CN115048506A - Test question generation system, method and device based on knowledge graph and storage medium - Google Patents
Test question generation system, method and device based on knowledge graph and storage medium Download PDFInfo
- Publication number
- CN115048506A CN115048506A CN202210743044.8A CN202210743044A CN115048506A CN 115048506 A CN115048506 A CN 115048506A CN 202210743044 A CN202210743044 A CN 202210743044A CN 115048506 A CN115048506 A CN 115048506A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- proposition
- test question
- knowledge point
- library
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 265
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a test question generating system, a method, a device and a storage medium based on a knowledge graph, wherein the system comprises: the test question generating server and the user terminal; the test question generation server is used for: constructing a knowledge graph; acquiring test questions in the field corresponding to the knowledge graph in the network resource to generate a test question library; extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library; acquiring all knowledge points in a current examination proposition schema, and determining subdivision knowledge points to be examined corresponding to all the knowledge points from a proposition knowledge point library; determining proposition contents corresponding to the subdivision knowledge points to be examined from the question library based on the subdivision knowledge points to be examined; sending the proposition content corresponding to the subdivision knowledge point to be examined to a user terminal for selection by a propositor; and receiving the operation of the proposition person on proposition content selection fed back by the user terminal, and generating corresponding test question content. The invention assists the proposition through the knowledge map, lightens the workload of the proposition person and ensures the pertinence of the proposition.
Description
Technical Field
The invention relates to the technical field of test question generation, in particular to a test question generation system, a test question generation method, a test question generation device and a storage medium based on a knowledge graph.
Background
One of the most important and effective methods for measuring teaching effects is examination, and examination questions need to be customized to the examination. The customized test questions are work with strong speciality, technicality and comprehensiveness, and a person who puts questions needs to have strong subject professional background and basic technique of putting questions and also has high comprehensive capability of predicting education development, course reform, situation of learning, test results and the like.
With the help of the existing developed network resources, a propositor can obtain a large number of existing propositions from the network resources, however, the propositions have no pertinence to different students. To solve the problem, the proposition person usually needs to screen massive propositions according to the learning conditions of students, and the workload is huge and a great deal of time and energy are consumed.
Disclosure of Invention
The embodiment of the invention aims to provide a test question generation system, a test question generation method, a test question generation device and a storage medium based on a knowledge graph, which are used for assisting in proposing a question through the knowledge graph, reducing the workload of a propositor and ensuring the pertinence of the proposition.
In order to solve the above technical problem, in a first aspect, an embodiment of the present invention provides a test question generation system based on a knowledge graph, including: the test question generating server and the user terminal;
the test question generation server is used for: constructing a knowledge graph of at least one domain; obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library; extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library; acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library; determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined; sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal for selection by a propositor; receiving the operation of the proposition person on the proposition content selection fed back by the user terminal, and generating corresponding test question content;
the user terminal is configured to: responding to the operation of the proposition person on the proposition content selection, and feeding back to the test question generation server.
As one preferred scheme, the test question generating server executes the test questions in the domain corresponding to the knowledge graph in the network resource to generate a test question bank in the following manner:
extracting existing knowledge points from course schemas and course catalogues of the teaching material library;
determining knowledge points of the corresponding field of the knowledge graph based on the existing knowledge points;
and acquiring test questions related to knowledge points in the domain corresponding to the knowledge map from network resources by using a crawler technology, and generating a test question library.
As one preferred solution, the test question generating server performs the following steps of extracting initial question-proposing knowledge points from the test questions in the test question library to obtain a question-proposing knowledge point library:
carrying out knowledge point labeling on each test question of the test question library, and determining an initial proposition knowledge point of each test question;
and classifying and sorting the initial proposition knowledge points of all the test questions in the test question library to form a proposition knowledge point library.
As one preferable scheme, before the test question generating server executes the acquiring of each knowledge point in the current examination proposition schema and determines the subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library, the test question generating server is further configured to:
expanding the initial proposition knowledge point based on the knowledge graph to obtain a target proposition knowledge point; the target proposition knowledge point is an initial proposition knowledge point and an extended proposition knowledge point which are associated and matched with the knowledge graph;
updating the proposition knowledge point base based on the target proposition knowledge point;
the test question generation server executes the acquiring of each knowledge point in the current examination proposition schema in the following way, and determines the subdivision knowledge points to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library:
acquiring each knowledge point in the current examination proposition schema, and determining the subdivision knowledge points to be examined corresponding to each knowledge point in the current examination proposition schema from the target proposition knowledge points in the proposition knowledge point library.
As one preferred solution, the test question generating server performs the building of the knowledge graph of at least one domain by:
performing semantic recognition on character resources of a target subject course to extract each knowledge point corresponding to the target subject course; wherein the text resources of the target subject course comprise a course outline and a course catalog;
determining the logical relationship of each knowledge point in the target subject course; wherein the logical relationship comprises one or more of a parallel relationship, an inclusion relationship, a synonymy relationship and a progressive relationship;
determining a course knowledge entity model corresponding to the target subject course based on each knowledge point in the target subject course and the logic relationship of each knowledge point;
and constructing a knowledge graph corresponding to the field of the target subject course based on the course knowledge entity model.
In a second aspect, an embodiment of the present invention further provides a method for generating test questions based on a knowledge graph, including:
constructing a knowledge graph of at least one domain;
obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library;
extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library;
acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library;
determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined;
sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal for selection by a propositor;
and receiving the operation of the proposition person on the proposition content selection fed back by the user terminal, and generating corresponding test question content.
As one of the preferable schemes, the obtaining of the test questions in the network resources in the field corresponding to the knowledge graph and the generating of the test question library include:
extracting existing knowledge points from course schemas and course catalogues of the teaching material library;
determining knowledge points of the corresponding field of the knowledge graph based on the existing knowledge points;
and acquiring test questions related to knowledge points in the domain corresponding to the knowledge map from network resources by using a crawler technology, and generating a test question library.
As one preferable scheme, extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library includes:
carrying out knowledge point labeling on each test question of the test question library, and determining an initial proposition knowledge point of each test question;
and classifying and sorting the initial proposition knowledge points of all the test questions in the test question library to form a proposition knowledge point library.
In a third aspect, a further embodiment of the present invention provides a test question generating apparatus based on a knowledge graph, including:
the knowledge graph building module is used for building a knowledge graph of at least one field;
the test question bank generating module is used for acquiring test questions in the network resources in the field corresponding to the knowledge map and generating a test question bank;
the system comprises a proposition knowledge point base acquisition module, a proposition knowledge point database acquisition module and a proposition analysis module, wherein the proposition knowledge point base acquisition module is used for extracting initial proposition knowledge points from the test questions of the test question base to obtain a proposition knowledge point base;
the examination detail knowledge point determination module is used for acquiring each knowledge point in the current examination proposition schema and determining examination detail knowledge points corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library;
the proposition content determining module is used for determining proposition content corresponding to the subdivision knowledge points to be examined from the question library based on the subdivision knowledge points to be examined;
the sending module is used for sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal so as to be selected by a propositor;
and the receiving module is used for receiving the operation of the proposition person on the choice of the proposition content fed back by the user terminal and generating corresponding test question content.
In a fourth aspect, a further embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, a device on which the computer-readable storage medium is located is controlled to execute the method according to the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that at least one point in the following is realized:
the test question generating system based on the knowledge graph comprises a test question generating server and a user terminal, and specifically, the test question generating server comprises: constructing a knowledge graph of at least one domain; obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library; extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library; acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library; determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined; sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal for selection by a propositor; receiving the operation of the proposition person on the proposition content selection fed back by the user terminal, and generating corresponding test question content; and by the user terminal: responding to the operation of the proposition person on the proposition content selection, and feeding back to the test question generation server. Based on the method, the knowledge graph is constructed through the test question generating server, so that the problem proposing is assisted, the workload of a problem proposing person is reduced, the problem proposing is efficient, the coverage of knowledge points is comprehensive, and meanwhile, the final selection operation can be performed on the contents of the problem proposing by the final problem proposing person, so that the pertinence of the problem proposing is ensured. Correspondingly, the invention also provides a test question generation method and device based on the knowledge graph and a storage medium.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an embodiment of a knowledge-graph based test question generation system according to the present invention;
FIG. 2 is a flow chart of an embodiment of the method for generating test questions based on knowledge-graph according to the present invention;
fig. 3 is a schematic structural diagram of an embodiment of the test question generation apparatus based on knowledge graph according to 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.
In the description of the present invention, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, features defined as "first," "second," "third," etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in a specific case to those of ordinary skill in the art.
In the description of the present invention, it is to be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms used in the specification of the present invention are for the purpose of describing specific embodiments only, and are not intended to limit the present invention, and those skilled in the art can understand the specific meanings of the above terms in the present invention in a specific case.
Example one
Referring to fig. 1, fig. 1 is a schematic structural diagram of an embodiment of a test question generation system based on a knowledge graph according to the present invention. The embodiment can be suitable for application scenes in which a propositor needs to carry out proposition. In the present embodiment, the test question generation system based on the knowledge graph specifically includes a test question generation server 11 and a user terminal 12.
The test question generation server 11 is configured to: constructing a knowledge graph of at least one domain; obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library; extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library; acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library; determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined; sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal 12 for selection by a propositor; receiving the operation of the proposition person on the proposition content selection fed back by the user terminal 12, and generating corresponding test question content;
the user terminal 12 is configured to: responding to the operation of the proposition person to the proposition content selection and feeding back to the test question generating server 11.
In the embodiment of the present invention, the test question generating server 11 is configured to automatically generate test questions of different subject courses, where each subject course corresponds to a different field. The test question generation server 11 may include one or more processors and memory. A memory coupled to the processor for storing one or more programs; when executed by the one or more processors, cause the one or more processors to perform the functions described above. The user terminal 12 may be a personal computer (pc), a smart phone, a tablet computer, an electronic book reader, a portable computer, or other mobile terminal device having a display function.
First, the test question generation server 11 constructs a knowledge graph corresponding to the field according to the definition of the target subject.
As one preferred solution, the test question generating server 11 performs the construction of the knowledge graph of at least one domain by the following specific steps:
performing semantic recognition on character resources of a target subject course to extract each knowledge point corresponding to the target subject course; wherein the text resources of the target subject course comprise a course outline and a course catalog;
determining the logical relationship of each knowledge point in the target subject course; wherein the logical relationship comprises one or more of a parallel relationship, an inclusion relationship, a synonymy relationship and a progressive relationship;
determining a course knowledge entity model corresponding to the target subject course based on each knowledge point in the target subject course and the logic relationship of each knowledge point;
and constructing a knowledge graph corresponding to the field of the target subject course based on the course knowledge entity model.
In detail, based on the text resources of the existing target subject course, such as the course outline and the course catalog, semantic recognition is performed on the text resources, so as to extract each knowledge point of the target subject course. After obtaining the knowledge points of the target subject course, fusing and processing the knowledge points to obtain the logical relationship of each knowledge point. Optionally, based on the logical relationship of each knowledge point, the duplicate knowledge points may be deleted to be sorted into high-quality knowledge points. And forming corresponding course knowledge entity models by arranging all knowledge points in the target subject courses and corresponding logic relations. In each course knowledge entity model, knowledge point nodes, knowledge chains and knowledge units to which each knowledge point belongs are determined, so that a visual knowledge graph corresponding to the field of the target subject course can be formed based on the course knowledge entity model.
After the knowledge graph of the target field is obtained, the test questions in the field can be obtained from the network resources, and thus a test question bank is generated.
As one preferred scheme, the test question generating server 11 executes the following steps to obtain the test questions in the domain corresponding to the knowledge graph in the network resource, and generates a test question bank:
extracting existing knowledge points from course schemas and course catalogues of the teaching material library;
determining knowledge points of the corresponding field of the knowledge graph based on the existing knowledge points;
and acquiring test questions related to knowledge points in the domain corresponding to the knowledge map from network resources by using a crawler technology, and generating a test question library.
In detail, a Web crawler (Web crawler) is a program or script for automatically fetching information of the world wide Web according to a certain rule, and this technology is widely used in internet search engines or other similar websites, and can automatically collect all the page contents that can be accessed by the internet search engines to obtain or update the contents and retrieval modes of these websites. The crawler is divided into three parts, namely data acquisition, processing and storage in general, according to the functional distinction; technically, the method can be divided into a general web crawler and a focused crawler.
In this embodiment, the crawling targets of the web crawler are knowledge points in the internet in the domain corresponding to the knowledge graph, so as to crawl from the test questions of the network resources to the test questions associated with the knowledge points in the domain corresponding to the knowledge graph. Furthermore, all the crawled test questions are uniformly put into a database to serve as a test question library. As an example, a set of questions (Q) in the question bank is represented as Q i =｛Q 1 , Q 2 , Q 3 , Q 4 , Q 5 , …, Q n Wherein i is a positive integer, i is not less than 1 and not more than n, n is a positive integer, Q n And representing the nth test question in the test question bank.
As one of the preferable schemes, the test question generating server 11 specifically executes the extraction of the initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library by:
carrying out knowledge point labeling on each test question of the test question library, and determining an initial proposition knowledge point of each test question;
and classifying and sorting the initial proposition knowledge points of all the test questions in the test question library to form a proposition knowledge point library.
In this embodiment, although the test questions in the test question library are obtained based on the association relationship between the knowledge points of the knowledge graph, the number of specific knowledge points included in each test question is unclear, for example, a part of the test questions may include one knowledge point, and a part of the test questions includes a plurality of knowledge points, so that further labeling operation needs to be performed on the crawled test questions.
In one embodiment, the knowledge points of each test question in the test question library can be labeled based on the knowledge points in the corresponding field of the knowledge map. Extracting feature words of each test question, comparing the similarity of the feature words of each test question with one or more knowledge points in the corresponding field of the knowledge graph, and if the similarity of the feature words of each test question and one or more knowledge points in the corresponding field of the knowledge graph is greater than or equal to a first preset value, marking the corresponding knowledge points as initial question setting knowledge points of each test question; and if the similarity between the feature words of each test question and one or more knowledge points in the corresponding field of the knowledge map is smaller than a first preset value, rejecting the corresponding knowledge points. Thus, each test question can be labeled with one or more initial propositional knowledge points.
In another embodiment, each test in the test library may be annotated with a knowledge point based on the text resources of the target subject course, such as the course outline and the course catalog. In detail, extracting knowledge points in the text resources of the target subject course, extracting feature words of each test question, comparing the similarity of the feature words of each test question with one or more knowledge points in the text resources of the target subject course, and if the similarity of the feature words of each test question and one or more knowledge points in the text resources of the target subject course is more than or equal to a first preset value, marking the corresponding knowledge points as initial proposing knowledge points of each test question; and if the similarity between the feature words of each test question and one or more knowledge points in the text resources of the target subject course is smaller than a first preset value, removing the corresponding knowledge points. Thus, each test question can be labeled with one or more initial propositional knowledge points.
After the knowledge points of all the test questions in the test question library are labeled, classifying and sorting the initial proposition knowledge points of all the test questions, taking the initial physical subjects as an example, classifying the mechanical knowledge points into one class, classifying the thermal knowledge points into another class, and combining and de-weighting the repeated knowledge points in each class to form a final proposition knowledge point library. As an example, a set of propositional knowledge points (P) in a propositional knowledge points library is represented as P fj =｛P 1j , P 2j , P 3j , P 4j , P 5j , …, P mj Wherein f is a positive integer and is not less than 1 and not more than fm and j are positive integers, j is more than or equal to 1 and less than or equal to k, m and k are positive integers, P fj Propositional knowledge point set represented in the f-th domain, e.g. P 1j Represents a propositional knowledge point set in the 1 st domain, and P 1j =｛P 11 , P 12 , P 13 , P 14 , P 15 , …, P 1k ｝，P 1k Propositional knowledge points of kth, e.g. P, represented in domain 1 11 The 1 st propositional knowledge point in the 1 st domain is represented. Therefore, based on the propositional knowledge point library, the propositional knowledge points are covered comprehensively.
As one of the preferable schemes, before the test question generating server 11 executes the acquiring of each knowledge point in the current examination proposition schema and determines the subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library, the test question generating server 11 is further configured to:
expanding the initial proposition knowledge point based on the knowledge graph to obtain a target proposition knowledge point; the target proposition knowledge point is an initial proposition knowledge point and an extended proposition knowledge point which are associated and matched with the knowledge graph;
and updating the proposition knowledge point base based on the target proposition knowledge point.
In this embodiment, to further enrich the initial proposition knowledge point, the initial proposition knowledge point may be expanded based on the knowledge map. In detail, firstly determining the field of initial proposition knowledge points, extracting knowledge points corresponding to the field of the initial proposition knowledge points from a knowledge graph, then calculating the similarity between the initial proposition knowledge points and the knowledge points in the field corresponding to the knowledge graph, and then judging whether the similarity between the initial proposition knowledge points and the knowledge points in the field corresponding to the knowledge graph is more than or equal to a second preset value and less than 100 percent, wherein the second preset value is more than the first preset value:
if the similarity between the initial proposition knowledge points and the knowledge points in the corresponding field of the knowledge map is judged to be more than or equal to a second preset value and less than 100 percent, determining the knowledge points in the corresponding field of the knowledge map as the extended proposition knowledge points;
if the similarity between the initial proposition knowledge point and the knowledge point of the corresponding field of the knowledge map is judged to be smaller than a second preset value, the knowledge point of the corresponding field of the knowledge map is not determined as an expanded proposition knowledge point;
and if the similarity between the initial proposition knowledge point and the knowledge point in the corresponding field of the knowledge map is judged to be equal to 100%, determining the knowledge point in the corresponding field of the knowledge map as the initial proposition knowledge point.
As an example, the set of propositional knowledge points (P ') in the updated propositional knowledge point library is represented as P' fj' =｛P' 1j' , P' 2j' , P' 3j' , P' 4j' , P' 5'j , …, P' m'j' Wherein f is a positive integer, and f is more than or equal to 1 and less than or equal to m ', j ' is a positive integer, and j ' is more than or equal to 1 and less than or equal to k ', m ' and k ' are positive integers, and m ' is more than or equal to m, k ' is more than or equal to k, and P ' fj' Representing propositional knowledge point sets in the f-th domain, e.g. P' 1j' Represents a set of propositional knowledge points in the 1 st domain, and P' 1j' =｛P' 11 , P' 12 , P' 13 , P' 14 , P' 15 , …, P' 1k' - }, e.g. P' 11 Denotes the 1 st propositional knowledge point, P 'in the 1 st domain' 1k' The kth propositional knowledge point in the 1 st domain is represented.
The test question generating server 11 specifically executes the acquiring of each knowledge point in the current examination proposition schema, and determines the subdivision knowledge points to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library by the following method:
acquiring each knowledge point in the current examination proposition schema, and determining the subdivision knowledge points to be examined corresponding to each knowledge point in the current examination proposition schema from the target proposition knowledge points in the proposition knowledge point library.
In detail, it can be understood that the knowledge points in the current examination proposition schema are generally upper general information, and a proposition person generally needs to surround the knowledge points in the current examination proposition schema and determine the next-level knowledge points of the knowledge points, so as to determine the content of the examination questions, and it takes much work. Thus, due to each knowledge in the knowledge-graphThe logic relation of the points is definite, so that the subdivision knowledge points to be examined corresponding to the upper knowledge points in the current examination proposition schema can be matched through the matching step of the target proposition knowledge points from the proposition knowledge point library, so that a proposition person can determine the next-level knowledge points of the knowledge points without spending more workload. As an example, the set of subdivided knowledge Points (PE) to be considered is denoted T fj' =｛T 1j' , T 2j' , T 3j' , T 4j' , T 5j' , …, T m'j' Wherein f is a positive integer, f is more than or equal to 1 and less than or equal to m ', j' is a positive integer, j 'is more than or equal to 1 and less than or equal to k', m 'and k' are positive integers, m 'is more than or equal to m, k' is more than or equal to k, T fj' Set of subdivided knowledge points to be considered, e.g. T, represented in the f-th domain 1j' Represents the set of subdivided knowledge points to be considered in the 1 st domain, and T 1j' =｛T 11 , T 12 , T 13 , T 14 , T 15 , …, T 1k' }, e.g. T 11 Denotes the 1 st segment knowledge point to be examined, P 'in the 1 st domain' 1k' Indicating the k' th subdivision knowledge point to be considered in the 1 st domain.
As shown in fig. 1, after obtaining the subdivided knowledge points of the examination to be examined of the current examination, the examination question generating server 11 generates corresponding topic content and transmits the topic content to the user terminal 12, so that the person who sets the questions performs a selection operation at the user terminal 12 to determine the final topic content. The user terminal 12 feeds back an operation of a proposition person for proposition content selection to the test question generation server 11, and then the test question generation server 11 generates corresponding test question content.
To sum up, the test question generation system based on the knowledge graph provided by the embodiment of the present invention includes a test question generation server 11 and a user terminal 12, and specifically, through the test question generation server 11: constructing a knowledge graph of at least one domain; obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library; extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library; acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library; determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined; sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal 12 for selection by a propositor; receiving the operation of the proposition person on the proposition content selection fed back by the user terminal 12, and generating corresponding test question content; and by the user terminal 12: responding to the operation of the proposition person to the proposition content selection and feeding back to the test question generating server 11. Based on the above, the invention constructs the knowledge map through the test question generating server 11, thereby assisting the proposition, reducing the workload of the proposition person, ensuring the high efficiency of proposition and the comprehensive coverage of knowledge points, and simultaneously ensuring the pertinence of the proposition as the final proposition person can carry out the final selection operation on the proposition content.
Example two
On the basis of the first embodiment, as shown in fig. 2, the embodiment of the present invention further provides a test question generation method based on a knowledge graph, which includes the following steps:
s110, constructing a knowledge graph of at least one field;
s120, obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library;
s130, extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library;
s140, acquiring each knowledge point in the current examination proposition schema, and determining the subdivision knowledge points to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library;
s150, determining proposition contents corresponding to the subdivision knowledge points to be examined from the question library based on the subdivision knowledge points to be examined;
s160, sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal 12 for selection by a propositor;
s170, receiving the operation of the proposition person on the proposition content selection fed back by the user terminal 12, and generating corresponding test question content.
It can be understood that the test question generation method based on the knowledge graph in the embodiment of the present invention may be applied to the test question generation server 11, and the test question generation server 11 may be configured to execute the steps S110 to S170, and details of each step may refer to corresponding contents in the above-mentioned embodiment, which are not described herein again.
As one of the preferable schemes, the step S120 of obtaining the test questions in the network resources in the field corresponding to the knowledge graph and generating the test question library includes the following sub-steps:
s121, extracting existing knowledge points from the course outline and the course catalog of the teaching material library;
s122, determining knowledge points of the corresponding field of the knowledge graph based on the existing knowledge points;
s123, obtaining the test questions related to the knowledge points in the domain corresponding to the knowledge map from the network resources by using a crawler technology, and generating a test question library.
It is understood that the test question generating server 11 can be used to execute the steps S121-S123, and the detailed content of each step can refer to the corresponding content in the above-mentioned embodiment, which is not described herein again.
As one of the preferable schemes, the step S130 extracts an initial proposition knowledge point from the test questions in the test question library to obtain a proposition knowledge point library, and includes the following sub-steps:
s131, carrying out knowledge point labeling on each test question in the test question library, and determining an initial proposition knowledge point of each test question;
s132, classifying and sorting the initial proposition knowledge points of all the test questions in the test question library to form a proposition knowledge point library.
It is understood that the test question generating server 11 can be used to execute the steps S131 to S132, and the detailed content of each step can refer to the corresponding content in the above-mentioned embodiment, which is not described herein again.
In summary, in the test question generation method based on the knowledge graph provided by the embodiment, specifically, the knowledge graph of at least one field is constructed; obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library; extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library; acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library; determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined; sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal 12 for selection by a propositor; receiving the operation of the proposition person to select the proposition content fed back by the user terminal 12, and generating the corresponding test question content. Based on the method, the knowledge graph is constructed, so that the proposition is assisted, the workload of a proposition person is reduced, the proposition is efficient, the knowledge points are covered comprehensively, and the final selection operation of the proposition content can be performed by the final proposition person, so that the pertinence of the proposition is ensured.
EXAMPLE III
On the basis of the first embodiment, as shown in fig. 3, an embodiment of the present invention further provides a test question generation apparatus based on a knowledge graph, including:
a knowledge graph construction module 201, configured to construct a knowledge graph of at least one domain;
the test question bank generating module 202 is used for acquiring test questions in the network resources in the field corresponding to the knowledge graph and generating a test question bank;
a proposition knowledge point base obtaining module 203, configured to extract an initial proposition knowledge point from the test questions in the test question base, and obtain a proposition knowledge point base;
the examination detail knowledge point determination module 204 is configured to obtain each knowledge point in the current examination proposition schema, and determine, from the proposition knowledge point library, an examination detail knowledge point corresponding to each knowledge point in the current examination proposition schema;
a proposition content determining module 205, configured to determine proposition content corresponding to the to-be-considered subdivision knowledge point from the test question library based on the to-be-considered subdivision knowledge point;
a sending module 206, configured to send the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal 12, so that a propositor can select the proposition content;
a receiving module 207, configured to receive the operation of the proposition content selection by the proposition person fed back by the user terminal 12, and generate corresponding test question content.
For the specific limitation of the test question generation device based on the knowledge graph, reference may be made to the above limitation of the test question generation method based on the knowledge graph, and details thereof are not repeated here. The modules of the test question generation device based on the knowledge graph can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Example four
Embodiments of the present invention further provide a computer-readable storage medium including program instructions, which when executed by a processor implement the steps of the method for generating test questions based on a knowledge graph according to any one of the above embodiments. For example, the computer readable storage medium may be the above-mentioned memory including program instructions executable by the processor of the computer terminal device to perform the above-mentioned method for generating test questions based on a knowledge graph, and to achieve technical effects consistent with the above-mentioned method.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A knowledge-graph-based test question generation system, comprising: the test question generating server and the user terminal;
the test question generation server is used for: constructing a knowledge graph of at least one domain; obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library; extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library; acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library; determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined; sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal for selection by a propositor; receiving the operation of the proposition person on the proposition content selection fed back by the user terminal, and generating corresponding test question content;
the user terminal is configured to: responding to the operation of the proposition person on the proposition content selection, and feeding back to the test question generation server.
2. The system of claim 1, wherein the test question generation server is configured to execute the obtaining of the test questions in the network resource corresponding to the knowledge graph to generate the test question library by:
extracting existing knowledge points from course schemas and course catalogues of the teaching material library;
determining knowledge points of the corresponding field of the knowledge graph based on the existing knowledge points;
and acquiring test questions related to knowledge points in the domain corresponding to the knowledge map from network resources by using a crawler technology, and generating a test question library.
3. The system of claim 2, wherein the test question generation server performs the extracting of the initial propositional knowledge points from the test questions of the test question library to obtain a propositional knowledge point library by:
carrying out knowledge point labeling on each test question of the test question library, and determining an initial proposition knowledge point of each test question;
and classifying and sorting the initial proposition knowledge points of all the test questions in the test question library to form a proposition knowledge point library.
4. The system of claim 3, wherein before the test question generation server performs the obtaining of the knowledge points in the current test proposition schema and determining the subdivided knowledge points to be examined corresponding to the knowledge points in the current test proposition schema from the proposition knowledge point library, the test question generation server is further configured to:
expanding the initial proposition knowledge point based on the knowledge graph to obtain a target proposition knowledge point; the target proposition knowledge point is an initial proposition knowledge point and an extended proposition knowledge point which are associated and matched with the knowledge graph;
updating the proposition knowledge point base based on the target proposition knowledge point;
the test question generation server executes the acquiring of each knowledge point in the current examination proposition schema in the following way, and determines the subdivision knowledge points to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library:
acquiring each knowledge point in the current examination proposition schema, and determining the subdivision knowledge points to be examined corresponding to each knowledge point in the current examination proposition schema from the target proposition knowledge points in the proposition knowledge point library.
5. The system of generating knowledge-graph-based test questions of any one of claims 1-4, wherein the test question generation server performs the constructing the knowledge graph of the at least one domain by:
performing semantic recognition on character resources of a target subject course to extract each knowledge point corresponding to the target subject course; wherein the text resources of the target subject course comprise a course outline and a course catalog;
determining the logical relationship of each knowledge point in the target subject course; wherein the logical relationship comprises one or more of a parallel relationship, an inclusion relationship, a synonymy relationship and a progressive relationship;
determining a course knowledge entity model corresponding to the target subject course based on each knowledge point in the target subject course and the logic relationship of each knowledge point;
and constructing a knowledge graph corresponding to the field of the target subject course based on the course knowledge entity model.
6. A test question generation method based on a knowledge graph is characterized by comprising the following steps:
constructing a knowledge graph of at least one domain;
obtaining test questions in the network resources in the field corresponding to the knowledge graph, and generating a test question library;
extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library;
acquiring each knowledge point in a current examination proposition schema, and determining a subdivision knowledge point to be examined corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library;
determining proposition contents corresponding to the subdivision knowledge points to be examined from the test question library based on the subdivision knowledge points to be examined;
sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal for selection by a propositor;
and receiving the operation of the proposition person on the proposition content selection fed back by the user terminal, and generating corresponding test question content.
7. The method for generating test questions based on the knowledge graph as claimed in claim 6, wherein the obtaining of the test questions in the network resource corresponding to the knowledge graph to generate the test question bank comprises:
extracting existing knowledge points from course schemas and course catalogues of the teaching material library;
determining knowledge points of the corresponding field of the knowledge graph based on the existing knowledge points;
and acquiring test questions related to knowledge points in the domain corresponding to the knowledge map from network resources by using a crawler technology, and generating a test question library.
8. The method for generating test questions based on the knowledge graph of claim 7, wherein the extracting initial proposition knowledge points from the test questions in the test question library to obtain a proposition knowledge point library comprises:
carrying out knowledge point labeling on each test question of the test question library, and determining an initial proposition knowledge point of each test question;
and classifying and sorting the initial proposition knowledge points of all the test questions in the test question library to form a proposition knowledge point library.
9. A test question generation device based on a knowledge graph is characterized by comprising:
the knowledge graph building module is used for building a knowledge graph of at least one field;
the test question bank generating module is used for acquiring test questions in the network resources in the field corresponding to the knowledge map and generating a test question bank;
the system comprises a proposition knowledge point base acquisition module, a proposition knowledge point database acquisition module and a proposition analysis module, wherein the proposition knowledge point base acquisition module is used for extracting initial proposition knowledge points from the test questions of the test question base to obtain a proposition knowledge point base;
the examination detail knowledge point determination module is used for acquiring each knowledge point in the current examination proposition schema and determining examination detail knowledge points corresponding to each knowledge point in the current examination proposition schema from the proposition knowledge point library;
the proposition content determining module is used for determining proposition content corresponding to the subdivision knowledge points to be examined from the question library based on the subdivision knowledge points to be examined;
the sending module is used for sending the proposition content corresponding to the subdivision knowledge point to be examined to the user terminal so as to be selected by a propositor;
and the receiving module is used for receiving the operation of the proposition person on the choice of the proposition content fed back by the user terminal and generating corresponding test question content.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method for generating a knowledge-graph-based test question according to any one of claims 6 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210743044.8A CN115048506A (en) | 2022-06-29 | 2022-06-29 | Test question generation system, method and device based on knowledge graph and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210743044.8A CN115048506A (en) | 2022-06-29 | 2022-06-29 | Test question generation system, method and device based on knowledge graph and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115048506A true CN115048506A (en) | 2022-09-13 |
Family
ID=83163897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210743044.8A Pending CN115048506A (en) | 2022-06-29 | 2022-06-29 | Test question generation system, method and device based on knowledge graph and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115048506A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116955589A (en) * | 2023-09-19 | 2023-10-27 | 山东山大鸥玛软件股份有限公司 | Intelligent proposition method, system, proposition terminal and storage medium based on teaching material knowledge graph |
| CN117274006A (en) * | 2023-11-21 | 2023-12-22 | 山东山大鸥玛软件股份有限公司 | Proposition method, system, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095619A (en) * | 2014-05-07 | 2015-11-25 | 北大方正集团有限公司 | Processing method and apparatus for examination question information |
| CN110377689A (en) * | 2019-06-17 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Paper intelligent generation method, device, computer equipment and storage medium |
| CN113127731A (en) * | 2021-03-16 | 2021-07-16 | 西安理工大学 | Knowledge graph-based personalized test question recommendation method |
-
2022
- 2022-06-29 CN CN202210743044.8A patent/CN115048506A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095619A (en) * | 2014-05-07 | 2015-11-25 | 北大方正集团有限公司 | Processing method and apparatus for examination question information |
| CN110377689A (en) * | 2019-06-17 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Paper intelligent generation method, device, computer equipment and storage medium |
| CN113127731A (en) * | 2021-03-16 | 2021-07-16 | 西安理工大学 | Knowledge graph-based personalized test question recommendation method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116955589A (en) * | 2023-09-19 | 2023-10-27 | 山东山大鸥玛软件股份有限公司 | Intelligent proposition method, system, proposition terminal and storage medium based on teaching material knowledge graph |
| CN116955589B (en) * | 2023-09-19 | 2024-01-30 | 山东山大鸥玛软件股份有限公司 | Intelligent proposition method, system, proposition terminal and storage medium based on teaching material knowledge graph |
| CN117274006A (en) * | 2023-11-21 | 2023-12-22 | 山东山大鸥玛软件股份有限公司 | Proposition method, system, equipment and storage medium |
| CN117274006B (en) * | 2023-11-21 | 2024-03-12 | 山东山大鸥玛软件股份有限公司 | Proposition method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837550B (en) | Knowledge graph-based question answering method and device, electronic equipment and storage medium | |
| US20180032890A1 (en) | Method and system for improving content searching in a question and answer customer support system by using a crowd-machine learning hybrid predictive model | |
| CN115048506A (en) | Test question generation system, method and device based on knowledge graph and storage medium | |
| CN110597962A (en) | Search result display method, device, medium and electronic equipment | |
| CN109522562B (en) | Webpage knowledge extraction method based on text image fusion recognition | |
| US20200118022A1 (en) | Determining Comprehensiveness of Question Paper Given Syllabus | |
| CN114139056A (en) | Intelligent search recommendation method and system based on online learning course | |
| CN111191012A (en) | Knowledge graph generation apparatus, method and computer program product thereof | |
| CN112100401A (en) | Knowledge graph construction method, device, equipment and storage medium for scientific and technological service | |
| CN105930490A (en) | Intelligent selecting system for teaching resources | |
| CN111192170B (en) | Question pushing method, device, equipment and computer readable storage medium | |
| CN117573985B (en) | Information pushing method and system applied to intelligent online education system | |
| CN109934631A (en) | Question and answer information processing method, device and computer equipment | |
| CN112330387A (en) | Virtual broker applied to house-watching software | |
| CN110209804B (en) | Target corpus determining method and device, storage medium and electronic device | |
| CN115757720A (en) | Project information searching method, device, equipment and medium based on knowledge graph | |
| CN116010704A (en) | Enterprise peer recommendation method, electronic equipment and storage medium | |
| CN112818212B (en) | Corpus data acquisition method, corpus data acquisition device, computer equipment and storage medium | |
| CN112200602B (en) | Neural network model training method and device for advertisement recommendation | |
| CN113656545A (en) | Intelligent interviewing method and device, computer equipment and storage medium | |
| CN109597873B (en) | Corpus data processing method and device, computer readable medium and electronic equipment | |
| CN112328871A (en) | Reply generation method, device, equipment and storage medium based on RPA module | |
| CN113836377A (en) | Information association method and device, electronic equipment and storage medium | |
| Liu | Simulation of E-learning in English personalized learning recommendation system based on Markov chain algorithm and adaptive learning algorithm | |
| CN113569091A (en) | Video data processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220913 |
|
| RJ01 | Rejection of invention patent application after publication |