occurrences of each knowledge point to be examined in the jth segment; Δδ 2k represents the correction value of the occurrence frequency proportion corresponding to s 2k , which is a preset value and its value range is [0.01, 0.02]; 根据所述F、所述s1k、所述s2k和如下公式(4)，计算第k个待考察知识点在所述文本主体内容中的权重占比wk，则有：According to F, s 1k , s 2k and the following formula (4), the weight proportion w k of the kth knowledge point to be examined in the main content of the text is calculated, and then: 公式(4)中，a表示与s1k相关的常数，取值为0.7，b表示与s2k相关的常数，取值为0.3；In formula (4), a represents a constant related to s 1k , with a value of 0.7, and b represents a constant related to s 2k , with a value of 0.3; 其中，所述步骤A5、根据所述权重占比对所述多个第一目标子内容进行筛选，得到留下的第二目标子内容，包括：The step A5 of screening the plurality of first target sub-contents according to the weight proportions to obtain the remaining second target sub-contents includes: 确定对应的权重占比等于或大于预设权重占比阈值的目标待考察知识点；Determine the target knowledge points to be examined whose corresponding weight ratio is equal to or greater than the preset weight ratio threshold; 获取包括所述目标待考察知识点的每个第一目标子内容，将包括所述目标待考察知识点的每个第一目标子内容作为所述第二目标子内容；Acquire each first target sub-content including the target knowledge point to be examined, and use each first target sub-content including the target knowledge point to be examined as the second target sub-content; 步骤A6、根据所述第二目标子内容，生成包含待考察知识点的、且与所述题型一致的题目，包括：Step A6: generating, based on the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type, including: 针对每个第二目标子内容执行如下操作：从当前的第二目标子内容中提取出其所包含的目标待考察知识点；根据当前的第二目标子内容和提取出的所述目标待考察知识点，生成提取出的所述目标待考察知识点对应的、与所述题型一致的题目。The following operations are performed for each second target sub-content: the target knowledge points to be examined contained in the current second target sub-content are extracted; and questions corresponding to the extracted target knowledge points to be examined and consistent with the question type are generated based on the current second target sub-content and the extracted target knowledge points to be examined. 2.如权利要求1所述的题目自动衍生生成方法，其特征在于，所述步骤S10，获取学生信息，并获取所述学生信息所对应的待考察知识点，包括：2. The method for automatically generating questions according to claim 1, wherein the step S10 of obtaining student information and obtaining the knowledge points to be examined corresponding to the student information comprises: 获取学生信息，所述学生信息包括学生特征信息、学生年级信息、学生能力信息和历史测试信息；其中，所述学生特征信息包括学生学号、学生姓名、学生班级、学生年龄中的任一项或多项；Acquire student information, wherein the student information includes student characteristic information, student grade information, student ability information and historical test information; wherein the student characteristic information includes any one or more of the student ID, student name, student class and student age; 根据所述学生年级信息，获取与所述学生年级信息相匹配的学科信息；According to the student grade information, obtaining subject information matching the student grade information; 根据所述学科信息，提取所述学科信息中与所述学生信息相匹配的所有学科知识点；According to the subject information, extract all subject knowledge points in the subject information that match the student information; 根据所述学生能力信息和历史测试信息，获取所述学生信息对应的已掌握知识点；According to the student ability information and historical test information, obtain the mastered knowledge points corresponding to the student information; 将所述已掌握知识点与对应的所述所有学科知识点进行比对，获取所述学生信息对应的未掌握知识点，作为所述学生信息所对应的待考察知识点。The mastered knowledge points are compared with the corresponding knowledge points of all subjects to obtain the unmastered knowledge points corresponding to the student information as the knowledge points to be examined corresponding to the student information. 3.如权利要求2所述的题目自动衍生生成方法，其特征在于，所述根据所述学生信息和所述待考察知识点，确定与所述学生信息和所述待考察知识点相匹配的题型，包括：3. The method for automatically generating questions according to claim 2, wherein determining the question type matching the student information and the knowledge point to be tested based on the student information and the knowledge point to be tested comprises: 获取所述待考察知识点对应的难度系数；Obtaining the difficulty coefficient corresponding to the knowledge point to be examined; 根据所述学生能力信息，获取所述学生信息所对应的学生可接受的题目的难度系数范围；According to the student ability information, obtaining a range of difficulty coefficients of questions that are acceptable to the student corresponding to the student information; 判断所述待考察知识点对应的难度系数是否超出所述难度系数范围；Determine whether the difficulty coefficient corresponding to the knowledge point to be examined exceeds the difficulty coefficient range; 若未超出所述难度系数范围，则确定第一题型为所述与所述学生信息和所述待考察知识点相匹配的题型；所述第一题型包括问答题、填空题中的任一种题型；If the difficulty coefficient does not exceed the range, determining the first question type as the question type that matches the student information and the knowledge point to be tested; the first question type includes any one of a composition question and a fill-in-the-blank question; 若超出所述难度系数范围，则确定第二题型为所述与所述学生信息和所述待考察知识点相匹配的题型，所述第二题型包括判断题、选择题中的任一种题型。If it exceeds the difficulty coefficient range, the second question type is determined to be the question type that matches the student information and the knowledge points to be tested, and the second question type includes any one of true-or-false questions and multiple-choice questions. 4.如权利要求1所述的题目自动衍生生成方法，其特征在于，所述方法还包括：4. The method for automatically generating a topic according to claim 1, further comprising: 将生成的题目推送至学生信息对应的学生终端，供学生基于生成的题目进行相应的测试；Push the generated questions to the student terminal corresponding to the student information, so that the students can take the corresponding test based on the generated questions; 获取所述学生信息对应的学生基于生成的题目进行测试得到的测试结果和所述学生的反馈信息。The test results obtained by taking a test based on the generated questions by the student corresponding to the student information and the feedback information of the student are obtained. 5.如权利要求1所述的题目自动衍生生成方法，其特征在于，所述方法还包括：5. The method for automatically generating a topic according to claim 1, further comprising: 根据生成的所述题目，查找系统题库，识别所述系统题库中是否存在与所述题目相同的已有题目；According to the generated question, searching a system question bank to identify whether there is an existing question identical to the question in the system question bank; 若不存在与所述题目相同的已有题目，则保存所述题目至所述系统题目；If there is no existing question identical to the question, save the question to the system question; 若存在与所述题目相同的已有题目，则重新执行步骤S30以生成新的题目。If there is an existing topic that is the same as the topic, step S30 is re-executed to generate a new topic.
CN202010905871.3A 2020-09-01 2020-09-01 Automatic derivation generation method for questions Active CN112035654B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010905871.3A CN112035654B (en) 2020-09-01 2020-09-01 Automatic derivation generation method for questions

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010905871.3A CN112035654B (en) 2020-09-01 2020-09-01 Automatic derivation generation method for questions

Publications (2)

Publication Number Publication Date
CN112035654A CN112035654A (en) 2020-12-04
CN112035654B true CN112035654B (en) 2025-04-22

Family

ID=73592184

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010905871.3A Active CN112035654B (en) 2020-09-01 2020-09-01 Automatic derivation generation method for questions

Country Status (1)

Country Link
CN (1) CN112035654B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1996030844A1 (en) * 1995-03-28 1996-10-03 Takashi Ogata Support system for automation of story structure preparation
CN111192170A (en) * 2019-12-25 2020-05-22 平安国际智慧城市科技股份有限公司 Topic pushing method, device, equipment and computer readable storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106960025B (en) * 2017-03-19 2019-09-27 北京工业大学 A personalized document recommendation method based on domain knowledge graph

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1996030844A1 (en) * 1995-03-28 1996-10-03 Takashi Ogata Support system for automation of story structure preparation
CN111192170A (en) * 2019-12-25 2020-05-22 平安国际智慧城市科技股份有限公司 Topic pushing method, device, equipment and computer readable storage medium

Also Published As

Publication number Publication date
CN112035654A (en) 2020-12-04

Similar Documents

Publication Publication Date Title
US9959776B1 (en) System and method for automated scoring of texual responses to picture-based items
US10755185B2 (en) Rating difficulty of questions
US9348900B2 (en) Generating an answer from multiple pipelines using clustering
Correia et al. Automatic generation of cloze question stems
US10665122B1 (en) Application of semantic vectors in automated scoring of examination responses
US8473278B2 (en) Systems and methods for identifying collocation errors in text
US20070122792A1 (en) Language capability assessment and training apparatus and techniques
US20110270883A1 (en) Automated Short Free-Text Scoring Method and System
BR122017002789B1 (en) systems and methods for language learning
CN103688254B (en) Example-based error detection system, method, and error detection device for automated assessment writing
WO2025082156A1 (en) Performance self-query system and method
Kwankajornkiet et al. Automatic multiple-choice question generation from Thai text
JP2006039353A (en) Multiple-choice language test question automatic creation device and computer program
Canning et al. Relative complexity in a model of word difficulty: The role of loanwords in vocabulary size tests
Craig et al. Scaling address parsing sequence models through active learning
Park et al. Is the sky pure today? AwkChecker: an assistive tool for detecting and correcting collocation errors
Duran et al. Some issues on the normalization of a corpus of products reviews in Portuguese
CN112035654B (en) Automatic derivation generation method for questions
CN114003733A (en) A data enhancement method and system applied to power text
CN113850087A (en) A translation scoring method and related equipment
WO2025082158A1 (en) Intelligent chinese proficiency diagnosis method
US20100076943A1 (en) Foreign-Language Learning Method Utilizing An Original Language to Review Corresponding Foreign Languages and Foreign-Language Learning Database System Thereof
CN113705208B (en) A method and device for automatically generating Chinese questions based on domain terms and key sentences
Dickinson et al. Building a Korean web corpus for analyzing learner language
Alzahrani et al. AutoScor: an automated system for essay questions scoring

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