CN112035654A - Automatic topic derivation and generation method - Google Patents

Automatic topic derivation and generation method Download PDF

Info

Publication number
CN112035654A
CN112035654A CN202010905871.3A CN202010905871A CN112035654A CN 112035654 A CN112035654 A CN 112035654A CN 202010905871 A CN202010905871 A CN 202010905871A CN 112035654 A CN112035654 A CN 112035654A
Authority
CN
China
Prior art keywords
student
content
question
target sub
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010905871.3A
Other languages
Chinese (zh)
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/CN112035654A/en
Publication of CN112035654A publication Critical patent/CN112035654A/en
Pending legal-status Critical Current

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
    • G06F16/30—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; CALCULATING OR 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; 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—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

Landscapes

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

Abstract

The invention discloses a topic automatic derivation generation method, which comprises the following steps: step S10, obtaining student information and obtaining an identification point to be observed corresponding to the student information; step S20, determining question patterns matched with the student information and the knowledge points to be investigated according to the student information and the knowledge points to be investigated; and step S30, generating a question corresponding to the knowledge point to be examined and consistent with the question type according to the question type and the knowledge point to be examined. The technical scheme can automatically generate questions according to the recognition points to be observed of the students, the generated questions and the existing questions are low in repetition probability, the question generation efficiency is improved, and the examination effect of the questions on the students is improved.

Description

Automatic topic derivation and generation method
Technical Field
The invention relates to the technical field of data processing, in particular to an automatic topic derivation generation method.
Background
With the development and popularization of computer technology and the internet, the work, study and life style of people are greatly changed, for example, people increasingly utilize computers to obtain knowledge, and the computers also provide more and more convenient services for people; in the field of education, computer technology also provides convenience to teachers and students.
At present, aiming at practice problems or test problems which are usually contacted by teachers or students, the teachers basically search questions from a question bank according to the teaching requirements of the subject, the questions are easy to repeat with the existing questions, the question repetition rate is high, and the examination of the students is not facilitated.
Disclosure of Invention
The invention provides an automatic topic derivation and generation method.
The invention provides an automatic topic derivation generation method, which comprises the following steps of S10-S30:
step S10, obtaining student information and obtaining an identification point to be observed corresponding to the student information;
step S20, determining question patterns matched with the student information and the knowledge points to be investigated according to the student information and the knowledge points to be investigated;
and step S30, generating a question corresponding to the knowledge point to be examined and consistent with the question type according to the question type and the knowledge point to be examined.
Preferably, in step S10, the acquiring student information and acquiring the to-be-inspected identification point corresponding to the student information includes:
acquiring student information, wherein the student information comprises student characteristic information, student grade information, student capability information and historical test information; the student characteristic information comprises any one or more of student number, student name, student class and student age;
acquiring 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 historical test information;
and comparing the mastered knowledge points with all corresponding subject knowledge points to obtain the mastered knowledge points corresponding to the student information as the to-be-observed knowledge points corresponding to the student information.
Preferably, the determining the question type matched with the student information and the knowledge point to be investigated according to the student information and the knowledge point to be investigated includes:
acquiring a difficulty coefficient corresponding to the identification point to be observed;
according to the student capability information, acquiring a difficulty coefficient range of a subject which is acceptable by a student and corresponds to the student information;
judging whether the difficulty coefficient corresponding to the knowledge point to be inspected exceeds the difficulty coefficient range or not;
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 investigated; the first question type comprises any one of question types of question answering questions and blank filling questions;
and 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 investigated, 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 obtaining a test result obtained by testing the student corresponding to the student information based on the generated question and feedback information of the student.
Preferably, the method further comprises:
searching a system question bank according to the generated question, and identifying whether the existing question which is the same as the question exists in the system question bank;
if the existing questions same as the questions do not exist, storing the questions to the system questions;
if there is an existing topic that is the same as the topic, step S30 is re-executed to generate a new topic.
Preferably, when there are a plurality of knowledge points to be investigated, the generating a topic corresponding to the knowledge point to be investigated and consistent with the topic type according to the topic type and the knowledge point to be investigated includes steps a1-a 6:
a1, acquiring a text from a preset text library, and splitting the text to obtain a text abstract and a text main body content corresponding to the text;
step A2, judging whether the text abstract comprises at least M1 recognition points to be observed, if so, continuing the step A3; if not, return to step A1; m1 is a positive integer equal to or greater than 1;
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 inspected in 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 inspected;
step A4, calculating the weight ratio of the knowledge points to be examined in the text main body content, wherein the knowledge points are included in each first target sub-content;
a5, screening the plurality of first target sub-contents according to the weight proportion to obtain a second remaining target sub-content;
and A6, generating a question which contains the knowledge point to be examined and is consistent with the question type according to the second target sub-content.
Preferably, the step a4, calculating the weight proportion of the knowledge point to be investigated included in each first target sub-content in the main text content, includes:
calculating a degree of association between the plurality of first target sub-contents according to the following formula (1):
Figure BDA0002661440570000041
in the formula (1), giRepresenting 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+1Representing the ratio of the knowledge points to be mastered included in the (i + 1) th first target sub-content to all the knowledge points to be mastered; gi-1Representing the ratio of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered; diRepresenting the ratio of the storage space occupied by the ith first target sub-content to the storage space occupied by the text main body content; di+1Indicating that the (i + 1) th first target sub-content occupiesA ratio of storage space to storage space occupied by the text body content; di-1Representing the ratio of the storage space occupied by the i-1 st first target sub-content to the storage space occupied by the text main body content; n is the total number of first target sub-content;
calculating the space proportion s of all the first target sub-contents including the kth recognition point to be observed in the text main body content by using the formula (2)1kThen, there are:
Figure BDA0002661440570000042
wherein m represents a total number of paragraphs of the text body content; hkjRepresenting the number of lines occupied by a first target sub-content including a k-th recognition point to be observed in the j section; h isjRepresents the total number of lines included in the j section; delta1kDenotes s1kThe corresponding space-to-space ratio correction value is a preset value with the value range of [0.01, 0.05 ]]；
Calculating the occurrence frequency ratio s of all first target sub-contents including the k-th recognition point to be observed in the text main body content by using the formula (3)2kThen, there are:
Figure BDA0002661440570000051
wherein, PkjRepresenting the occurrence times of the kth to-be-observed recognition point in the jth segment; gkjRepresenting the total occurrence number of each knowledge point to be examined appearing in the j section; delta2kDenotes s2kThe corresponding appearance frequency ratio correction value is a preset value with the value range of [0.01, 0.02 ]]；
According to said F, said s1kS said2kAnd the following formula (4) is used for calculating the weight ratio w of the kth recognition point to be observed in the main body content of the textkThen, there are:
Figure BDA0002661440570000052
in the formula (4), a represents and s1kThe correlation constant is 0.7, and b represents s2kThe correlation constant takes a value of 0.3.
Preferably, the step a5, screening the plurality of first target sub-contents according to the weight percentage, to obtain a remaining second target sub-content, includes:
determining a target knowledge point to be inspected, wherein the corresponding weight ratio is equal to or greater than a preset weight ratio threshold;
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;
step A6, generating a question containing the knowledge point to be examined and consistent with the question type according to the second target sub-content, comprising:
performing the following operations for each second target sub-content: extracting target knowledge points to be examined from the current second target sub-content; and generating a question corresponding to the extracted target knowledge point to be examined and consistent with the question type according to the current second target sub-content and the extracted target knowledge point to be examined.
The question automatic derivation generation method can intelligently and automatically generate questions according to the recognition points to be examined of the students, avoids repetition with the existing test questions, has low question repetition rate, can improve the examination and examination effects of the students, has high question generation speed, improves the question generation efficiency and accuracy, 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 solution of the present invention is further described below by means of the accompanying drawings and examples.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic workflow diagram of an embodiment of a topic automatic derivation generation method of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides an automatic topic derivation generation method, which aims to automatically derive and generate a corresponding topic according to related knowledge points and replace a traditional topic generation mode of manual topic generation.
FIG. 1 is a schematic diagram of a workflow of an embodiment of a topic automatic derivation generation method according to the present invention; the title automatic derivation generation method of the present invention can be implemented as steps S10-S30 as follows:
and step S10, obtaining student information and obtaining an identification point to be observed corresponding to the student information.
And step S20, determining question patterns matched with the student information and the knowledge points to be investigated according to the student information and the knowledge points to be investigated.
And step S30, generating a question corresponding to the knowledge point to be examined and consistent with the question type according to the question type and the knowledge point to be examined.
In an embodiment, the step S10 of obtaining the student information and obtaining the to-be-observed recognition point corresponding to the student information may be implemented as:
acquiring student information, wherein the student information comprises student characteristic information, student grade information, student capability information and historical test information; the student characteristic information comprises any one or more of student number, student name, student class and student age;
acquiring 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 historical test information;
and comparing the mastered knowledge points with all corresponding subject knowledge points to obtain the mastered knowledge points corresponding to the student information as the to-be-observed knowledge points corresponding to the student information.
In one embodiment, the determining the topic type matching the student information and the knowledge point to be reviewed according to the student information and the knowledge point to be reviewed may be implemented as:
acquiring a difficulty coefficient corresponding to the identification point to be observed;
according to the student capability information, acquiring a difficulty coefficient range of a subject which is acceptable by a student and corresponds to the student information;
judging whether the difficulty coefficient corresponding to the knowledge point to be inspected exceeds the difficulty coefficient range or not;
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 investigated; the first question type comprises any one of question types of question answering questions and blank filling questions;
and 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 investigated, 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 obtaining a test result obtained by testing the student corresponding to the student information based on the generated question and feedback information of the student.
In one embodiment, the method may further comprise the steps of:
searching a system question bank according to the generated question, and identifying whether the existing question which is the same as the question exists in the system question bank;
if the existing questions same as the questions do not exist, storing the questions to the system questions;
if there is an existing topic that is the same as the topic, step S30 is re-executed to generate a new topic.
The technical scheme can conveniently and quickly expand the questions in the system questions and improve the question expansion speed of the system question bank.
In one embodiment, when there are a plurality of knowledge points to be investigated (for example, when the recognition points to be investigated are a plurality of knowledge points in english, the knowledge points in english may be words, idioms, grammars, fixed sentences or structures, etc.), in this case, generating topics corresponding to the knowledge points to be investigated and corresponding to the topic models according to the topic models and the knowledge points to be investigated may include steps a1-a 6:
step A1, acquiring a text (such as an English novel) from a preset text library, and splitting the text to obtain a text abstract and a text main body content corresponding to the text;
step A2, judging whether the text abstract comprises at least M1 recognition points to be observed, if so, continuing the step A3; if not, return to step A1; m1 is a positive integer equal to or greater than 1;
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 inspected in 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 inspected;
step A4, calculating the weight ratio of the knowledge points to be examined in the text main body content, wherein the knowledge points are included in each first target sub-content;
a5, screening the plurality of first target sub-contents according to the weight proportion to obtain a second remaining target sub-content;
and A6, generating a question which contains the knowledge point 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 proportion of the knowledge point to be investigated included in each first target sub-content in the main text content includes:
calculating a degree of association between the plurality of first target sub-contents according to the following formula (1):
Figure BDA0002661440570000091
in the formula (1), giRepresenting 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+1Representing the ratio of the knowledge points to be mastered included in the (i + 1) th first target sub-content to all the knowledge points to be mastered; gi-1Representing the ratio of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered; diRepresenting the ratio of the storage space occupied by the ith first target sub-content to the storage space occupied by the text main body content; di+1Representing the ratio of the storage space occupied by the (i + 1) th first target sub-content to the storage space occupied by the text main body content; di-1Representing the ratio of the storage space occupied by the i-1 st first target sub-content to the storage space occupied by the text main body content; n is the total number of first target sub-content;
calculating the space proportion s of all the first target sub-contents including the kth recognition point to be observed in the text main body content by using the formula (2)1kThen, there are:
Figure BDA0002661440570000101
wherein m represents a total number of paragraphs of the text body content; hkjRepresenting the number of lines occupied by a first target sub-content including a k-th recognition point to be observed in the j section; h isjRepresents the total number of lines included in the j section; delta1kDenotes s1kThe corresponding space-to-space ratio correction value is a preset value with the value range of [0.01, 0.05 ]]；
Calculating the occurrence frequency ratio s of all first target sub-contents including the k-th recognition point to be observed in the text main body content by using the formula (3)2kThen, there are:
Figure BDA0002661440570000102
wherein, PkjRepresenting the occurrence times of the kth to-be-observed recognition point in the jth segment; gkjRepresenting the total occurrence number of each knowledge point to be examined appearing in the j section; delta2kDenotes s2kThe corresponding appearance frequency ratio correction value is a preset value with the value range of [0.01, 0.02 ]]；
According to said F, said s1kS said2kAnd the following formula (4) is used for calculating the weight ratio w of the kth recognition point to be observed in the main body content of the textkThen, there are:
Figure BDA0002661440570000103
in the formula (4), a represents and s1kThe correlation constant is 0.7, and b represents s2kThe correlation constant takes a value of 0.3.
In an embodiment, the step a5 of screening the plurality of first target sub-contents according to the weight percentage to obtain a remaining second target sub-content includes:
determining a target knowledge point to be inspected, wherein the corresponding weight ratio is equal to or greater than a preset weight ratio threshold;
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;
step A6, generating a question containing the knowledge point to be examined and consistent with the question type according to the second target sub-content, comprising:
performing the following operations for each second target sub-content: extracting target knowledge points to be examined from the current second target sub-content; and generating a question corresponding to the extracted target knowledge point to be examined and consistent with the question type according to the current second target sub-content and the extracted target knowledge point to be examined.
For example, when the question type is a choice question, the current second target sub-content is a section of English which comprises three sentences, the section of English comprises two knowledge points to be investigated, one of the knowledge points is an English vocabulary, and the other is a fixed sentence pattern structure; then, "generating a topic corresponding to the extracted target knowledge point to be examined and consistent with the topic type according to the current second target sub-content and the extracted target knowledge point to be examined" may be implemented as follows: and eliminating the target knowledge points to be examined in the current second target sub-content, replacing the target knowledge points with brackets, and giving a plurality of corresponding selectable filling items for each bracket so as to generate the title.
The question automatic derivation generation method can intelligently and automatically generate questions according to the recognition points to be examined of the students, avoids repetition with the existing test questions, has low question repetition rate, can improve the examination and examination effects of the students, has high question generation speed, improves the question generation efficiency and accuracy, and improves the intelligence and objectivity of the question generation.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (8)

1. A method for generating automatic derivation of topics, the method comprising steps S10-S30:
step S10, obtaining student information and obtaining an identification point to be observed corresponding to the student information;
step S20, determining question patterns matched with the student information and the knowledge points to be investigated according to the student information and the knowledge points to be investigated;
and step S30, generating a question corresponding to the knowledge point to be examined and consistent with the question type according to the question type and the knowledge point to be examined.
2. The topic automatic derivation generation method of claim 1, wherein the step S10 of obtaining student information and obtaining an identification point to be observed corresponding to the student information comprises:
acquiring student information, wherein the student information comprises student characteristic information, student grade information, student capability information and historical test information; the student characteristic information comprises any one or more of student number, student name, student class and student age;
acquiring 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 historical test information;
and comparing the mastered knowledge points with all corresponding subject knowledge points to obtain the mastered knowledge points corresponding to the student information as the to-be-observed knowledge points corresponding to the student information.
3. The topic automatic derivation generation method according to claim 2, wherein the determining the topic type matching the student information and the knowledge point to be reviewed according to the student information and the knowledge point to be reviewed comprises:
acquiring a difficulty coefficient corresponding to the identification point to be observed;
according to the student capability information, acquiring a difficulty coefficient range of a subject which is acceptable by a student and corresponds to the student information;
judging whether the difficulty coefficient corresponding to the knowledge point to be inspected exceeds the difficulty coefficient range or not;
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 investigated; the first question type comprises any one of question types of question answering questions and blank filling questions;
and 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 investigated, wherein the second question type comprises any one of a judgment question and a selection question.
4. The method for automatic topic derivation generation according to claim 1, wherein 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 obtaining a test result obtained by testing the student corresponding to the student information based on the generated question and feedback information of the student.
5. The method for automatic topic derivation generation according to claim 1, wherein the method further comprises:
searching a system question bank according to the generated question, and identifying whether the existing question which is the same as the question exists in the system question bank;
if the existing questions same as the questions do not exist, storing the questions to the system questions;
if there is an existing topic that is the same as the topic, step S30 is re-executed to generate a new topic.
6. The method for automatically deriving and generating topics according to any one of claims 1 to 5, wherein when there are a plurality of knowledge points to be investigated, the generating topics corresponding to the knowledge points to be investigated and corresponding to the topic type according to the topic type and the knowledge points to be investigated comprises steps A1-A6:
a1, acquiring a text from a preset text library, and splitting the text to obtain a text abstract and a text main body content corresponding to the text;
step A2, judging whether the text abstract comprises at least M1 recognition points to be observed, if so, continuing the step A3; if not, return to step A1; m1 is a positive integer equal to or greater than 1;
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 inspected in 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 inspected;
step A4, calculating the weight ratio of the knowledge points to be examined in the text main body content, wherein the knowledge points are included in each first target sub-content;
a5, screening the plurality of first target sub-contents according to the weight proportion to obtain a second remaining target sub-content;
and A6, generating a question which contains the knowledge point to be examined and is consistent with the question type according to the second target sub-content.
7. The topic automatic derivation generation method according to claim 6, wherein the step a4 of calculating the weight ratio of the knowledge points to be investigated included in each first target sub-content in the main text content comprises:
calculating a degree of association between the plurality of first target sub-contents according to the following formula (1):
Figure FDA0002661440560000031
in the formula (1), giRepresenting 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+1Representing the ratio of the knowledge points to be mastered included in the (i + 1) th first target sub-content to all the knowledge points to be mastered; gi-1Representing the ratio of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered; diRepresenting the ratio of the storage space occupied by the ith first target sub-content to the storage space occupied by the text main body content; di+1Representing the ratio of the storage space occupied by the (i + 1) th first target sub-content to the storage space occupied by the text main body content; di-1Representing the ratio of the storage space occupied by the i-1 st first target sub-content to the storage space occupied by the text main body content; n is the total number of first target sub-content;
calculating the space proportion s of all the first target sub-contents including the kth recognition point to be observed in the text main body content by using the formula (2)1kThen, there are:
Figure FDA0002661440560000041
wherein m represents a total number of paragraphs of the text body content; hkjRepresenting the number of lines occupied by a first target sub-content including a k-th recognition point to be observed in the j section; h isjRepresents the total number of lines included in the j section; delta1kDenotes s1kThe corresponding space-to-space ratio correction value is a preset value with the value range of [0.01, 0.05 ]]；
Calculating the occurrence frequency ratio s of all first target sub-contents including the k-th recognition point to be observed in the text main body content by using the formula (3)2kThen, there are:
Figure FDA0002661440560000042
wherein, PkjRepresenting the occurrence times of the kth to-be-observed recognition point in the jth segment; gkjRepresenting the total occurrence number of each knowledge point to be examined appearing in the j section; delta2kDenotes s2kThe corresponding appearance frequency ratio correction value is a preset value with the value range of [0.01, 0.02 ]]；
According to said F, said s1kS said2kAnd the following formula (4) is used for calculating the weight ratio w of the kth recognition point to be observed in the main body content of the textkThen, there are:
Figure FDA0002661440560000043
in the formula (4), a represents and s1kThe correlation constant is 0.7, and b represents s2kThe correlation constant takes a value of 0.3.
8. The topic automatic derivation generation method of claim 6, wherein the step a5 of filtering the plurality of first target sub-contents according to the weight ratio to obtain a remaining second target sub-content comprises:
determining a target knowledge point to be inspected, wherein the corresponding weight ratio is equal to or greater than a preset weight ratio threshold;
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;
step A6, generating a question containing the knowledge point to be examined and consistent with the question type according to the second target sub-content, comprising:
performing the following operations for each second target sub-content: extracting target knowledge points to be examined from the current second target sub-content; and generating a question corresponding to the extracted target knowledge point to be examined and consistent with the question type according to the current second target sub-content and the extracted target knowledge point to be examined.
CN202010905871.3A 2020-09-01 2020-09-01 Automatic topic derivation and generation method Pending CN112035654A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010905871.3A CN112035654A (en) 2020-09-01 2020-09-01 Automatic topic derivation and generation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010905871.3A CN112035654A (en) 2020-09-01 2020-09-01 Automatic topic derivation and generation method

Publications (1)

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

Family

ID=73592184

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010905871.3A Pending CN112035654A (en) 2020-09-01 2020-09-01 Automatic topic derivation and generation method

Country Status (1)

Country Link
CN (1) CN112035654A (en)

Similar Documents

Publication Publication Date Title
Correia et al. Automatic generation of cloze question stems
US20150243181A1 (en) Systems and Methods for Automated Scoring of Textual Responses to Picture-Based Items
CN110569393B (en) Short video cutting method for air classroom
CN108280065B (en) Foreign text evaluation method and device
CN107943940A (en) Data processing method, medium, system and electronic equipment
CN111597305B (en) Entity marking method, entity marking device, computer equipment and storage medium
CN107844531B (en) Answer output method and device and computer equipment
CN111462546A (en) Voice teaching method, device, equipment and storage medium
Stüker et al. Towards Context-Dependent Phonetic Spelling Error Correction in Children's Freely Composed Text for Diagnostic and Pedagogical Purposes.
CN110390032B (en) Method and system for reading handwritten composition
Forbes-Riley et al. Investigating human tutor responses to student uncertainty for adaptive system development
CN112015882A (en) Automatic generation method and system for language text questions
Etxeberria et al. Weighted finite-state transducers for normalization of historical texts
CN116720509A (en) Construction method of emotion dictionary in student teaching evaluation field
CN112035654A (en) Automatic topic derivation and generation method
CN116306592A (en) Senile dementia scale error correction method, system and medium based on reading understanding
CN115114417A (en) Automatic scoring method and device for Chinese blank filling questions
CN114241835A (en) Student spoken language quality evaluation method and device
CN110941709B (en) Information screening method and device, electronic equipment and readable storage medium
Alzahrani et al. AutoScor: an automated system for essay questions scoring
CN113435213A (en) Method and device for returning answers aiming at user questions and knowledge base
CN112560431A (en) Method, apparatus, device, storage medium, and computer program product for generating test question tutoring information
Richter et al. Tracking the evolution of written language competence: an NLP–based approach
Rose Improving the production efficiency and well-formedness of automatically-generated multiple-choice cloze vocabulary questions
CN112131889A (en) Intelligent Chinese subjective question scoring method and system based on big data

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