CN112015883A - English question automatic generation method and system - Google Patents
English question automatic generation method and system Download PDFInfo
- Publication number
- CN112015883A CN112015883A CN202010856592.2A CN202010856592A CN112015883A CN 112015883 A CN112015883 A CN 112015883A CN 202010856592 A CN202010856592 A CN 202010856592A CN 112015883 A CN112015883 A CN 112015883A
- Authority
- CN
- China
- Prior art keywords
- english
- learning data
- test
- data record
- questions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 476
- 238000012216 screening Methods 0.000 claims description 52
- 238000012545 processing Methods 0.000 claims description 27
- 238000011156 evaluation Methods 0.000 claims description 20
- 230000009286 beneficial effect Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 abstract description 6
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
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
- G06F16/345—Summarisation for human users
-
- 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)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Computational Linguistics (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)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides an automatic English question generation method and system, which can form corresponding learning data record sets according to different difficulty levels of English historical learning data records of a preset test object in the aspects of grammar, pronunciation, vocabulary and the like, and then screen different types of English test questions from a preset English test question library according to the learning data record sets to form a proper English test question paper, so that test questions matched with the historical learning records of the preset test object can be intelligently generated, and the automation and reliability of English test question formation are improved.
Description
Technical Field
The invention relates to the technical field of intelligent education, in particular to an English question automatic generation method and system.
Background
English is an ancient Chinese language expression mode, and has larger difference compared with a Chinese expression mode in the aspects of grammar, pronunciation, vocabulary and the like, so that students generally have larger difficulty in the English learning process, and teachers also have certain difficulty in the process of establishing test questions aiming at English knowledge. Therefore, the prior art urgently needs a mode for automatically generating English test questions aiming at the characteristics of grammar, pronunciation and vocabulary of English knowledge data.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an automatic generation method and system of English subjects, which determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records by acquiring English history learning data records of preset test objects and processing the data type contents of the English history learning data records, determine the difficulty levels corresponding to the English grammar learning data records, the English voice learning data records and the English vocabulary learning data records respectively, divide the English grammar learning data records, the English voice learning data records and the English vocabulary learning data records with the same difficulty level into the same learning data record set, and then screen a plurality of different types of English test subjects matched with the learning data record set from a preset English test subject database, selecting corresponding number of different types of English test questions from the plurality of different types of English test questions according to the test duration for testing the preset test object, so as to form an English test question book; therefore, the automatic English test question generation method and the system can form corresponding learning data record sets according to different difficulty levels of English historical learning data records of the preset test object in the aspects of grammar, pronunciation, vocabulary and the like, and then screen different types of English test questions from the preset English test question library according to the learning data record sets to form a proper English test question paper, so that test questions matched with the historical learning records of the preset test object can be intelligently generated, and the automation and the reliability of English test question formation are improved.
The invention provides an automatic English title generation method, which is characterized by comprising the following steps:
step S1, obtaining English historical learning data records of a preset test object, and performing data type content processing on the English historical learning data records, thereby determining a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records;
step S2, determining difficulty levels corresponding to the english grammar learning data record, the english speech learning data record, and the english vocabulary learning data record, and dividing the english grammar learning data record, the english speech learning data record, and the english vocabulary learning data record having the same difficulty level into the same learning data record set;
step S3, screening a plurality of English test questions of different types matched with the learning data record set from a preset English test question library, and selecting corresponding number of English test questions of different types from the English test questions of different types according to the test duration of the preset test object to form an English test question volume;
further, in step S1, an english history learning data record of a preset test object is obtained, and data content distinguishing processing is performed on the english history learning data record, so as to determine that a plurality of english grammar learning data records, a plurality of english voice learning data records, and a plurality of english vocabulary learning data records specifically include,
step S101, obtaining a history online learning data record of the preset test object in the history online learning process, and performing English related screening processing on the history online learning data record, so as to extract and obtain an English history learning data record of the preset test object;
step S102, performing data content distinguishing processing on the English historical learning data records so as to determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records which are contained in the English historical learning data records;
further, in the step S2, determining the difficulty levels corresponding to the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record, and dividing the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record having the same difficulty level into the same learning data record set specifically includes,
step S201, determining grammar knowledge point information, voice knowledge point information and vocabulary knowledge point information which correspond to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively according to preset English test outline information;
step S202, comparing the grammar knowledge point information, the voice knowledge point information and the vocabulary knowledge point information with a preset knowledge point database respectively, so as to determine difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively;
step S203, dividing English grammar learning data records, English voice learning data records and English vocabulary learning data records with the same difficulty level evaluation value into the same learning data record set, thereby obtaining a plurality of learning data record sets with different difficulty level evaluation values;
further, in step S3, the method includes screening a plurality of different types of english test questions matching the learning data record set from a preset english test question library, and selecting a corresponding number of different types of english test questions from the plurality of different types of english test questions according to a test duration of testing the preset test object to form an english test question book,
step S301, according to the difficulty level of the learning data record set, screening a plurality of English test questions of different types matched with the difficulty level from the preset English test question library;
step S302, determining the number of the selected questions, the blank filling questions and the question and answer questions in the English test question paper for testing the preset test object according to the test duration for testing the preset test object;
step S303, selecting a corresponding number of English grammar test selection questions or blank filling questions or question and answer questions from the English test questions of different types according to the number of the questions, and selecting English listening test selection questions or blank filling questions or question and answer questions and English vocabulary test selection questions or blank filling questions or question and answer questions, thereby generating the English test question book.
The invention also provides an English question automatic generation system which is characterized by comprising an English historical learning data record acquisition module, an English historical learning data record distinguishing module, a learning data record set module and an English test question book generation module; wherein the content of the first and second substances,
the English historical learning data record acquisition module is used for acquiring an English historical learning data record of a preset test object;
the English historical learning data record distinguishing module is used for carrying out data type content processing on the English historical learning data records so as to determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records;
the learning data record set is set into a module for determining the difficulty levels corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively, and dividing the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record with the same difficulty level into the same learning data record set;
the English test question generating module is used for screening a plurality of different types of English test questions matched with the learning data record set from a preset English test question library, and selecting corresponding quantities of different types of English test questions from the plurality of different types of English test questions according to the test duration of the preset test object so as to form an English test question book;
further, the obtaining of the english historical learning data record of the preset test object by the english historical learning data record obtaining module specifically includes obtaining an online historical learning data record of the preset test object in an online historical learning process, and performing english-related screening processing on the online historical learning data record, so as to extract and obtain the english historical learning data record of the preset test object;
the English historical learning data record distinguishing module is used for carrying out data type content processing on the English historical learning data record, and specifically comprises the step of carrying out data content distinguishing processing on the English historical learning data record, so that a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records contained in the English historical learning data record are determined;
further, the learning data record set is set into a module to determine the difficulty levels corresponding to the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record, and the specific steps of dividing the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record with the same difficulty level into the same learning data record set include,
determining grammar knowledge point information, voice knowledge point information and vocabulary knowledge point information which correspond to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively according to preset English test outline information;
comparing the grammar knowledge point information, the voice knowledge point information and the vocabulary knowledge point information with a preset knowledge point database respectively, thereby determining difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively;
finally, dividing English grammar learning data records, English voice learning data records and English vocabulary learning data records with the same difficulty level evaluation value into the same learning data record set, thereby obtaining a plurality of learning data record sets with different difficulty level evaluation values;
further, the english test question generating module selects a plurality of different types of english test questions matching the learning data record set from a preset english test question library, and extracts a corresponding number of different types of english test questions from the plurality of different types of english test questions according to a test duration for testing the preset test object, thereby forming an english test question book specifically including,
screening a plurality of English test questions of different types matched with the difficulty level from the preset English test question library according to the difficulty level of the learning data record set,
then determining the number of the respective questions of the selected questions, the filling-in-blank questions and the question and answer questions in the English test question book for testing the preset test object according to the test duration for testing the preset test object,
and finally, selecting a corresponding number of English grammar test selection questions or blank filling questions or question and answer questions from the English test questions of different types according to the number of the questions, and selecting the English listening test selection questions or blank filling questions or question and answer questions and English vocabulary test selection questions or blank filling questions or question and answer questions so as to generate the English test question book.
Compared with the prior art, the English title automatic generation method and the system determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records by acquiring the English history learning data records of a preset test object and processing the data type content of the English history learning data records, determine the difficulty levels corresponding to the English grammar learning data records, the English voice learning data records and the English vocabulary learning data records respectively, divide the English grammar learning data records, the English voice learning data records and the English vocabulary learning data records with the same difficulty level into the same learning data record set, screen a plurality of different types of test titles matched with the learning data record set from a preset English test title library, and test duration according to the preset test object, selecting corresponding number of different types of English test questions from the plurality of different types of English test questions to form an English test question book; therefore, the automatic English test question generation method and the system can form corresponding learning data record sets according to different difficulty levels of English historical learning data records of the preset test object in the aspects of grammar, pronunciation, vocabulary and the like, and then screen different types of English test questions from the preset English test question library according to the learning data record sets to form a proper English test question paper, so that test questions matched with the historical learning records of the preset test object can be intelligently generated, and the automation and the reliability of English test question formation are improved.
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 in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention 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 invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of an English title automatic generation method provided by the present invention.
FIG. 2 is a schematic structural diagram of an English title automatic generation system provided by the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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, a schematic flow chart of an english title automatic generation method according to an embodiment of the present invention is shown. The automatic English title generation method comprises the following steps:
step S1, obtaining English historical learning data records of a preset test object, and performing data type content processing on the English historical learning data records, thereby determining a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records;
step S2, determining the difficulty level corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record, and dividing the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record with the same difficulty level into the same learning data record set;
step S3, screening a plurality of different types of english test questions matching the learning data record set from a preset english test question library, and selecting a corresponding number of different types of english test questions from the plurality of different types of english test questions according to the test duration of the test performed on the preset test object, thereby forming an english test question volume.
The automatic English question generation method can form corresponding learning data record sets according to different difficulty levels of English historical learning data records of a preset test object in the aspects of grammar, pronunciation, vocabulary and the like, and then obtains different types of English test questions by screening from a preset English test question library according to the learning data record sets to form a proper English test question paper, so that test questions matched with the historical learning records of the preset test object can be intelligently generated, and the automation and reliability of English test question formation are improved.
Preferably, in step S1, an english history learning data record of a preset test object is obtained, and data content distinguishing processing is performed on the english history learning data record, so as to determine that a plurality of english grammar learning data records, a plurality of english voice learning data records and a plurality of english vocabulary learning data records specifically include,
step S101, obtaining a history online learning data record of the preset test object in the history online learning process, and performing English related screening processing on the history online learning data record, thereby extracting and obtaining an English history learning data record of the preset test object;
and step S102, performing data content distinguishing processing on the English historical learning data record so as to determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records contained in the English historical learning data record.
English grammar learning data records, English voice learning data records and English vocabulary learning data records are obtained by screening and distinguishing on-line learning data records of a preset test object, so that the English learning history of the preset test object can be comprehensively and accurately determined.
Preferably, in the step S2, determining the difficulty level corresponding to each of the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record, and dividing the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record having the same difficulty level into the same learning data record set specifically includes,
step S201, determining grammar knowledge point information, voice knowledge point information and vocabulary knowledge point information corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record according to preset English test outline information;
step S202, comparing the grammar knowledge point information, the voice knowledge point information and the vocabulary knowledge point information with a preset knowledge point database respectively, thereby determining difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively;
step S203, the english grammar learning data records, the english voice learning data records and the english vocabulary learning data records having the same difficulty level evaluation values are divided into the same learning data record set, so as to obtain a plurality of learning data record sets having different difficulty level evaluation values.
By analyzing the knowledge points of the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record, the difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record can be determined, and therefore the corresponding learning data record set can be accurately obtained.
Preferably, in step S3, the method includes screening a plurality of different types of english test questions matching the learning data record set from a preset english test question library, and selecting a corresponding number of different types of english test questions from the plurality of different types of english test questions according to a test duration of testing the preset test object, so as to form an english test question book,
step S301, according to the difficulty level of the learning data record set, screening a plurality of English test questions of different types matched with the difficulty level from the preset English test question library;
step S302, determining the number of the selected questions, the blank filling questions and the question and answer questions in the English test question book for testing the preset test object according to the test duration for testing the preset test object;
step S303, selecting a corresponding number of English grammar test selection questions or blank filling questions or question and answer questions from the English test questions of different types according to the number of the questions, and generating the English test question book.
According to the test duration of the preset test object, different types of English test questions with corresponding quantity are selected from different types of English test questions, and the English test question book matched with the learning experience of the preset test object can be generated.
In one embodiment, in step S301, screening, according to the difficulty level of the learning data record set itself, a plurality of different types of english test subjects matching the difficulty level from the preset english test subject library further includes:
step A1: determining the difficulty level of each English test question in the preset English test question library by using a formula (1):
wherein N isaRepresenting the difficulty level of the a-th English test question in the preset English test question library; daiRepresenting the average score of the ith English test question in the preset English test question library in the ith historical test; faiRepresenting the full score value of the ith English test question in the preset English test question library in the ith test history; n represents the total times of historical tests of the a-th English test question in the preset English test question library;
step A2: calculating the matching degree value between the difficulty level of each English test question in the preset English test question library and the difficulty level of the learning data record set by using a formula (2):
wherein Z isaRepresenting a matching degree value between the difficulty level of the a-th English test question in the preset English test question library and the difficulty level of the learning data record set; n represents the difficulty level of the learning data record set;
step A3: determining the English test question with the matching degree value equal to or smaller than a preset threshold value as the English test question screened for the first time;
step A4: classifying the English test questions screened for the first time by using a formula (3) to obtain a classification probability value:
wherein, FaiRepresents the a-th English test screened for the first timeProbability that a topic belongs to a topic of type i; siF corresponding to the alpha English test question screened for the first time is calculated according to the formula (3)aiBefore, the number of the English test questions belonging to the ith class of questions is determined; s represents F corresponding to the alpha-English test question screened for the first time and calculated according to the formula (3)aiBefore, the number of the English test questions in the classification is finished; patRepresenting the frequency of occurrence of the tth characteristic information corresponding to the ith type of title in the a-th English test title screened for the first time; m represents the total number of the characteristic information corresponding to the ith type of title;
when said F isaiWhen the number is equal to or more than 60%, the a-th English test question screened for the first time is considered to belong to the i-th question type; if a certain English test question belongs to a plurality of question types, selecting the FaiThe question type corresponding to the maximum value is used as the final attributive type of the alpha English test question screened for the first time;
when said F isaiAnd when the difficulty level of the learning data record set is less than 60%, independently forming a new class of English test questions until all English test questions screened for the first time are classified, and finally screening different classes of English test questions matched with the difficulty level of the learning data record set.
The beneficial effects of the above technical scheme are: the difficulty level of the English test questions in the preset English test question library is obtained by using a formula (1), so that the difficulty of the English test questions in the preset English test question library is quantified by using the formula, and the subsequent difficulty level can be matched with the difficulty level of the learning data record set, so that the screening of the subsequent questions is ensured; obtaining a matching degree value by using a formula (2) so as to screen English test questions in the preset English test question library for one time by using the matching degree value obtained by the formula and screen out English test questions matched with the difficulty level; finally, a classification probability value is obtained by using a formula (3), the English test questions in the preset English test question library after primary screening can be accurately classified by using the classification probability value, secondary screening is carried out according to the classification value, and different types of English test questions matched with the difficulty level are finally selected; the formula and the steps increase the screening precision of the Chinese and English test questions in the preset English test question library, and a twice screening mode is used, so that the screened questions are more in line with the requirements, the types of the selected questions can be ensured to be diversified, and the difficulty is matched with the difficulty level.
Fig. 2 is a schematic structural diagram of an automatic english title generation system according to an embodiment of the present invention. The English question automatic generation system comprises an English historical learning data record acquisition module, an English historical learning data record distinguishing module, a learning data record set-up module and an English test question volume generation module; wherein the content of the first and second substances,
the English historical learning data record acquisition module is used for acquiring an English historical learning data record of a preset test object;
the English historical learning data record distinguishing module is used for carrying out data type content processing on the English historical learning data record so as to determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records;
the learning data record set is set into a module for determining the difficulty levels corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively, and dividing the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record with the same difficulty level into the same learning data record set;
the English test question book generating module is used for screening a plurality of different types of English test questions matched with the learning data record set from a preset English test question library, and selecting corresponding quantities of different types of English test questions from the plurality of different types of English test questions according to the test duration of the preset test object, so as to form an English test question book.
The automatic English question generation system can form corresponding learning data record sets according to different difficulty levels of English historical learning data records of a preset test object in the aspects of grammar, pronunciation, vocabulary and the like, and then obtains different types of English test questions by screening from a preset English test question library according to the learning data record sets to form a proper English test question paper, so that test questions matched with the historical learning records of the preset test object can be intelligently generated, and the automation and reliability of English test question formation are improved.
Preferably, the obtaining of the english historical learning data record of the preset test object by the english historical learning data record obtaining module specifically includes obtaining an online historical learning data record of the preset test object in the online historical learning process, and performing english-related screening processing on the online historical learning data record, so as to extract and obtain the english historical learning data record of the preset test object;
the English historical learning data record distinguishing module is used for carrying out data type content processing on the English historical learning data record, and specifically comprises the step of carrying out data content distinguishing processing on the English historical learning data record, so that a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records contained in the English historical learning data record are determined.
English grammar learning data records, English voice learning data records and English vocabulary learning data records are obtained by screening and distinguishing on-line learning data records of a preset test object, so that the English learning history of the preset test object can be comprehensively and accurately determined.
Preferably, the learning data record set is configured to determine difficulty levels corresponding to the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record, and the dividing the english grammar learning data record, the english voice learning data record and the english vocabulary learning data record having the same difficulty level into the same learning data record set specifically includes,
determining grammar knowledge point information, voice knowledge point information and vocabulary knowledge point information which correspond to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively according to preset English test outline information;
comparing the grammar knowledge point information, the voice knowledge point information and the vocabulary knowledge point information with a preset knowledge point database respectively, thereby determining difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively;
and finally, dividing English grammar learning data records, English voice learning data records and English vocabulary learning data records with the same difficulty level evaluation values into the same learning data record set, thereby obtaining a plurality of learning data record sets with different difficulty level evaluation values.
By analyzing the knowledge points of the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record, the difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record can be determined, and therefore the corresponding learning data record set can be accurately obtained.
Preferably, the english test question volume generating module screens a plurality of different types of english test questions matched with the learning data record set from a preset english test question library, and extracts a corresponding number of different types of english test questions from the plurality of different types of english test questions according to a test duration for testing the preset test object, so as to form an english test question volume specifically including,
according to the difficulty level of the learning data record set, screening a plurality of English test questions of different types matched with the difficulty level from the preset English test question library,
then determining the number of the selected questions, the filling-in-blank questions and the question-answering questions in the English test question book for testing the preset test object according to the test duration for testing the preset test object,
and finally, selecting a corresponding number of English grammar test selection questions or blank filling questions or question and answer questions from the English test questions of different types according to the number of the questions, and selecting the English listening test selection questions or blank filling questions or question and answer questions and English vocabulary test selection questions or blank filling questions or question and answer questions so as to generate the English test question book.
According to the test duration of the preset test object, different types of English test questions with corresponding quantity are selected from different types of English test questions, and the English test question book matched with the learning experience of the preset test object can be generated.
In an embodiment, the screening, according to the difficulty level of the learning data record set itself, a plurality of different types of english test questions matching the difficulty level from the preset english test question library further includes:
step A1: determining the difficulty level of each English test question in the preset English test question library by using a formula (1):
wherein N isaRepresenting the difficulty level of the a-th English test question in the preset English test question library; daiRepresenting the average score of the ith English test question in the preset English test question library in the ith historical test; faiRepresenting the full score value of the ith English test question in the preset English test question library in the ith test history; n represents the total times of historical tests of the a-th English test question in the preset English test question library;
step A2: calculating the matching degree value between the difficulty level of each English test question in the preset English test question library and the difficulty level of the learning data record set by using a formula (2):
wherein Z isaRepresenting a matching degree value between the difficulty level of the a-th English test question in the preset English test question library and the difficulty level of the learning data record set; n represents the difficulty level of the learning data record set;
step A3: determining the English test question with the matching degree value equal to or smaller than a preset threshold value as the English test question screened for the first time;
step A4: classifying the English test questions screened for the first time by using a formula (3) to obtain a classification probability value:
wherein, FaiRepresenting the probability that the a-th English test question screened for the first time belongs to the i-th class question; siF corresponding to the alpha English test question screened for the first time is calculated according to the formula (3)aiBefore, the number of the English test questions belonging to the ith class of questions is determined; s represents F corresponding to the alpha-English test question screened for the first time and calculated according to the formula (3)aiBefore, the number of the English test questions in the classification is finished; patRepresenting the frequency of occurrence of the tth characteristic information corresponding to the ith type of title in the a-th English test title screened for the first time; m represents the total number of the characteristic information corresponding to the ith type of title;
when said F isaiWhen the number is equal to or more than 60%, the a-th English test question screened for the first time is considered to belong to the i-th question type; if a certain English test question belongs to a plurality of question types, selecting the FaiThe question type corresponding to the maximum value is used as the final attributive type of the alpha English test question screened for the first time;
when said F isaiWhen the number of the subjects is less than 60%, a new category of subject type is formed independently until the subjects are screened for the first timeAnd finally screening different types of English test questions matched with the difficulty level of the learning data record set until all English test questions are classified.
The beneficial effects of the above technical scheme are: the difficulty level of the English test questions in the preset English test question library is obtained by using a formula (1), so that the difficulty of the English test questions in the preset English test question library is quantified by using the formula, and the subsequent difficulty level can be matched with the difficulty level of the learning data record set, so that the screening of the subsequent questions is ensured; obtaining a matching degree value by using a formula (2) so as to screen English test questions in the preset English test question library for one time by using the matching degree value obtained by the formula and screen out English test questions matched with the difficulty level; finally, a classification probability value is obtained by using a formula (3), the English test questions in the preset English test question library after primary screening can be accurately classified by using the classification probability value, secondary screening is carried out according to the classification value, and different types of English test questions matched with the difficulty level are finally selected; the formula and the steps increase the screening precision of the Chinese and English test questions in the preset English test question library, and a twice screening mode is used, so that the screened questions are more in line with the requirements, the types of the selected questions can be ensured to be diversified, and the difficulty is matched with the difficulty level.
As can be seen from the content of the above embodiments, the method and system for automatically generating english titles determine a plurality of english grammar learning data records, a plurality of english voice learning data records and a plurality of english vocabulary learning data records by obtaining the english history learning data records of the preset test object and performing data type content processing on the english history learning data records, determine the difficulty levels corresponding to the english grammar learning data records, the english voice learning data records and the english vocabulary learning data records, divide the english grammar learning data records, the english voice learning data records and the english vocabulary learning data records having the same difficulty level into the same learning data record set, and then screen a plurality of different types of english test titles matching with the learning data record set from the preset english test title library, selecting corresponding number of different types of English test questions from the plurality of different types of English test questions according to the test duration for testing the preset test object, so as to form an English test question book; therefore, the automatic English test question generation method and the system can form corresponding learning data record sets according to different difficulty levels of English historical learning data records of the preset test object in the aspects of grammar, pronunciation, vocabulary and the like, and then screen different types of English test questions from the preset English test question library according to the learning data record sets to form a proper English test question paper, so that test questions matched with the historical learning records of the preset test object can be intelligently generated, and the automation and the reliability of English test question formation are improved.
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 (10)
1. The English title automatic generation method is characterized by comprising the following steps:
step S1, obtaining English historical learning data records of a preset test object, and performing data type content processing on the English historical learning data records, thereby determining a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records;
step S2, determining difficulty levels corresponding to the english grammar learning data record, the english speech learning data record, and the english vocabulary learning data record, and dividing the english grammar learning data record, the english speech learning data record, and the english vocabulary learning data record having the same difficulty level into the same learning data record set;
and step S3, screening a plurality of different types of English test questions matched with the learning data record set from a preset English test question library, and selecting corresponding quantities of different types of English test questions from the plurality of different types of English test questions according to the test duration of the preset test object to form an English test question book.
2. The automatic English title generation method of claim 1, wherein:
in step S1, an english history learning data record of a preset test object is obtained, and data content distinguishing processing is performed on the english history learning data record, so as to determine that a plurality of english grammar learning data records, a plurality of english voice learning data records, and a plurality of english vocabulary learning data records specifically include,
step S101, obtaining a history online learning data record of the preset test object in the history online learning process, and performing English related screening processing on the history online learning data record, so as to extract and obtain an English history learning data record of the preset test object;
and step S102, performing data content distinguishing processing on the English historical learning data records so as to determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records contained in the English historical learning data records.
3. The automatic English title generation method of claim 1, wherein:
in step S2, determining difficulty levels corresponding to the english grammar learning data record, the english speech learning data record, and the english vocabulary learning data record, and dividing the english grammar learning data record, the english speech learning data record, and the english vocabulary learning data record having the same difficulty level into the same learning data record set specifically includes,
step S201, determining grammar knowledge point information, voice knowledge point information and vocabulary knowledge point information which correspond to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively according to preset English test outline information;
step S202, comparing the grammar knowledge point information, the voice knowledge point information and the vocabulary knowledge point information with a preset knowledge point database respectively, so as to determine difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively;
step S203, the english grammar learning data records, the english voice learning data records and the english vocabulary learning data records having the same difficulty level evaluation values are divided into the same learning data record set, so as to obtain a plurality of learning data record sets having different difficulty level evaluation values.
4. The automatic English title generation method of claim 1, wherein:
in step S3, a plurality of different types of english test questions matched with the learning data record set are screened from a preset english test question library, and a corresponding number of different types of english test questions are extracted from the plurality of different types of english test questions according to a test duration of testing the preset test object, so as to form an english test question book specifically including,
step S301, according to the difficulty level of the learning data record set, screening a plurality of English test questions of different types matched with the difficulty level from the preset English test question library;
step S302, determining the number of the selected questions, the blank filling questions and the question and answer questions in the English test question paper for testing the preset test object according to the test duration for testing the preset test object;
step S303, selecting a corresponding number of English grammar test selection questions or blank filling questions or question and answer questions from the English test questions of different types according to the number of the questions, and selecting English listening test selection questions or blank filling questions or question and answer questions and English vocabulary test selection questions or blank filling questions or question and answer questions, thereby generating the English test question book.
5. The method for automatically generating english subjects according to claim 4, wherein the step of screening a plurality of different types of english test subjects matching the difficulty level from the preset english test subject library according to the difficulty level of the learning data record set itself further comprises:
step A1: determining the difficulty level of each English test question in the preset English test question library by using a formula (1):
wherein N isaRepresenting the difficulty level of the a-th English test question in the preset English test question library; daiRepresenting the average score of the ith English test question in the preset English test question library in the ith historical test; faiRepresenting the full score value of the ith English test question in the preset English test question library in the ith test history; n represents the total times of historical tests of the a-th English test question in the preset English test question library;
step A2: calculating the matching degree value between the difficulty level of each English test question in the preset English test question library and the difficulty level of the learning data record set by using a formula (2):
wherein Z isaRepresenting the difficulty level of the a-th English test question in the preset English test question library and the learning dataRecording the matching degree value between the difficulty grades of the set; n represents the difficulty level of the learning data record set;
step A3: determining the English test question with the matching degree value equal to or smaller than a preset threshold value as the English test question screened for the first time;
step A4: classifying the English test questions screened for the first time by using a formula (3) to obtain a classification probability value:
wherein, FaiRepresenting the probability that the a-th English test question screened for the first time belongs to the i-th class question; siF corresponding to the alpha English test question screened for the first time is calculated according to the formula (3)aiBefore, the number of the English test questions belonging to the ith class of questions is determined; s represents F corresponding to the alpha-English test question screened for the first time and calculated according to the formula (3)aiBefore, the number of the English test questions in the classification is finished; patRepresenting the frequency of occurrence of the tth characteristic information corresponding to the ith type of title in the a-th English test title screened for the first time; m represents the total number of the characteristic information corresponding to the ith type of title;
when said F isaiWhen the number is equal to or more than 60%, the a-th English test question screened for the first time is considered to belong to the i-th question type; if a certain English test question belongs to a plurality of question types, selecting the FaiThe question type corresponding to the maximum value is used as the final attributive type of the alpha English test question screened for the first time;
when said F isaiAnd when the difficulty level of the learning data record set is less than 60%, independently forming a new class of English test questions until all English test questions screened for the first time are classified, and finally screening different classes of English test questions matched with the difficulty level of the learning data record set.
The beneficial effects of the above technical scheme are: the difficulty level of the English test questions in the preset English test question library is obtained by using a formula (1), so that the difficulty of the English test questions in the preset English test question library is quantified by using the formula, and the subsequent difficulty level can be matched with the difficulty level of the learning data record set, so that the screening of the subsequent questions is ensured; obtaining a matching degree value by using a formula (2) so as to screen English test questions in the preset English test question library for one time by using the matching degree value obtained by the formula and screen out English test questions matched with the difficulty level; finally, a classification probability value is obtained by using a formula (3), the English test questions in the preset English test question library after primary screening can be accurately classified by using the classification probability value, secondary screening is carried out according to the classification value, and different types of English test questions matched with the difficulty level are finally selected; the formula and the steps increase the screening precision of the Chinese and English test questions in the preset English test question library, and a twice screening mode is used, so that the screened questions are more in line with the requirements, the types of the selected questions can be ensured to be diversified, and the difficulty is matched with the difficulty level.
6. The English question automatic generation system is characterized by comprising an English historical learning data record acquisition module, an English historical learning data record distinguishing module, a learning data record set-up module and an English test question book generation module; wherein the content of the first and second substances,
the English historical learning data record acquisition module is used for acquiring an English historical learning data record of a preset test object;
the English historical learning data record distinguishing module is used for carrying out data type content processing on the English historical learning data records so as to determine a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records;
the learning data record set is set into a module for determining the difficulty levels corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively, and dividing the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record with the same difficulty level into the same learning data record set;
the English test question book generating module is used for screening a plurality of different types of English test questions matched with the learning data record set from a preset English test question library, and picking corresponding quantities of different types of English test questions from the plurality of different types of English test questions according to the test duration of the preset test object to form an English test question book.
7. The automatic English title generation system of claim 6, wherein:
the English historical learning data record acquisition module is used for acquiring English historical learning data records of a preset test object, and specifically comprises the steps of acquiring on-history learning data records of the preset test object in the on-history learning process, and performing English related screening processing on the on-history learning data records so as to extract and obtain the English historical learning data records of the preset test object;
the English historical learning data record distinguishing module is used for carrying out data type content processing on the English historical learning data record, and specifically comprises the step of carrying out data content distinguishing processing on the English historical learning data record, so that a plurality of English grammar learning data records, a plurality of English voice learning data records and a plurality of English vocabulary learning data records contained in the English historical learning data record are determined.
8. The automatic English title generation system of claim 6, wherein:
the learning data record set is set into a module to determine the difficulty levels corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record, and the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record with the same difficulty level are divided into the same learning data record set,
determining grammar knowledge point information, voice knowledge point information and vocabulary knowledge point information which correspond to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively according to preset English test outline information;
comparing the grammar knowledge point information, the voice knowledge point information and the vocabulary knowledge point information with a preset knowledge point database respectively, thereby determining difficulty level evaluation values corresponding to the English grammar learning data record, the English voice learning data record and the English vocabulary learning data record respectively;
and finally, dividing English grammar learning data records, English voice learning data records and English vocabulary learning data records with the same difficulty level evaluation values into the same learning data record set, thereby obtaining a plurality of learning data record sets with different difficulty level evaluation values.
9. The automatic English title generation system of claim 6, wherein:
the English test question book generating module screens a plurality of different types of English test questions matched with the learning data record set from a preset English test question library, extracts corresponding quantities of different types of English test questions from the plurality of different types of English test questions according to the test duration of the preset test object, and accordingly forms an English test question book specifically comprising,
screening a plurality of English test questions of different types matched with the difficulty level from the preset English test question library according to the difficulty level of the learning data record set,
then determining the number of the respective questions of the selected questions, the filling-in-blank questions and the question and answer questions in the English test question book for testing the preset test object according to the test duration for testing the preset test object,
and finally, selecting a corresponding number of English grammar test selection questions or blank filling questions or question and answer questions from the English test questions of different types according to the number of the questions, and selecting the English listening test selection questions or blank filling questions or question and answer questions and English vocabulary test selection questions or blank filling questions or question and answer questions so as to generate the English test question book.
10. The automatic English title generation system of claim 8, wherein:
according to the difficulty level of the learning data record set, screening a plurality of English test questions of different types matched with the difficulty level from the preset English test question library further comprises:
step A1: determining the difficulty level of each English test question in the preset English test question library by using a formula (1):
wherein N isaRepresenting the difficulty level of the a-th English test question in the preset English test question library; daiRepresenting the average score of the ith English test question in the preset English test question library in the ith historical test; faiRepresenting the full score value of the ith English test question in the preset English test question library in the ith test history; n represents the total times of historical tests of the a-th English test question in the preset English test question library;
step A2: calculating the matching degree value between the difficulty level of each English test question in the preset English test question library and the difficulty level of the learning data record set by using a formula (2):
wherein Z isaRepresenting a matching degree value between the difficulty level of the a-th English test question in the preset English test question library and the difficulty level of the learning data record set; n represents the difficulty level of the learning data record set;
step A3: determining the English test question with the matching degree value equal to or smaller than a preset threshold value as the English test question screened for the first time;
step A4: classifying the English test questions screened for the first time by using a formula (3) to obtain a classification probability value:
wherein, FaiRepresenting the probability that the a-th English test question screened for the first time belongs to the i-th class question; siF corresponding to the alpha English test question screened for the first time is calculated according to the formula (3)aiBefore, the number of the English test questions belonging to the ith class of questions is determined; s represents F corresponding to the alpha-English test question screened for the first time and calculated according to the formula (3)aiBefore, the number of the English test questions in the classification is finished; patRepresenting the frequency of occurrence of the tth characteristic information corresponding to the ith type of title in the a-th English test title screened for the first time; m represents the total number of the characteristic information corresponding to the ith type of title;
when said F isaiWhen the number is equal to or more than 60%, the a-th English test question screened for the first time is considered to belong to the i-th question type; if a certain English test question belongs to a plurality of question types, selecting the FaiThe question type corresponding to the maximum value is used as the final attributive type of the alpha English test question screened for the first time;
when said F isaiAnd when the number is less than 60 percent, a new topic type is formed separately,and finally screening different types of English test questions matched with the difficulty level of the learning data record set until all the English test questions screened for the first time are classified and finished.
The beneficial effects of the above technical scheme are: the difficulty level of the English test questions in the preset English test question library is obtained by using a formula (1), so that the difficulty of the English test questions in the preset English test question library is quantified by using the formula, and the subsequent difficulty level can be matched with the difficulty level of the learning data record set, so that the screening of the subsequent questions is ensured; obtaining a matching degree value by using a formula (2) so as to screen English test questions in the preset English test question library for one time by using the matching degree value obtained by the formula and screen out English test questions matched with the difficulty level; finally, a classification probability value is obtained by using a formula (3), the English test questions in the preset English test question library after primary screening can be accurately classified by using the classification probability value, secondary screening is carried out according to the classification value, and different types of English test questions matched with the difficulty level are finally selected; the formula and the steps increase the screening precision of the Chinese and English test questions in the preset English test question library, and a twice screening mode is used, so that the screened questions are more in line with the requirements, the types of the selected questions can be ensured to be diversified, and the difficulty is matched with the difficulty level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856592.2A CN112015883A (en) | 2020-08-24 | 2020-08-24 | English question automatic generation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856592.2A CN112015883A (en) | 2020-08-24 | 2020-08-24 | English question automatic generation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112015883A true CN112015883A (en) | 2020-12-01 |
Family
ID=73504216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010856592.2A Pending CN112015883A (en) | 2020-08-24 | 2020-08-24 | English question automatic generation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112015883A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307773A (en) * | 2020-12-02 | 2021-02-02 | 上海交通大学 | Automatic generation method of custom problem data of machine reading understanding system |
| CN114781373A (en) * | 2022-04-29 | 2022-07-22 | 华侨大学 | MCT shape-filling intelligent question setting method and system based on knowledge constraint |
-
2020
- 2020-08-24 CN CN202010856592.2A patent/CN112015883A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307773A (en) * | 2020-12-02 | 2021-02-02 | 上海交通大学 | Automatic generation method of custom problem data of machine reading understanding system |
| CN114781373A (en) * | 2022-04-29 | 2022-07-22 | 华侨大学 | MCT shape-filling intelligent question setting method and system based on knowledge constraint |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111144191B (en) | Font identification method, font identification device, electronic equipment and storage medium | |
| CN108647211B (en) | Method for pushing learning content of children | |
| CN110443427A (en) | Result prediction method and its system based on cognitive knowledge spectrum | |
| CN110659352B (en) | Test question examination point identification method and system | |
| CN109949637B (en) | Automatic answering method and device for objective questions | |
| CN112015883A (en) | English question automatic generation method and system | |
| WO2022159729A1 (en) | Machine learning for video analysis and feedback | |
| CN105786898B (en) | A kind of construction method and device of domain body | |
| CN111597305B (en) | Entity marking method, entity marking device, computer equipment and storage medium | |
| CN116259004B (en) | Student learning state detection method and system applied to online education | |
| CN109800309A (en) | Classroom Discourse genre classification methods and device | |
| CN104347071A (en) | Method and system for generating oral test reference answer | |
| CN113836894B (en) | Multi-dimensional English composition scoring method and device and readable storage medium | |
| CN116012131A (en) | Method, system, device and medium for evaluating credit risk of user | |
| CN112015882A (en) | Automatic generation method and system for language text questions | |
| CN115859128B (en) | Analysis method and system based on interaction similarity of archive data | |
| CN112116181B (en) | Classroom quality model training method, classroom quality evaluation method and classroom quality evaluation device | |
| CN109599096A (en) | A kind of data screening method and device | |
| CN114241835A (en) | Student spoken language quality evaluation method and device | |
| CN114691903A (en) | Intelligent course testing method and system, electronic equipment and storage medium | |
| CN111967255A (en) | Internet-based automatic language test paper evaluation method and storage medium | |
| CN113255836A (en) | Job data processing method and device, computer equipment and storage medium | |
| CN111708951A (en) | Test question recommendation method and device | |
| CN110069783A (en) | A kind of answer content evaluating method and device | |
| CN111612324B (en) | Multi-dimensional assessment method based on oral English examination |
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 |